CN118747330A - A device monitoring method and system based on chromaticity spectrum mapping - Google Patents

Abstract

The present invention relates to the field of GIS equipment monitoring technology, and in particular to an equipment monitoring method and system based on chromaticity spectrum mapping. The method comprises the following steps: collecting real-time vibration information of GIS equipment, and performing time-frequency conversion analysis on the real-time vibration information to obtain a number of real-time sub-vibration features; analyzing each real-time sub-vibration feature, and converting and generating a real-time chromaticity spectrum based on the analysis result; analyzing the real-time chromaticity spectrum based on a first operating state analysis model to determine the real-time equipment component status of the GIS equipment, configuring a variety of parameter information in the real-time chromaticity spectrum through analysis of the real-time vibration information, and using the real-time chromaticity spectrum as input data, and determining the corresponding real-time equipment component status by the first operating state analysis model. The present invention improves the accuracy and breadth of component operating state identification by performing vibration time-frequency conversion and chromaticity spectrum mapping on GIS equipment.

Description

A device monitoring method and system based on chromaticity spectrum mapping

Technical Field

The present invention relates to the field of GIS equipment monitoring technology, and in particular to an equipment monitoring method and system based on chromaticity spectrum mapping.

Background Art

Gas insulated metal-enclosed switchgear (GIS) in substations has been widely used in the power field due to its advantages of small footprint, high system integration, and strong operational safety and reliability. According to relevant statistics, 44% of GIS equipment failures are caused by mechanical defects. Therefore, in order to ensure the safe operation of GIS, it is of great significance to carry out online monitoring and intelligent diagnosis technology research on potential mechanical defects of GIS. However, since the GIS vibration signal contains rich equipment status information and has the advantage of not being interfered by electromagnetic waves, good experimental results have been achieved by identifying the mechanical state of GIS based on vibration signal analysis. However, the conventional feature extraction method based on vibration signals has a good identification effect for monitoring objects with simple structures and single working modes, but for GIS equipment with large and complex structures and various types of mechanical defects, it is usually difficult to achieve effective characterization of different GIS states, which will cause missed and misjudgment of defects, and the conventional contact-based vibration monitoring method has low safety.

Summary of the invention

Based on this, it is necessary to provide a device monitoring method and system based on chromaticity spectrum mapping to solve at least one of the above technical problems.

To achieve the above object, a device monitoring method based on chromaticity spectrum mapping is provided, the method comprising the following steps:

Step S1: collecting real-time vibration information of GIS equipment, and performing time-frequency conversion analysis on the real-time vibration information using complex Gabor-Morlet wavelet transform, and performing time-frequency conversion analysis on the real-time vibration information to obtain a real-time sub-vibration feature set;

Step S2: performing a single feature analysis on the real-time sub-vibration feature set to generate a single feature analysis result; performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

Step S3: construct a first operating status analysis model; perform component status analysis on the real-time chromaticity spectrum based on the first operating status analysis model to obtain real-time device component status data of the GIS device.

The present invention can obtain the characteristics of the vibration signal in time and frequency by collecting the real-time vibration information of the GIS equipment and using the complex Gabor-Morlet wavelet transform for time-frequency conversion analysis. Such analysis helps to understand the mode, frequency components and change trend of the equipment vibration, and provides basic data for subsequent state evaluation. By performing time-frequency conversion analysis on the real-time vibration information, a real-time sub-vibration feature set can be obtained. These feature sets contain information on vibration components in different frequency ranges, making further analysis and judgment more comprehensive and accurate. By performing a single feature analysis on the real-time sub-vibration feature set, key vibration feature parameters such as peak value, frequency, amplitude, etc. can be extracted. These single feature analysis results are used to evaluate the operating state of the equipment and provide a basis for subsequent state judgment. According to the single feature analysis results, the real-time sub-vibration feature set is mapped to a chromaticity spectrum, and the vibration characteristics can be displayed in a visual manner. The chromaticity spectrum can intuitively display the intensity and frequency distribution of the vibration, which helps to quickly observe and analyze the vibration state of the equipment. According to the analysis results and feature extraction of the first to fourth steps, a first operating state analysis model can be constructed. This model is based on machine learning, deep learning or other related technologies, and is used to determine the operating state of the equipment and identify abnormal conditions. Based on the first operation status analysis model, the real-time chromaticity spectrum is used to analyze the component status, and the vibration characteristics can be matched with the different component states of the equipment, thereby obtaining the real-time equipment component status data of the GIS equipment. These data can be used for equipment health monitoring, fault prediction and maintenance decision-making. Therefore, the present invention improves the accuracy and breadth of component operation status identification by performing vibration time-frequency conversion and chromaticity spectrum mapping on GIS equipment.

In this specification, a device monitoring system based on chromaticity spectrum mapping is provided, which is used to execute the above-mentioned device monitoring method based on chromaticity spectrum mapping. The device monitoring system based on chromaticity spectrum mapping includes:

The vibration information analysis module is used to collect the real-time vibration information of GIS equipment and perform time-frequency conversion analysis on the real-time vibration information using complex Gabor-Morlet wavelet transform to obtain the real-time sub-vibration feature set;

A chromaticity spectrum generation module is used to perform a single feature analysis on the real-time sub-vibration feature set to generate a single feature analysis result; perform chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

The operation status analysis module is used to construct a first operation status analysis model; based on the first operation status analysis model, component status analysis is performed on the real-time chromaticity spectrum to obtain real-time device component status data of the GIS device.

The beneficial effect of the present invention is that by collecting the real-time vibration information of GIS equipment and using the complex Gabor-Morlet wavelet transform for time-frequency conversion analysis, efficient processing and analysis of vibration signals can be achieved. This helps to timely discover abnormal vibration conditions of the equipment and warn of possible faults in advance. Single feature analysis is performed on the real-time sub-vibration feature set, and a chromaticity spectrum is generated, which can intuitively display the vibration characteristics and state changes of the equipment. This helps engineers and operators to understand the operating status of the equipment more quickly, perform fault diagnosis and maintenance. By constructing a first operating status analysis model, the component status analysis of the real-time chromaticity spectrum can be systematically performed, and the real-time equipment component status data of the equipment can be further extracted. This helps to establish an equipment status monitoring and prediction model to achieve intelligent management and optimized maintenance of the equipment status. Based on the above analysis results, real-time monitoring and analysis of the operating status of GIS equipment can be achieved, abnormal status and potential faults of the equipment can be discovered in time, so as to warn in advance and take corresponding maintenance measures, reduce the equipment failure rate, and extend the life of the equipment. By implementing the above analysis and prediction model, accurate maintenance of GIS equipment can be achieved, unnecessary maintenance and downtime can be avoided, maintenance costs can be reduced, and the reliability and stability of the equipment can be improved.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is a schematic diagram of a process flow of a device monitoring method based on chromaticity spectrum mapping;

FIG2 is a schematic flow chart of detailed implementation steps for performing chromaticity spectrum mapping on a real-time sub-vibration feature set according to a single feature analysis result in step S2 of FIG1 ;

FIG3 is a schematic flow chart of detailed implementation steps for constructing a first operating status analysis model in step S3 in FIG1 ;

The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings.

DETAILED DESCRIPTION

The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor methods and/or microcontroller methods.

It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and/or" used herein includes any and all combinations of one or more of the listed associated items.

To achieve the above object, please refer to Figures 1 to 3, a device monitoring method based on chromaticity spectrum mapping, the method comprises the following steps:

Step S1: collecting real-time vibration information of GIS equipment, and performing time-frequency conversion analysis on the real-time vibration information using complex Gabor-Morlet wavelet transform, and performing time-frequency conversion analysis on the real-time vibration information to obtain a real-time sub-vibration feature set;

Step S2: performing a single feature analysis on the real-time sub-vibration feature set to generate a single feature analysis result; performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

Step S3: construct a first operating status analysis model; perform component status analysis on the real-time chromaticity spectrum based on the first operating status analysis model to obtain real-time device component status data of the GIS device.

The present invention can obtain the characteristics of the vibration signal in time and frequency by collecting the real-time vibration information of the GIS equipment and using the complex Gabor-Morlet wavelet transform for time-frequency conversion analysis. Such analysis helps to understand the mode, frequency components and change trend of the equipment vibration, and provides basic data for subsequent state evaluation. By performing time-frequency conversion analysis on the real-time vibration information, a real-time sub-vibration feature set can be obtained. These feature sets contain information on vibration components in different frequency ranges, making further analysis and judgment more comprehensive and accurate. By performing a single feature analysis on the real-time sub-vibration feature set, key vibration feature parameters such as peak value, frequency, amplitude, etc. can be extracted. These single feature analysis results are used to evaluate the operating state of the equipment and provide a basis for subsequent state judgment. According to the single feature analysis results, the real-time sub-vibration feature set is mapped to a chromaticity spectrum, and the vibration characteristics can be displayed in a visual manner. The chromaticity spectrum can intuitively display the intensity and frequency distribution of the vibration, which helps to quickly observe and analyze the vibration state of the equipment. According to the analysis results and feature extraction of the first to fourth steps, a first operating state analysis model can be constructed. This model is based on machine learning, deep learning or other related technologies, and is used to determine the operating state of the equipment and identify abnormal conditions. Based on the first operation status analysis model, the real-time chromaticity spectrum is used to analyze the component status, and the vibration characteristics can be matched with the different component states of the equipment, thereby obtaining the real-time equipment component status data of the GIS equipment. These data can be used for equipment health monitoring, fault prediction and maintenance decision-making. Therefore, the present invention improves the accuracy and breadth of component operation status identification by performing vibration time-frequency conversion and chromaticity spectrum mapping on GIS equipment.

In the embodiment of the present invention, referring to FIG. 1 , a schematic diagram of a step flow of a device monitoring method based on chromaticity spectrum mapping of the present invention is shown. In this example, the device monitoring method based on chromaticity spectrum mapping includes the following steps:

Step S1: collecting real-time vibration information of GIS equipment, and performing time-frequency conversion analysis on the real-time vibration information using complex Gabor-Morlet wavelet transform, and performing time-frequency conversion analysis on the real-time vibration information to obtain a real-time sub-vibration feature set;

In an embodiment of the present invention, by using sensor devices such as vibration sensors or accelerometers, which are installed at key parts of the GIS equipment, the vibration information of the GIS equipment is collected in real time. The collection frequency needs to be high enough to ensure real-time monitoring and capture of equipment vibration. The collected real-time vibration information is subjected to time-frequency conversion analysis using the complex Gabor-Morlet wavelet transform. Gabor-Morlet wavelet transform is a commonly used time-frequency analysis method that can provide information in both the time and frequency domains and is suitable for the analysis of non-stationary signals. After the time-frequency conversion analysis, vibration features such as frequency, amplitude, etc. are extracted from the obtained time-frequency image. According to the distribution and change trend of the vibration features, a real-time sub-vibration feature set is constructed. More specifically, the vibration signal y={y ₁ ,y ₂ ,…y _n } of the GIS equipment is converted into the time-frequency domain using the complex Gabor-Morlet wavelet transform:

In the formula, a and b represent the scale and displacement factor respectively. represents the wavelet basis function, is the conjugate of ψ(·).

Then the frequency domain expression of WT(a,b) is:

In the formula, They represent the wavelet transform of time domain signals /f(ω) and ψ(ω), ω represents the frequency, Represents an imaginary number.

Step S2: performing a single feature analysis on the real-time sub-vibration feature set to generate a single feature analysis result; performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

In an embodiment of the present invention, a single feature analysis is performed for each vibration feature in the real-time sub-vibration feature set. These features include frequency, amplitude, energy, etc. The statistics of each vibration feature, such as mean, standard deviation, maximum value, minimum value, etc., and other related indicators, such as spectrum peak, etc., can be calculated. The results obtained from the single feature analysis are integrated to form a single feature analysis result. These results can be presented in the form of tables, charts, etc. for subsequent analysis and comparison. For each feature, some thresholds or reference ranges can be set to determine whether it is within the normal range, so as to make a preliminary assessment of the device status. The vibration features in the real-time sub-vibration feature set are mapped to a chromaticity spectrum. The chromaticity spectrum presents the changes of vibration features in time and frequency in the form of an image, usually represented by a heat map. After mapping the vibration features to the chromaticity spectrum, the changes of the vibration features over time and frequency can be intuitively observed, which is convenient for discovering abnormal vibration patterns and trends.

Step S3: construct a first operating status analysis model; perform component status analysis on the real-time chromaticity spectrum based on the first operating status analysis model to obtain real-time device component status data of the GIS device.

In an embodiment of the present invention, historical data and equipment operation conditions are collected, including vibration feature sets under normal and abnormal conditions, component status data, etc. Suitable machine learning or statistical modeling methods, such as support vector machines (SVM), decision trees, neural networks, etc., are selected to construct a first operating status analysis model. In the process of model construction, it is necessary to consider selecting appropriate features, setting appropriate model parameters, and performing model evaluation and optimization to improve the accuracy and generalization ability of the model. The real-time chromaticity spectrum is used as the input data of the model, and the component status analysis is performed through the first operating status analysis model. In the component status analysis process, the model can evaluate the status of each component of the GIS equipment based on the vibration characteristics in the real-time chromaticity spectrum to determine whether it is in normal working condition. If the status of a component is found to be abnormal, the corresponding real-time equipment component status data is generated, and an alarm is issued or further inspection and maintenance measures are recommended.

Preferably, in step S2, performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result includes:

Perform fast Fourier transformation on the real-time sub-vibration feature set to generate a vibration pitch spectrum diagram;

Extracting frequency components from the vibration pitch spectrum to obtain vibration frequency components; performing chromaticity order mapping on the vibration frequency components, and normalizing the mapping results to generate vibration chromaticity order data;

The corresponding frequency band amplitudes of the vibration frequency components are accumulated according to the vibration chromaticity order data to obtain a real-time chromaticity spectrum.

The present invention can convert the vibration signal from the time domain to the frequency domain by performing fast Fourier transformation on the real-time sub-vibration feature set, and obtain a vibration pitch spectrum. This spectrum can show the energy distribution of the vibration signal at different frequencies, which is helpful for analyzing the frequency components and main frequency areas of the vibration. The main frequency components in the vibration signal can be obtained by extracting the frequency components of the vibration pitch spectrum. These frequency components correspond to different vibration modes or vibration sources in the vibration signal. By extracting these components, the characteristics and sources of the vibration can be better understood. The vibration frequency components are mapped to chromaticity order, and the frequency information of the vibration can be mapped to different color orders on the chromaticity spectrum. Such mapping can intuitively represent the distribution of the vibration frequency, which is helpful for observing the strength and relative relationship of different frequency components. Normalization processing can ensure that the chromaticity spectrum at different time points is comparable and consistent. Vibration chromaticity order data can be generated through chromaticity order mapping and normalization processing. These data can be used for further analysis and visualization, such as displaying the distribution of vibration frequency through heat maps, or representing the intensity and change trend of vibration through color coding. According to the vibration chromaticity order data, the corresponding frequency band amplitude of the vibration frequency component can be accumulated to obtain a real-time chromaticity spectrum. This chromaticity spectrum can intuitively display the intensity and changes of different frequency components at different time points, providing an important reference for equipment status analysis and fault diagnosis.

As an example of the present invention, referring to FIG2 , in this example, the chromaticity spectrum mapping of the real-time sub-vibration feature set according to the single feature analysis result includes the following steps:

Step S21: performing fast Fourier transform on the real-time sub-vibration feature set to generate a vibration pitch spectrum diagram;

In an embodiment of the present invention, a real-time sub-vibration feature set is obtained from step S1, including time domain data or spectrum data of a vibration signal. The real-time sub-vibration feature set is converted from the time domain to the frequency domain using a fast Fourier transform (FFT) algorithm. FFT is an efficient algorithm that can convert a time domain signal into a frequency domain signal and provide spectrum information of the signal. The frequency domain data obtained by the FFT transformation is plotted into a spectrum diagram, in which the horizontal axis represents the frequency and the vertical axis represents the amplitude or energy of the vibration signal. The spectrum diagram can intuitively display the distribution of the vibration signal at different frequencies, that is, the pitch spectrum diagram of the vibration signal. More specifically, a calculation formula can be used to calculate the pitch of the real-time sub-vibration feature set. The calculation formula is as follows:

Wherein, p represents pitch, and its relationship with frequency is p=69+12log ₂ (f/440), k∈[0,N-1] represents the index number of the frequency component, and N represents the signal length.

Step S22: extracting frequency components from the vibration pitch spectrum to obtain vibration frequency components; performing chromaticity order mapping on the vibration frequency components, and normalizing the mapping results to generate vibration chromaticity order data;

In an embodiment of the present invention, the main vibration frequency components are extracted from the vibration pitch spectrum diagram by peak detection or spectrum analysis. A threshold can be set or an adaptive algorithm can be used to identify frequency components with significant amplitudes as the main components of the vibration frequency. The extracted vibration frequency components are subjected to chromaticity order mapping to different positions on the chromaticity wheel. Chromaticity order mapping is a commonly used method for converting frequency components into corresponding pitch orders, usually using logarithmic or linear mapping. The mapping results are normalized to map the vibration frequency components to a uniform range for subsequent data processing and analysis. Normalization can be achieved through linear transformation or other mathematical methods to ensure that the values of all frequency components are within a certain range. The specific corresponding mapping algorithm is as follows.

χ(k)=12[log ₂ (f _s /N×k/f _ref )]/12;

Wherein, fs represents the signal sampling frequency, and f _ref represents the reference frequency, which is the frequency value of a lower set of pitches A in the twelve-tone scale.

Therefore, the chromaticity vector ξ _ve is:

In the formula, c represents a variable, and ξ _ve (c) reflects the energy of the frequency band to which each scale component belongs.

Furthermore, the chromaticity vector is normalized to obtain:

ξ _norm (c)=ξ _ve (c)/Pξ _ve (c)P.

Step S23: Accumulate the corresponding frequency band amplitudes of the vibration frequency components according to the vibration chromaticity order data, so as to obtain a real-time chromaticity spectrum.

In the embodiment of the present invention, the vibration frequency components and the corresponding frequency band amplitudes are accumulated according to the vibration chromaticity order data. For each frequency band, the vibration chromaticity order data is traversed, and the amplitudes of the vibration frequency components falling within the frequency band are accumulated. The accumulated frequency band amplitudes are used as data of the real-time chromaticity spectrum. The real-time chromaticity spectrum is an image with the frequency band as the horizontal axis and the vibration amplitude as the vertical axis, which is used to represent the distribution of vibration energy in different frequency bands.

Preferably, constructing the first operating status analysis model in step S3 includes:

Obtain historical vibration information and historical maintenance logs of GIS equipment;

Performing time-frequency conversion analysis on historical vibration information to obtain a number of historical sub-vibration feature sets, and performing chromaticity spectrum mapping on the historical sub-vibration feature sets to generate a historical chromaticity spectrum;

Conduct maintenance time sequence analysis on historical maintenance logs to determine the historical equipment component operation status data at different time nodes;

Based on different time nodes, the historical chromaticity spectrum and the historical equipment component operation status data are temporally correlated to obtain a time-correlated historical chromaticity spectrum;

The time-correlated historical chromaticity spectra and historical equipment component operation status data are divided into data sets to generate model training sets and model test sets;

The model training set is trained using the LeNet-5 neural network algorithm to generate a first operating state training model. The first operating state training model is optimized and iterated using the model test set to generate a first operating state analysis model.

The present invention obtains historical vibration information and historical maintenance logs of GIS equipment, which contain the vibration conditions and maintenance records of the equipment in the past period of time. By analyzing these historical data, the operation mode, vibration characteristics and maintenance conditions of the equipment can be identified, providing a basis for subsequent analysis and modeling. By performing time-frequency conversion analysis on the historical vibration information, several historical sub-vibration feature sets can be obtained. By performing chromaticity spectrum mapping on these feature sets, historical chromaticity spectra can be generated. These spectra can reflect the vibration characteristics and frequency distribution of the equipment at different time points, which is helpful to understand the historical vibration state of the equipment. By performing maintenance timing analysis on the historical maintenance logs, the historical equipment component operation status data at different time nodes can be determined. These data record the maintenance and repair conditions of the equipment at different periods, and can be used to judge the health status and maintenance history of the equipment. The historical chromaticity spectrum and the historical equipment component operation status data are time-correlated, and a time-correlated historical chromaticity spectrum can be obtained. Such a spectrum can correspond the vibration characteristics to the equipment status information, and provide a more comprehensive historical data analysis result. The time-correlated historical chromaticity spectrum and the historical equipment component operation status data are divided into data sets to generate a model training set and a model test set. These data sets are used to train and evaluate the first operating status analysis model. The model training set is trained using the LeNet-5 neural network algorithm to generate the first operating status training model. The training model is optimized and iterated using the model test set to generate a more accurate and reliable first operating status analysis model. This model can be used for real-time equipment status analysis and fault prediction.

As an example of the present invention, referring to FIG3 , the step of constructing the first operating state analysis model in this example includes:

Step S31: Obtain historical vibration information and historical maintenance logs of GIS equipment;

In the embodiment of the present invention, historical vibration information of GIS equipment is collected, including vibration signal data collected by sensors such as vibration sensors or accelerometers. Such vibration information should include vibration data during the operation of the equipment, covering vibration characteristics in different time periods and under different operating conditions. Historical maintenance logs of GIS equipment are collected to record the maintenance and overhaul of the equipment, including information such as maintenance date, maintenance content, and replacement parts. These maintenance logs can be recorded and archived in the form of equipment maintenance records, maintenance reports, or maintenance databases.

Step S32: performing time-frequency conversion analysis on the historical vibration information to obtain a number of historical sub-vibration feature sets, and performing chromaticity spectrum mapping on the historical sub-vibration feature sets to generate a historical chromaticity spectrum;

In an embodiment of the present invention, by performing time-frequency conversion analysis on historical vibration information, a method similar to step S1 can be adopted, such as using algorithms such as complex Gabor-Morlet wavelet transform. The historical vibration information is converted into time-frequency domain data to obtain a number of historical sub-vibration feature sets. A chromaticity spectrum mapping is performed on each historical sub-vibration feature set, and the vibration features are mapped to the chromaticity spectrum to intuitively display the time-frequency characteristics of the historical vibration information. The chromaticity spectrum can reflect the distribution of vibration signals at different frequencies and times, which is helpful to discover the laws and trends of historical vibrations. The chromaticity spectra of all historical sub-vibration feature sets are integrated and summarized to obtain a historical chromaticity spectrum. The historical chromaticity spectrum can be statistically analyzed and visualized to reveal the vibration characteristics and operating status of GIS equipment in different historical periods.

Step S33: Perform maintenance time sequence analysis on historical maintenance logs to determine historical equipment component operation status data at different time nodes;

In an embodiment of the present invention, past equipment maintenance logs are collected, and these logs include equipment maintenance records, fault reports, repair records, etc. These logs are usually recorded in text form and also contain timestamps and other relevant information. The collected historical maintenance logs are cleaned and organized to ensure the integrity and accuracy of the data. This involves operations such as removing duplicate data, filling missing values, and unifying time formats. The cleaned historical maintenance log data is converted into time series data, that is, a sequence of data arranged in chronological order. The data at each time point should include the operating status of the equipment components, such as normal, under maintenance, faulty, etc. The data is analyzed using time series analysis technology to determine the operating status of equipment components at different time nodes. Common time series analysis methods include time series models, sliding window analysis, periodic analysis, etc.

Step S34: Correlate the historical chromaticity spectrum with the historical equipment component operation status data in a time-correlated manner based on different time nodes to obtain a time-correlated historical chromaticity spectrum;

In an embodiment of the present invention, the historical chromaticity spectrum data and the historical equipment component operation status data are time-correlated. This can be achieved through timestamps or time intervals to ensure that each time point or time period has corresponding chromaticity spectrum and equipment component operation status data. Based on the time-correlated data, a time-correlated historical chromaticity spectrum is generated. This can be a data structure that visualizes the chromaticity spectrum data and the equipment operation status data on the same graph, or a data structure that represents the relationship between chromaticity and equipment status obtained by a statistical analysis method.

Step S35: dividing the time-correlated historical chromaticity spectrogram and historical equipment component operation status data into data sets to generate a model training set and a model test set;

In an embodiment of the present invention, the division ratio of the training set and the test set is determined according to the actual situation. Usually, the training set will occupy most of the data, while the test set will occupy a smaller proportion. For example, a common division ratio is 80% of the data for training and 20% of the data for testing. The time-related historical data set is randomly divided into a training set and a test set according to a determined ratio. Make sure to maintain the time order when dividing to avoid confusion of time series data. If the number of samples of different equipment states in the historical data is unbalanced, you can consider taking some strategies to balance the number of samples of different categories in the training set and the test set when dividing the data set to avoid the model being biased towards the category with a larger number of samples. Make sure that each sample in the training set and the test set is correctly labeled with the corresponding equipment component operating status. These labels will serve as the target of model training and testing.

Step S36: Use the LeNet-5 neural network algorithm to perform model training on the model training set to generate a first operating state training model; use the model test set to perform model optimization iteration on the first operating state training model to generate a first operating state analysis model.

In the embodiment of the present invention, a neural network model is constructed according to the network structure of LeNet-5. LeNet-5 includes two convolutional layers, two pooling layers and three fully connected layers, and is suitable for processing image data.

Compile the constructed LeNet-5 model and select appropriate loss functions, optimizers, and evaluation indicators. The loss function can be the cross entropy loss function, the optimizer can be the Adam optimizer, and the evaluation indicator can be the accuracy rate, etc. Use the prepared training data to train the LeNet-5 model. During the training process, the model parameters are continuously adjusted through the back propagation algorithm to minimize the loss function. Use a validation set other than the training set to evaluate the trained model and evaluate the performance of the model on the validation set, including indicators such as accuracy, precision, and recall. Save the trained first running state training model to disk for subsequent use. The specific calculation formulas for the convolution layer and pooling layer of the LeNet-5 neural network algorithm are:

Where f(g) represents the activation function, which can be an optional ReLU function, Xi _,j represents the input element of the i-th row and j-th column, σ represents the convolution kernel element, m and n represent the size of the convolution kernel, and δ represents the error offset. D(g) represents downsampling, and Yi,j represents the element in the pooling area.

Preferably, the obtaining of historical vibration information and historical maintenance logs of GIS equipment includes:

Apply a preset fault to the GIS equipment, and after each preset fault is applied, use a vibration sensor to collect historical vibration information data of the GIS equipment;

Perform fault maintenance on GIS equipment based on historical vibration information data to obtain historical maintenance data;

The cloud platform is used to upload data logs of historical maintenance data to obtain historical maintenance logs.

The present invention can simulate the vibration characteristics under real fault conditions by applying preset faults and using vibration sensors to collect historical vibration information data of GIS equipment. These historical vibration information data provide detailed records of the vibration modes and characteristics of the equipment under different fault conditions. By analyzing these data, the vibration characteristics corresponding to various fault modes can be identified, providing a basis for subsequent fault inspection and status analysis. Fault inspection based on historical vibration information data can obtain historical inspection data by repairing and replacing parts of the equipment. These data record the maintenance and maintenance records of the equipment at different time points, including information such as replaced parts, maintenance process and maintenance results. By analyzing these data, the maintenance history and maintenance status of the equipment can be understood, providing a basis for health assessment and prediction of the equipment. By uploading data logs of historical inspection data using the cloud platform, historical inspection records can be centrally stored and managed. By uploading historical inspection logs, data backup and sharing can be achieved, which is convenient for subsequent data analysis and query. The cloud platform also provides data processing and visualization functions, so that historical inspection logs can be more conveniently analyzed and applied.

In the embodiment of the present invention, a preset fault scenario is designed and implemented for the GIS equipment, such as simulating damage or abnormality of a certain component of the equipment. A sensor device such as a vibration sensor or an accelerometer is installed on the GIS equipment to monitor the vibration of the equipment in real time. After each preset fault is applied, the sensor is used to collect historical vibration information data of the GIS equipment. These data will record the vibration characteristics of the equipment in the fault state and can be used for subsequent fault diagnosis and prediction. Based on the collected historical vibration information data, the vibration characteristics and patterns of the GIS equipment in the fault state are analyzed. According to the vibration characteristics, fault diagnosis and positioning are performed to determine the faulty components or problems of the equipment. Corresponding maintenance and repair work is carried out to repair or replace damaged equipment components to restore the normal operation of the equipment. The historical maintenance data is uploaded to the cloud platform for centralized management and storage. The advantages of cloud storage can be used to back up, archive and analyze the historical maintenance data to achieve long-term storage and effective use of data. A data log system is established on the cloud platform to ensure the integrity, traceability and security of the historical maintenance data, which is convenient for subsequent data query and analysis.

Preferably, the performing model optimization iteration on the first operating state training model using the model test set includes:

Establish a real-time vibration collection timeline based on the real-time vibration information of the GIS equipment, and mark the time points of the real-time vibration collection timeline based on the preset time interval to generate re-detection points;

Extracting vibration information at a time point on a real-time vibration collection timeline according to adjacent re-detection points to obtain first vibration information extraction data and second vibration information extraction data; performing repeated vibration segment discrimination on the first vibration information extraction data and the second vibration information extraction data, and when determining that there is no repeated vibration information segment, performing chromaticity spectrum mapping on the first vibration information extraction data and the second vibration information extraction data without the repeated information segment to generate a first chromaticity spectrum and a second chromaticity spectrum;

Performing a joint analysis of the first chromaticity spectrum and the second chromaticity spectrum to generate a joint analysis spectrum group;

Performing a comparison analysis on each chromaticity spectrum of the joint analysis spectrum group, and constructing a vibration contrast chromaticity spectrum based on the comparison analysis results, performing a vibration accuracy feature analysis on the vibration contrast chromaticity spectrum, and generating vibration chromaticity spectrum accuracy feature data;

Based on the vibration chromaticity spectrum accuracy feature data, a model optimization strategy is constructed for the first operating state training model to generate a model optimization strategy;

The first operating state training model is optimized and iterated using the model test set according to the model optimization strategy, thereby generating a first operating state analysis model.

The present invention can generate re-detection points by establishing a real-time vibration acquisition timeline and marking the time points of the timeline according to a preset time interval. These re-detection points are used to extract vibration information in the real-time vibration acquisition timeline for subsequent analysis and modeling. According to adjacent re-detection points, vibration information is extracted in the real-time vibration acquisition timeline to obtain first vibration information extraction data and second vibration information extraction data. Repeated vibration segments are identified for these information, and non-repeated information segments are extracted for chromaticity spectrum mapping to generate a first chromaticity spectrum and a second chromaticity spectrum. These chromaticity spectra reflect the vibration characteristics and frequency distribution of the equipment, providing a basis for subsequent analysis and comparison. The first chromaticity spectrum and the second chromaticity spectrum are jointly analyzed to generate a joint analysis spectrum group. Then, through the comparison analysis of each chromaticity spectrum, a vibration contrast chromaticity spectrum can be constructed for vibration accuracy feature analysis. These feature data can provide more accurate and detailed vibration information, providing a basis for model optimization. Based on the vibration chromaticity spectrum accuracy feature data, a model optimization strategy can be constructed. These strategies can include measures such as feature selection, model parameter adjustment, and algorithm optimization, aiming to improve the accuracy and robustness of the model. Then, the first operating state training model is optimized and iterated using the model test set, and a more accurate and reliable first operating state analysis model is generated by continuously adjusting and updating the model.

In an embodiment of the present invention, real-time vibration information is obtained by using a GIS device, and a real-time vibration collection timeline is established. According to a preset time interval, a time point is marked on the timeline to generate a re-detection point. Based on adjacent re-detection points, vibration information is extracted from the real-time vibration collection timeline to obtain first vibration information extraction data and second vibration information extraction data. Repeated vibration segments are discriminated for the first vibration information extraction data and the second vibration information extraction data to determine non-repeated vibration information segments. Chroma spectrum mapping is performed using the first vibration information extraction data and the second vibration information extraction data without repeated information segments to generate a first chroma spectrum and a second chroma spectrum. The first chroma spectrum and the second chroma spectrum are jointly analyzed to generate a joint analysis spectrum group. A comparison analysis is performed on each chroma spectrum in the joint analysis spectrum group, and a vibration contrast chroma spectrum is constructed according to the comparison results. A vibration accuracy feature analysis is performed on the vibration contrast chroma spectrum to extract relevant feature data. A model optimization strategy is constructed based on the vibration chroma spectrum accuracy feature data. This may include measures in terms of feature selection, model parameter adjustment, and algorithm optimization. The first operating state training model is optimized and iterated using the model test set. According to the model optimization strategy, the model is adjusted and updated to generate a more accurate and reliable first operating state analysis model.

Preferably, the performing of comparison analysis of each chromaticity spectrum on the joint analysis spectrum group and the performing of vibration accuracy characteristic analysis on the vibration contrast chromaticity spectrum comprises:

Establishing a collection rule for chromaticity collection points, and collecting point chromaticity of the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group according to the collection rule to obtain the point chromaticity of the chromaticity spectrum; recording chromaticity information of the point chromaticity of the chromaticity spectrum to generate chromaticity spectrum collection point information data, wherein the chromaticity information record includes a chromaticity record and a position record of the collection point, and the chromaticity spectrum collection point information data includes first chromaticity spectrum collection point information data of the first chromaticity spectrum and second chromaticity spectrum collection point information data of the second chromaticity spectrum;

Perform chromaticity difference analysis on the chromaticity spectrum acquisition point information data to generate a first chromaticity acquisition point difference amount and a second chromaticity acquisition point difference amount;

Compare the difference amount of the first chromaticity acquisition point and the difference amount of the second chromaticity acquisition point with a preset chromaticity acquisition difference threshold; if the difference amount of the first chromaticity acquisition point and the difference amount of the second chromaticity acquisition point are both less than the preset chromaticity acquisition difference threshold, calculate the average value of the difference amount of the first chromaticity acquisition point and the second chromaticity acquisition point to obtain the average value of the difference amount of the chromaticity acquisition point; use the average value of the difference amount of the chromaticity acquisition point to perform corresponding chromaticity replacement on the blocks with different chromaticity in the joint analysis spectrum group, so as to obtain a vibration contrast chromaticity spectrum;

The vibration accuracy characteristic analysis of the vibration contrast chromaticity spectrum is performed based on the difference amount of the first acquisition point and the difference amount of the second acquisition point to generate vibration chromaticity spectrum accuracy characteristic data.

The present invention can ensure consistent point chromaticity acquisition of the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group by establishing a chromaticity acquisition point acquisition rule. This helps to ensure the accuracy and reliability of subsequent analysis. By performing chromaticity difference analysis on the chromaticity spectrum acquisition point information data, the difference between the first chromaticity spectrum and the second chromaticity spectrum can be quantified. This helps to determine the blocks with differences and provide a basis for subsequent chromaticity replacement. By using the average value of the chromaticity difference amount to perform chromaticity replacement on the blocks with chromaticity differences in the joint analysis spectrum group, a vibration contrast chromaticity spectrum can be generated. Such processing can highlight the effect of vibration contrast and provide a clearer and easier to observe chromaticity spectrum. Based on the difference amount of the first acquisition point and the difference amount of the second acquisition point, the vibration accuracy feature analysis is performed on the vibration contrast chromaticity spectrum. This helps to further understand the characteristics and behavior of vibration and generate relevant feature data. These feature data can provide important indicators for model optimization and performance evaluation.

In the embodiment of the present invention, the chromaticity collection point collection rules are designed, including the selection and interval of the collection points. These rules should take into account the importance of vibration characteristics and ensure that the collected data can fully reflect the vibration situation. According to the chromaticity collection point collection rules, the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group are subjected to point chromaticity collection. The collected data should include chromaticity records and position records for subsequent analysis and comparison. The chromaticity spectrum collection point information data is subjected to difference analysis, and the difference amount of the first chromaticity collection point and the difference amount of the second chromaticity collection point are calculated. The difference amount of the first chromaticity collection point and the difference amount of the second chromaticity collection point are compared with the preset chromaticity collection difference threshold. If the difference amount is less than the threshold, the average value of the difference amount is calculated, and the chromaticity block with a large difference is replaced with the corresponding chromaticity to make the chromaticity more consistent. Based on the difference amount of the first collection point and the difference amount of the second collection point, the vibration contrast chromaticity spectrum is subjected to vibration accuracy feature analysis, including the extraction and analysis of features such as the amplitude, frequency, and period of vibration. According to the results of the vibration accuracy feature analysis, vibration chromaticity spectrum accuracy feature data is generated. These data can be used for subsequent model optimization and fault diagnosis.

Preferably, the step of establishing a chromaticity acquisition point collection rule and performing point chromaticity acquisition on the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group according to the chromaticity acquisition point collection rule comprises:

Collecting information on the sequence of collection points and the distance between adjacent collection points of the joint analysis spectrum group to obtain collection point sequence data and adjacent collection point distance information data; sorting the collection point sequence data and the adjacent collection point distance information data to generate a collection point sequence;

Performing random scanning mapping analysis on the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group according to the acquisition point sequence, and recording the analysis results to obtain first chromaticity recording data and second chromaticity recording data; performing chromaticity sorting on the first chromaticity recording data and the second chromaticity recording data to generate a chromaticity reference sequence;

According to the acquisition point sequence, a plurality of chromaticity scanning and mapping analyses are performed on the remaining spectra except the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group, and in each scanning and mapping analysis, the first acquisition point in the acquisition point sequence of the remaining spectra except the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group is transformed relative to the first chromaticity spectrum and the second chromaticity spectrum, so as to generate a plurality of chromaticity comparison sequences;

Calculate the chromaticity similarity of each chromaticity comparison sequence and the chromaticity reference sequence respectively to obtain the chromaticity comparison similarity degree; mark the chromaticity comparison sequence corresponding to the chromaticity comparison similarity degree greater than the preset similarity threshold with sequence information, thereby generating the chromaticity collection point collection rule;

According to the chromaticity acquisition point acquisition rule, point chromaticity acquisition is performed on the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group to obtain the point chromaticity of the chromaticity spectrum.

The present invention can obtain accurate collection point layout and arrangement by collecting the collection point order and adjacent collection point spacing information in the joint analysis spectrum group. This helps to establish consistent collection rules and ensure the consistency and comparability of subsequent chromaticity collection processes. By sorting the collection point sequence and performing random scanning mapping analysis on the first chromaticity spectrum and the second chromaticity spectrum according to the sorted sequence, the chromaticity information can be recorded and a reference sequence can be generated. Such processing helps to establish an accurate chromaticity reference benchmark and provide a basis for subsequent chromaticity comparison. By performing multiple chromaticity scanning mapping analyses on other spectra except the first chromaticity spectrum and the second chromaticity spectrum, and changing the position of the collection point sequence, multiple chromaticity comparison sequences can be generated. Such processing can increase the diversity and comprehensiveness of the comparison and improve the accuracy and reliability of the chromaticity comparison. By calculating the chromaticity similarity between each chromaticity comparison sequence and the chromaticity reference sequence, the degree of similarity can be determined. According to a preset similarity threshold, the comparison sequence with a similarity higher than the threshold is marked, thereby determining the chromaticity collection point collection rule. Such processing helps to screen out reliable collection points and improve the accuracy and consistency of the chromaticity spectrum. According to the chromaticity collection point collection rules, the first chromaticity spectrum and the second chromaticity spectrum are collected to obtain accurate chromaticity data of the chromaticity spectrum points. This provides basic data for subsequent analysis and processing, and is helpful for further vibration feature analysis and research.

In an embodiment of the present invention, the information of the sequence of acquisition points and the spacing between adjacent acquisition points is collected for the joint analysis spectrum group. This can be accomplished by image processing technology or manual annotation. The acquisition point sequence data and the adjacent acquisition point spacing information data are sorted to obtain a set of ordered acquisition point sequences. According to the acquisition point sequence, the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group are randomly scanned and mapped for analysis. During each scanning and mapping analysis, the analysis results are recorded to obtain the first chromaticity recording data and the second chromaticity recording data. The first chromaticity recording data and the second chromaticity recording data are chromatically sorted to obtain a chromaticity reference sequence. According to the acquisition point sequence, multiple chromaticity scanning and mapping analyses are performed on other spectra except the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group. During each scanning and mapping analysis, the first acquisition point in the acquisition point sequence of other spectra except the first chromaticity spectrum and the second chromaticity spectrum is transformed relative to the first chromaticity spectrum and the second chromaticity spectrum to generate multiple chromaticity comparison sequences. The chromaticity similarity of each chromaticity comparison sequence and the chromaticity reference sequence is calculated to obtain the chromaticity comparison similarity. According to the preset similarity threshold, the chromaticity comparison sequence whose chromaticity comparison similarity is greater than the threshold is marked, thereby generating a chromaticity collection point collection rule. According to the chromaticity collection point collection rule, the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group are subjected to point chromaticity collection to obtain point chromaticity data of the chromaticity spectrum.

Preferably, the vibration accuracy characteristic analysis of the vibration contrast chromaticity spectrum based on the difference between the first acquisition point and the second acquisition point includes:

Calculate the vibration accuracy characteristics of the vibration contrast chromaticity spectrum based on the difference between the first acquisition point and the second acquisition point using the accuracy characteristic formula to obtain the vibration chromaticity spectrum accuracy characteristic data;

The accuracy characteristic formula is as follows:

Wherein, J is the corresponding value of the accuracy feature between the real-time chromaticity spectra, _k1 is the accuracy conversion coefficient, _c1 is the position adjustment coefficient of the first acquisition point, _x1 is the difference of the first acquisition point, _Δx1 is the standard difference of the first acquisition point, _c2 is the position adjustment coefficient of the second acquisition point, _x2 is the difference of the second acquisition point, _Δx2 is the standard difference of the second acquisition point, _b1 is the chromaticity adjustment constant of the first acquisition point, and _b2 is the chromaticity adjustment constant of the second acquisition point.

The present invention can calculate the accuracy feature data of the vibration chromaticity spectrum according to the difference between the first acquisition point and the second acquisition point by using the accuracy feature formula. This characteristic value reflects the accuracy between the vibration chromaticity spectrum and provides a quantitative evaluation index. In the accuracy feature formula, the difference between the first acquisition point and the second acquisition point can be adjusted and weighted by setting the accuracy conversion coefficient and the position adjustment coefficient ( _c1 and _c2 ). This helps to flexibly control the weight distribution of the accuracy feature calculation according to actual needs and the importance of vibration characteristics. The difference standard ( _Δx1 and _Δx2 ) and the chromaticity adjustment constant ( _b1 and _b2 ) in the formula are used to standardize and adjust the difference between the first acquisition point and the second acquisition point. Such processing can reasonably control and adjust the range and chromaticity adjustment of the vibration feature according to actual conditions and data characteristics. The vibration chromaticity spectrum accuracy feature data obtained by calculation can be further analyzed and compared. This helps to understand the relationship between vibration features, evaluate the accuracy and reliability of vibration comparison, and provide important reference indicators for subsequent model optimization and performance evaluation.

In the embodiment of the present invention, by using a given accuracy characteristic formula, the accuracy characteristic value J of the vibration contrast chromaticity spectrum is calculated according to the difference amount _x1 of the first acquisition point and the difference amount _x2 of the second acquisition point. The characteristic value J reflects the corresponding value of the accuracy characteristic between the real-time chromaticity spectrum. The higher the characteristic value J, the higher the accuracy of the vibration contrast chromaticity spectrum. The calculated characteristic value J is analyzed, and the accuracy of the vibration contrast chromaticity spectrum is judged according to the size of the characteristic value. A higher characteristic value indicates that the similarity between the chromaticity spectrum is higher and the accuracy is better.

Preferably, performing component status analysis on the real-time chromaticity spectrum based on the first operating status analysis model in step S3 includes:

Importing the real-time chromaticity spectrum into the first operation status analysis model to perform GIS equipment status operation analysis and generate GIS equipment status operation analysis data;

Perform equipment anomaly identification on GIS equipment status operation analysis data to generate GIS equipment anomaly identification data; use GIS equipment anomaly identification data to perform anomaly classification on GIS equipment status operation analysis data to generate GIS equipment abnormal fault classification results;

Based on the abnormal fault classification results of GIS equipment, closed-loop feedback control is performed to generate a GIS closed-loop feedback control strategy; according to the GIS closed-loop feedback control strategy, abnormal regulation is performed on the GIS equipment abnormal identification data to perform normal operation monitoring of GIS equipment.

The present invention can obtain the state operation analysis data of the GIS equipment by importing the real-time chromaticity spectrum into the first operation state analysis model for analysis. These data provide a comprehensive evaluation of the current operation state of the GIS equipment, including the calculation results of various key parameters and indicators. By performing abnormal identification on the state operation analysis data of the GIS equipment, the existing abnormal conditions of the equipment can be detected. Further, the abnormal data is classified, and different types of abnormal faults are distinguished and classified. This helps to discover equipment problems in advance and carry out timely maintenance and processing. Based on the classification results of the abnormal faults of the GIS equipment, a closed-loop feedback control strategy can be established. The strategy can provide corresponding control schemes and operation guidance according to different abnormal conditions and fault types to ensure the normal operation of the GIS equipment. Such strategy generation is an intelligent decision based on the analysis results, which can improve the efficiency of equipment maintenance and management. By using the abnormal identification data of the GIS equipment for abnormal regulation, corresponding measures and adjustments can be taken for the detected abnormal conditions. This helps to improve the operation state of the equipment and avoid further faults. At the same time, by monitoring and analyzing the abnormal identification data, the normal operation of the GIS equipment can be monitored in real time, and potential problems can be discovered and solved in time.

In an embodiment of the present invention, the GIS equipment state operation analysis is performed by importing the real-time chromaticity spectrum into the first operation state analysis model, involving technologies such as image processing, pattern recognition and machine learning, so as to extract features from the chromaticity spectrum and perform state analysis. Generate GIS equipment state operation analysis data, including equipment operation status and performance characteristics. Perform abnormal identification on the GIS equipment state operation analysis data. This can be done by setting a threshold or using a supervised learning method to identify abnormal states. The abnormal identification result includes information such as the location, type and degree of the abnormality, and generates GIS equipment abnormal identification data. The GIS equipment state operation analysis data is abnormally classified using the GIS equipment abnormal identification data, involving the use of expert rules, machine learning algorithms or deep learning models to classify the abnormalities. The abnormal classification result includes information such as the abnormality type, cause, and impact, and generates a GIS equipment abnormal fault classification result. Based on the GIS equipment abnormal fault classification result, a closed-loop feedback control strategy is designed. This includes determining the abnormal handling method, adjusting equipment parameters, or taking other measures to deal with abnormal situations to ensure the normal operation of the equipment. According to the closed-loop feedback control strategy, the abnormal identification data of GIS equipment is regulated abnormally, including sending alarms, adjusting equipment parameters, starting backup equipment, and real-time monitoring of the equipment's operating conditions to ensure that the equipment can still operate normally under abnormal circumstances.

In this specification, a device monitoring system based on chromaticity spectrum mapping is provided, which is used to execute the above-mentioned device monitoring method based on chromaticity spectrum mapping. The device monitoring system based on chromaticity spectrum mapping includes:

The vibration information analysis module is used to collect the real-time vibration information of GIS equipment and perform time-frequency conversion analysis on the real-time vibration information using complex Gabor-Morlet wavelet transform to obtain the real-time sub-vibration feature set;

A chromaticity spectrum generation module is used to perform a single feature analysis on the real-time sub-vibration feature set to generate a single feature analysis result; perform chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

The operation status analysis module is used to construct a first operation status analysis model; based on the first operation status analysis model, component status analysis is performed on the real-time chromaticity spectrum to obtain real-time device component status data of the GIS device.

The beneficial effect of the present invention is that by collecting the real-time vibration information of GIS equipment and using the complex Gabor-Morlet wavelet transform for time-frequency conversion analysis, efficient processing and analysis of vibration signals can be achieved. This helps to timely discover abnormal vibration conditions of the equipment and warn of possible faults in advance. Single feature analysis is performed on the real-time sub-vibration feature set, and a chromaticity spectrum is generated, which can intuitively display the vibration characteristics and state changes of the equipment. This helps engineers and operators to understand the operating status of the equipment more quickly, perform fault diagnosis and maintenance. By constructing a first operating status analysis model, the component status analysis of the real-time chromaticity spectrum can be systematically performed, and the real-time equipment component status data of the equipment can be further extracted. This helps to establish an equipment status monitoring and prediction model to achieve intelligent management and optimized maintenance of the equipment status. Based on the above analysis results, real-time monitoring and analysis of the operating status of GIS equipment can be achieved, abnormal status and potential faults of the equipment can be discovered in time, so as to warn in advance and take corresponding maintenance measures, reduce the equipment failure rate, and extend the life of the equipment. By implementing the above analysis and prediction model, accurate maintenance of GIS equipment can be achieved, unnecessary maintenance and downtime can be avoided, maintenance costs can be reduced, and the reliability and stability of the equipment can be improved.

Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims (10)

1. The device monitoring method based on the chromaticity spectrum mapping is characterized by comprising the following steps of:

Step S1: collecting real-time vibration information of GIS equipment, performing time-frequency conversion analysis on the real-time vibration information by utilizing complex Gabor-Morlet wavelet transformation, and performing time-frequency conversion analysis on the real-time vibration information to obtain a real-time sub-vibration feature set;

Step S2: performing single characteristic analysis on the real-time sub-vibration characteristic set to generate a single characteristic analysis result; performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

step S3: constructing a first running state analysis model; and carrying out component state analysis on the real-time chromaticity diagram based on the first running state analysis model to obtain real-time equipment component state data of the GIS equipment.

2. The apparatus monitoring method based on chromaticity diagram mapping as recited in claim 1, wherein chromaticity diagram mapping the real-time sub-vibration feature set based on single feature analysis results in step S2 comprises:

performing fast Fourier transform on the real-time sub-vibration feature set to generate a vibration pitch spectrogram;

Extracting frequency components from the vibration pitch spectrogram to obtain vibration frequency components; mapping the chromaticity orders of the vibration frequency components, and normalizing the mapping results to generate vibration chromaticity order data;

and carrying out corresponding frequency band amplitude accumulation on the vibration frequency components according to the vibration chromaticity order data, thereby obtaining a real-time chromaticity spectrum.

3. The chromaticity-mapping-based device monitoring method as recited in claim 1, wherein constructing a first operational state analysis model in step S3 comprises:

acquiring historical vibration information and historical maintenance logs of GIS equipment;

Performing time-frequency conversion analysis on the historical vibration information to obtain a plurality of historical sub-vibration feature sets, and performing chromaticity spectrum mapping on the historical sub-vibration feature sets to generate a historical chromaticity spectrum;

performing maintenance time sequence analysis on the historical maintenance log to determine the historical equipment part running state data of different time nodes;

performing time corresponding correlation on the historical chromaticity diagram and the running state data of the historical equipment part based on different time nodes to obtain a time correlated historical chromaticity diagram;

carrying out data set division on the time-associated historical chromatograms and the running state data of the historical equipment parts to generate a model training set and a model testing set;

Performing model training on the model training set by using a LeNet-5 neural network algorithm to generate a first running state training model; and carrying out model optimization iteration on the first running state training model by using the model test set so as to generate a first running state analysis model.

4. The chromaticity-mapping-based device monitoring method as recited in claim 3, wherein obtaining historical vibration information and historical maintenance log of a GIS device comprises:

applying preset faults to the GIS equipment, and acquiring historical vibration information data of the GIS equipment by using a vibration sensor after applying the preset faults each time;

Performing fault maintenance on the GIS equipment based on the historical vibration information data to obtain historical maintenance data;

and uploading the data log of the historical overhaul data by using the cloud platform, so as to obtain the historical overhaul log.

5. The chromaticity-map-based device monitoring method as recited in claim 3, wherein performing model optimization iterations on the first operational state training model using a model test set comprises:

Establishing a real-time vibration acquisition time line according to real-time vibration information of GIS equipment, and marking time points of the real-time vibration acquisition time line based on a preset time interval to generate a re-detection point;

Performing time point vibration information extraction on the real-time vibration acquisition time line according to the adjacent re-detection points to obtain first vibration information extraction data and second vibration information extraction data; repeating vibration section discrimination is carried out on the first vibration information extraction data and the second vibration information extraction data, and when no repeating vibration information section is determined, chromaticity spectrum mapping is carried out according to the first vibration information extraction data and the second vibration information extraction data without the repeating information section, so that a first chromaticity spectrum and a second chromaticity spectrum are generated;

performing spectrum joint analysis on the first chromaticity spectrum and the second chromaticity spectrum to generate a joint analysis spectrum group;

Performing comparison analysis on each chromaticity spectrum of the combined analysis spectrum set, constructing a vibration comparison chromaticity spectrum based on the comparison analysis result, and performing vibration accuracy characteristic analysis on the vibration comparison chromaticity spectrum to generate vibration chromaticity spectrum accuracy characteristic data;

Performing model optimization strategy construction on the first running state training model based on the vibration chromaticity spectrum accuracy characteristic data to generate a model optimization strategy;

and carrying out model optimization iteration on the first running state training model by using the model test set according to the model optimization strategy, thereby generating a first running state analysis model.

6. The chromaticity spectrum mapping-based device monitoring method as recited in claim 5, wherein the performing each chromaticity spectrum map comparison analysis on the set of combined analysis spectra and performing vibration accuracy feature analysis on the vibration comparison chromaticity spectra comprises:

Establishing a chromaticity acquisition point acquisition rule, and carrying out point chromaticity acquisition on a first chromaticity spectrum and a second chromaticity spectrum in the joint analysis spectrum group according to the chromaticity acquisition point acquisition rule to obtain chromaticity spectrum point chromaticity; chromaticity information recording is carried out on chromaticity spectrogram point chromaticity to generate chromaticity spectrum acquisition point information data, wherein the chromaticity information recording comprises chromaticity recording and position recording of acquisition points, and the chromaticity spectrum acquisition point information data comprises first chromaticity spectrum acquisition point information data of a first chromaticity spectrum and second chromaticity spectrum acquisition point information data of a second chromaticity spectrum;

performing chromaticity difference analysis on the chromaticity spectrum acquisition point information data to generate a first chromaticity acquisition point difference amount and a second chromaticity acquisition point difference amount;

comparing the difference between the first chromaticity acquisition point difference and the second chromaticity acquisition point difference with a preset chromaticity acquisition difference threshold, and if the difference between the first chromaticity acquisition point difference and the second chromaticity acquisition point difference is smaller than the preset chromaticity acquisition difference threshold, calculating the average value of the difference between the first chromaticity acquisition point difference and the second chromaticity acquisition point difference to obtain the average value of the difference between the chromaticity acquisition points; performing corresponding chromaticity replacement on the block with the difference in chromaticity in the joint analysis map set by using the average value of the chromaticity acquisition point difference quantity, so as to obtain a vibration contrast chromaticity map;

And carrying out vibration accuracy characteristic analysis on the vibration contrast chromaticity diagram based on the first acquisition point difference quantity and the second acquisition point difference quantity, and generating vibration chromaticity diagram accuracy characteristic data.

7. The method for monitoring a device based on chromaticity diagram mapping as recited in claim 6, wherein establishing chromaticity acquisition point acquisition rules, and performing point chromaticity acquisition on the first chromaticity diagram and the second chromaticity diagram in the joint analysis diagram group according to the chromaticity acquisition point acquisition rules comprises:

Acquiring acquisition point sequence and information of intervals between adjacent acquisition points to the joint analysis map set to obtain acquisition point sequence data and adjacent acquisition point interval information data; sorting the acquisition points according to the acquisition point sequence data and the adjacent acquisition point interval information data to generate an acquisition point sequence;

performing random scanning mapping analysis on the first chromaticity diagram and the second chromaticity diagram in the joint analysis diagram set according to the acquisition point sequence, and recording analysis results to obtain first chromaticity record data and second chromaticity record data; performing chroma sequencing on the first chroma recording data and the second chroma recording data to generate a chroma reference sequence;

Performing a plurality of chromaticity scanning mapping analyses on the rest of the maps except the first chromaticity map and the second chromaticity map in the joint analysis map set according to the acquisition point sequence, and transforming the positions of the first acquisition point in the acquisition point sequence of the rest of the maps except the first chromaticity map and the second chromaticity map in the joint analysis map set relative to the first chromaticity map and the second chromaticity map during each scanning mapping analysis to generate a plurality of chromaticity comparison sequences;

Calculating the chromaticity similarity between each chromaticity comparison sequence and the chromaticity reference sequence to obtain chromaticity comparison similarity; carrying out sequence information marking on a chromaticity comparison sequence corresponding to a chromaticity comparison similarity degree larger than a preset similarity threshold value, so as to generate a chromaticity acquisition point acquisition rule;

And carrying out point chromaticity acquisition on the first chromaticity spectrum and the second chromaticity spectrum in the joint analysis spectrum group according to a chromaticity acquisition point acquisition rule to obtain chromaticity spectrum point chromaticity.

8. The chromaticity diagram-mapping-based device monitoring method as recited in claim 6, wherein performing a vibration-contrast chromaticity diagram based on the first and second collection point variance amounts includes:

performing vibration accuracy characteristic calculation on the vibration contrast chromaticity diagram based on the first acquisition point difference quantity and the second acquisition point difference quantity by utilizing an accuracy characteristic formula to obtain vibration chromaticity diagram accuracy characteristic data;

The accuracy characteristic formula is specifically shown as follows:

Wherein J is a corresponding value of the precision characteristic between real-time chromaticity-patterns, k ₁ is a precision conversion coefficient, c ₁ is a first acquisition point position adjustment coefficient, x ₁ is a first acquisition point difference amount, Δx ₁ is a first acquisition point difference standard amount, c ₂ is a second acquisition point position adjustment coefficient, x ₂ is a second acquisition point difference amount, Δx ₂ is a second acquisition point difference standard amount, b ₁ is a first acquisition point chromaticity adjustment constant, and b ₂ is a second acquisition point chromaticity adjustment constant.

9. The chromaticity-mapping-based device monitoring method as recited in claim 1, wherein performing component state analysis on the real-time chromaticity-spectrum based on the first operational state analysis model in step S3 comprises:

Importing the real-time chromaticity diagram into a first running state analysis model to perform GIS equipment state running analysis, and generating GIS equipment state running analysis data;

Performing equipment anomaly identification on GIS equipment state operation analysis data to generate GIS equipment anomaly identification data; carrying out abnormal classification on the GIS equipment state operation analysis data by utilizing GIS equipment abnormal identification data to generate GIS equipment abnormal fault classification results;

Performing closed-loop feedback control based on the GIS equipment abnormal fault classification result to generate a GIS closed-loop feedback control strategy; and carrying out abnormal regulation and control on the abnormal identification data of the GIS equipment according to the GIS closed-loop feedback control strategy so as to execute monitoring of normal operation of the GIS equipment.

10. A chromaticity-mapping-based device monitoring system for performing the chromaticity-mapping-based device monitoring method as recited in claim 1, the chromaticity-mapping-based device monitoring system comprising:

The vibration information analysis module is used for collecting real-time vibration information of the GIS equipment, performing time-frequency conversion analysis on the real-time vibration information by utilizing complex Gabor-Morlet wavelet transformation, and performing time-frequency conversion analysis on the real-time vibration information to obtain a real-time sub-vibration characteristic set;

the chromaticity spectrum generation module is used for carrying out single characteristic analysis on the real-time sub-vibration characteristic set to generate a single characteristic analysis result; performing chromaticity spectrum mapping on the real-time sub-vibration feature set according to the single feature analysis result to generate a real-time chromaticity spectrum;

The running state analysis module is used for constructing a first running state analysis model; and carrying out component state analysis on the real-time chromaticity diagram based on the first running state analysis model to obtain real-time equipment component state data of the GIS equipment.