CN117334020B - Equipment operation fault prediction system and method of intelligent sand mill - Google Patents
Equipment operation fault prediction system and method of intelligent sand mill Download PDFInfo
- Publication number
- CN117334020B CN117334020B CN202311380953.0A CN202311380953A CN117334020B CN 117334020 B CN117334020 B CN 117334020B CN 202311380953 A CN202311380953 A CN 202311380953A CN 117334020 B CN117334020 B CN 117334020B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- operation parameter
- topology
- consistency
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/185—Electrical failure alarms
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Emergency Management (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Probability & Statistics with Applications (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Crushing And Grinding (AREA)
Abstract
The invention discloses a device operation fault prediction system and method of an intelligent sand mill, which are characterized in that a plurality of operation parameters of the sand mill are collected, including a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency, a machine sealing cylinder pressure difference and the like, and a data processing and analyzing algorithm is introduced at the rear end to carry out time sequence association analysis on the operation parameters of the sand mill, so that whether the operation state of the sand mill is abnormal or not is judged, and an early warning prompt is sent out when the abnormality is detected.
Description
Technical Field
The invention relates to the technical field of intelligent prediction, in particular to a device operation fault prediction system and method of an intelligent sand mill.
Background
ALC-3900L moxa mill is a machine for continuously dispersing and superfine grinding solid materials in liquid, and is suitable for secondary and tertiary regrinding operation of nonferrous metal concentrating mills (gold, copper, lead, zinc, molybdenum and nickel) and ferrous metal concentrating mills. During operation of the sander, equipment may experience various failures due to prolonged high-intensity work and wear of materials, such as bearing damage, seal failure, motor overload, etc., which may not only result in equipment downtime for maintenance, but also may cause interruption and loss of production lines.
Conventional sand mill equipment failure detection systems typically focus only on static parameter values of the sand mill, and ignore dynamic variation characteristics of the parameters. However, during operation of the sander, the parameter values will change over time, and these dynamic features are of great importance for fault detection and early warning. In addition, conventional fault detection systems typically perform threshold analysis based on a few predefined operating parameters to perform fault detection, such as host operating frequency, feed operating frequency, and the like. Such parameter selection limitations may not fully reflect the operational status of the device, resulting in inaccurate and timely detection of some potential faults. In addition, in the conventional system, each operation parameter of the sand mill is usually used as an independent index to perform fault detection, and the correlation between the parameters is ignored. In practice, there are complex interactions and dependencies between the individual parameters of the sander. For example, there may be some correlation between the host operating frequency and the feed operating frequency, and merely considering their individual values may not accurately determine the operating state of the device, resulting in an inaccurate or false positive determination of the fault.
Accordingly, an optimized intelligent sander equipment operation failure prediction system is desired.
Disclosure of Invention
The embodiment of the invention provides a device operation fault prediction system and method of an intelligent sand mill, wherein the device operation fault prediction system and method is characterized in that by collecting a plurality of operation parameters of the sand mill, including a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency, a machine sealing cylinder pressure difference and the like, and introducing a data processing and analysis algorithm at the rear end to perform time sequence association analysis on the operation parameters of the sand mill, whether the operation state of the sand mill is abnormal or not is judged, and an early warning prompt is sent out when the abnormality is detected.
The embodiment of the invention also provides a device operation fault prediction method of the intelligent sand mill, which comprises the following steps:
acquiring operation parameters of a sand mill to be detected at a plurality of preset time points within a preset time period, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference;
Arranging the operation parameters of the plurality of preset time points into operation parameter time sequence input matrixes according to a time dimension and a sample dimension;
performing inter-parameter time sequence correlation characteristic analysis on the operation parameter time sequence input matrix to obtain operation parameter global time sequence characteristics;
And determining whether to generate a fault early warning prompt based on the global time sequence characteristic of the operation parameter.
The embodiment of the invention also provides a device operation fault prediction system of the intelligent sand mill, which comprises:
The system comprises a parameter acquisition module, a control module and a control module, wherein the parameter acquisition module is used for acquiring operation parameters of a sand mill to be detected at a plurality of preset time points in a preset time period, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference;
The matrix arrangement module is used for arranging the operation parameters of the plurality of preset time points into operation parameter time sequence input matrixes according to the time dimension and the sample dimension;
The correlation characteristic analysis module is used for carrying out inter-parameter time sequence correlation characteristic analysis on the operation parameter time sequence input matrix so as to obtain operation parameter global time sequence characteristics;
And the fault early warning prompt generation module is used for determining whether to generate a fault early warning prompt or not based on the global time sequence characteristics of the operation parameters.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1A is a schematic diagram of a working principle of an mugwort grinding machine according to an embodiment of the present invention.
Fig. 1B is a schematic structural diagram of an mugwort grinding machine according to an embodiment of the present invention.
Fig. 2 is a flowchart of a device operation fault prediction method of an intelligent sand mill according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a system architecture of a device operation failure prediction method of an intelligent sand mill according to an embodiment of the present invention.
Fig. 4 is a flowchart of the substeps of step 130 in a method for predicting equipment operation failure of an intelligent sand mill according to an embodiment of the present invention.
Fig. 5 is a block diagram of an equipment operation failure prediction system of an intelligent sand mill provided in an embodiment of the invention.
Fig. 6 is an application scenario diagram of a device operation fault prediction method of an intelligent sand mill provided in an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the embodiments of the invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the present invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present invention.
In describing embodiments of the present invention, unless otherwise indicated and limited thereto, the term "connected" should be construed broadly, for example, it may be an electrical connection, or may be a communication between two elements, or may be a direct connection, or may be an indirect connection via an intermediate medium, and it will be understood by those skilled in the art that the specific meaning of the term may be interpreted according to circumstances.
It should be noted that, the term "first\second\third" related to the embodiment of the present invention is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that embodiments of the invention described herein may be practiced in sequences other than those illustrated or described herein.
In the invention, an ALC-3900L moxa sand mill is a machine for continuously dispersing and superfine grinding solid materials in liquid, has the structure and operation characteristics shown in figure 1A, and is suitable for secondary and tertiary regrinding operation of nonferrous metal concentrating mills (gold, copper, lead, zinc, molybdenum and nickel) and ferrous metal concentrating mills. The content of 200 meshes (74 micrometers) in the open circuit grinding product can reach 70-100% as required, and the equipment processing capacity can reach 20-100 tons per hour (depending on the type and fineness requirements of the ore).
As shown in fig. 1B, the moxa sand mill comprises a main motor 1, a speed reducer 2, a shaft seat 3, a feed inlet 4, a main shaft 5, a stirring disc 6, a classifying wheel 7, a cylinder 8, a discharge pipe 9 and the like, wherein the cylinder 8 of the mill can translate along the axial direction of a rail, and the operation is convenient during maintenance, so that the working efficiency is improved. The working part of the mugwort sand mill consists of a main shaft 5, a plurality of stirring discs 6 which are connected in parallel and in series on the shaft and a grading disc at the tail end, and the working principle is that the stirring discs 6 are driven by the main shaft 5 to rotate at high speed, ore pulp after slag separation is stably input into the mill, the stirring discs 6 drive ore grinding media and ore pulp in the cylinder 8 to move axially and spirally and automatically, and minerals and the ore grinding media are radially distributed from the mill shaft to the inner wall of the cylinder 8 according to the particle size under the centrifugal force generated by the high-speed rotation and the violent stirring action of the stirring discs 6, so that the selective ore grinding of large-medium large-particle minerals and small-particle minerals is realized. In addition, an independent ore grinding area is arranged between every two stirring discs 6, and ore pulp particles are finer after the ore pulp particles are subjected to certain ore feeding pressure, so that a new process of internal grading and open-circuit ore grinding is realized.
The speed of the main shaft 5 of the moxa-sand mill is controlled by a frequency conversion system, the rotating speed can be regulated steplessly, the speed of the main shaft 5 determines the kinetic energy of ore grinding, and the fineness of the product is directly influenced; the flow of the ore pulp material is controlled and regulated by a feed pump through a frequency converter, and the flow determines the residence time of the material in the grinding cavity, so that the fineness of the product is directly influenced; in addition, the higher the filling rate of the grinding medium, the better the grinding efficiency; therefore, aiming at a plurality of different materials, different grinding effects can be obtained by adjusting the rotating speed of the main shaft 5, the filling rate of the grinding medium and the feeding amount per unit time so as to meet the process requirements.
The Ai Shamo machine can ensure the optimal recovery rate of magnetic, heavy, floating and leaching operations based on the internal grading and selective grinding principle. Compared with a single ball mill using a grinding medium of 40 mm, the electric charge is saved by more than 30% when the grinding ore dressing roughing concentrate is ground by using the grinding medium of 2-6 mm. The moxa sand mill is a key technology for developing low-grade, multi-metal symbiosis and fine-grained kanban mineral resources, and is proved in the wide application of foreign metal mines for more than 20 years.
The moxa sand mill has the following advantages: the open circuit grinding is simple in process; selectively grinding, and having narrow particle size distribution; the grinding efficiency is high, energy and ball saving and consumption reduction; the device has compact structure and simple operation and maintenance.
However, conventional systems typically only focus on the static parameter values of the sander, ignoring the dynamic nature of the parameter over time. During the operation of the sander, the parameter values will change with time, these dynamic features have significance for fault detection and early warning, and ignoring the dynamic features may result in inaccurate and timely fault detection.
Conventional systems typically perform threshold analysis based on a few predefined operating parameters, such as host operating frequency, feed operating frequency, etc., and such parameter selection limitations may not fully reflect the operating state of the device, resulting in inaccurate and timely detection of some potential faults. For such complex equipment of a sand mill, the operation of the equipment may not be fully known by only relying on a few parameters.
Conventional systems typically use individual operating parameters of the sander as independent indicators for fault detection, ignoring the correlation between the parameters. In fact, there are complex interactions and dependencies between the parameters of the sander, for example, there may be a certain correlation between the operating frequency of the main machine and the frequency of the feeding operation, and considering only their individual values may not accurately determine the operating state of the apparatus, resulting in an inaccurate determination of the fault or a false alarm.
Conventional systems typically require manual thresholding and parameter analysis, and lack the ability to be intelligent and automated, which is not efficient and reliable enough for sand mill monitoring in a mass production environment. Modern fault detection systems should have intelligent capabilities, and can automatically learn and adapt to the operation characteristics of the equipment, so as to realize automatic fault detection and early warning.
The traditional sand mill equipment operation fault detection system has the defects of neglecting dynamic characteristics, limiting parameter selection, neglecting the correlation among parameters, lacking intelligent and automatic capabilities and the like. To overcome these problems, new generation fault detection systems should focus on analysis of dynamic characteristics, integrate information of multiple parameters, consider correlations between parameters, and have intelligent and automated capabilities.
In one embodiment of the present invention, fig. 2 is a flowchart of a method for predicting equipment operation failure of an intelligent sand mill according to an embodiment of the present invention. Fig. 3 is a schematic diagram of a system architecture of a device operation failure prediction method of an intelligent sand mill according to an embodiment of the present invention. As shown in fig. 2 and 3, the equipment operation failure prediction method of the intelligent sand mill according to the embodiment of the invention comprises the following steps: 110, acquiring operation parameters of a sand mill to be detected at a plurality of preset time points in a preset time period, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference; 120, arranging the operation parameters of the plurality of preset time points into an operation parameter time sequence input matrix according to a time dimension and a sample dimension; 130, performing inter-parameter time sequence correlation feature analysis on the operation parameter time sequence input matrix to obtain an operation parameter global time sequence feature; 140, determining whether to generate a fault early warning prompt based on the operation parameter global time sequence characteristic.
In the step 110, the operation parameters of the sand mill to be detected at a plurality of preset time points within a preset time period are obtained, so that accurate operation parameter data are ensured to be obtained, the data can be acquired through a sensor or an equipment monitoring system, and the frequency and the time point of data acquisition are enough to meet the monitoring requirement on the operation state of the sand mill. The operation parameter data of a plurality of time points are acquired, and basic data are provided for subsequent fault detection and early warning.
In the step 120, the operation parameters of the plurality of predetermined time points are arranged into an operation parameter time sequence input matrix according to the time dimension and the sample dimension, so that the operation parameters of different time points are arranged according to a correct sequence, so as to construct an accurate time sequence input matrix, and data can be organized in a form of a matrix or a data frame, so that consistency of a data structure is ensured, and the data structure is easy to process. The time sequence input matrix is constructed, so that operation parameter data of a plurality of time points are integrated, and subsequent parameter analysis and feature extraction are facilitated.
In the step 130, inter-parameter timing correlation feature analysis is performed on the operation parameter timing input matrix to obtain an operation parameter global timing feature. By means of a proper statistical analysis method, a time sequence analysis method or a machine learning method, characteristic analysis is carried out on the time sequence input matrix of the operation parameters, time sequence relativity and global time sequence characteristics among different parameters are explored, and methods such as correlation analysis, spectrum analysis and a time sequence model can be considered. The mutual influence and the dependency relationship among different parameters can be revealed through the time sequence correlation characteristic analysis among the parameters, the global time sequence characteristic is extracted, and a more accurate basis is provided for subsequent fault early warning.
In step 140, it is determined whether a fault warning cue is generated based on the operating parameter global timing characteristic. According to a preset fault judging rule, threshold or model, and by combining with the global time sequence characteristics of the operation parameters, judging whether the sand mill has faults or not, and generating corresponding early warning prompts, a rule engine, a machine learning model or other fault judging algorithms can be used for judging. The fault early warning is carried out based on the global time sequence characteristics, so that the accuracy and timeliness of fault detection can be improved, potential faults can be found early, and the downtime and production loss are reduced.
By acquiring operation parameters, constructing a time sequence input matrix, analyzing time sequence correlation characteristics among parameters and performing fault early warning based on global time sequence characteristics, the fault detection capability of sand mill equipment can be improved, timely measures can be taken to maintain and repair, and the production efficiency and the product quality are improved.
Aiming at the technical problems, the technical conception of the invention is that by collecting a plurality of operation parameters of the sand mill, including a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency, a machine sealing cylinder pressure difference and the like, and introducing a data processing and analyzing algorithm at the rear end to carry out time sequence correlation analysis on the operation parameters of the sand mill, judging whether the operation state of the sand mill is abnormal or not, and sending an early warning prompt when the abnormality is detected, the invention can realize automatic detection and early warning of the working state of the sand mill, thereby improving the reliability and stability of sand mill equipment, reducing the downtime and production loss caused by faults, and improving the production efficiency and the product quality.
Specifically, in the technical scheme of the invention, firstly, the operation parameters of the sand mill to be detected at a plurality of preset time points in a preset time period are obtained, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference.
The main machine operation frequency refers to the operation frequency of a main motor of the sand mill, usually in units of hertz (Hz), the main machine operation frequency can reflect the operation state and the rotation speed of the main motor, and is one of important indexes of the normal operation of the sand mill, and abnormal main machine operation frequency may mean motor faults or other problems.
The feed operating frequency refers to the operating frequency of the sander feeder, typically in hertz (Hz), which reflects the operational status and feed rate of the feeder, and plays an important role in the sand feed of the sander, and abnormal feed operating frequencies may lead to unstable operation or yield degradation of the sander.
The main machine protection pressure refers to a pressure threshold value set by a protection device of a main motor of the sand mill. When the host operates, if the current or temperature of the main motor exceeds a set threshold value, the host protecting device can trigger and stop the operation of the main motor to protect the main motor from being damaged, and the host protecting pressure can be used for monitoring the working state of the main motor and the normal operation of the protecting device.
The machine sealing pressure refers to a pressure value set when the sand mill is started, the machine sealing is a key component for preventing the leakage of materials in the sand mill and the entry of external impurities, and the machine sealing pressure can reflect the sealing performance and normal starting operation of a machine sealing system.
The machine seal operating frequency refers to the operating frequency of the sand mill, typically in hertz (Hz), and may reflect the operating state and operating speed of the machine seal system, and abnormal machine seal operating frequency may mean a failure or abnormality of the machine seal system.
The differential pressure of the machine seal cylinder refers to the differential pressure of two sides of the sand mill seal cylinder. The machine seal cylinder differential pressure can be used to monitor the sealing performance of the machine seal system and the working state of the machine seal cylinder, and abnormal machine seal cylinder differential pressure can mean leakage or other problems of the machine seal system.
By acquiring and monitoring the operation parameters, the working state and performance of the sand mill can be comprehensively known, abnormal conditions can be timely found, fault detection and early warning can be carried out, and the reliability, the production efficiency and the product quality of the sand mill can be improved.
Next, considering that the operation parameter data of the sand mill to be detected has a time-sequential cooperative association relationship in the time dimension, in order to more accurately detect the operation state of the sand mill, the operation parameters of the plurality of predetermined time points need to be arranged into an operation parameter time sequence input matrix according to the time dimension and the sample dimension, so as to integrate the distribution information of the operation parameters of the sand mill in the time dimension and the sample dimension.
Fig. 4 is a flowchart of the substeps of step 130 in a method for predicting equipment operation failure of an intelligent sand mill according to an embodiment of the present invention. As shown in fig. 4, performing inter-parameter timing correlation feature analysis on the operation parameter timing input matrix to obtain an operation parameter global timing feature, including: 131, performing matrix partitioning processing on the operation parameter time sequence input matrix, and then obtaining a sequence of operation parameter local time sequence semantic feature vectors through a ViT model comprising an embedded layer; 132, performing consistency association analysis on the sequence of the operation parameter local time sequence semantic feature vector to obtain an operation parameter consistency topological feature matrix; and 133, performing association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature.
Further, feature mining of the operational parameter timing input matrix is performed using a convolutional neural network model with excellent performance in terms of data implicitly-correlated feature extraction, but pure CNN methods have difficulty in learning explicit global and remote semantic information interactions due to inherent limitations of convolutional operations. And, it is also considered that the operation parameter time sequence collaborative correlation characteristics related to the sand mill in the operation parameter time sequence input matrix have different correlation relations in each local time sequence and each operation parameter sample dimension. Therefore, in the technical scheme of the invention, in order to more fully capture and characterize the relevant characteristics of each operation parameter of the sand mill in the time dimension, the operation parameter time sequence input matrix is further subjected to matrix partitioning processing and then is encoded in a ViT model comprising an embedded layer, so that relevant characteristic information of each operation parameter of the sand mill in the time dimension in each local matrix block of the operation parameter time sequence input matrix is extracted, and a sequence of operation parameter local time sequence semantic characteristic vectors is obtained.
In one embodiment of the present invention, performing a consistency correlation analysis on the sequence of the operation parameter local time sequence semantic feature vectors to obtain an operation parameter consistency topology feature matrix, including: calculating cosine similarity between any two operation parameter local time sequence semantic feature vectors in the sequence of the operation parameter local time sequence semantic feature vectors to obtain an operation parameter consistency topology matrix; and extracting the characteristics of the operation parameter consistency topology matrix by a topology characteristic extractor based on a deep neural network model to obtain the operation parameter consistency topology characteristic matrix.
The deep neural network model is a convolutional neural network model.
Then, it is considered that there is an association relationship based on the entirety of the operation parameter time series input matrix between the respective operation parameter local time series association characteristic information about the sand mill in each local matrix block of the operation parameter time series input matrix. And, it is also considered that if the operation state of the sander is normal, there is a correlation feature having consistency between local time-series correlation feature information on each operation parameter of the sander in each local time period. Therefore, in the technical scheme of the invention, the cosine similarity between any two operation parameter local time sequence semantic feature vectors in the sequence of the operation parameter local time sequence semantic feature vectors is further calculated to obtain the operation parameter consistency topology matrix.
And then, carrying out feature mining on the operation parameter consistency topology matrix in a topology feature extractor based on a convolutional neural network model so as to extract consistency association topology feature information of each operation parameter of the sand mill in a time dimension and a sample dimension, thereby obtaining the operation parameter consistency topology feature matrix.
In one embodiment of the present invention, performing graph structure-based association encoding on the sequence of the operation parameter local time sequence semantic feature vectors and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature, including: and passing the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topological feature matrix through a graph neural network model to obtain the consistency topological operation parameter global time sequence feature matrix.
And taking each operation parameter local time sequence semantic feature vector in the sequence of operation parameter local time sequence semantic feature vectors as the feature representation of the node, taking the operation parameter consistency topological feature matrix as the feature representation of the edge between the nodes, and obtaining the operation parameter time sequence semantic feature matrix obtained by two-dimensionally arranging the operation parameter local time sequence semantic feature vectors and the operation parameter consistency topological feature matrix through a graph neural network model so as to obtain a consistency topological operation parameter global time sequence feature matrix. Specifically, the graph neural network model performs graph structure data coding on the operation parameter time sequence semantic feature matrix and the operation parameter consistency topological feature matrix through a learnable neural network parameter to obtain a consistency topological operation parameter global time sequence feature matrix containing irregular operation parameter local time sequence consistency topological association features of the sand mill and local time sequence association feature information of each operation parameter.
In one embodiment of the present invention, determining whether to generate a fault warning hint based on the operational parameter global timing feature includes: expanding the global time sequence feature matrix of the consistent topology operation parameters into global time sequence feature vectors of the consistent topology operation parameters; optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter; the global time sequence feature vector of the optimized consistency topology operation parameter passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the sand mill to be detected is abnormal or not; and generating a fault early warning prompt based on the classification result.
In the technical scheme of the application, when the sequence of the operation parameter local time sequence semantic feature vectors and the operation parameter consistency topological feature matrix are used for obtaining the consistency topological operation parameter global time sequence feature matrix through a graph neural network model, each row feature vector of the consistency topological operation parameter global time sequence feature matrix can express the cross-space context association expression of the cross-space association feature of the operation parameter under the local time sequence-sample cross dimension space, and further the topological association expression under the space pre-similarity topology, therefore, if the cross-space context association feature under the single cross dimension space is used as a foreground object feature, the graph neural network model can also introduce background distribution noise when introducing the cross-space topological association expression, and simultaneously, the error space probability of the cross-space association feature matrix relative to the sequence of the operation parameter local time sequence feature vector is caused by the space heterogeneous distribution of the high-dimensional feature under each local time sequence-sample cross dimension space, so that the consistency topological operation parameter global time sequence feature matrix is mapped by the cross-space, and the error probability of the cross-space feature matrix is subjected to the overall time sequence feature matrix is subjected to the high-rank distribution expression, and the overall time sequence feature matrix is subjected to the high-rank distribution representation, and the error probability of the overall time sequence feature matrix is subjected to the overall time sequence feature, and the overall time sequence feature matrix is subjected to the overall time sequence feature, and the overall time sequence feature is subjected to the overall time sequence feature, and the overall sequence feature is subjected to the high-sequence feature, and the overall sequence feature, and the high probability is subjected to the overall sequence feature, and the high probability and the overall sequence feature, and the high probability.
Therefore, preferably, when the global time sequence feature matrix of the consistent topology operation parameter is subjected to classification training through a classifier, each feature value of the global time sequence feature vector of the consistent topology operation parameter obtained by expanding the global time sequence feature matrix of the consistent topology operation parameter is optimized, which is specifically expressed as: optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter by using the following optimization formula to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter; wherein, the optimization formula is:
Wherein V is the global timing feature vector of the consistent topology operating parameter, V i and V j are the ith and jth feature values of the global timing feature vector of the consistent topology operating parameter, and Is the global feature mean value of the global time sequence feature vector of the consistent topology operation parameter, and v' i is the ith feature value of the global time sequence feature vector of the optimized consistent topology operation parameter.
Specifically, aiming at the fact that the local probability density of probability density distribution in a probability space is not matched due to cross dimension space probability density mapping errors of the global time sequence feature vector of the consistent topology operation parameter in a high-dimensional feature space, global self-consistent relation of coding behaviors of the high-dimensional feature manifold of the global time sequence feature vector of the consistent topology operation parameter in the probability space is simulated through regularized global self-consistent class coding, so that error landscapes of feature manifold in a high-dimensional open space are adjusted, self-consistent matching class coding of the high-dimensional feature manifold of the global time sequence feature vector of the consistent topology operation parameter to explicit probability space is achieved, and accordingly the convergence of probability density distribution of regression probability of the global time sequence feature vector of the consistent topology operation parameter is improved, and accuracy of classification results obtained through a classifier is improved. Therefore, the automatic detection and early warning of the working state of the sand mill can be realized based on the operation parameters of the sand mill, so that the reliability and stability of the sand mill equipment are improved, the downtime and production loss caused by faults are reduced, and the production efficiency and the product quality are improved.
In one embodiment of the present invention, the global time sequence feature vector of the optimized consistent topology operation parameter is passed through a classifier to obtain a classification result, where the classification result is used to indicate whether the operation state of the sand mill to be detected is abnormal, and the method includes: performing full-connection coding on the global time sequence feature vector of the optimized consistency topology operation parameter by using a plurality of full-connection layers of the classifier to obtain a coding classification feature vector; and passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
And then, the global time sequence feature vector of the optimized consistency topology operation parameter passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the sand mill to be detected is abnormal or not. Specifically, the classification label of the classifier is a judgment label for judging whether the running state of the sand mill to be detected is abnormal, so that after the classification result is obtained, whether the running state of the sand mill is abnormal or not can be judged based on the classification result, and a fault early warning prompt is generated based on the classification result.
In conclusion, the equipment operation fault prediction method of the intelligent sand mill based on the embodiment of the invention is clarified, and the automatic detection and early warning of the working state of the sand mill can be realized, so that the reliability and stability of the sand mill equipment are improved, the downtime and production loss caused by faults are reduced, and the production efficiency and the product quality are improved.
Fig. 5 is a block diagram of an equipment operation failure prediction system of an intelligent sand mill provided in an embodiment of the invention. As shown in fig. 5, the equipment operation failure prediction system 200 of the intelligent sand mill includes: the parameter obtaining module 210 is configured to obtain operation parameters of the sand mill to be detected at a plurality of predetermined time points within a predetermined time period, where the operation parameters include a host operation frequency, a feeding operation frequency, a host protection pressure, a machine seal opening pressure, a machine seal operation frequency, and a machine seal cylinder differential pressure; a matrix arrangement module 220, configured to arrange the operation parameters of the plurality of predetermined time points into an operation parameter time sequence input matrix according to a time dimension and a sample dimension; the correlation characteristic analysis module 230 is configured to perform inter-parameter time sequence correlation characteristic analysis on the operation parameter time sequence input matrix to obtain an operation parameter global time sequence characteristic; the fault early warning prompt generation module 240 is configured to determine whether to generate a fault early warning prompt based on the global timing characteristic of the operation parameter.
In the equipment operation fault prediction system of the intelligent sand mill, the association characteristic analysis module comprises: the embedded coding unit is used for performing matrix partitioning processing on the operation parameter time sequence input matrix and then obtaining a sequence of operation parameter local time sequence semantic feature vectors through a ViT model comprising an embedded layer; the consistency association analysis unit is used for carrying out consistency association analysis on the sequence of the operation parameter local time sequence semantic feature vector so as to obtain an operation parameter consistency topological feature matrix; and the association coding unit is used for carrying out association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature.
It will be appreciated by those skilled in the art that the specific operation of the individual steps in the above-described equipment operation failure prediction system of the intelligent sand mill has been described in detail in the above description of the equipment operation failure prediction method of the intelligent sand mill with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
As described above, the apparatus operation failure prediction system 200 of the intelligent sand mill according to the embodiment of the present invention may be implemented in various terminal apparatuses, such as a server for apparatus operation failure prediction of the intelligent sand mill, and the like. In one example, the equipment operation failure prediction system 200 of the intelligent sander according to an embodiment of the present invention may be integrated into the terminal equipment as one software module and/or hardware module. For example, the intelligent sander equipment operation failure prediction system 200 may be a software module in the operating system of the terminal equipment, or may be an application developed for the terminal equipment; of course, the intelligent sander equipment failure prediction system 200 could equally be one of the numerous hardware modules of the terminal equipment.
Alternatively, in another example, the device operational failure prediction system 200 of the intelligent sander and the terminal device may be separate devices, and the device operational failure prediction system 200 of the intelligent sander may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
Fig. 6 is an application scenario diagram of a device operation fault prediction method of an intelligent sand mill provided in an embodiment of the present invention. As shown in fig. 6, in this application scenario, first, the operation parameters of the sand mill to be detected at a plurality of predetermined time points within a predetermined period of time are acquired (e.g., C as illustrated in fig. 6); the obtained operating parameters are then input into a server (e.g., S as illustrated in fig. 6) that deploys the equipment operation failure prediction algorithm of the intelligent sander, wherein the server is capable of processing the operating parameters based on the equipment operation failure prediction algorithm of the intelligent sander to determine whether a failure warning cue is generated.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (3)
1. An equipment operation fault prediction method of an intelligent sand mill is characterized by comprising the following steps:
acquiring operation parameters of a sand mill to be detected at a plurality of preset time points within a preset time period, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference;
Arranging the operation parameters of the plurality of preset time points into operation parameter time sequence input matrixes according to a time dimension and a sample dimension;
performing inter-parameter time sequence correlation characteristic analysis on the operation parameter time sequence input matrix to obtain operation parameter global time sequence characteristics;
Determining whether to generate a fault early warning prompt based on the global time sequence characteristic of the operation parameter;
The inter-parameter time sequence correlation characteristic analysis is performed on the operation parameter time sequence input matrix to obtain an operation parameter global time sequence characteristic, and the method comprises the following steps:
Performing matrix partitioning processing on the operation parameter time sequence input matrix, and then obtaining a sequence of operation parameter local time sequence semantic feature vectors through a ViT model comprising an embedded layer;
Carrying out consistency association analysis on the sequence of the operation parameter local time sequence semantic feature vector to obtain an operation parameter consistency topological feature matrix;
Performing association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature;
The consistency association analysis is performed on the sequence of the operation parameter local time sequence semantic feature vector to obtain an operation parameter consistency topology feature matrix, and the method comprises the following steps:
Calculating cosine similarity between any two operation parameter local time sequence semantic feature vectors in the sequence of the operation parameter local time sequence semantic feature vectors to obtain an operation parameter consistency topology matrix;
extracting features of the operation parameter consistency topology matrix by a topology feature extractor based on a deep neural network model to obtain the operation parameter consistency topology feature matrix;
The deep neural network model is a convolutional neural network model;
Performing association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature, wherein the method comprises the following steps of: the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix are processed through a graph neural network model to obtain the consistency topology operation parameter global time sequence feature matrix;
wherein determining whether to generate a fault early warning cue based on the operational parameter global timing characteristic comprises:
expanding the global time sequence feature matrix of the consistent topology operation parameters into global time sequence feature vectors of the consistent topology operation parameters;
optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter;
The global time sequence feature vector of the optimized consistency topology operation parameter passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the sand mill to be detected is abnormal or not;
generating a fault early warning prompt based on the classification result;
Wherein, optimize each eigenvalue of the global time sequence eigenvector of the operation parameter of the consistency topology to obtain the global time sequence eigenvector of the operation parameter of the optimization consistency topology, comprising:
optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter by using the following optimization formula to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter;
Wherein, the optimization formula is:
wherein, Is the consistent topology operating parameter global timing feature vector,AndIs the first global time sequence characteristic vector of the consistent topology operation parameterAnd (d)Characteristic values, andIs the global feature mean of the global timing feature vector of the consistent topology operating parameters,Is the first of the global time sequence feature vectors of the optimized consistent topology operation parametersAnd characteristic values.
2. The equipment operation fault prediction method of an intelligent sand mill according to claim 1, wherein the optimizing consistency topology operation parameter global time sequence feature vector is passed through a classifier to obtain a classification result, and the classification result is used for indicating whether the operation state of the sand mill to be detected is abnormal or not, and the method comprises the following steps:
Performing full-connection coding on the global time sequence feature vector of the optimized consistency topology operation parameter by using a plurality of full-connection layers of the classifier to obtain a coding classification feature vector; and
And the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
3. An intelligent sand mill equipment operation fault prediction system, comprising:
The system comprises a parameter acquisition module, a control module and a control module, wherein the parameter acquisition module is used for acquiring operation parameters of a sand mill to be detected at a plurality of preset time points in a preset time period, wherein the operation parameters comprise a main machine operation frequency, a feeding operation frequency, a main machine protection pressure, a machine sealing opening pressure, a machine sealing operation frequency and a machine sealing cylinder pressure difference;
The matrix arrangement module is used for arranging the operation parameters of the plurality of preset time points into operation parameter time sequence input matrixes according to the time dimension and the sample dimension;
The correlation characteristic analysis module is used for carrying out inter-parameter time sequence correlation characteristic analysis on the operation parameter time sequence input matrix so as to obtain operation parameter global time sequence characteristics;
the fault early warning prompt generation module is used for determining whether to generate a fault early warning prompt or not based on the global time sequence characteristics of the operation parameters;
Wherein, the association characteristic analysis module includes:
the embedded coding unit is used for performing matrix partitioning processing on the operation parameter time sequence input matrix and then obtaining a sequence of operation parameter local time sequence semantic feature vectors through a ViT model comprising an embedded layer;
the consistency association analysis unit is used for carrying out consistency association analysis on the sequence of the operation parameter local time sequence semantic feature vector so as to obtain an operation parameter consistency topological feature matrix;
The association coding unit is used for carrying out association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature;
The consistency association analysis is performed on the sequence of the operation parameter local time sequence semantic feature vector to obtain an operation parameter consistency topology feature matrix, and the method comprises the following steps:
Calculating cosine similarity between any two operation parameter local time sequence semantic feature vectors in the sequence of the operation parameter local time sequence semantic feature vectors to obtain an operation parameter consistency topology matrix;
extracting features of the operation parameter consistency topology matrix by a topology feature extractor based on a deep neural network model to obtain the operation parameter consistency topology feature matrix;
The deep neural network model is a convolutional neural network model;
Performing association coding based on a graph structure on the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix to obtain a consistency topology operation parameter global time sequence feature matrix as the operation parameter global time sequence feature, wherein the method comprises the following steps of: the sequence of the operation parameter local time sequence semantic feature vector and the operation parameter consistency topology feature matrix are processed through a graph neural network model to obtain the consistency topology operation parameter global time sequence feature matrix;
wherein determining whether to generate a fault early warning cue based on the operational parameter global timing characteristic comprises:
expanding the global time sequence feature matrix of the consistent topology operation parameters into global time sequence feature vectors of the consistent topology operation parameters;
optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter;
The global time sequence feature vector of the optimized consistency topology operation parameter passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the sand mill to be detected is abnormal or not;
generating a fault early warning prompt based on the classification result;
Wherein, optimize each eigenvalue of the global time sequence eigenvector of the operation parameter of the consistency topology to obtain the global time sequence eigenvector of the operation parameter of the optimization consistency topology, comprising:
optimizing each characteristic value of the global time sequence characteristic vector of the consistent topology operation parameter by using the following optimization formula to obtain the global time sequence characteristic vector of the optimized consistent topology operation parameter;
Wherein, the optimization formula is:
wherein, Is the consistent topology operating parameter global timing feature vector,AndIs the first global time sequence characteristic vector of the consistent topology operation parameterAnd (d)Characteristic values, andIs the global feature mean of the global timing feature vector of the consistent topology operating parameters,Is the first of the global time sequence feature vectors of the optimized consistent topology operation parametersAnd characteristic values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380953.0A CN117334020B (en) | 2023-10-24 | 2023-10-24 | Equipment operation fault prediction system and method of intelligent sand mill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380953.0A CN117334020B (en) | 2023-10-24 | 2023-10-24 | Equipment operation fault prediction system and method of intelligent sand mill |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117334020A CN117334020A (en) | 2024-01-02 |
| CN117334020B true CN117334020B (en) | 2024-10-22 |
Family
ID=89277153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311380953.0A Active CN117334020B (en) | 2023-10-24 | 2023-10-24 | Equipment operation fault prediction system and method of intelligent sand mill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117334020B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117557967B (en) * | 2024-01-11 | 2024-03-29 | 陕西开来机电设备制造有限公司 | Intelligent management system for safety protection of belt conveyor |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799366A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Mechanical failure prediction feature extraction method |
| CN103050971A (en) * | 2013-01-30 | 2013-04-17 | 武汉大学 | Power grid cascading failure inhibition method based on operation limit matching model |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9760428B1 (en) * | 2013-12-19 | 2017-09-12 | Amdocs Software Systems Limited | System, method, and computer program for performing preventative maintenance in a network function virtualization (NFV) based communication network |
| CN105490840A (en) * | 2015-11-26 | 2016-04-13 | 电子科技大学 | Fault diagnosis test point selection method based on network topological structure |
| CN106824407B (en) * | 2017-02-14 | 2019-02-15 | 浙江艾领创矿业科技有限公司 | A kind of agitator mill and the method using the agitator mill grinding mineral |
| CN107609569B (en) * | 2017-07-31 | 2020-11-03 | 北京映翰通网络技术股份有限公司 | Power distribution network ground fault positioning method based on multi-dimensional feature vectors |
| CN109088754A (en) * | 2018-07-31 | 2018-12-25 | 北京航空航天大学 | A kind of COMMUNICATION NETWORK PERFORMANCES failure reason and characteristic parameter association relationship analysis method |
| CN116247824B (en) * | 2023-03-30 | 2023-11-17 | 国网河南省电力公司安阳供电公司 | Control method and system of electric power equipment |
| CN116557787B (en) * | 2023-07-11 | 2023-09-15 | 杭州国辰智企科技有限公司 | Intelligent evaluation system and method for pipe network state |
-
2023
- 2023-10-24 CN CN202311380953.0A patent/CN117334020B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101799366A (en) * | 2010-01-27 | 2010-08-11 | 北京信息科技大学 | Mechanical failure prediction feature extraction method |
| CN103050971A (en) * | 2013-01-30 | 2013-04-17 | 武汉大学 | Power grid cascading failure inhibition method based on operation limit matching model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117334020A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chao et al. | Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals | |
| CN117334020B (en) | Equipment operation fault prediction system and method of intelligent sand mill | |
| CN110879580B (en) | An analysis and monitoring method for large-scale non-stationary transient continuous process | |
| CN112926749A (en) | Intelligent power grid information equipment monitoring system and method | |
| CN105204436A (en) | Graded-early-warning-based fault diagnosis method of numerically-controlled machine tool | |
| CN117244678B (en) | Intelligent monitoring control system and method for sand mill | |
| CN104134120A (en) | System and method for monitoring ore-dressing production indexes | |
| CN117258931A (en) | Automatic control system and method for sand mill | |
| CN115628930B (en) | A Prediction Method of Downhole Cutting Condition of Roadheader Based on RBF Neural Network | |
| CN116821811A (en) | Coal grinding unit fault diagnosis method and system based on multi-layer graph convolutional neural network | |
| CN116049654A (en) | Safety monitoring and early warning method and system for coal preparation equipment | |
| CN106406257B (en) | A kind of the floatation of iron ore concentrate grade flexible measurement method and system of case-based reasioning | |
| CN111080476A (en) | User electricity stealing behavior analysis and early warning method based on data center | |
| CN119186851A (en) | Intelligent control system and method for rotating speed of centrifugal machine | |
| CN118959087A (en) | An intelligent monitoring method for shield machine tool wear | |
| CN115438402A (en) | Real-time prediction method and device for TBM tunneling rock mass conditions based on rock-machine mutual feedback perception relationship | |
| CN112090478B (en) | A Fault Diagnosis Method for Crusher Based on Linear Regression | |
| CN119312118A (en) | A rapid identification method for the root cause of coal mill failure in multiple operating scenarios | |
| CN118051826A (en) | Slurry circulation fault monitoring method based on shield big data platform | |
| CN112434755A (en) | Data anomaly sensing method based on heterogeneous system | |
| CN115569727A (en) | Intelligent control system and control method for lithium battery recovery | |
| CN117232822A (en) | System and method for diagnosing faults of vertical mill equipment | |
| CN113029624B (en) | Fault detection method for cement raw material grinding process | |
| CN116378764A (en) | Shield circulation system blockage early warning method | |
| CN112884027B (en) | Cutting process real-time state monitoring method and device based on pattern recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |