CN120278703A - Street lamp wisdom fortune dimension optimization management platform based on big data analysis - Google Patents
Street lamp wisdom fortune dimension optimization management platform based on big data analysis Download PDFInfo
- Publication number
- CN120278703A CN120278703A CN202510364690.7A CN202510364690A CN120278703A CN 120278703 A CN120278703 A CN 120278703A CN 202510364690 A CN202510364690 A CN 202510364690A CN 120278703 A CN120278703 A CN 120278703A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- sub
- street lamp
- value
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- Algebra (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a street lamp intelligent operation and maintenance optimization management platform based on big data analysis, which comprises an acquisition module, an extraction module, an evaluation module, a determination module and an optimization module, wherein the acquisition module is used for acquiring target data of intelligent street lamps in a preset time period, the extraction module is used for extracting characteristics of the target data to obtain target characteristics, the evaluation module is used for inputting the target characteristics into a pre-trained big data analysis model to evaluate, determining an operation and maintenance evaluation value of the intelligent street lamps, the determination module is used for comparing the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold value, and taking the intelligent street lamps as intelligent street lamps to be optimized when the operation and maintenance evaluation value is smaller than or equal to the preset operation and maintenance evaluation threshold value, the optimization module is used for inquiring a target optimization strategy of the intelligent street lamps to be optimized, optimizing the intelligent street lamps based on the target optimization strategy, improving data processing and analysis capacity in the operation and maintenance process of the street lamps, establishing a scientific evaluation system and improving operation and maintenance efficiency based on the accurate optimization strategy.
Description
Technical Field
The invention relates to the field of intelligent energy-saving street lamp illumination, in particular to a street lamp intelligent operation and maintenance optimization management platform based on big data analysis.
Background
With the acceleration of the urban lighting system, the scale of the urban lighting system is continuously expanding, and the intelligent street lamp is gradually popularized and widely applied to all corners of the city as an important component of the urban lighting system. The intelligent energy-saving street lamp not only has the traditional lighting function, but also integrates various sensors and communication equipment, can realize various functions such as intelligent lighting control, environment monitoring, video monitoring and the like, and provides powerful support for intelligent management of cities.
However, operation and maintenance management of the intelligent energy-saving street lamp still faces a plurality of challenges:
The intelligent energy-saving street lamp can generate a large amount of target data such as illumination intensity, current and voltage, fault alarm information and the like in the operation process. These data are rich in information, but most of the data are not fully utilized due to the lack of effective data processing and analysis means. The existing management mode can only simply store and display data, and potential problems behind the data cannot be deeply mined, so that potential faults and performance degradation trends of the street lamp cannot be found in time.
In the traditional street lamp operation and maintenance management, the evaluation of the intelligent energy-saving street lamp mainly depends on manual experience and simple index judgment, and a scientific and comprehensive evaluation system is lacked. The evaluation mode is strong in subjectivity, inaccurate evaluation is easy to occur, and the actual running state and performance level of the intelligent street lamp cannot be accurately reflected. For example, whether the street lamp works normally is judged only according to whether the street lamp is lighted or not, but important indexes such as illumination intensity, energy consumption and the like are ignored, so that potential problems can be ignored, and the service life and the lighting effect of the street lamp are influenced.
Because of the lack of an effective data support and scientific evaluation system, the conventional street lamp operation and maintenance management often adopts a regular inspection and post maintenance mode. The method not only consumes a great deal of manpower, material resources and time, but also can not discover and solve the problem of the faults of the street lamp in time, so that the faults of the street lamp can not be repaired in time, and the urban illumination quality and traffic safety are affected. In addition, for different types of street lamp faults, a targeted optimization strategy is lacked, accurate operation and maintenance cannot be realized, and the operation and maintenance efficiency is further reduced.
In the operation and maintenance management process of the street lamp, when the street lamp is found to have problems, a unified processing mode is often adopted, and personalized optimization strategies aiming at different street lamps and different fault types are lacked. The optimization mode of 'one-cut' can not fully consider the actual situation and the running environment of the street lamp, and can cause poor optimization effect and even cause new problems. For example, for some street lamp faults caused by environmental factors, if the influence of the environmental factors is not considered, the problem may not be solved fundamentally by simply replacing the street lamp components, and the operation and maintenance cost may be increased.
In summary, the existing intelligent street lamp operation and maintenance management mode has the problems of insufficient data processing and analysis capability, lack of a scientific evaluation system, low operation and maintenance efficiency, inaccurate optimization strategy and the like, and cannot meet the requirements of intelligent and efficient management of the urban lighting system. Therefore, a street lamp intelligent operation and maintenance optimization management platform based on big data analysis is needed to improve the operation and maintenance management level of intelligent street lamps and ensure the stable operation of the urban lighting system.
Disclosure of Invention
The present invention aims to solve, at least to some extent, one of the technical problems in the above-described technology. Therefore, the invention aims to provide the street lamp intelligent operation and maintenance optimization management platform based on big data analysis, so that the data processing and analysis capability in the street lamp operation and maintenance process is improved, a scientific evaluation system is established, and the operation and maintenance efficiency is improved based on a precise optimization strategy.
In order to achieve the above purpose, an embodiment of the present invention provides a street lamp intelligent operation and maintenance optimization management platform based on big data analysis, including:
The acquisition module is used for acquiring target data of the intelligent street lamp in a preset time period;
the extraction module is used for extracting the characteristics of the target data to obtain target characteristics;
The evaluation module is used for inputting the target characteristics into a pre-trained big data analysis model for evaluation and determining an operation and maintenance evaluation value of the intelligent street lamp;
The determining module is used for comparing the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold value, and when the operation and maintenance evaluation value is smaller than or equal to the preset operation and maintenance evaluation threshold value, the intelligent street lamp is used as an intelligent street lamp to be optimized;
The optimizing module is used for inquiring a target optimizing strategy of the intelligent street lamp to be optimized and optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
Preferably, the acquiring module includes:
The first acquisition sub-module is used for acquiring the operation data of the intelligent street lamp in a preset time period to obtain first data;
the second acquisition sub-module is used for acquiring monitoring image data of the intelligent street lamp in a preset time period to obtain second data;
The first determining sub-module is used for taking the first data and the second data as target data of the intelligent street lamp.
Preferably, the device further comprises a preprocessing module, wherein the preprocessing module is used for preprocessing the target data before the extracting module performs feature extraction on the target data to obtain target features, so as to obtain preprocessed target data.
Preferably, the preprocessing module includes:
the data cleaning sub-module is used for cleaning the first data to obtain the first data after the data cleaning;
the noise reduction sub-module is used for carrying out image noise reduction on the second data to obtain noise-reduced second data;
and the second determining submodule is used for taking the first data after data cleaning and the second data after noise reduction as target data after preprocessing.
Preferably, the data cleaning sub-module comprises:
A dividing unit for:
Taking one type of data in the first data as target type data;
uniformly dividing the data in the target class data into a plurality of target class sub-data based on the time sequence;
A first calculation unit configured to:
Any target class sub-data is taken as first target class sub-data;
calculating an abnormal evaluation value corresponding to the first target class sub-data;
a first determining unit configured to:
comparing the abnormal evaluation value with a preset evaluation threshold, and taking the first target class sub-data as second target class sub-data when the abnormal evaluation value is greater than or equal to the preset evaluation threshold;
traversing all target category sub-data to obtain a plurality of second target category sub-data;
a second calculation unit configured to:
Any one of the sub-data of the second target class is fetched;
calculating local fluctuation indexes of all data points in the sub-data of the second target class based on a first preset algorithm;
A second determination unit configured to:
comparing the local fluctuation index of each data point with a preset fluctuation threshold value, and taking the data point when the local fluctuation index of the data point is more than or equal to the preset fluctuation threshold value as a abnormal data point;
traversing all the sub-data of the second target class to obtain a plurality of abnormal data points;
A data cleaning unit for:
Deleting a plurality of abnormal data points to obtain target class data after data cleaning;
and traversing all kinds of data in the first data to obtain the first data after data cleaning.
Preferably, the first calculation unit includes:
The acquisition subunit is used for arbitrarily acquiring one target class sub-data as first target class sub-data;
The first calculating subunit is used for calculating the average value of the data values corresponding to all the data points in the first target class sub-data to obtain a first average value;
A second computing subunit for:
Acquiring target class sub-data adjacent to the first target class sub-data, calculating the average value of the data values corresponding to all data points in the first target class sub-data and the target class sub-data adjacent to the first target class sub-data, and obtaining a second average value;
a third calculation subunit configured to:
Calculating the absolute value of the difference value between the first average value and the second average value to obtain a first difference value;
calculating the first target class sub-data and the extremely poor data values corresponding to all data points in the target class sub-data adjacent to the first target class sub-data to obtain a second difference value;
And the determining subunit is used for determining the abnormal evaluation value of the first target class sub-data based on the first difference value and the second difference value.
Preferably, the noise reduction sub-module includes:
an acquisition unit configured to:
Taking a monitoring image of an intelligent street lamp in the second data, and carrying out gray scale processing;
dividing a monitoring image of the intelligent street lamp after gray level processing into a plurality of sub-images;
clustering the plurality of sub-images to obtain a plurality of sub-image sets;
taking any sub-image set as a target sub-image set;
Taking one sub-image in the target sub-image set as a target sub-image;
taking one pixel point in the target sub-image as a first pixel point;
the third calculation unit is used for calculating the brightness value and the ambiguity value of the first pixel point respectively;
the comparison unit is used for comparing the brightness value of the first pixel point with a preset brightness threshold value and comparing the ambiguity value of the first pixel point with the preset ambiguity threshold value;
A third determination unit configured to:
When the brightness value of the first pixel point is smaller than the preset brightness threshold value and the ambiguity value of the first pixel point is larger than the preset ambiguity threshold value, the first pixel point is used as the pixel point to be noise reduced;
traversing all the pixel points to obtain a plurality of pixel points to be noise reduced;
Noise reduction unit for:
denoising a plurality of pixel points to be denoised based on a filtering algorithm to obtain a denoised target sub-image;
Determining the noise reduction amplitude of each pixel point to be noise reduced in the target sub-image based on the target sub-image and the noise reduced target sub-image;
denoising other sub-images in the target sub-image set based on the denoising amplitude of each pixel point to be denoised;
traversing all sub-image sets to obtain a monitoring image of the intelligent street lamp after noise reduction;
and traversing the monitoring images of all intelligent street lamps in the second data to obtain the second data after noise reduction.
Preferably, the third calculation unit includes:
a luminance calculating subunit configured to:
Determining a target area by taking the first pixel point as a center and taking a preset distance as a radius;
calculating the gray average value of each pixel point in the target area as the brightness value of the first pixel point;
An ambiguity calculating subunit configured to:
calculating the sum of squares of gray difference values of the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum;
obtaining the total number of other pixel points except the first pixel point in the target area to obtain a target value;
And taking the ratio of the target sum value to the target numerical value as the ambiguity value of the first pixel point.
Preferably, the method for constructing the big data analysis model comprises the following steps:
acquiring a big data analysis training data set;
Training the neural network model based on the big data analysis training data set to obtain an initial big data analysis model;
acquiring a big data analysis test data set;
And testing the initial big data analysis model based on the big data analysis test data set, and obtaining a trained big data analysis model when the test result is qualified.
Preferably, the optimization module comprises:
The inquiring sub-module is used for inquiring the intelligent operation and maintenance optimizing database based on the target characteristics of the intelligent street lamp to be optimized and determining a target optimizing strategy of the intelligent street lamp to be optimized;
And the optimizing sub-module is used for optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
The invention discloses a street lamp intelligent operation and maintenance optimization management platform based on big data analysis, which is used for acquiring target data of intelligent street lamps in a preset time period, providing a rich data basis for comprehensively grasping the running state of the street lamps, extracting features of the target data, extracting key information from massive data to obtain target features, inputting the target features into a pre-trained big data analysis model for evaluation, determining an evaluation value of the intelligent street lamps, evaluating the target features through the big data analysis model, avoiding subjectivity and limitation of the traditional evaluation mode which mainly depends on artificial experience and simple index judgment, and timely finding potential faults and performance decline trend of the street lamps by utilizing the strong analysis capability of the big data analysis model. For example, by analyzing the energy consumption data of the street lamp, whether the street lamp has abnormal energy consumption can be found in advance, measures can be taken in time to process the street lamp, further deterioration of the problem is avoided, and the intelligent street lamp to be optimized can be accurately identified by comparing the evaluation value with a preset evaluation threshold. The accurate identification mode avoids blindness of regular inspection and post maintenance in the traditional operation and maintenance mode, can discover the fault problem of the street lamp in time, and improves the timeliness of operation and maintenance. Meanwhile, aiming at the query target optimization strategy of the intelligent street lamp to be optimized, personalized optimization measures can be adopted according to the actual conditions and fault types of different street lamps, so that accurate operation and maintenance are realized, and the operation and maintenance efficiency is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention may be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical scheme of the invention is further described in detail through the drawings and the embodiments.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a block diagram of a street lamp intelligent operation and maintenance optimization management platform based on big data analysis according to one embodiment of the invention;
FIG. 2 is a block diagram of an acquisition module according to one embodiment of the invention;
FIG. 3 is a block diagram of a preprocessing module according to one embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention.
Example 1
As shown in fig. 1, a street lamp intelligent operation and maintenance optimization management platform based on big data analysis includes:
The acquisition module is used for acquiring target data of the intelligent street lamp in a preset time period;
the extraction module is used for extracting the characteristics of the target data to obtain target characteristics;
The evaluation module is used for inputting the target characteristics into a pre-trained big data analysis model for evaluation and determining an operation and maintenance evaluation value of the intelligent street lamp;
The determining module is used for comparing the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold value, and when the operation and maintenance evaluation value is smaller than or equal to the preset operation and maintenance evaluation threshold value, the intelligent street lamp is used as an intelligent street lamp to be optimized;
The optimizing module is used for inquiring a target optimizing strategy of the intelligent street lamp to be optimized and optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
In this embodiment, the target data includes operation data of the intelligent street lamp and monitoring image data of the intelligent street lamp.
In this embodiment, the target features include electrical performance related features, lighting effect related features, fault and anomaly related features, and environmental related features.
In this embodiment, the big data analysis model is a pre-trained evaluation model.
The technical scheme has the advantages that the intelligent street lamp target data in a preset time period are obtained, a rich data basis is provided for comprehensively mastering the running state of the street lamp, the target data are subjected to feature extraction, key information can be extracted from massive data to obtain target features, the target features are input into a pre-trained big data analysis model to be evaluated, the evaluation value of the intelligent street lamp is determined, the big data analysis model is used for evaluating the target features, subjectivity and limitation that the traditional evaluation mode mainly depends on manual experience and simple index judgment are avoided, and potential faults and performance decline trend of the street lamp can be found in time by utilizing the strong analysis capability of the big data analysis model. For example, by analyzing the energy consumption data of the street lamp, whether the street lamp has abnormal energy consumption can be found in advance, measures can be taken in time to process the street lamp, further deterioration of the problem is avoided, and the intelligent street lamp to be optimized can be accurately identified by comparing the evaluation value with a preset evaluation threshold. The accurate identification mode avoids blindness of regular inspection and post maintenance in the traditional operation and maintenance mode, can discover the fault problem of the street lamp in time, and improves the timeliness of operation and maintenance. Meanwhile, aiming at the query target optimization strategy of the intelligent street lamp to be optimized, personalized optimization measures can be adopted according to the actual conditions and fault types of different street lamps, so that accurate operation and maintenance are realized, and the operation and maintenance efficiency is improved.
Example 2
As shown in fig. 2, the acquisition module includes:
The first acquisition sub-module is used for acquiring the operation data of the intelligent street lamp in a preset time period to obtain first data;
the second acquisition sub-module is used for acquiring monitoring image data of the intelligent street lamp in a preset time period to obtain second data;
The first determining sub-module is used for taking the first data and the second data as target data of the intelligent street lamp.
In this embodiment, the operation data includes electrical operation data of the street lamp, lighting related data, street lamp equipment status data, street lamp surrounding environment perception data, and the like.
The intelligent street lamp target data set integrated provides abundant data support for city managers, is beneficial to making more scientific and reasonable decisions, improves the efficiency and scientificity of city management, and provides abundant data support for the city managers by comprehensively acquiring and analyzing the operation data and monitoring image data of the intelligent street lamp, thereby being beneficial to realizing more scientific and efficient city management.
Example 3
The device further comprises a preprocessing module, wherein the preprocessing module is used for preprocessing the target data before the extracting module performs feature extraction on the target data to obtain target features, so as to obtain preprocessed target data.
Example 4
As shown in fig. 3, the preprocessing module includes:
the data cleaning sub-module is used for cleaning the first data to obtain the first data after the data cleaning;
the noise reduction sub-module is used for carrying out image noise reduction on the second data to obtain noise-reduced second data;
and the second determining submodule is used for taking the first data after data cleaning and the second data after noise reduction as target data after preprocessing.
The intelligent street lamp system has the advantages that the quality of intelligent street lamp operation data and monitoring image data is effectively improved through data cleaning and noise reduction processing, more accurate and reliable data support is provided for subsequent data analysis and decision, the data cleaning and noise reduction processing is integrated into the preprocessing module, rapid and efficient processing of original data is achieved, the data processing flow is optimized, the preprocessed target data is more accurate and complete, the overall performance of the intelligent street lamp system is improved, the efficiency and scientificity of city management are improved, comprehensive and efficient preprocessing of the original data is achieved through cooperative work of all sub-modules in the preprocessing module, and a solid foundation is provided for subsequent data analysis and decision.
Example 5
A data cleansing sub-module, comprising:
A dividing unit for:
Taking one type of data in the first data as target type data;
uniformly dividing the data in the target class data into a plurality of target class sub-data based on the time sequence;
A first calculation unit configured to:
Any target class sub-data is taken as first target class sub-data;
calculating an abnormal evaluation value corresponding to the first target class sub-data;
a first determining unit configured to:
comparing the abnormal evaluation value with a preset evaluation threshold, and taking the first target class sub-data as second target class sub-data when the abnormal evaluation value is greater than or equal to the preset evaluation threshold;
traversing all target category sub-data to obtain a plurality of second target category sub-data;
a second calculation unit configured to:
Any one of the sub-data of the second target class is fetched;
calculating local fluctuation indexes of all data points in the sub-data of the second target class based on a first preset algorithm;
A second determination unit configured to:
comparing the local fluctuation index of each data point with a preset fluctuation threshold value, and taking the data point when the local fluctuation index of the data point is more than or equal to the preset fluctuation threshold value as a abnormal data point;
traversing all the sub-data of the second target class to obtain a plurality of abnormal data points;
A data cleaning unit for:
Deleting a plurality of abnormal data points to obtain target class data after data cleaning;
and traversing all kinds of data in the first data to obtain the first data after data cleaning.
In this embodiment, the first preset algorithm includes:
Wherein A b,c represents the local fluctuation index of the c-th data point in the b-th second target class sub-data, Y b,c represents the data value of the c-th data point in the b-th second target class sub-data, Y b,c,x represents the data value of the x-th data point in the neighborhood of the c-th data point in the b-th second target class sub-data, d b,c,x represents the distance between the c-th data point and the x-th data point in the neighborhood of the c-th data point in the b-th second target class sub-data, V represents the total number of data points in the neighborhood of the c-th data point, sigma represents a parameter controlling the weight attenuation, norm () represents a normalization function, exp () represents an exponential function based on natural constants.
The technical scheme comprises the working principle that one type of target class data in first data is selected, the target class data is divided into a plurality of target class sub-data based on time sequence uniformity, the plurality of sub-data are equivalent to the first target class sub-data and have sequence, one sub-data is selected as the first target class sub-data, an abnormal evaluation value of the first target class sub-data is calculated, the data is divided into a plurality of data blocks, the degree of abnormality among the data blocks is judged firstly, so that the calculated amount of overall data cleaning is reduced, when the abnormal evaluation value is determined to be greater than or equal to a preset evaluation threshold, the first target class sub-data is used as second target class sub-data, all the target class sub-data are traversed to obtain a plurality of second target class sub-data, screening of the first target class sub-data is completed at the moment, abnormal data point identification is carried out on the data in each second target class sub-data, the local fluctuation index of each data point in each second target class sub-data is calculated, because the degree of the data point in continuous operation data point is greater than the data point is judged, the abnormal data point is obtained after the first data point is traversed, and the abnormal data is cleaned, and the abnormal data is obtained after the abnormal data is obtained.
The technical scheme has the beneficial effects that the target class data is uniformly segmented based on the time sequence through the segmentation unit, so that the fine analysis of the data in the subsequent step is facilitated. The method can ensure uniformity and continuity of data in a time dimension, provides a solid foundation for subsequent calculation of abnormal evaluation values, can accurately identify target class sub-data with higher abnormal evaluation values through combined use of the first calculation unit and the second determination unit, further calculates local fluctuation indexes of data points in the second target class sub-data, compares the local fluctuation indexes with a preset fluctuation threshold value, and accordingly accurately identifies abnormal data points, and the data cleaning unit obtains target class data after data cleaning by deleting a plurality of abnormal data points. The process not only removes noise and abnormal values in the data, but also maintains the integrity and consistency of the data, and provides a more accurate and reliable data basis for subsequent data analysis and decision. And traversing all kinds of data in the first data, so that the whole data set is ensured to be subjected to effective cleaning treatment, and the quality of the whole data is improved.
Example 6
A first computing unit comprising:
The acquisition subunit is used for arbitrarily acquiring one target class sub-data as first target class sub-data;
The first calculating subunit is used for calculating the average value of the data values corresponding to all the data points in the first target class sub-data to obtain a first average value;
A second computing subunit for:
Acquiring target class sub-data adjacent to the first target class sub-data, calculating the average value of the data values corresponding to all data points in the first target class sub-data and the target class sub-data adjacent to the first target class sub-data, and obtaining a second average value;
a third calculation subunit configured to:
Calculating the absolute value of the difference value between the first average value and the second average value to obtain a first difference value;
calculating the first target class sub-data and the extremely poor data values corresponding to all data points in the target class sub-data adjacent to the first target class sub-data to obtain a second difference value;
And the determining subunit is used for determining the abnormal evaluation value of the first target class sub-data based on the first difference value and the second difference value.
In this embodiment, the abnormality evaluation value of the first target class sub-data includes:
T=ew+eq
wherein T represents an abnormal evaluation value of the first target class sub-data, e represents a natural constant, w represents a first difference value, and q represents a second difference value.
The technical scheme has the working principle that the acquisition subunit takes one target class sub-data from the data set as the first target class sub-data. The method comprises the steps of starting a data processing process, providing basic data for subsequent calculation, and calculating the average value of data values corresponding to all data points in the first target class sub-data by a first calculation subunit to obtain a first average value. The second calculating subunit further obtains the adjacent target class sub-data of the first target class sub-data, calculates the average value of the data values corresponding to all the data points in the two parts of data, and obtains a second average value. The method comprises the steps of obtaining a first difference value by calculating the absolute value of the difference value between a first mean value and a second mean value, and obtaining a second difference value by calculating the range of data values corresponding to all data points in the first target class sub-data and adjacent sub-data. The determination subunit comprehensively evaluates the abnormality degree of the first target class sub-data based on the first difference value and the second difference value and gives an abnormality evaluation value. The step is the core of abnormality detection, and whether the data has abnormality can be judged by comparing the difference value with a preset threshold value or standard.
The technical scheme has the beneficial effect that the fine change of the data in time sequence or space distribution can be captured by calculating the mean value of the first target class sub-data and the difference between the mean value of the first target class sub-data and the mean value of the adjacent sub-data. The difference analysis based on the mean value is beneficial to accurately identifying abnormal fluctuation of the data, meanwhile, the calculation range further enhances the sensitivity of abnormal detection, the range reflects the difference between the maximum value and the minimum value in the data set and is an important index for measuring the fluctuation range of the data, the first difference value and the second difference value are combined to determine the abnormal degree of the data which can be evaluated more comprehensively by the subunits, the first calculation unit can efficiently process a large-scale data set through parallel calculation or pipeline processing, the data transmission and calculation process among the subunits can be optimized to reduce the calculation time and the resource consumption, and the accurate abnormal detection is beneficial to timely finding and correcting errors or abnormal values in the data, so that the quality and the reliability of the data are improved. The design of the first computing unit provides powerful support for data anomaly detection tasks by improving the accuracy of anomaly detection, enhancing the flexibility of data processing, improving the data processing efficiency, promoting the improvement of data quality and supporting various application scenes. The design not only improves the efficiency and accuracy of data processing, but also provides a reliable basis for subsequent data analysis and decision making.
Example 7
A noise reduction sub-module, comprising:
an acquisition unit configured to:
Taking a monitoring image of an intelligent street lamp in the second data, and carrying out gray scale processing;
dividing a monitoring image of the intelligent street lamp after gray level processing into a plurality of sub-images;
clustering the plurality of sub-images to obtain a plurality of sub-image sets;
taking any sub-image set as a target sub-image set;
Taking one sub-image in the target sub-image set as a target sub-image;
taking one pixel point in the target sub-image as a first pixel point;
the third calculation unit is used for calculating the brightness value and the ambiguity value of the first pixel point respectively;
the comparison unit is used for comparing the brightness value of the first pixel point with a preset brightness threshold value and comparing the ambiguity value of the first pixel point with the preset ambiguity threshold value;
A third determination unit configured to:
When the brightness value of the first pixel point is smaller than the preset brightness threshold value and the ambiguity value of the first pixel point is larger than the preset ambiguity threshold value, the first pixel point is used as the pixel point to be noise reduced;
traversing all the pixel points to obtain a plurality of pixel points to be noise reduced;
Noise reduction unit for:
denoising a plurality of pixel points to be denoised based on a filtering algorithm to obtain a denoised target sub-image;
Determining the noise reduction amplitude of each pixel point to be noise reduced in the target sub-image based on the target sub-image and the noise reduced target sub-image;
denoising other sub-images in the target sub-image set based on the denoising amplitude of each pixel point to be denoised;
traversing all sub-image sets to obtain a monitoring image of the intelligent street lamp after noise reduction;
and traversing the monitoring images of all intelligent street lamps in the second data to obtain the second data after noise reduction.
In this embodiment, the filtering algorithm includes, but is not limited to, a median filtering algorithm, a mean filtering algorithm.
The technical scheme comprises the working principle that a monitoring image of an intelligent street lamp in second data is taken, gray processing is carried out, the monitoring image of the intelligent street lamp after gray processing is divided into a plurality of sub-images, the sub-images are clustered to obtain a plurality of sub-image sets, the clustering purpose is to divide parts with similar content in the monitoring image into one type to obtain a plurality of sub-image sets, noise reduction is carried out on one sub-image in the sets to obtain noise reduction coefficients, the same noise reduction processing is carried out on other sub-images in the same set based on the noise reduction coefficients, a third calculation unit is used for filtering the first pixel by calculating brightness values and ambiguity values of the first pixel to obtain a plurality of pixels to be noise reduced, and noise reduction is carried out on the pixels to be noise reduced based on a filtering algorithm.
The technical scheme has the advantages that the module can efficiently process a large number of intelligent street lamp monitoring images through gray level processing, sub-image dividing and clustering, the processing mode reduces the calculation complexity, improves the image processing efficiency, and can accurately identify the pixel points needing noise reduction through calculating the brightness value and the ambiguity value of the pixel points and comparing the brightness value and the ambiguity value with the preset threshold value. The method avoids blindly carrying out noise reduction on all the pixel points, thereby improving the pertinence and the effect of noise reduction, and carries out noise reduction on the identified pixel points to be noise reduced based on a filtering algorithm, and the module can intelligently remove noise in an image. Meanwhile, by determining the noise reduction amplitude and carrying out noise reduction on other sub-images, the module can ensure that the noise reduction effect of the whole target sub-image set is consistent, and the overall quality of the image is improved.
Example 8
A third computing unit comprising:
a luminance calculating subunit configured to:
Determining a target area by taking the first pixel point as a center and taking a preset distance as a radius;
calculating the gray average value of each pixel point in the target area as the brightness value of the first pixel point;
An ambiguity calculating subunit configured to:
calculating the sum of squares of gray difference values of the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum;
obtaining the total number of other pixel points except the first pixel point in the target area to obtain a target value;
And taking the ratio of the target sum value to the target numerical value as the ambiguity value of the first pixel point.
The technical scheme has the advantages that the brightness calculation subunit determines the target area by taking the first pixel point as the center and taking the preset distance as the radius, calculates the gray level average value of all the pixel points in the area as the brightness value of the first pixel point, can more accurately reflect the average brightness condition around the first pixel point, avoids errors possibly caused by the brightness value of a single pixel point, and can more accurately identify the pixel points needing noise reduction by calculating the square sum of gray level difference values of the first pixel point and other pixel points except the first pixel point in the target area and dividing the sum by the total number of the pixel points except the first pixel point in the target area. This helps to improve the accuracy of the noise reduction process, avoid excessive processing of the clear pixel points, and ensure that the blurred pixel points are sufficiently noise-reduced.
Example 9
The method for constructing the big data analysis model comprises the following steps:
acquiring a big data analysis training data set;
Training the neural network model based on the big data analysis training data set to obtain an initial big data analysis model;
acquiring a big data analysis test data set;
And testing the initial big data analysis model based on the big data analysis test data set, and obtaining a trained big data analysis model when the test result is qualified.
In this embodiment of the present invention, the process is performed,
Wherein phi i represents a first evaluation value of the ith moment of the intelligent street lamp, U i represents voltage values of two ends of the ith moment of the intelligent street lamp, I i represents current values of two ends of the ith moment of the intelligent street lamp, R i represents an internal resistance value of the ith moment of the intelligent street lamp, t 1 represents a used time value of the intelligent street lamp, t 2 represents ideal use time of the intelligent street lamp, and alpha represents an aging coefficient of the intelligent street lamp; Delta represents the failure times of the intelligent street lamp;
Obtaining the output power and rated power of the intelligent street lamp;
Taking the ratio of the output power to the rated power as the illumination output index of the intelligent street lamp;
Taking a monitoring image of any intelligent street lamp, and acquiring the moving speed of a moving object in each lane of the monitoring image; determining the moving distance of the moving object in each lane based on the moving speed and unit time of the moving object in each lane, dividing each lane by taking the moving distance of the moving object as long and the width of the corresponding lane as wide, and determining the corresponding target area of each lane;
Calculating an illumination demand index of each lane based on a preset algorithm;
The intelligent street lamp comprises a monitoring image of an intelligent street lamp, a light source, a control unit and a control unit, wherein C i,a represents an illumination demand index of an a-th lane in the monitoring image of the intelligent street lamp corresponding to the i-th moment, v represents a moving speed of a moving object in the a-th lane, θ represents a connecting line direction of a central point of the moving object and a central point in a current target area, and an included angle between the connecting line direction and a running direction of the moving object;
Taking the average value of the illumination demand indexes of all lanes as the illumination demand index of the intelligent street lamp;
taking the ratio of the illumination demand index of the intelligent street lamp to the illumination output index of the intelligent street lamp as a second evaluation value of the intelligent street lamp;
Acquiring a preset weight value;
determining an operation and maintenance evaluation value of the intelligent street lamp based on the first evaluation value, the second evaluation value and a preset weight value of the intelligent street lamp;
Wherein P represents an operation and maintenance evaluation value of the intelligent street lamp, phi i represents a first evaluation value of the ith moment of the intelligent street lamp, beta 1 represents a first preset weight, n represents the total number of moments in the target data, C i,a represents an illumination demand index of an a-th lane in a monitoring image of the intelligent street lamp corresponding to the ith moment, m represents the total number of lanes in the monitoring image, beta 2 represents a second preset weight, and beta 1+β2 =1.
The technical scheme has the beneficial effects that the construction method of the big data analysis model improves the accuracy of the operation and maintenance evaluation value of the intelligent street lamp through multiple aspects of targeted training, accurate performance evaluation, generalization capability improvement, business process optimization, data-driven decision culture promotion and the like.
Example 10
An optimization module comprising:
The inquiring sub-module is used for inquiring the intelligent operation and maintenance optimizing database based on the target characteristics of the intelligent street lamp to be optimized and determining a target optimizing strategy of the intelligent street lamp to be optimized;
And the optimizing sub-module is used for optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
The intelligent street lamp optimizing method has the advantages that the inquiring sub-module can quickly inquire in the intelligent operation and maintenance optimizing database and determine the target optimizing strategy based on the target characteristics of the intelligent street lamp to be optimized, the complicated process of manually analyzing and judging the optimizing strategy in the traditional method is avoided, the optimizing efficiency is remarkably improved, and the inquiring sub-module can acquire the optimizing strategy matched with the target characteristics of the intelligent street lamp to be optimized through the support of the intelligent operation and maintenance optimizing database.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, it is intended that the present invention also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. Street lamp wisdom fortune dimension optimization management platform based on big data analysis, its characterized in that includes:
The acquisition module is used for acquiring target data of the intelligent street lamp in a preset time period;
the extraction module is used for extracting the characteristics of the target data to obtain target characteristics;
The evaluation module is used for inputting the target characteristics into a pre-trained big data analysis model for evaluation and determining an operation and maintenance evaluation value of the intelligent street lamp;
The determining module is used for comparing the operation and maintenance evaluation value with a preset operation and maintenance evaluation threshold value, and when the operation and maintenance evaluation value is smaller than or equal to the preset operation and maintenance evaluation threshold value, the intelligent street lamp is used as an intelligent street lamp to be optimized;
The optimizing module is used for inquiring a target optimizing strategy of the intelligent street lamp to be optimized and optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
2. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 1, wherein obtain the module, include:
The first acquisition sub-module is used for acquiring the operation data of the intelligent street lamp in a preset time period to obtain first data;
the second acquisition sub-module is used for acquiring monitoring image data of the intelligent street lamp in a preset time period to obtain second data;
The first determining sub-module is used for taking the first data and the second data as target data of the intelligent street lamp.
3. The street lamp intelligent operation and maintenance optimization management platform based on big data analysis as claimed in claim 2, further comprising a preprocessing module, wherein the preprocessing module is used for preprocessing target data before the extracting module performs feature extraction on the target data to obtain target features, so as to obtain preprocessed target data.
4. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 3, wherein the preprocessing module includes:
the data cleaning sub-module is used for cleaning the first data to obtain the first data after the data cleaning;
the noise reduction sub-module is used for carrying out image noise reduction on the second data to obtain noise-reduced second data;
and the second determining submodule is used for taking the first data after data cleaning and the second data after noise reduction as target data after preprocessing.
5. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 4, wherein data washs sub-module, includes:
A dividing unit for:
Taking one type of data in the first data as target type data;
uniformly dividing the data in the target class data into a plurality of target class sub-data based on the time sequence;
A first calculation unit configured to:
Any target class sub-data is taken as first target class sub-data;
calculating an abnormal evaluation value corresponding to the first target class sub-data;
a first determining unit configured to:
comparing the abnormal evaluation value with a preset evaluation threshold, and taking the first target class sub-data as second target class sub-data when the abnormal evaluation value is greater than or equal to the preset evaluation threshold;
traversing all target category sub-data to obtain a plurality of second target category sub-data;
a second calculation unit configured to:
Any one of the sub-data of the second target class is fetched;
calculating local fluctuation indexes of all data points in the sub-data of the second target class based on a first preset algorithm;
A second determination unit configured to:
comparing the local fluctuation index of each data point with a preset fluctuation threshold value, and taking the data point when the local fluctuation index of the data point is more than or equal to the preset fluctuation threshold value as a abnormal data point;
traversing all the sub-data of the second target class to obtain a plurality of abnormal data points;
A data cleaning unit for:
Deleting a plurality of abnormal data points to obtain target class data after data cleaning;
and traversing all kinds of data in the first data to obtain the first data after data cleaning.
6. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 5, wherein first computing unit includes:
The acquisition subunit is used for arbitrarily acquiring one target class sub-data as first target class sub-data;
The first calculating subunit is used for calculating the average value of the data values corresponding to all the data points in the first target class sub-data to obtain a first average value;
A second computing subunit for:
Acquiring target class sub-data adjacent to the first target class sub-data, calculating the average value of the data values corresponding to all data points in the first target class sub-data and the target class sub-data adjacent to the first target class sub-data, and obtaining a second average value;
a third calculation subunit configured to:
Calculating the absolute value of the difference value between the first average value and the second average value to obtain a first difference value;
calculating the first target class sub-data and the extremely poor data values corresponding to all data points in the target class sub-data adjacent to the first target class sub-data to obtain a second difference value;
And the determining subunit is used for determining the abnormal evaluation value of the first target class sub-data based on the first difference value and the second difference value.
7. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 4, wherein fall the submodule of making an uproar, include:
an acquisition unit configured to:
Taking a monitoring image of an intelligent street lamp in the second data, and carrying out gray scale processing;
dividing a monitoring image of the intelligent street lamp after gray level processing into a plurality of sub-images;
clustering the plurality of sub-images to obtain a plurality of sub-image sets;
taking any sub-image set as a target sub-image set;
Taking one sub-image in the target sub-image set as a target sub-image;
taking one pixel point in the target sub-image as a first pixel point;
the third calculation unit is used for calculating the brightness value and the ambiguity value of the first pixel point respectively;
the comparison unit is used for comparing the brightness value of the first pixel point with a preset brightness threshold value and comparing the ambiguity value of the first pixel point with the preset ambiguity threshold value;
A third determination unit configured to:
When the brightness value of the first pixel point is smaller than the preset brightness threshold value and the ambiguity value of the first pixel point is larger than the preset ambiguity threshold value, the first pixel point is used as the pixel point to be noise reduced;
traversing all the pixel points to obtain a plurality of pixel points to be noise reduced;
Noise reduction unit for:
denoising a plurality of pixel points to be denoised based on a filtering algorithm to obtain a denoised target sub-image;
Determining the noise reduction amplitude of each pixel point to be noise reduced in the target sub-image based on the target sub-image and the noise reduced target sub-image;
denoising other sub-images in the target sub-image set based on the denoising amplitude of each pixel point to be denoised;
traversing all sub-image sets to obtain a monitoring image of the intelligent street lamp after noise reduction;
and traversing the monitoring images of all intelligent street lamps in the second data to obtain the second data after noise reduction.
8. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 7, wherein the third calculation unit includes:
a luminance calculating subunit configured to:
Determining a target area by taking the first pixel point as a center and taking a preset distance as a radius;
calculating the gray average value of each pixel point in the target area as the brightness value of the first pixel point;
An ambiguity calculating subunit configured to:
calculating the sum of squares of gray difference values of the first pixel point and other pixel points except the first pixel point in the target area to obtain a target sum;
obtaining the total number of other pixel points except the first pixel point in the target area to obtain a target value;
And taking the ratio of the target sum value to the target numerical value as the ambiguity value of the first pixel point.
9. The street lamp intelligent operation and maintenance optimization management platform based on big data analysis as claimed in claim 1, wherein the construction method of the big data analysis model comprises the following steps:
acquiring a big data analysis training data set;
Training the neural network model based on the big data analysis training data set to obtain an initial big data analysis model;
acquiring a big data analysis test data set;
And testing the initial big data analysis model based on the big data analysis test data set, and obtaining a trained big data analysis model when the test result is qualified.
10. The street lamp wisdom fortune dimension optimization management platform based on big data analysis of claim 1, wherein optimizing module includes:
The inquiring sub-module is used for inquiring the intelligent operation and maintenance optimizing database based on the target characteristics of the intelligent street lamp to be optimized and determining a target optimizing strategy of the intelligent street lamp to be optimized;
And the optimizing sub-module is used for optimizing the intelligent street lamp to be optimized based on the target optimizing strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510364690.7A CN120278703B (en) | 2025-03-26 | 2025-03-26 | A Smart Operation and Maintenance Optimization Management Platform for Streetlights Based on Big Data Analytics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510364690.7A CN120278703B (en) | 2025-03-26 | 2025-03-26 | A Smart Operation and Maintenance Optimization Management Platform for Streetlights Based on Big Data Analytics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN120278703A true CN120278703A (en) | 2025-07-08 |
| CN120278703B CN120278703B (en) | 2026-01-06 |
Family
ID=96244031
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510364690.7A Active CN120278703B (en) | 2025-03-26 | 2025-03-26 | A Smart Operation and Maintenance Optimization Management Platform for Streetlights Based on Big Data Analytics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120278703B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190331301A1 (en) * | 2016-12-30 | 2019-10-31 | Du Yuchuan | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing |
| CN111246645A (en) * | 2020-02-26 | 2020-06-05 | 辽宁百思特达半导体科技有限公司 | Multifunctional intelligent lamp pole control system and control method based on 5G communication |
| CN111797706A (en) * | 2020-06-11 | 2020-10-20 | 昭苏县西域马业有限责任公司 | Image-based parasite egg shape recognition system and method |
| WO2022235809A1 (en) * | 2021-05-04 | 2022-11-10 | Innopeak Technology, Inc. | Image restoration for under-display cameras |
| CN119273323A (en) * | 2024-08-14 | 2025-01-07 | 江苏现代照明集团有限公司 | A smart street lamp intelligent monitoring system and method based on cloud computing |
| CN119295048A (en) * | 2024-09-29 | 2025-01-10 | 深圳市胜远威智能科技有限公司 | A smart park comprehensive operation and maintenance intelligent management platform |
| CN119693186A (en) * | 2024-12-04 | 2025-03-25 | 杭州戈虎达科技有限公司 | A transmission line monitoring method based on edge computing |
-
2025
- 2025-03-26 CN CN202510364690.7A patent/CN120278703B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190331301A1 (en) * | 2016-12-30 | 2019-10-31 | Du Yuchuan | Method for leakage detection of underground pipeline corridor based on dynamic infrared thermal image processing |
| CN111246645A (en) * | 2020-02-26 | 2020-06-05 | 辽宁百思特达半导体科技有限公司 | Multifunctional intelligent lamp pole control system and control method based on 5G communication |
| CN111797706A (en) * | 2020-06-11 | 2020-10-20 | 昭苏县西域马业有限责任公司 | Image-based parasite egg shape recognition system and method |
| WO2022235809A1 (en) * | 2021-05-04 | 2022-11-10 | Innopeak Technology, Inc. | Image restoration for under-display cameras |
| CN119273323A (en) * | 2024-08-14 | 2025-01-07 | 江苏现代照明集团有限公司 | A smart street lamp intelligent monitoring system and method based on cloud computing |
| CN119295048A (en) * | 2024-09-29 | 2025-01-10 | 深圳市胜远威智能科技有限公司 | A smart park comprehensive operation and maintenance intelligent management platform |
| CN119693186A (en) * | 2024-12-04 | 2025-03-25 | 杭州戈虎达科技有限公司 | A transmission line monitoring method based on edge computing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN120278703B (en) | 2026-01-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114170480B (en) | A Multi-Threshold Semi-Supervised Intelligent Detection Method for Road Anomalies Based on YOLO V5 | |
| CN114581692B (en) | Vibration damper fault detection method and system based on intelligent pattern recognition | |
| CN118887805A (en) | An intelligent transportation infrastructure inspection management platform based on artificial intelligence | |
| CN119450870A (en) | Street light detection big data analysis and processing system based on smart transportation | |
| CN115170988A (en) | Power grid line fault identification method and system based on deep learning | |
| Chen et al. | The machined surface defect detection of improved superpixel segmentation and two-level region aggregation based on machine vision | |
| CN110636134A (en) | Urban road damage monitoring and maintaining method and system | |
| CN116503817A (en) | Street lighting monitoring method, system, terminal, medium and lighting system based on image recognition | |
| CN120257057A (en) | Intelligent detection system, equipment and storage medium for hidden dangers of expansion joints of GIS equipment based on deep learning | |
| CN117057784B (en) | Street lamp running state monitoring method and system | |
| CN119272116A (en) | A method and system for intelligent detection of appearance quality of prefabricated beams | |
| CN120278703B (en) | A Smart Operation and Maintenance Optimization Management Platform for Streetlights Based on Big Data Analytics | |
| CN112132088A (en) | Inspection point location missing inspection identification method | |
| Cheng et al. | Automated real-time pavement distress analysis | |
| CN118351316B (en) | Bridge inhaul cable apparent defect segmentation method based on deep learning | |
| CN114240995A (en) | A motion state detection method of structural system based on SSD-improved inter-frame difference method-Hough transform | |
| CN110782431B (en) | A deep learning-based detection method for icing areas of high-voltage wires | |
| CN120236183A (en) | An intelligent crack monitoring system based on machine vision and cloud platform | |
| CN117764303B (en) | A road inspection data analysis system and method based on artificial intelligence | |
| CN112188478A (en) | Resident population data acquisition method based on big data analysis | |
| CN118230269A (en) | Lane health detection method, device and storage medium | |
| CN114590199B (en) | LED car light fault diagnosis feedback system | |
| CN112115876A (en) | Water-soluble method experimental process identification method based on 3D convolutional neural network | |
| CN119850628B (en) | Bearing surface quality detection and evaluation system based on visual cognitive model | |
| CN120508940A (en) | Intelligent street lamp illumination data quality control system |
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 |