CN118157326A - Method and device for adjusting running state of power station transformer, medium and electronic equipment - Google Patents
Method and device for adjusting running state of power station transformer, medium and electronic equipment Download PDFInfo
- Publication number
- CN118157326A CN118157326A CN202410566349.5A CN202410566349A CN118157326A CN 118157326 A CN118157326 A CN 118157326A CN 202410566349 A CN202410566349 A CN 202410566349A CN 118157326 A CN118157326 A CN 118157326A
- Authority
- CN
- China
- Prior art keywords
- data
- transformer
- detection result
- processing module
- abnormality detection
- 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
- 238000000034 method Methods 0.000 title claims abstract description 121
- 238000001514 detection method Methods 0.000 claims abstract description 178
- 238000004458 analytical method Methods 0.000 claims abstract description 125
- 230000005672 electromagnetic field Effects 0.000 claims abstract description 88
- 230000005856 abnormality Effects 0.000 claims abstract description 81
- 238000012544 monitoring process Methods 0.000 claims abstract description 72
- 238000005457 optimization Methods 0.000 claims abstract description 52
- 230000000737 periodic effect Effects 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims description 164
- 238000004422 calculation algorithm Methods 0.000 claims description 65
- 230000002159 abnormal effect Effects 0.000 claims description 45
- 238000005516 engineering process Methods 0.000 claims description 34
- 238000013527 convolutional neural network Methods 0.000 claims description 26
- 230000036541 health Effects 0.000 claims description 24
- 238000007781 pre-processing Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000012300 Sequence Analysis Methods 0.000 claims description 17
- 238000004140 cleaning Methods 0.000 claims description 15
- 238000013507 mapping Methods 0.000 claims description 15
- 238000009499 grossing Methods 0.000 claims description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 8
- 238000013450 outlier detection Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 7
- 230000001932 seasonal effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000011425 standardization method Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 238000012731 temporal analysis Methods 0.000 claims description 4
- 238000000700 time series analysis Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 11
- 238000007405 data analysis Methods 0.000 description 10
- 238000012423 maintenance Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000005684 electric field Effects 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013079 data visualisation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of power engineering, and provides a method, a device, a medium and electronic equipment for adjusting the running state of a power station transformer, wherein the method for adjusting the running state of the power station transformer comprises the following steps: acquiring transformer monitoring data of a power station; trend analysis results are generated by carrying out trend and periodic pattern analysis on the operation data of the transformer; generating a data abnormality detection result by performing abnormality detection on operation data of the transformer; generating a thermal anomaly detection result by performing infrared image detection on an infrared image containing a transformer; detecting electromagnetic field data of the transformer to generate an electromagnetic field abnormality detection result; and generating a load optimization scheme according to the operation data, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result of the transformer, and adjusting the load of the transformer according to the load optimization scheme. The method can reduce the damage risk of the transformer.
Description
Technical Field
The invention relates to the technical field of power engineering, in particular to a method and a device for adjusting the running state of a power station transformer, a medium and electronic equipment.
Background
In the technical field of monitoring of electric power systems, the emphasis is on monitoring and controlling the running states of various devices in a power grid, ensuring the continuity and reliability of power supply, covering various stages from power generation, transmission to distribution, and involving a large number of monitoring devices, control systems and data analysis methods, along with the development of technology, the field increasingly adopts information technology and automation technology, such as internet of things, big data analysis and artificial intelligence, so as to improve the efficiency and response speed of the electric power system.
The method for adjusting the running state of the transformer of the power station is a technology for monitoring and evaluating the running state of the transformer in real time, aims to ensure the safe and efficient running of the transformer and discover potential faults or anomalies in time, and mainly aims to reduce the power failure event caused by the faults of the transformer, improve the reliability and stability of a power system, and can discover and adjust the anomalies in time by monitoring various parameters in the running process of the transformer in real time.
In the related technology, the power station transformer running state adjusting method relies on a simple data analysis technology, is difficult to accurately identify a complex fault mode and predict potential risks, and lacks deep data analysis and comprehensive fault detection means, so that fault diagnosis is not timely and accurate enough, thereby delaying processing time and increasing the risk of equipment damage.
Disclosure of Invention
The invention aims to provide a method, a device, a medium and electronic equipment for adjusting the running state of a power station transformer, so as to solve the problems in the related art.
In order to achieve the above object, the present invention provides a method for adjusting the operation state of a power station transformer, comprising:
acquiring transformer monitoring data of a power station, wherein the transformer monitoring data comprises operation data of a transformer, electromagnetic field data of the transformer and an infrared image containing the transformer;
performing trend and periodic mode analysis on the operation data of the transformer by a time sequence analysis method to generate a trend analysis result;
Performing anomaly detection on the operation data of the transformer through an outlier detection algorithm to generate a data anomaly detection result;
Performing infrared image detection on an infrared image containing the transformer through a convolutional neural network to generate a thermal region abnormality detection result, wherein the thermal region abnormality detection result represents the distribution condition of a region of which the surface temperature of the transformer is not in a preset temperature range;
detecting electromagnetic field data of the transformer through an electromagnetic field change analysis technology to generate an electromagnetic field abnormality detection result;
Generating a load optimization scheme according to the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and adjusting the load of the transformer according to the load optimization scheme so as to adjust the operation state of the transformer.
Optionally, before the trend and periodic pattern analysis is performed on the operation data of the transformer by the time series analysis method and the trend analysis result is generated, the power station transformer operation state adjustment method further includes:
and cleaning the operation data of the transformer through a data preprocessing algorithm.
Optionally, the data cleaning of the operation data of the transformer by the data preprocessing algorithm includes:
Filtering out a missing value and an invalid value in the operation data of the transformer through a data screening algorithm to obtain first processing data;
performing data standardization on the first processing data by a Z-score standardization method to obtain second processing data;
removing random noise in the second processing data by a moving average method to obtain third processing data;
filling the missing value in the third processing data by a linear interpolation method to realize data cleaning of the operation data of the transformer.
Optionally, after the load of the transformer is adjusted according to the load optimization scheme to adjust the operation state of the transformer, the power station transformer operation state adjustment method further includes:
acquiring monitoring data of the transformer to obtain secondary monitoring data;
And generating an operation parameter adjustment scheme according to the secondary monitoring data, and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
Optionally, after the operation parameters of the transformer are adjusted according to the operation parameter adjustment scheme to adjust the operation state of the transformer, the power station transformer operation state adjustment method further includes:
acquiring monitoring data of the transformer to obtain tertiary monitoring data;
and generating a transformer running state evaluation report according to the tertiary monitoring data and a preset health scoring model.
Optionally, the trend and periodicity pattern analysis is performed on the operation data of the transformer by using a time sequence analysis method, so as to generate a trend analysis result, which includes:
Extracting trend data in the operation data of the transformer through a seasonal and trend decomposition algorithm;
Smoothing the trend data through an exponential smoothing method to generate smoothed trend data;
Analyzing and identifying a periodic pattern in the smoothed trend data through an autocorrelation algorithm to obtain periodic pattern data;
And analyzing the trend data and the periodic pattern data by a time sequence analysis method to generate a trend analysis result.
Optionally, the detecting the abnormality of the operation data of the transformer by the outlier detection algorithm, generating a data abnormality detection result includes:
Identifying abnormal values in the operation data of the transformer by a box graph analysis method to obtain fourth processing data;
Performing further outlier analysis on the fourth processed data by a Z-score method to determine outlier data;
Grouping the abnormal value data by a K-means clustering method to obtain a clustering grouping result;
and carrying out abnormal mode and potential fault identification on the clustering grouping result by using a correlation rule analysis method, and generating a data abnormal detection result.
Optionally, the infrared image detection is performed on the infrared image including the transformer through a convolutional neural network, and a thermal anomaly detection result is generated, including:
performing image preprocessing on an infrared image containing the transformer to generate a preprocessed image;
Extracting image features of the preprocessed image through a convolutional neural network to generate a feature mapping result;
Performing hot zone anomaly detection on the feature mapping result through a classification layer of a convolutional neural network to generate a preliminary hot zone detection result;
and carrying out hot zone abnormality detection on the preliminary hot zone detection result through a threshold segmentation algorithm to generate a hot zone abnormality detection result.
Optionally, the detecting electromagnetic field data of the transformer by electromagnetic field variation analysis technology, generating an electromagnetic field anomaly detection result, includes:
carrying out data normalization processing on electromagnetic field data of the transformer;
extracting time-frequency characteristics of electromagnetic field data subjected to data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data;
And carrying out anomaly detection on the time-frequency characteristic data through an anomaly detection algorithm to generate an electromagnetic field anomaly detection result.
Optionally, the generating a load optimization scheme according to the operation data of the transformer, the trend analysis result, the data anomaly detection result, the hot zone anomaly detection result, and the electromagnetic field anomaly detection result includes:
Analyzing load demands through a demand analysis algorithm based on the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and generating a demand analysis result;
generating a load optimization model corresponding to the demand analysis result according to the demand analysis result;
And solving the load optimization model by a simplex method to generate a load optimization scheme.
The invention also provides a device for adjusting the running state of the power station transformer, which comprises:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring transformer monitoring data of a power station, and the transformer monitoring data comprise operation data of a transformer, electromagnetic field data of the transformer and an infrared image containing the transformer;
the first processing module is used for carrying out trend and periodic mode analysis on the operation data of the transformer through a time sequence analysis method to generate a trend analysis result;
The second processing module is used for carrying out anomaly detection on the operation data of the transformer through an outlier detection algorithm to generate a data anomaly detection result;
The third processing module is used for carrying out infrared image detection on an infrared image containing the transformer through a convolutional neural network to generate a thermal region abnormality detection result, wherein the thermal region abnormality detection result represents the distribution condition of a region of which the surface temperature of the transformer is not in a preset temperature range;
The fourth processing module is used for detecting electromagnetic field data of the transformer through an electromagnetic field change analysis technology and generating an electromagnetic field abnormality detection result;
And the fifth processing module is used for generating a load optimization scheme according to the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and adjusting the load of the transformer according to the load optimization scheme so as to adjust the operation state of the transformer.
Optionally, the power station transformer operation state adjustment device further includes:
and the sixth processing module is used for cleaning the operation data of the transformer through a data preprocessing algorithm.
Optionally, the sixth processing module includes:
The first sub-processing module is used for filtering out missing values and invalid values in the operation data of the transformer through a data screening algorithm to obtain first processing data;
The second sub-processing module is used for carrying out data standardization on the first processing data through a Z-score standardization method to obtain second processing data;
The third sub-processing module is used for removing random noise in the second processing data through a moving average method to obtain third processing data;
and the fourth sub-processing module is used for filling the missing value in the third processing data by a linear interpolation method to realize data cleaning on the operation data of the transformer.
Optionally, the power station transformer operation state adjustment device further includes:
the second acquisition module is used for acquiring the monitoring data of the transformer to obtain secondary monitoring data;
And the seventh processing module is used for generating an operation parameter adjustment scheme according to the secondary monitoring data and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
Optionally, the power station transformer operation state adjustment device further includes:
The third acquisition module is used for acquiring the monitoring data of the transformer to obtain tertiary monitoring data;
and the eighth processing module is used for generating a transformer running state evaluation report according to the tertiary monitoring data and a preset health scoring model.
Optionally, the first processing module includes:
a fifth sub-processing module for extracting trend data from the operation data of the transformer through a seasonal and trend decomposition algorithm;
The sixth sub-processing module is used for smoothing the trend data through an exponential smoothing method to generate smoothed trend data;
a seventh sub-processing module, configured to analyze and identify a periodic pattern in the smoothed trend data by using an autocorrelation algorithm, so as to obtain periodic pattern data;
And the eighth sub-processing module is used for analyzing the trend data and the periodic pattern data through a time sequence analysis method to generate a trend analysis result.
Optionally, the second processing module includes:
A ninth sub-processing module, configured to identify an abnormal value in the operation data of the transformer by using a box-type graph analysis method, so as to obtain fourth processed data;
a tenth sub-processing module, configured to perform further outlier analysis on the fourth processed data by using a Z-score method, and determine outlier data;
The eleventh sub-processing module is used for grouping the abnormal value data through a K-means clustering method to obtain a clustering grouping result;
And the twelfth sub-processing module is used for identifying the abnormal mode and potential faults of the clustering grouping result through an association rule analysis method and generating a data abnormal detection result.
Optionally, the third processing module includes:
A thirteenth sub-processing module, configured to perform image preprocessing on an infrared image including the transformer, and generate a preprocessed image;
the fourteenth sub-processing module is used for extracting image features of the preprocessed image through a convolutional neural network and generating a feature mapping result;
A fifteenth sub-processing module, configured to perform a hot zone anomaly detection on the feature mapping result through a classification layer of the convolutional neural network, and generate a preliminary hot zone detection result;
And the sixteenth sub-processing module is used for carrying out hot zone abnormality detection on the preliminary hot zone detection result through a threshold segmentation algorithm to generate a hot zone abnormality detection result.
Optionally, the fourth processing module includes:
Seventeenth sub-processing module, which is used for carrying out data normalization processing on electromagnetic field data of the transformer;
The eighteenth sub-processing module is used for extracting the time-frequency characteristics of the electromagnetic field data after the data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data;
And the nineteenth sub-processing module is used for carrying out anomaly detection on the time-frequency characteristic data through an anomaly detection algorithm to generate an electromagnetic field anomaly detection result.
Optionally, the fifth processing module includes:
The twentieth sub-processing module is used for analyzing load demands through a demand analysis algorithm based on the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result to generate a demand analysis result;
a twenty-first sub-processing module, configured to generate a load optimization model corresponding to the demand analysis result according to the demand analysis result;
And the twenty-second sub-processing module is used for solving the load optimization model through a simplex method to generate a load optimization scheme.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the power station transformer operating state adjustment method described above.
The present invention also provides an electronic device including:
a memory having a computer program stored thereon;
and the processor is used for executing the computer program in the memory to realize the steps of the power station transformer operation state adjustment method.
The technical scheme provided by the embodiment of the invention can comprise the following beneficial effects:
Potential risks and faults of the transformer are accurately identified through time sequence analysis and anomaly detection, infrared images are detected through a convolutional neural network, electromagnetic field data are comprehensively and carefully detected, and an excellent load optimization scheme is generated to conduct load optimization so as to adjust the running state of the transformer based on running data of the transformer and combined trend analysis results, data anomaly detection results, hot zone anomaly detection results and electromagnetic field anomaly detection results, so that problems are timely prevented and solved, and damage risks of the transformer are reduced.
Additional features and advantages of the invention will be set forth in the detailed description which follows.
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 description serve to explain, without limitation, the invention. In the drawings:
Fig. 1 is a flow chart illustrating a method of power plant transformer operating state adjustment, according to an exemplary embodiment.
FIG. 2 is a flow chart illustrating another power plant transformer operating condition adjustment method according to an exemplary embodiment.
Fig. 3 is a flowchart illustrating sub-steps of step S2, according to an exemplary embodiment.
Fig. 4 is a flowchart illustrating sub-steps of step S3, according to an exemplary embodiment.
Fig. 5 is a flowchart illustrating sub-steps of step S4, according to an exemplary embodiment.
Fig. 6 is a flowchart illustrating sub-steps of step S5, according to an exemplary embodiment.
Fig. 7 is a flowchart illustrating sub-steps of step S6, according to an exemplary embodiment.
Fig. 8 is a block diagram illustrating a power plant transformer operating condition adjustment device according to an exemplary embodiment.
Fig. 9 is a block diagram of an electronic device, according to an example embodiment.
Fig. 10 is a block diagram of another electronic device, shown in accordance with an exemplary embodiment.
Detailed Description
The following describes specific embodiments of the present invention in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the invention, are not intended to limit the invention.
In the following description, the words "first," "second," and the like are used merely for distinguishing between the descriptions and not for indicating or implying a relative importance or order.
In the technical field of monitoring of electric power systems, the emphasis is on monitoring and controlling the running states of various devices in a power grid, ensuring the continuity and reliability of power supply, covering various stages from power generation, transmission to distribution, and involving a large number of monitoring devices, control systems and data analysis methods, along with the development of technology, the field increasingly adopts information technology and automation technology, such as internet of things, big data analysis and artificial intelligence, so as to improve the efficiency and response speed of the electric power system.
The method for adjusting the running state of the transformer of the power station is a technology for monitoring and evaluating the running state of the transformer in real time, aims to ensure the safe and efficient running of the transformer and discover potential faults or anomalies in time, and mainly aims to reduce the power failure event caused by the faults of the transformer, improve the reliability and stability of a power system, and can discover and adjust the anomalies in time by monitoring various parameters in the running process of the transformer in real time.
In the related technology, the power station transformer running state adjusting method relies on a simple data analysis technology, is difficult to accurately identify a complex fault mode and predict potential risks, and lacks deep data analysis and comprehensive fault detection means, so that fault diagnosis is not timely and accurate enough, thereby delaying processing time and increasing the risk of equipment damage.
In order to solve the technical problems, potential risks and faults of the transformer are accurately identified through time sequence analysis and anomaly detection, the infrared image is detected through a convolutional neural network, and electromagnetic field data are comprehensively and carefully analyzed, so that the fault detection of the transformer is more comprehensive and careful, and an excellent load optimization scheme is generated to perform load optimization based on the operation data of the transformer and the combination of trend analysis results, data anomaly detection results, hot zone anomaly detection results and electromagnetic field anomaly detection results so as to adjust the operation state of the transformer, thereby timely preventing and solving the problems and reducing the damage risk of the transformer.
Fig. 1 is a flow chart illustrating a method of power plant transformer operating state adjustment, according to an exemplary embodiment. As shown in fig. 1, the power station transformer operation state adjustment method may be applied to an electronic device, and the power station transformer operation state adjustment method may include steps S1 to S6.
Step S1, transformer monitoring data of a power station are obtained.
The transformer monitoring data comprises operation data of the transformer, electromagnetic field data of the transformer and infrared images containing the transformer.
The operational data of the transformer may be, but is not limited to, voltage of the transformer, current of the transformer, bushing data of the transformer, dielectric loss of the transformer, oil chromatography data of the transformer, etc.
The electromagnetic field data of the transformer may be, but is not limited to, electric field strength, magnetic induction strength, electromagnetic field spectrum, and the like.
The infrared image containing the transformer can be an infrared image containing a part or whole of the transformer acquired by a thermal infrared imager.
And S2, carrying out trend and periodic pattern analysis on the operation data of the transformer by a time sequence analysis method to generate a trend analysis result.
And S3, performing abnormality detection on the operation data of the transformer through an outlier detection algorithm to generate a data abnormality detection result.
Firstly, decomposing operation data of a transformer according to a time sequence so as to independently analyze characteristics of each part of data, and then identifying and analyzing a change rule in the time sequence data through trend analysis and periodic pattern analysis, wherein the trend analysis comprises linear analysis and nonlinear analysis to obtain a trend analysis result, and detecting abnormal values and outliers in the time sequence data to obtain a data abnormality detection result.
And S4, carrying out infrared image detection on the infrared image containing the transformer through a convolutional neural network to generate a thermal anomaly detection result.
The detection result of the abnormal thermal region represents the distribution condition of the region of the surface temperature of the transformer, which is not in the preset temperature range.
And detecting the infrared image through a convolutional neural network, and identifying the region with abnormal surface temperature of the transformer in the infrared image.
In other embodiments, the surface temperature of the corresponding region may be indicated by the joints at different positions of the transformer, so as to improve the efficiency of generating the thermal anomaly detection result.
And S5, detecting electromagnetic field data of the transformer through an electromagnetic field change analysis technology, and generating an electromagnetic field abnormality detection result.
Electromagnetic field data are detected through an electromagnetic field change analysis technology, and the abnormal situation of an electromagnetic field is identified.
Electromagnetic field data of the transformer may be detected from different dimensions. For example, the electromagnetic field abnormality detection result may include a case where the electric field intensity of the transformer is not within a preset electric field intensity range, the electromagnetic field abnormality detection result may also include a case where the magnetic field intensity of the transformer is not within a preset magnetic field intensity range, the electromagnetic field abnormality detection result may also include a case where the magnetic induction intensity of the transformer is not within a preset magnetic induction intensity range, the electromagnetic field abnormality detection result may also include a case where the spectral characteristic of the transformer is not within a preset spectral characteristic, and the like.
And S6, generating a load optimization scheme according to the operation data, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result of the transformer, and adjusting the load of the transformer according to the load optimization scheme so as to adjust the operation state of the transformer.
Through time sequence analysis and anomaly detection, potential risks and faults of the transformer are accurately identified, the infrared image is detected through the convolutional neural network, electromagnetic field data are comprehensively and finely detected, and an excellent load optimization scheme is generated to optimize the load so as to adjust the running state of the transformer and optimize the load distribution based on the running data of the transformer and the combined trend analysis result, the data anomaly detection result, the hot zone anomaly detection result and the electromagnetic field anomaly detection result, so that problems are timely prevented and solved, and the damage risk of the transformer is reduced.
In one possible embodiment, before trend and periodic pattern analysis is performed on the operation data of the transformer by the time series analysis method, the power station transformer operation state adjustment method further includes:
and cleaning the operation data of the transformer through a data preprocessing algorithm.
By cleaning the operation data of the transformer, the quality and usability of the operation data of the transformer are improved, and false alarms are reduced.
In one possible implementation, the data cleansing of the operational data of the transformer by the data preprocessing algorithm may include:
Filtering out missing values and invalid values in the operation data of the transformer through a data screening algorithm to obtain first processing data;
carrying out data standardization on the first processing data by a Z-score standardization method to obtain second processing data;
Removing random noise in the second processing data by a moving average method to obtain third processing data;
Filling missing values in the third processing data by a linear interpolation method, and realizing data cleaning on the operation data of the transformer.
By adopting a data screening algorithm, the missing value and invalid record in the operation data of the transformer are detected and identified, and the authenticity and usability of the data are ensured. And the data after screening is standardized by a Z-score standardization method so as to eliminate scale differences among different monitoring parameters and enhance the comparability of the data. Random noise is removed by applying a moving average method to maintain the main trend of data and ensure the smoothness of the data. The missing values are filled through a linear interpolation method to maintain the continuity and the integrity of data, ensure the standards of the operation data of the transformer in terms of quality, integrity and consistency, and provide a reliable basis for subsequent data analysis and anomaly detection.
In a possible implementation manner, referring to fig. 2 on the basis of fig. 1, fig. 2 is a flowchart illustrating another method for adjusting the operation state of a transformer of a power station according to an exemplary embodiment, and after adjusting the load of the transformer to adjust the operation state of the transformer according to a load optimization scheme, the method for adjusting the operation state of the transformer of the power station may further include step S7 and step S8.
And S7, acquiring monitoring data of the transformer to obtain secondary monitoring data.
And S8, generating an operation parameter adjustment scheme according to the secondary monitoring data, and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
The secondary monitoring data may be transformer monitoring data of the transformer substation acquired after the load of the transformer is adjusted.
And adjusting the operation parameters by adopting a fuzzy logic control algorithm based on the secondary monitoring data to generate an operation parameter adjustment scheme. The operating parameters may be, but are not limited to, output voltage, output current, harmonic filtering, zero sequence current, short circuit impedance, oil level control, cooling mode, etc.
Furthermore, an intelligent scheduling strategy can be adopted to make an operation plan of the transformer, an optimal scheduling scheme is generated to ensure that the equipment operates in an optimal state, then the operation state adjustment is implemented by means of an intelligent decision support system, the operation condition of the transformer is monitored, an operation state adjustment result is generated, data monitoring, fuzzy logic control, scheduling strategy and intelligent decision support are integrated, comprehensive intelligent management is provided for the health state monitoring of the transformer of the power station, the stability, safety and high efficiency of the equipment are ensured, and therefore potential problems are reduced to the greatest extent, and the reliability of the equipment is improved.
In a possible embodiment, referring to fig. 2, after adjusting the operation parameters of the transformer to adjust the operation state of the transformer according to the operation parameter adjustment scheme, the power station transformer operation state adjustment method may further include step S9 and step S10.
And S9, acquiring monitoring data of the transformer to obtain tertiary monitoring data.
And step S10, generating a transformer running state evaluation report according to the three monitoring data and a preset health scoring model.
The tertiary monitoring data may be transformer monitoring data of the transformer substation acquired after the operation parameters of the transformer are adjusted.
And inputting the three-time monitoring data into a preset health scoring model to obtain a transformer running state evaluation report. The transformer operating state evaluation report is specifically a health status and performance score report of the transformer.
In other embodiments, the generation manner of the transformer operation state evaluation report may also be as follows:
Firstly, adopting a characteristic standardization technology to the third monitoring data to generate preprocessing evaluation data; then, based on the preprocessing evaluation data, adopting a random forest algorithm to perform model training on the health state of the transformer, and generating a health scoring model; furthermore, based on the health scoring model, performing health state assessment by adopting a machine learning inference technology, and generating a preliminary health assessment result; and finally, based on the preliminary health evaluation result, performing evaluation result optimization by adopting a post-processing technology, and generating a transformer running state evaluation report.
Preprocessing the running state adjustment result through a characteristic standardization technology to generate preprocessing evaluation data so as to ensure the consistency and comparability of the data. The health scoring model is trained through machine learning technologies such as random forest algorithm and the like so as to accurately evaluate the health state of the transformer. Preliminary health assessment results, including health scores and status classifications, are generated by assessing the pre-processed assessment data using machine learning inference techniques. The preliminary evaluation result is optimized through the post-processing technology, other relevant factors are considered, a transformer running state evaluation report is generated, wherein the report comprises detailed health state description, recommended maintenance measures and performance scores, the data preprocessing, machine learning model training and evaluation and the application of the post-processing technology are integrated, comprehensive evaluation and reporting are provided for the health state of the power station transformer, operators can better know the state of the equipment, and the maintenance strategies are formulated to ensure the reliability and performance of the equipment.
In one possible implementation, referring to fig. 3, step S2 may include steps S21 to S24.
And S21, extracting trend data in the operation data of the transformer through a seasonal and trend decomposition algorithm.
Step S22, smoothing the trend data through an exponential smoothing method to generate smoothed trend data.
Step S23, analyzing and identifying the periodic pattern in the smoothed trend data through an autocorrelation algorithm to obtain periodic pattern data.
And S24, analyzing the trend data and the periodic pattern data by a time sequence analysis method to generate a trend analysis result.
The seasonal and trend decomposition algorithm is used for extracting trend data, long-term change trend of the data is captured, in step S22, the trend data is smoothed by adopting an exponential smoothing method to remove noise and irregular fluctuation, the trend is ensured to be more stable, in step S23, a periodic mode is analyzed and identified through an autocorrelation algorithm, periodic fluctuation characteristics in the data are revealed, the time sequence analysis is carried out through step S24, trend data and periodic mode data are integrated, a trend analysis report is generated, the trend analysis report comprises long-term trend description and periodic mode information, an important basis is provided for predicting the health condition of equipment, comprehensive analysis of the power station transformer operation data is ensured, and potential problems are found early and the reliability of a power system is improved.
In one possible implementation, referring to fig. 4, step S3 may include steps S31 to S34.
Step S31, identifying abnormal values in the operation data of the transformer by a box graph analysis method to obtain fourth processing data.
And S32, further performing outlier analysis on the fourth processed data by a Z-score method to determine outlier data.
And S33, grouping the abnormal value data by a K-means clustering method to obtain a clustering grouping result.
And step S34, carrying out abnormal mode and potential fault identification on the clustering grouping result by using a correlation rule analysis method, and generating a data abnormal detection result.
In step S31, the abnormal values are identified by using a box graph analysis method, a preliminary abnormal value identification result is generated, existing abnormal data points are identified, in step S32, the preliminary abnormal values are subjected to deeper analysis by using a Z-score method, abnormal value data are generated, the deviation degree of the abnormal values is recorded, in step S33, the abnormal values are grouped by using a K-means clustering algorithm, abnormal value clustering analysis results are generated, similar abnormal value composition is revealed, in step S34, the association and pattern among the abnormal values are mined by using an association rule analysis method, so that abnormal patterns and potential faults are identified, data abnormality detection results are generated, including description of the potential faults and related abnormal value clustering information, powerful monitoring and evaluation tools are provided for the operation state of the power station transformer, early problem discovery is facilitated, necessary maintenance measures are adopted, and reliability and continuous operation of equipment are ensured.
In one possible implementation, referring to fig. 5, step S4 may include steps S41 to S44.
In step S41, an image preprocessing is performed on the infrared image including the transformer, and a preprocessed image is generated.
The image preprocessing algorithm may be, but is not limited to, noise suppression, temperature range stretching, thermal tone mapping, image sharpening, image correction, and the like.
And step S42, extracting image features of the preprocessed image through a convolutional neural network, and generating a feature mapping result.
And step S43, carrying out hot zone anomaly detection on the feature mapping result through a classification layer of the convolutional neural network to generate a preliminary hot zone detection result.
And S44, performing thermal region abnormality detection on the preliminary thermal region detection result through a threshold segmentation algorithm to generate a thermal region abnormality detection result.
In step S41, the image preprocessing algorithm is used to process the infrared image, so as to improve the quality, accuracy and reliability of the infrared image, and provide a better basis for subsequent analysis, detection, identification and other applications. In step S42, the image features are extracted by using the convolutional neural network to generate a feature mapping result, the feature mapping result is helpful for identifying the abnormal hot zone, in step S43, the classification layer of the convolutional neural network is used for carrying out preliminary abnormal hot zone identification on the features, the position of the abnormal hot zone is identified, in step S44, the hot zone identification is refined through a threshold segmentation algorithm, the false identification is reduced, an abnormal hot zone detection report is generated, the information such as the position, the size and the temperature of the abnormal hot zone is included, the information of an infrared image is fully utilized, a powerful image analysis tool is provided for monitoring the health state of a power station transformer, the potential problems are helped to be accurately identified, necessary maintenance measures are taken, and the reliability and the performance of equipment are ensured.
In one possible implementation, referring to fig. 6, step S5 may include steps S51 to S53.
Step S51, performing data normalization processing on electromagnetic field data of the transformer.
And S52, extracting time-frequency characteristics of the electromagnetic field data subjected to the data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data.
Step S53, the time-frequency characteristic data is subjected to anomaly detection through an anomaly detection algorithm, and an electromagnetic field anomaly detection result is generated.
In step S51, the electromagnetic field data is subjected to data normalization processing to ensure consistency and comparability of the data, in step S52, a time-frequency analysis technique is used to extract time-frequency characteristics of the electromagnetic field to reflect the variation condition of the electromagnetic field, in step S53, an anomaly detection algorithm is used to identify anomaly patterns in the electromagnetic field, and identify potential problems.
In other embodiments, electromagnetic field abnormality detection results can be presented in a visual form through a data visualization technology, such as graphic representation, feature description and fault information and maintenance suggestions, electromagnetic field analysis and data visualization technology are combined, a powerful tool is provided for monitoring and evaluating the health state of the power station transformer, early problem discovery is facilitated, necessary maintenance measures are taken, and reliability and performance of equipment are ensured.
In one possible implementation, referring to fig. 7, step S6 may include steps S61 to S63.
Step S61, analyzing load demands through a demand analysis algorithm based on operation data, trend analysis results, data abnormality detection results, hot zone abnormality detection results and electromagnetic field abnormality detection results of the transformer, and generating a demand analysis result.
For example, an analysis model may be established based on an analysis algorithm, and the operation data, the trend analysis result, the data anomaly detection result, the hot zone anomaly detection result, and the electromagnetic field anomaly detection result of the transformer are input into the analysis model, so that the requirement analysis result may be obtained.
Step S62, according to the demand analysis result, generating a load optimization model corresponding to the demand analysis result.
Based on the demand analysis result, a linear programming model is adopted to construct a load optimization problem, optimization modeling is carried out, and a load optimization model is generated.
And step S63, solving the load optimization model through a simplex method to generate a load optimization scheme.
Based on the load optimization model, solving the linear programming problem by adopting a simplex method, and carrying out load distribution optimization to generate a load optimization scheme.
In step S62, a linear programming model is constructed, the load balancing problem is formed into a mathematical model, and in consideration of the objective function and the constraint condition, in step S63, a simplex method or other linear programming solving method is adopted, so as to obtain the optimization result of load distribution.
In other embodiments, a specific load adjustment strategy and scheme can be formulated by means of an intelligent decision method, reasonable distribution of loads and safety of equipment operation are ensured, data analysis, optimization modeling and intelligent decision are integrated, and a feasible load optimization scheme is provided for monitoring and maintaining the health state of a power station transformer so as to ensure the reliability and performance of the equipment.
Based on the same inventive concept, to implement the above method embodiments, the present embodiment provides a power station transformer operation state adjustment device 600, referring to fig. 8, the power station transformer operation state adjustment device 600 may be applied to an electronic device, and the power station transformer operation state adjustment device 600 may include:
A first acquisition module 601, configured to acquire transformer monitoring data of a power station, where the transformer monitoring data includes operation data of a transformer, electromagnetic field data of the transformer, and an infrared image including the transformer;
The first processing module 602 is configured to perform trend and periodic pattern analysis on the operation data of the transformer by using a time sequence analysis method, so as to generate a trend analysis result;
The second processing module 603 is configured to perform anomaly detection on the operation data of the transformer through an outlier detection algorithm, and generate a data anomaly detection result;
The third processing module 604 is configured to perform infrared image detection on an infrared image including a transformer through a convolutional neural network, and generate a thermal anomaly detection result, where the thermal anomaly detection result characterizes a distribution situation of a region where a surface temperature of the transformer is not within a preset temperature range;
a fourth processing module 605, configured to detect electromagnetic field data of the transformer by using an electromagnetic field variation analysis technique, and generate an electromagnetic field anomaly detection result;
The fifth processing module 606 is configured to generate a load optimization scheme according to the operation data, the trend analysis result, the data anomaly detection result, the hot zone anomaly detection result, and the electromagnetic field anomaly detection result of the transformer, and adjust the load of the transformer according to the load optimization scheme to adjust the operation state of the transformer.
Optionally, the power station transformer operating state adjustment device 600 further includes:
And the sixth processing module is used for cleaning the operation data of the transformer through a data preprocessing algorithm.
Optionally, the sixth processing module includes:
The first sub-processing module is used for filtering the missing value and the invalid value in the operation data of the transformer through a data screening algorithm to obtain first processing data;
The second sub-processing module is used for carrying out data standardization on the first processing data through a Z-score standardization method to obtain second processing data;
the third sub-processing module is used for removing random noise in the second processing data through a moving average method to obtain third processing data;
and the fourth sub-processing module is used for filling the missing value in the third processing data by a linear interpolation method to realize data cleaning on the operation data of the transformer.
Optionally, the power station transformer operating state adjustment device 600 further includes:
The second acquisition module is used for acquiring monitoring data of the transformer to obtain secondary monitoring data;
And the seventh processing module is used for generating an operation parameter adjustment scheme according to the secondary monitoring data and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
Optionally, the power station transformer operating state adjustment device 600 further includes:
the third acquisition module is used for acquiring monitoring data of the transformer to obtain tertiary monitoring data;
and the eighth processing module is used for generating a transformer running state evaluation report according to the tertiary monitoring data and a preset health scoring model.
Optionally, the first processing module 602 includes:
the fifth sub-processing module is used for extracting trend data in the operation data of the transformer through a seasonal and trend decomposition algorithm;
the sixth sub-processing module is used for smoothing the trend data through an exponential smoothing method and generating smoothed trend data;
The seventh sub-processing module is used for analyzing and identifying the periodic pattern in the smoothed trend data through an autocorrelation algorithm to obtain periodic pattern data;
And the eighth sub-processing module is used for analyzing the trend data and the periodic pattern data through a time sequence analysis method to generate a trend analysis result.
Optionally, the second processing module 603 includes:
a ninth sub-processing module, configured to identify an abnormal value in the operation data of the transformer by using a box graph analysis method, to obtain fourth processed data;
a tenth sub-processing module, configured to perform further outlier analysis on the fourth processed data by using a Z-score method, and determine outlier data;
The eleventh sub-processing module is used for grouping the abnormal value data through a K-means clustering method to obtain a clustering grouping result;
And the twelfth sub-processing module is used for carrying out abnormal mode and potential fault identification on the clustering grouping result through the association rule analysis method and generating a data abnormal detection result.
Optionally, the third processing module 604 includes:
A thirteenth sub-processing module, configured to perform image preprocessing on an infrared image including the transformer, and generate a preprocessed image;
the fourteenth sub-processing module is used for extracting image features of the preprocessed image through a convolutional neural network to generate a feature mapping result;
the fifteenth sub-processing module is used for detecting the hotspots of the feature mapping result through the classification layer of the convolutional neural network to generate a preliminary hotspots detection result;
and the sixteenth sub-processing module is used for carrying out hot zone abnormality detection on the preliminary hot zone detection result through a threshold segmentation algorithm to generate a hot zone abnormality detection result.
Optionally, the fourth processing module 605 includes:
Seventeenth sub-processing module, which is used for carrying out data normalization processing on electromagnetic field data of the transformer;
The eighteenth sub-processing module is used for extracting the time-frequency characteristics of the electromagnetic field data after the data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data;
And the nineteenth sub-processing module is used for carrying out anomaly detection on the time-frequency characteristic data through an anomaly detection algorithm to generate an electromagnetic field anomaly detection result.
Optionally, the fifth processing module 606 includes:
The twentieth sub-processing module is used for analyzing the load demand through a demand analysis algorithm based on the operation data, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result of the transformer to generate a demand analysis result;
The twenty-first sub-processing module is used for generating a load optimization model corresponding to the demand analysis result according to the demand analysis result;
And the twenty-second sub-processing module is used for solving the load optimization model through a simplex method to generate a load optimization scheme.
The specific manner in which the respective modules perform the operations in relation to the power station transformer operating condition adjustment device in the above-described embodiment has been described in detail in relation to the embodiment of the power station transformer operating condition adjustment method, and will not be described in detail herein.
Fig. 9 is a block diagram illustrating an electronic device 1900 according to an example embodiment. For example, electronic device 1900 may be provided as a server. Referring to fig. 9, the electronic device 1900 includes a first processor 1922, which may be one or more in number, and a first memory 1932 for storing computer programs executable by the first processor 1922. The computer program stored in the first memory 1932 may include one or more modules each corresponding to a set of instructions. Further, the first processor 1922 may be configured to execute the computer program to perform the power plant transformer operating state adjustment method described above.
In addition, the electronic device 1900 may further include a power component 1926 and a first communication component 1950, the power component 1926 may be configured to perform power management of the electronic device 1900, and the first communication component 1950 may be configured to enable communication of the electronic device 1900, e.g., wired or wireless communication. In addition, the electronic device 1900 may also include an input/output interface 1958. The electronic device 1900 may operate in accordance with an operating system stored in the first memory 1932.
In another exemplary embodiment, a computer readable storage medium is also provided comprising program instructions which, when executed by the first processor, implement the steps of the power plant transformer operating state adjustment method described above. For example, the non-transitory computer readable storage medium may be the first memory 1932 described above that includes program instructions executable by the first processor 1922 of the electronic device 1900 to perform the power plant transformer operating state adjustment method described above.
In another exemplary embodiment, a computer program product is also provided, which comprises a computer program executable by a programmable apparatus, the computer program having code portions for performing the above-described power plant transformer operating state adjustment method when being executed by the programmable apparatus.
Fig. 10 is a block diagram of an electronic device 700, according to an example embodiment. As shown in fig. 10, the electronic device 700 may include: a second processor 701, a second memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input/output (I/O) interface 704, and a second communication component 705.
The second processor 701 is configured to control the overall operation of the electronic device 700, so as to complete all or part of the steps in the power station transformer operation state adjustment method described above. The second memory 702 is used to store various types of data to support operation on the electronic device 700, which may include, for example, instructions for any application or method operating on the electronic device 700, as well as application-related data, such as contact data, transceived messages, pictures, audio, video, and the like. The second Memory 702 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as a static random access second Memory (Static Random Access Memory, SRAM for short), an electrically erasable programmable Read-Only second Memory (ELECTRICALLY ERASABLE PROGRAMMABLE READ-Only Memory, EEPROM for short), an erasable programmable Read-Only second Memory (Erasable Programmable Read-Only Memory, EPROM for short), a programmable Read-Only second Memory (Programmable Read-Only Memory, PROM for short), a Read-Only second Memory (ROM for short), a magnetic second Memory, a flash second Memory, a magnetic disk, or an optical disk. The multimedia component 703 can include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. The screen may be used to display transformer monitoring data, infrared images containing transformers, transformer operating status assessment reports, and the like. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the second memory 702 or transmitted through the second communication component 705. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 704 provides an interface between the second processor 701 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The second communication component 705 is for wired or wireless communication between the electronic device 700 and other devices. Wireless Communication, such as Wi-Fi, bluetooth, near Field Communication (NFC) for short, 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or one or a combination of more of them, is not limited herein. The corresponding second communication component 705 may thus comprise: wi-Fi module, bluetooth module, NFC module, etc.
In an exemplary embodiment, the electronic device 700 may be implemented by one or more Application-specific integrated circuits (ASIC), digital signal second Processor (DIGITAL SIGNAL Processor, DSP), digital signal processing device (DIGITAL SIGNAL Processing Device, DSPD), programmable logic device (Programmable Logic Device, PLD), field programmable gate array (Field Programmable GATE ARRAY, FPGA), controller, microcontroller, micro-second Processor, or other electronic component for performing the power station transformer operating state adjustment method described above.
In another exemplary embodiment, a computer readable storage medium is also provided comprising program instructions which, when executed by the second processor, implement the steps of the power plant transformer operating state adjustment method described above. For example, the computer readable storage medium may be the second memory 702 comprising program instructions described above, which are executable by the second processor 701 of the electronic device 700 to perform the power plant transformer operating state adjustment method described above.
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to the specific details of the above embodiments, and various simple modifications can be made to the technical solution of the present invention within the scope of the technical concept of the present invention, and all the simple modifications belong to the protection scope of the present invention.
In addition, the specific features described in the above embodiments may be combined in any suitable manner without contradiction. The various possible combinations of the invention are not described in detail in order to avoid unnecessary repetition.
Moreover, any combination of the various embodiments of the invention can be made without departing from the spirit of the invention, which should also be considered as disclosed herein.
Claims (22)
1. A method for adjusting the operating state of a power station transformer, comprising:
acquiring transformer monitoring data of a power station, wherein the transformer monitoring data comprises operation data of a transformer, electromagnetic field data of the transformer and an infrared image containing the transformer;
performing trend and periodic mode analysis on the operation data of the transformer by a time sequence analysis method to generate a trend analysis result;
Performing anomaly detection on the operation data of the transformer through an outlier detection algorithm to generate a data anomaly detection result;
Performing infrared image detection on an infrared image containing the transformer through a convolutional neural network to generate a thermal region abnormality detection result, wherein the thermal region abnormality detection result represents the distribution condition of a region of which the surface temperature of the transformer is not in a preset temperature range;
detecting electromagnetic field data of the transformer through an electromagnetic field change analysis technology to generate an electromagnetic field abnormality detection result;
Generating a load optimization scheme according to the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and adjusting the load of the transformer according to the load optimization scheme so as to adjust the operation state of the transformer.
2. The power station transformer operating state adjustment method according to claim 1, characterized in that before the trend and periodic pattern analysis is performed on the operating data of the transformer by the time series analysis method, the power station transformer operating state adjustment method further comprises:
and cleaning the operation data of the transformer through a data preprocessing algorithm.
3. The method for adjusting the operation state of a power station transformer according to claim 2, wherein the data cleaning of the operation data of the transformer by the data preprocessing algorithm comprises:
Filtering out a missing value and an invalid value in the operation data of the transformer through a data screening algorithm to obtain first processing data;
performing data standardization on the first processing data by a Z-score standardization method to obtain second processing data;
removing random noise in the second processing data by a moving average method to obtain third processing data;
filling the missing value in the third processing data by a linear interpolation method to realize data cleaning of the operation data of the transformer.
4. The power plant transformer operating state adjustment method according to claim 1, characterized in that after the adjusting of the load of the transformer to adjust the operating state of the transformer according to the load optimization scheme, the power plant transformer operating state adjustment method further comprises:
acquiring monitoring data of the transformer to obtain secondary monitoring data;
And generating an operation parameter adjustment scheme according to the secondary monitoring data, and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
5. The power station transformer operating state adjustment method of claim 4, further comprising, after said adjusting the operating parameters of the transformer according to the operating parameter adjustment scheme to adjust the operating state of the transformer:
acquiring monitoring data of the transformer to obtain tertiary monitoring data;
and generating a transformer running state evaluation report according to the tertiary monitoring data and a preset health scoring model.
6. The power station transformer operating state adjustment method according to claim 1, wherein the trend and periodicity pattern analysis is performed on the operating data of the transformer by a time series analysis method, and generating a trend analysis result includes:
Extracting trend data in the operation data of the transformer through a seasonal and trend decomposition algorithm;
Smoothing the trend data through an exponential smoothing method to generate smoothed trend data;
Analyzing and identifying a periodic pattern in the smoothed trend data through an autocorrelation algorithm to obtain periodic pattern data;
And analyzing the trend data and the periodic pattern data by a time sequence analysis method to generate a trend analysis result.
7. The method for adjusting the operation state of a power station transformer according to claim 1, wherein the abnormality detection of the operation data of the transformer by the outlier detection algorithm generates a data abnormality detection result, comprising:
Identifying abnormal values in the operation data of the transformer by a box graph analysis method to obtain fourth processing data;
Performing further outlier analysis on the fourth processed data by a Z-score method to determine outlier data;
Grouping the abnormal value data by a K-means clustering method to obtain a clustering grouping result;
and carrying out abnormal mode and potential fault identification on the clustering grouping result by using a correlation rule analysis method, and generating a data abnormal detection result.
8. The method for adjusting the operation state of a power station transformer according to claim 1, wherein the performing infrared image detection on an infrared image including the transformer through a convolutional neural network to generate a thermal anomaly detection result comprises:
performing image preprocessing on an infrared image containing the transformer to generate a preprocessed image;
Extracting image features of the preprocessed image through a convolutional neural network to generate a feature mapping result;
Performing hot zone anomaly detection on the feature mapping result through a classification layer of a convolutional neural network to generate a preliminary hot zone detection result;
and carrying out hot zone abnormality detection on the preliminary hot zone detection result through a threshold segmentation algorithm to generate a hot zone abnormality detection result.
9. The method for adjusting the operation state of a power station transformer according to claim 1, wherein the detecting electromagnetic field data of the transformer by an electromagnetic field variation analysis technique to generate an electromagnetic field abnormality detection result comprises:
carrying out data normalization processing on electromagnetic field data of the transformer;
extracting time-frequency characteristics of electromagnetic field data subjected to data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data;
And carrying out anomaly detection on the time-frequency characteristic data through an anomaly detection algorithm to generate an electromagnetic field anomaly detection result.
10. The power station transformer operating state adjustment method according to claim 1, wherein the generating a load optimization scheme according to the operating data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result, the electromagnetic field abnormality detection result, comprises:
Analyzing load demands through a demand analysis algorithm based on the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and generating a demand analysis result;
generating a load optimization model corresponding to the demand analysis result according to the demand analysis result;
And solving the load optimization model by a simplex method to generate a load optimization scheme.
11. A power station transformer operating condition adjustment device, comprising:
the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring transformer monitoring data of a power station, and the transformer monitoring data comprise operation data of a transformer, electromagnetic field data of the transformer and an infrared image containing the transformer;
the first processing module is used for carrying out trend and periodic mode analysis on the operation data of the transformer through a time sequence analysis method to generate a trend analysis result;
The second processing module is used for carrying out anomaly detection on the operation data of the transformer through an outlier detection algorithm to generate a data anomaly detection result;
The third processing module is used for carrying out infrared image detection on an infrared image containing the transformer through a convolutional neural network to generate a thermal region abnormality detection result, wherein the thermal region abnormality detection result represents the distribution condition of a region of which the surface temperature of the transformer is not in a preset temperature range;
The fourth processing module is used for detecting electromagnetic field data of the transformer through an electromagnetic field change analysis technology and generating an electromagnetic field abnormality detection result;
And the fifth processing module is used for generating a load optimization scheme according to the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result, and adjusting the load of the transformer according to the load optimization scheme so as to adjust the operation state of the transformer.
12. The power plant transformer operating state adjustment device of claim 11, further comprising:
and the sixth processing module is used for cleaning the operation data of the transformer through a data preprocessing algorithm.
13. The power plant transformer operating state adjustment device according to claim 12, characterized in that the sixth processing module comprises:
The first sub-processing module is used for filtering out missing values and invalid values in the operation data of the transformer through a data screening algorithm to obtain first processing data;
The second sub-processing module is used for carrying out data standardization on the first processing data through a Z-score standardization method to obtain second processing data;
The third sub-processing module is used for removing random noise in the second processing data through a moving average method to obtain third processing data;
and the fourth sub-processing module is used for filling the missing value in the third processing data by a linear interpolation method to realize data cleaning on the operation data of the transformer.
14. The power plant transformer operating state adjustment device of claim 11, further comprising:
the second acquisition module is used for acquiring the monitoring data of the transformer to obtain secondary monitoring data;
And the seventh processing module is used for generating an operation parameter adjustment scheme according to the secondary monitoring data and adjusting the operation parameters of the transformer according to the operation parameter adjustment scheme so as to adjust the operation state of the transformer.
15. The power plant transformer operating state adjustment device of claim 14, further comprising:
The third acquisition module is used for acquiring the monitoring data of the transformer to obtain tertiary monitoring data;
and the eighth processing module is used for generating a transformer running state evaluation report according to the tertiary monitoring data and a preset health scoring model.
16. The power plant transformer operating state adjustment device according to claim 11, characterized in that the first processing module comprises:
a fifth sub-processing module for extracting trend data from the operation data of the transformer through a seasonal and trend decomposition algorithm;
The sixth sub-processing module is used for smoothing the trend data through an exponential smoothing method to generate smoothed trend data;
a seventh sub-processing module, configured to analyze and identify a periodic pattern in the smoothed trend data by using an autocorrelation algorithm, so as to obtain periodic pattern data;
And the eighth sub-processing module is used for analyzing the trend data and the periodic pattern data through a time sequence analysis method to generate a trend analysis result.
17. The power plant transformer operating state adjustment device according to claim 11, characterized in that the second processing module comprises:
A ninth sub-processing module, configured to identify an abnormal value in the operation data of the transformer by using a box-type graph analysis method, so as to obtain fourth processed data;
a tenth sub-processing module, configured to perform further outlier analysis on the fourth processed data by using a Z-score method, and determine outlier data;
The eleventh sub-processing module is used for grouping the abnormal value data through a K-means clustering method to obtain a clustering grouping result;
And the twelfth sub-processing module is used for identifying the abnormal mode and potential faults of the clustering grouping result through an association rule analysis method and generating a data abnormal detection result.
18. The power plant transformer operating state adjustment device according to claim 11, characterized in that the third processing module comprises:
A thirteenth sub-processing module, configured to perform image preprocessing on an infrared image including the transformer, and generate a preprocessed image;
the fourteenth sub-processing module is used for extracting image features of the preprocessed image through a convolutional neural network and generating a feature mapping result;
A fifteenth sub-processing module, configured to perform a hot zone anomaly detection on the feature mapping result through a classification layer of the convolutional neural network, and generate a preliminary hot zone detection result;
And the sixteenth sub-processing module is used for carrying out hot zone abnormality detection on the preliminary hot zone detection result through a threshold segmentation algorithm to generate a hot zone abnormality detection result.
19. The power plant transformer operating state adjustment device according to claim 11, characterized in that the fourth processing module comprises:
Seventeenth sub-processing module, which is used for carrying out data normalization processing on electromagnetic field data of the transformer;
The eighteenth sub-processing module is used for extracting the time-frequency characteristics of the electromagnetic field data after the data normalization processing by a time-frequency analysis technology to obtain time-frequency characteristic data;
And the nineteenth sub-processing module is used for carrying out anomaly detection on the time-frequency characteristic data through an anomaly detection algorithm to generate an electromagnetic field anomaly detection result.
20. The power plant transformer operating state adjustment device according to claim 11, characterized in that the fifth processing module comprises:
The twentieth sub-processing module is used for analyzing load demands through a demand analysis algorithm based on the operation data of the transformer, the trend analysis result, the data abnormality detection result, the hot zone abnormality detection result and the electromagnetic field abnormality detection result to generate a demand analysis result;
a twenty-first sub-processing module, configured to generate a load optimization model corresponding to the demand analysis result according to the demand analysis result;
And the twenty-second sub-processing module is used for solving the load optimization model through a simplex method to generate a load optimization scheme.
21. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the program, when executed by a processor, implements the steps of the power station transformer operating state adjustment method of any of claims 1-10.
22. An electronic device, comprising:
a memory having a computer program stored thereon;
a processor for executing the computer program in the memory for carrying out the steps of the power station transformer operating state adjustment method of any one of claims 1-10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410566349.5A CN118157326B (en) | 2024-05-09 | 2024-05-09 | Method and device for adjusting running state of power station transformer, medium and electronic equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410566349.5A CN118157326B (en) | 2024-05-09 | 2024-05-09 | Method and device for adjusting running state of power station transformer, medium and electronic equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118157326A true CN118157326A (en) | 2024-06-07 |
CN118157326B CN118157326B (en) | 2024-07-12 |
Family
ID=91301597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410566349.5A Active CN118157326B (en) | 2024-05-09 | 2024-05-09 | Method and device for adjusting running state of power station transformer, medium and electronic equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN118157326B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA3140345A1 (en) * | 2018-04-04 | 2022-05-24 | Schneider Electric USA, Inc. | Systems and methods for managing smart alarms |
CN116522746A (en) * | 2023-02-24 | 2023-08-01 | 天津三源电力信息技术股份有限公司 | Power distribution hosting method for high-energy-consumption enterprises |
CN117439256A (en) * | 2023-09-14 | 2024-01-23 | 华能江苏综合能源服务有限公司 | Power station equipment management method and system based on Internet of things |
CN117648543A (en) * | 2024-01-30 | 2024-03-05 | 金数信息科技(苏州)有限公司 | Self-evolving substation equipment learning method |
-
2024
- 2024-05-09 CN CN202410566349.5A patent/CN118157326B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA3140345A1 (en) * | 2018-04-04 | 2022-05-24 | Schneider Electric USA, Inc. | Systems and methods for managing smart alarms |
CN116522746A (en) * | 2023-02-24 | 2023-08-01 | 天津三源电力信息技术股份有限公司 | Power distribution hosting method for high-energy-consumption enterprises |
CN117439256A (en) * | 2023-09-14 | 2024-01-23 | 华能江苏综合能源服务有限公司 | Power station equipment management method and system based on Internet of things |
CN117648543A (en) * | 2024-01-30 | 2024-03-05 | 金数信息科技(苏州)有限公司 | Self-evolving substation equipment learning method |
Non-Patent Citations (1)
Title |
---|
廖毅;罗炜;蒋峰伟;李亚锦;于大洋;: "换流阀冷却能力多维度分析与预警模型", 南方电网技术, no. 07, 20 July 2020 (2020-07-20), pages 7 - 15 * |
Also Published As
Publication number | Publication date |
---|---|
CN118157326B (en) | 2024-07-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2000512766A (en) | Statistical pattern analysis method for partial discharge measurement in high voltage insulation | |
Mousavi et al. | Detecting incipient faults via numerical modeling and statistical change detection | |
Bhuiyan et al. | WPD for detecting disturbances in presence of noise in smart grid for PQ monitoring | |
CN117375237B (en) | Substation operation and maintenance method and system based on digital twin technology | |
CN116704733B (en) | Aging early warning method and system for aluminum alloy cable | |
CN113742993B (en) | Method, device, equipment and storage medium for predicting life loss of dry-type transformer | |
CN115358155A (en) | Power big data abnormity early warning method, device, equipment and readable storage medium | |
CN106680574B (en) | A kind of perception of substation equipment overvoltage and data processing method | |
CN112132811A (en) | Cable service condition comprehensive evaluation system | |
CN117498432A (en) | New energy power system electric energy quality assessment method | |
CN118157326B (en) | Method and device for adjusting running state of power station transformer, medium and electronic equipment | |
CN117390944A (en) | Substation operation condition simulation system | |
CN117611410A (en) | Electric power intelligent electric shock prevention safety method and system based on deep learning | |
Sim et al. | Missing data imputation algorithm for transmission systems based on multivariate imputation with principal component analysis | |
Alsumaidaee et al. | Fault detection for medium voltage switchgear using a deep learning Hybrid 1D-CNN-LSTM model | |
CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
CN111583594B (en) | Distribution box early warning system and early warning method | |
CN106443238A (en) | High-voltage equipment state evaluation method, high-voltage equipment on-line monitoring device evaluation method and apparatuses | |
Viereck et al. | Driving reliability with machine learning and improving operation by digitalization of power transformers | |
Godoy et al. | Multiple signal processing techniques based power quality disturbance detection, classification, and diagnostic software | |
CN117391459B (en) | Electric power operation risk early warning method and system based on deep learning | |
CN117272844B (en) | Method and system for predicting service life of distribution board | |
CN113721086B (en) | Method for monitoring the electrical insulation of an installation of an MV or HV electrical system | |
EP4231198A1 (en) | Method of generating a signal processing logic, device for controlling, monitoring, and/or analyzing a physical asset, and electric power system | |
CN118395358A (en) | Intelligent anti-misoperation topology analysis method for transformer substation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |