CN117216673B - Current transformer monitoring evaluation overhauls platform - Google Patents
Current transformer monitoring evaluation overhauls platform Download PDFInfo
- Publication number
- CN117216673B CN117216673B CN202311479403.4A CN202311479403A CN117216673B CN 117216673 B CN117216673 B CN 117216673B CN 202311479403 A CN202311479403 A CN 202311479403A CN 117216673 B CN117216673 B CN 117216673B
- Authority
- CN
- China
- Prior art keywords
- state
- current transformer
- module
- data
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 45
- 238000012544 monitoring process Methods 0.000 title claims abstract description 35
- 238000012423 maintenance Methods 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 19
- 238000012937 correction Methods 0.000 claims abstract description 15
- 238000012706 support-vector machine Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims description 38
- 238000000034 method Methods 0.000 claims description 19
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 230000009466 transformation Effects 0.000 claims description 12
- 230000001364 causal effect Effects 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000004140 cleaning Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000007639 printing Methods 0.000 claims description 3
- 239000000758 substrate Substances 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to the technical field of current transformers and discloses a current transformer monitoring, evaluating and overhauling platform which comprises a multi-mode sensor module, a monitoring module, a front training module, a state evaluating module, an overhauling decision correcting module and a historical state database, wherein the monitoring module is used for monitoring and evaluating the current transformer; the monitoring module is used for remotely receiving the data acquired by the multi-mode sensor module, and storing and outputting the data; the historical state database stores historical operation parameters and corresponding state evaluation results of the current transformer; the front training module trains a support vector machine model according to the data of the historical state database to obtain a classifier; the state evaluation module evaluates the state of the current transformer based on the acquired data; and the overhaul decision correction module corrects the overhaul strategy based on the state evaluation result. The invention can improve the state evaluation accuracy and maintenance efficiency of the current transformer.
Description
Technical Field
The invention relates to the technical field of current transformers, in particular to a current transformer monitoring, evaluating and overhauling platform.
Background
The electric power system is an important infrastructure of modern society and plays a vital supporting role for industrial, commercial and residential life. The current transformer is used as one of core elements in the power system, bears key tasks such as current measurement, protection and control, and has important significance for safe and stable operation of the power system. However, the conventional current transformer maintenance method has some limitations and challenges, so that it faces a series of problems in practical use.
The traditional state evaluation method can only provide single index evaluation, lacks comprehensive and comprehensive means for evaluating the state of the current transformer, mainly comprises regular inspection and emergency maintenance, and cannot accurately evaluate the state of the current transformer according to real-time monitoring data, so that state maintenance is blindly performed, the risk of equipment failure is increased, and the workload of equipment maintenance is increased.
The invention aims to develop a current transformer state evaluation method and a maintenance decision system based on multi-mode sensor fusion, intelligent algorithm and remote communication so as to overcome the limitation of the traditional method. The system can monitor multiple parameters of the current transformer in real time and accurately evaluate the health condition of the equipment by utilizing a data analysis technology. Meanwhile, the system can generate an optimal overhaul scheme according to the evaluation result, and the fault risk and the maintenance cost are reduced. The remote monitoring and communication functions also enable the user to view the equipment state in real time, and remotely control and manage the equipment state, so that the overall efficiency of operation and maintenance is improved.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the existing current transformer monitoring platform does not have an evaluation function based on monitoring data, cannot evaluate the state of the current transformer, and is poor in functionality because the state evaluation is required to be manually performed in the process of monitoring the state of the current transformer; secondly, the existing current transformer monitoring platform does not have a function of correcting an overhaul strategy based on real-time monitoring data, and cannot effectively guide the state overhaul work of the current transformer.
The invention solves the technical problems through the following technical scheme: the current transformer monitoring, evaluating and overhauling platform comprises a multi-mode sensor module, a monitoring module, a front training module, a state evaluation module, an overhauling decision correction module and a historical state database; the multi-mode sensor module is used for collecting real-time operation parameters of the current transformer; the monitoring module is used for remotely receiving the data acquired by the multi-mode sensor module, and storing and outputting the data; the historical state database stores historical operation parameters and corresponding state evaluation results of the current transformer; the front training module trains a support vector machine model according to the data of the historical state database to obtain a classifier; the state evaluation module evaluates the state of the current transformer based on the acquired data; the overhaul decision correction module corrects an overhaul strategy based on the state evaluation result; the state evaluation module comprises the following processing steps:
step B1: preprocessing data to obtain an operation parameter feature vector;
step B2: calculating classification probability: for the real-time operation parameter feature vector of the current transformer, calculating to obtain a prediction result of the current operation state of the current transformer by using a classifier, and for each state type, calculating a state type prediction value respectively, and further calculating a probability value of each state type;
step B3: determining a current state category; and judging the maximum probability value in all the state categories, and taking the state category corresponding to the maximum probability value as a state evaluation result of the current running state of the current transformer.
Further preferably, the pre-training module processes the following steps:
step A1: from history shapeReading the characteristic vector X of the historical operation parameters and the corresponding state category Z in the state database, and assuming that the number of the characteristic vector samples of the historical operation parameters in normal, attention, abnormal and serious states is N 1 、N 2 、N 3 、N 4 The corresponding state class is Z 1 、Z 2 、Z 3 、Z 4 Wherein the tag value of the state class is Z 1 =1、Z 2 =2、Z 3 =3、Z 4 =4;
Step A2: training a support vector machine model: training a support vector machine model by using the historical operating parameter feature vector X and the corresponding state class Z to obtain a classifier f (X) =b+w.X, wherein b is a bias term and w is a weight vector.
Further preferably, when the support vector machine model is trained, the CART decision tree (classification regression tree) is utilized to solve the minimum value of the risk function to obtain an optimal solution: and (5) adopting a Lagrangian multiplier method and a dual solution of kernel function optimization to obtain a regression equation of the support vector machine.
Further preferably, the process of calculating the prediction result of the current running state of the current transformer by using the classifier is as follows: splicing the real-time operation parameter feature vector and the historical operation parameter feature vector to form a multi-dimensional overlapped-scale reconstruction feature data set, and extracting space-time feature vectors according to the reconstruction feature data set by adopting a convolution unit; a feature fusion module is constructed, the space-time feature vectors output by each residual expansion causal convolution unit are subjected to weighted fusion, the weight of each residual expansion causal convolution unit is automatically adjusted by adopting a self-adaptive mechanism, a one-dimensional residual expansion causal convolution unit is used for obtaining initial weight, and a softmax function is selected as an activation function of the initial weight; and inputting the fused data into a multi-layer perceptron (MLP) prediction module for prediction, and finally outputting a prediction result of the current running state of the current transformer.
Further preferably, the probability values of the current transformer belonging to the four normal, attention, abnormal and serious state categories are p respectively 1 、p 2 、p 3 、p 4 The method comprises the steps of carrying out a first treatment on the surface of the Step B2 judgment of p 1 、p 2 、p 3 、p 4 Maximum probability value of (1), rootAccording to the state type corresponding to the maximum probability value, the tag value of the state type of the current transformer is set to be 1, 2, 3 or 4, and the current state type Z x The determination formula is as follows:
。
further preferably, the overhaul decision correction module adjusts the corresponding overhaul period according to the tag value and the probability value of the current state category of the real-time operation parameter feature vector of the current transformer:
;
wherein T is 1 、T 2 、T 3 、T 4 The maintenance periods under normal, attention, abnormal and serious states are respectively T x And correcting the corrected maintenance period for the maintenance decision correction module.
Further preferably, the multi-mode sensor module is composed of a temperature sensor, an oil level sensor, a vibration sensor and a partial discharge sensor and is used for collecting the temperature, the oil level, the vibration acceleration and the partial discharge amount of the current transformer.
Further preferably, the data preprocessing is: cleaning data acquired by a multi-mode sensor module according to wavelet multi-resolution analysis, selecting Laplace wavelets (Laplace wavelets) as wavelet bases, performing multi-layer wavelet transformation on four-dimensional actual measurement data of temperature, oil level, vibration acceleration and partial discharge capacity, quantifying an obtained wavelet transformation factor threshold, determining the number of wavelet transformation layers by adopting a hierarchical threshold estimation method, processing wavelet decomposition coefficients by utilizing a multi-dimensional threshold denoising method, performing inverse wavelet transformation reconstruction, removing outliers, missing values and invalid data, and obtaining denoised operation parameter feature vectors.
Further preferably, the monitoring module comprises a data receiving unit, a data storage unit and a data output unit; the data receiving unit is used for receiving the data transmitted by the communication module; the data storage unit is used for data storage; the data output unit is used for integrating and outputting data to the display device, the printing device and the intelligent terminal.
Further preferably, the states of the current transformer are classified into four state categories of normal, attention, abnormal and serious; the original data of the historical state database is obtained by manually carrying out state evaluation on typical current transformer operation parameters according to relevant standards and experience; meanwhile, the real-time operation parameters and the corresponding state evaluation results of the current transformer are continuously stored in the historical state database.
According to the invention, the front training module is constructed to optimize the classifier, the state evaluation of the current transformer is realized through the state evaluation module, the historical state database is updated in real time, and the corresponding overhaul period is adjusted through the overhaul decision correction module. The invention can improve the state evaluation accuracy and maintenance efficiency of the current transformer.
Drawings
Fig. 1 is a schematic diagram of a current transformer monitoring and evaluating maintenance platform structure of the invention.
In the figure: the system comprises a 10-multi-mode sensor module, a 20-monitoring module, a 30-state evaluation module, a 40-pre-training module, a 50-maintenance decision correction module and a 60-historical state database.
Detailed Description
In order to make the technical problems, technical schemes and beneficial effects to be solved more clear, the invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The current transformer monitoring, evaluating and overhauling platform comprises a multi-mode sensor module 10, a monitoring module 20, a pre-training module 40, a state evaluation module 30, an overhauling decision correction module 50 and a historical state database 60; the multi-mode sensor module 10 is composed of a temperature sensor, an oil level sensor, a vibration sensor and a partial discharge sensor, and is used for collecting real-time operation parameters such as temperature T, oil level W, vibration acceleration S, partial discharge amount P and the like of a current transformer. The monitoring module 20 is configured to remotely receive data collected by the multi-mode sensor module 10, and store and output the data; the state evaluation module 30 evaluates the state of the current transformer based on the collected data; the maintenance decision correction module 50 corrects the maintenance policy based on the status evaluation result.
The monitoring module 20 comprises a data receiving unit, a data storage unit and a data output unit; the data receiving unit is used for receiving the data transmitted by the communication module; the data storage unit is used for data storage; the data output unit is used for integrating and outputting data to the display device, the printing device and the intelligent terminal.
The historical state database 60 stores current transformer historical operating parameters and corresponding state evaluation results. The states of the current transformer are classified into four state categories of normal, attention, abnormal and serious. The original data of the historical state database 60 is obtained by carrying out state evaluation on typical current transformer operation parameters by field experts according to relevant standards and experience; meanwhile, the real-time operation parameters of the current transformer and the corresponding state evaluation results are continuously stored in the historical state database 60.
The pre-training module 40 processes the following steps:
step A1: reading the historical operating parameter feature vector X and corresponding state category Z from the historical state database 60 assumes that the number of historical operating parameter feature vector samples for normal, noted, abnormal, and severe states is N 1 、N 2 、N 3 、N 4 The corresponding state class is Z 1 、Z 2 、Z 3 、Z 4 Wherein the tag value of the state class is Z 1 =1、Z 2 =2、Z 3 =3、Z 4 =4。
Step A2: and training a support vector machine model. Training a support vector machine model by using the historical operating parameter feature vector X and the corresponding state class Z to obtain a classifier f (X) =b+w.X, wherein b is a bias term and w is a weight vector.
Preferably, in step A2, the optimal solution is obtained by solving the minimum value of the risk function using the CART decision tree:
;
;
in which x is i For the ith input variable, y i For the ith output variable, n is the number of samples: epsilon is the loss coefficient;is the i-th relaxation variable,/->An i-th relaxed variable branch; c is penalty factor, Q is basic risk function.
And (3) adopting a Lagrangian multiplier method and a dual solution of kernel function optimization to obtain a support vector machine regression equation:
;
wherein a is i And a i * Is a non-negative Lagrangian multiplier, K (x i X) is a radial basis function, expressed asG is the kernel width and x is the sample parameter.
The processing steps of the state evaluation module 30 in this embodiment are as follows:
step B1: and (5) preprocessing data. N operation parameters such as the temperature T, the oil level W, the vibration acceleration S, the partial discharge capacity P and the like of the current transformer are obtained, and pretreatment operations such as data cleaning, standardization and the like are performed to remove abnormal values, missing values and invalid data, so that the quality and the reliability of the data are ensured. The operation parameter characteristic vector after data preprocessing is X= { X 1 ,x 2 ,…,x N Where N is the number of operating parameters.
Cleaning data acquired by the multi-mode sensor module 10 according to wavelet multi-resolution analysis, selecting Laplace wavelets as wavelet substrates, performing multi-layer wavelet transformation on four-dimensional actual measurement data of temperature T, oil level W, vibration acceleration S and partial discharge capacity P, quantifying the threshold value of the obtained wavelet transformation factor, determining the number of wavelet transformation layers by adopting a hierarchical threshold estimation method, processing wavelet decomposition coefficients by utilizing a multi-dimensional threshold denoising method, performing inverse wavelet transformation reconstruction, removing abnormal values, missing values and invalid data, and obtaining denoised operation parameter feature vectors.
Step B2: the classification probability is calculated. Real-time operating parameter feature vector X for current transformer new Using the classifier f (X), calculating to obtain the prediction result f (X) of the current running state of the current transformer new ) For each state category, calculating a state category predicted value, and further calculating a probability value of each state category, wherein the calculation formula is as follows:
;
wherein,probability value for j-th state class, < ->And M is the number of state categories for the j-th state category predicted value. In this embodiment, the number of state classes is 4, and the probability values of the calculated real-time operation parameter feature vectors of the current transformer about the normal, attention, abnormal and serious state classes are p respectively 1 、p 2 、p 3 、p 4 。
For the real-time operation parameter feature vector of the current transformer, the process of calculating the prediction result of the current operation state of the current transformer by using the classifier is as follows:
splicing the real-time operation parameter feature vector and the historical operation parameter feature vector to form a multi-dimensional overlapped-scale reconstruction feature data set, and extracting space-time feature vectors according to the reconstruction feature data set by adopting a convolution unit; a feature fusion module is constructed, the space-time feature vectors output by each residual expansion causal convolution unit are subjected to weighted fusion, the weight of each residual expansion causal convolution unit is automatically adjusted by adopting a self-adaptive mechanism, a one-dimensional residual expansion causal convolution unit is used for obtaining initial weight, and a softmax function is selected as an activation function of the initial weight; and inputting the fused data into a multi-layer perceptron (MLP) prediction module for prediction, and finally outputting a prediction result of the current running state of the current transformer.
Step B3: determining the current state class Z x . Judgment of p 1 、p 2 、p 3 、p 4 According to the state category corresponding to the maximum probability value, the tag value of the state category of the current transformer of the new sample is set to be 1 (normal), 2 (attention), 3 (abnormal) or 4 (serious), and the current state category is determined according to the following formula:
;
the data monitored by the multi-mode sensor module 10 and the state evaluation result of the state evaluation module 30 are fed back to the historical state database 60 at the same time, and the pre-training module 40 retrains and corrects the state evaluation result according to the monitored data.
The overhaul decision correction module 50 according to the embodiment is based on the real-time operation parameter feature vector X of the current transformer new And (3) adjusting the corresponding overhaul period according to the tag value and the probability value of the current state category. The adjustment formula is as follows:
;
wherein T is 1 、T 2 、T 3 、T 4 The maintenance periods under normal, attention, abnormal and serious states are respectively T x The corrected service cycle is corrected for service decision correction module 50.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (7)
1. The current transformer monitoring, evaluating and overhauling platform is characterized by comprising a multi-mode sensor module, a monitoring module, a front training module, a state evaluation module, an overhauling decision correction module and a historical state database; the multi-mode sensor module is used for collecting real-time operation parameters of the current transformer; the monitoring module is used for remotely receiving the data acquired by the multi-mode sensor module, and storing and outputting the data; the historical state database stores historical operation parameters and corresponding state evaluation results of the current transformer; the front training module trains a support vector machine model according to the data of the historical state database to obtain a classifier; the state evaluation module evaluates the state of the current transformer based on the acquired data; the overhaul decision correction module corrects an overhaul strategy based on the state evaluation result; the state evaluation module comprises the following processing steps:
step B1: preprocessing data to obtain an operation parameter feature vector;
step B2: calculating classification probability: for the real-time operation parameter feature vector of the current transformer, calculating to obtain a prediction result of the current operation state of the current transformer by using a classifier, and for each state type, calculating a state type prediction value respectively, and further calculating a probability value of each state type;
step B3: determining a current state category; judging the maximum probability value in all the state categories, and taking the state category corresponding to the maximum probability value as a state evaluation result of the current running state of the current transformer;
the processing steps of the front training module are as follows:
step A1: reading the historical operating parameter feature vector X and the corresponding state class Z from the historical state database, assuming that the number of historical operating parameter feature vector samples for normal, noted, abnormal and severe states is N 1 、N 2 、N 3 、N 4 The corresponding state class is Z 1 、Z 2 、Z 3 、Z 4 Wherein the tag value of the state class is Z 1 =1、Z 2 =2、Z 3 =3、Z 4 =4;
Step A2: training a support vector machine model: training a support vector machine model by using a historical operation parameter feature vector X and a corresponding state class Z to obtain a classifier f (X) =b+w.X, wherein b is a bias term, and w is a weight vector;
the probability values of the current transformer belonging to the four state categories of normal, attention, abnormal and serious are p respectively 1 、p 2 、p 3 、p 4 The method comprises the steps of carrying out a first treatment on the surface of the Step B2 judgment of p 1 、p 2 、p 3 、p 4 The maximum probability value of the current transformer is set to be 1, 2, 3 or 4 according to the state class corresponding to the maximum probability value, and the current state class Z x The determination formula is as follows:
;
the overhaul decision correction module adjusts corresponding overhaul periods according to the tag value and the probability value of the current state category of the real-time operation parameter feature vector of the current transformer:
;
wherein T is 1 、T 2 、T 3 、T 4 The maintenance periods under normal, attention, abnormal and serious states are respectively T x And correcting the corrected maintenance period for the maintenance decision correction module.
2. The current transformer monitoring evaluation maintenance platform according to claim 1, wherein when the support vector machine model is trained, the optimal solution is obtained by solving the minimum value of the risk function by using a CART decision tree: and (5) adopting a Lagrangian multiplier method and a dual solution of kernel function optimization to obtain a regression equation of the support vector machine.
3. The current transformer monitoring and evaluating maintenance platform according to claim 1, wherein the process of calculating the prediction result of the current running state of the current transformer by using the classifier is as follows: splicing the real-time operation parameter feature vector and the historical operation parameter feature vector to form a multi-dimensional overlapped-scale reconstruction feature data set, and extracting space-time feature vectors according to the reconstruction feature data set by adopting a convolution unit; a feature fusion module is constructed, the space-time feature vectors output by each residual expansion causal convolution unit are subjected to weighted fusion, the weight of each residual expansion causal convolution unit is automatically adjusted by adopting a self-adaptive mechanism, a one-dimensional residual expansion causal convolution unit is used for obtaining initial weight, and a softmax function is selected as an activation function of the initial weight; and inputting the fused data into a multi-layer perceptron prediction module for prediction, and finally outputting a prediction result of the current running state of the current transformer.
4. The current transformer monitoring, evaluating and overhauling platform according to claim 1, wherein the multi-mode sensor module consists of a temperature sensor, an oil level sensor, a vibration sensor and a partial discharge sensor and is used for collecting the temperature of the current transformer、Oil level、Vibration acceleration and partial discharge amount.
5. The current transformer monitoring evaluation service platform according to claim 1, wherein the data preprocessing is: cleaning data acquired by a multi-mode sensor module according to wavelet multi-resolution analysis, selecting Laplace wavelets as wavelet substrates, performing multi-layer wavelet transformation on four-dimensional actual measurement data of temperature, oil level, vibration acceleration and partial discharge capacity, quantifying the threshold value of the obtained wavelet transformation factor, determining the number of wavelet transformation layers by adopting a hierarchical threshold estimation method, processing wavelet decomposition coefficients by utilizing a multi-dimensional threshold denoising method, performing wavelet inverse transformation reconstruction, and removing outliers, missing values and invalid data to obtain denoised operation parameter feature vectors.
6. The current transformer monitoring, evaluating and overhauling platform according to claim 1, wherein the monitoring module comprises a data receiving unit, a data storage unit and a data output unit; the data receiving unit is used for receiving the data transmitted by the communication module; the data storage unit is used for data storage; the data output unit is used for integrating and outputting data to the display device, the printing device and the intelligent terminal.
7. The current transformer monitoring evaluation maintenance platform according to claim 1, wherein the states of the current transformer are classified into four state categories of normal, attention, abnormal and serious; the original data of the historical state database is obtained by manually carrying out state evaluation on typical current transformer operation parameters according to relevant standards and experience; meanwhile, the real-time operation parameters and the corresponding state evaluation results of the current transformer are continuously stored in the historical state database.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311479403.4A CN117216673B (en) | 2023-11-08 | 2023-11-08 | Current transformer monitoring evaluation overhauls platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311479403.4A CN117216673B (en) | 2023-11-08 | 2023-11-08 | Current transformer monitoring evaluation overhauls platform |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117216673A CN117216673A (en) | 2023-12-12 |
CN117216673B true CN117216673B (en) | 2024-03-12 |
Family
ID=89039337
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311479403.4A Active CN117216673B (en) | 2023-11-08 | 2023-11-08 | Current transformer monitoring evaluation overhauls platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117216673B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102436226A (en) * | 2011-09-14 | 2012-05-02 | 文存润 | Online monitoring and condition maintenance management system |
CN113391239A (en) * | 2021-06-10 | 2021-09-14 | 国网四川省电力公司营销服务中心 | Transformer abnormality monitoring method and system based on edge calculation |
CN113449914A (en) * | 2021-06-25 | 2021-09-28 | 国网山东省电力公司梁山县供电公司 | Power system monitoring method and system |
CN114792319A (en) * | 2022-06-23 | 2022-07-26 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation inspection method and system based on transformer substation image |
CN115238754A (en) * | 2022-09-21 | 2022-10-25 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
DE102021124253A1 (en) * | 2021-09-20 | 2023-03-23 | Festo Se & Co. Kg | Machine learning method for anomaly detection in an electrical system |
CN115879044A (en) * | 2022-11-24 | 2023-03-31 | 国网安徽省电力有限公司超高压分公司 | CNN network-based GIS switching-on/off state current detection method and device |
CN116071036A (en) * | 2022-10-11 | 2023-05-05 | 国网四川省电力公司成都供电公司 | Transformer temperature state evaluation method, equipment and medium |
-
2023
- 2023-11-08 CN CN202311479403.4A patent/CN117216673B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102436226A (en) * | 2011-09-14 | 2012-05-02 | 文存润 | Online monitoring and condition maintenance management system |
CN113391239A (en) * | 2021-06-10 | 2021-09-14 | 国网四川省电力公司营销服务中心 | Transformer abnormality monitoring method and system based on edge calculation |
CN113449914A (en) * | 2021-06-25 | 2021-09-28 | 国网山东省电力公司梁山县供电公司 | Power system monitoring method and system |
DE102021124253A1 (en) * | 2021-09-20 | 2023-03-23 | Festo Se & Co. Kg | Machine learning method for anomaly detection in an electrical system |
CN114792319A (en) * | 2022-06-23 | 2022-07-26 | 国网浙江省电力有限公司电力科学研究院 | Transformer substation inspection method and system based on transformer substation image |
CN115238754A (en) * | 2022-09-21 | 2022-10-25 | 国网江西省电力有限公司电力科学研究院 | Power transformer short-term operation temperature prediction method based on multivariate perception |
CN116071036A (en) * | 2022-10-11 | 2023-05-05 | 国网四川省电力公司成都供电公司 | Transformer temperature state evaluation method, equipment and medium |
CN115879044A (en) * | 2022-11-24 | 2023-03-31 | 国网安徽省电力有限公司超高压分公司 | CNN network-based GIS switching-on/off state current detection method and device |
Non-Patent Citations (3)
Title |
---|
Fault detection and diagnosis in power transformers: a comprehensive review and classification of publications and methods;Ali Reza Abbasi;《Electric Power Systems Research》;1-21 * |
一种基于数据挖掘分析的设备状态评价方法;李金;高寿;;微型机与应用(24);76-79 * |
基于主成分分析和梯度提升树的变电设备状态评价;马洪斌 等;《 电力大数据 》;48-55 * |
Also Published As
Publication number | Publication date |
---|---|
CN117216673A (en) | 2023-12-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
CN116757534B (en) | Intelligent refrigerator reliability analysis method based on neural training network | |
CN107862763B (en) | Train safety early warning evaluation model training method, module and monitoring evaluation system | |
CN116308304B (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
CN117234785B (en) | Centralized control platform error analysis system based on artificial intelligence self-query | |
CN115587672A (en) | Distribution transformer load prediction and heavy overload early warning method and system | |
CN114266301A (en) | Intelligent power equipment fault prediction method based on graph convolution neural network | |
CN116611013A (en) | Anomaly detection and root cause analysis method and system for industrial time series data | |
CN112433907A (en) | Method and device for processing host operation parameter data of uninterruptible power supply and electronic device | |
CN115347915A (en) | Method and device for detecting running state of power line carrier communication equipment | |
CN117833468A (en) | Maintenance method for circuit breaker unit transmission control part of power distribution ring main unit in operation | |
CN117216673B (en) | Current transformer monitoring evaluation overhauls platform | |
CN110197289B (en) | Energy-saving equipment management system based on big data | |
CN117454771A (en) | Mechanical equipment dynamic maintenance decision-making method based on evaluation and prediction information | |
CN113434493A (en) | Non-invasive load decomposition method based on Transformer | |
CN110533300B (en) | Intelligent decision-making system for transformer based on game set pair cloud | |
CN116596517A (en) | Photovoltaic module cleaning decision method and system based on neural network model | |
CN116127324A (en) | Fault detection method and device for key components in uninterruptible power supply | |
CN116610940A (en) | Equipment fault diagnosis system based on wavelet transformation and deep neural network | |
CN114201825A (en) | Method and system for evaluating equipment performance degradation state based on combination characteristics | |
CN115713027A (en) | Transformer state evaluation method, device and system | |
CN115618752B (en) | Power load control method and system based on Autoformer model | |
CN116760033B (en) | Real-time power demand prediction system based on artificial intelligence | |
CN118150943B (en) | Distribution network ground fault positioning method, system, electronic equipment and storage medium | |
CN117767874A (en) | Photovoltaic system data acquisition method based on photovoltaic array power prediction |
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 |