CN117893955A - Ring main unit fault detection system - Google Patents
Ring main unit fault detection system Download PDFInfo
- Publication number
- CN117893955A CN117893955A CN202410279069.6A CN202410279069A CN117893955A CN 117893955 A CN117893955 A CN 117893955A CN 202410279069 A CN202410279069 A CN 202410279069A CN 117893955 A CN117893955 A CN 117893955A
- Authority
- CN
- China
- Prior art keywords
- fault
- image
- internal components
- internal
- main unit
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000007637 random forest analysis Methods 0.000 claims abstract description 48
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 24
- 230000004044 response Effects 0.000 claims abstract description 8
- 238000003066 decision tree Methods 0.000 claims description 33
- 238000004458 analytical method Methods 0.000 claims description 23
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 238000005192 partition Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000003745 diagnosis Methods 0.000 abstract description 2
- 230000005856 abnormality Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to a ring main unit fault detection system, which belongs to the technical field of power equipment on-line monitoring and fault diagnosis, and is characterized in that images of faults of internal components of a ring main unit in a historical period and corresponding fault types are collected; inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part; and constructing a random forest model by taking the main change characteristics of the internal components as explanatory variables, the corresponding fault types as response variables and selecting the main change characteristics of the internal components with the forefront importance sequences as prediction variables. The invention solves the problems that the state of the internal parts of the ring main unit is difficult to detect, the corresponding fault type is determined, and the fault detection efficiency is low.
Description
Technical Field
The invention belongs to the technical field of on-line monitoring and fault diagnosis of power equipment, and relates to a ring main unit fault detection system.
Background
The ring main unit is used as high-voltage switch equipment and is widely applied to the fields of urban residential communities, high-rise buildings, large public buildings, factory enterprises and the like, so that the real-time fault monitoring of the ring main unit is very important. When the ring main unit fails, the corresponding operation signal data, such as voltage or current data, is abnormal, so that the abnormality detection method is generally adopted to detect the abnormality of the ring main unit current data, and the ring main unit failure detection is further performed according to the current abnormality data.
However, in order to ensure safety when the ring main unit is in live operation, the cabin door must be closed, and the running states of the internal switch, the bus, the cable connector and other parts of the ring main unit cannot be directly observed and detected from the outside of the cabinet basically, so that inspection personnel cannot intuitively inspect and maintain the ring main unit, and the number of ring main units is large, so that great difficulty is brought to corresponding operation, maintenance and overhaul work. Therefore, the method capable of detecting the faults of the internal components is developed, so that the inspection personnel can quickly judge the fault type of the ring main unit, and the working efficiency is improved.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a ring main unit fault detection system.
The aim of the invention can be achieved by the following technical scheme:
the utility model provides a looped netowrk cabinet fault detection system, includes data acquisition module, fault analysis module and fault alarm module, data acquisition module, fault analysis module and fault alarm module communication connection, wherein:
the data acquisition module is used for shooting and acquiring images of the internal components of the ring main unit;
The fault analysis module is used for inputting the acquired images into a preset fault analysis model and outputting corresponding fault positions and fault types;
the fault alarm module is used for sending out corresponding fault alarms according to the output fault positions and fault types.
Further, in the fault analysis module, the preset fault analysis model includes the following construction steps:
s1, collecting images of faults of internal components of a ring main unit in a historical period and corresponding fault types;
S2, inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part;
S3, constructing a random forest model by taking main change characteristics of the internal components as explanatory variables and corresponding fault types as response variables.
Further, in step S2, the step of inputting the collected image into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal component without failure, and identifying main change features of the internal component, including the steps of:
s21, preprocessing the image to extract image characteristics and reduce noise, wherein the preprocessing comprises image scaling, clipping, graying and color conversion;
s22, constructing a convolutional neural network model, wherein the convolutional neural network model consists of a plurality of convolutional layers, a pooling layer and a full-connection layer, and the convolutional layers are used for extracting the characteristics of internal components in an image; the pooling layer is used for reducing the size of the feature map and retaining important features; the full connection layer is used for mapping the final characteristics into different prediction results;
S23, model training: inputting the prepared image data set into a convolutional neural network, and enabling the model to accurately identify the change characteristics of different internal components by adjusting parameters;
S24, feature extraction and comparison: and inputting the collected image data into a trained convolutional neural network model, extracting characteristics, comparing the characteristics with the difference between the standard images of the internal components without faults, and determining the internal components with the changes.
Further, in step S3, the construction of the random forest model using the main change feature of the internal component as an interpretation variable and the corresponding fault type as a response variable includes the following steps:
s31, randomly extracting L samples from a data set to serve as a training set;
s32, randomly and repeatedly extracting N main change features of the internal components as partition points, and determining and dividing the optimal partition points of the fault type by utilizing the coefficient of the Kerning so as to generate a decision tree;
S33, repeating the operations of the steps S31-S32 for M times to obtain M decision trees, and generating a random forest;
S34, calculating a prediction error of each decision tree in the random forest on the out-of-bag data;
S35, adding random disturbance of main change characteristics of internal components in the out-of-bag data, and calculating a prediction error of each decision tree of the random forest on the random disturbance;
s36, sorting the importance of main change features of the internal components according to the prediction error of the random forest on the out-of-bag data;
s37, selecting main change characteristics of n internal components before importance ranking as prediction variables, and constructing a final random forest model.
Further, in step S33, the determination of the M values of the M decision trees is specifically as follows:
generating random forests with different decision tree numbers by taking O decision trees as step sizes;
Calculating a prediction error of the random forest on the test sample;
and selecting a random forest with the minimum prediction error, and determining the number M of decision trees.
Further, in step S36, the importance of the main change features of the internal components is ordered according to the prediction error of the random forest on the out-of-bag data, and the calculation formula is as follows:
，
Wherein: PIM represents the degree of importance of the classification rules; m is the number of decision trees in the random forest; Representing the prediction error of the kth decision tree on the data outside the bag added with the random disturbance of the main change characteristics of the ith internal part; Representing the prediction error of the kth decision on the out-of-bag data without random disturbance.
Further, in the data acquisition module, the internal components include a switch, a bus, a cable, and a cable connector.
Further, in the fault analysis module, the step of inputting the collected image into a preset fault analysis model and outputting a corresponding fault position and fault type includes the following steps:
preprocessing the acquired image of the internal part of the ring main unit, inputting the image into a trained convolutional neural network model to extract image features, comparing the image features with a standard image of the internal part without faults, and determining main change features of the internal part;
When the internal part change characteristics do not exist, judging that the ring main unit has no fault;
when the internal part change characteristics exist, the internal part main change characteristics are input into a trained random forest model, and the fault type of the ring main unit is judged.
The invention has the beneficial effects that:
Collecting images of faults of internal components of the ring main unit in a historical period and corresponding fault types; inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part; and constructing a random forest model by taking main change characteristics of the internal components as explanatory variables and corresponding fault types as response variables. The invention solves the problems that the state of the internal parts of the ring main unit is difficult to detect, the corresponding fault type is determined, and the fault detection efficiency is low.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a block diagram of a ring main unit fault detection system according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the present invention for achieving the intended purpose, the following detailed description will refer to the specific implementation, structure, characteristics and effects according to the present invention with reference to the accompanying drawings and preferred embodiments.
Referring to fig. 1, the application provides a ring main unit fault detection system, which comprises a data acquisition module, a fault analysis module and a fault alarm module, wherein the data acquisition module, the fault analysis module and the fault alarm module are in communication connection, and the ring main unit fault detection system comprises:
the data acquisition module is used for shooting and acquiring images of the internal components of the ring main unit;
The fault analysis module is used for inputting the acquired images into a preset fault analysis model and outputting corresponding fault positions and fault types;
the fault alarm module is used for sending out corresponding fault alarms according to the output fault positions and fault types.
Further, in the fault analysis module, the preset fault analysis model includes the following construction steps:
s1, collecting images of faults of internal components of a ring main unit in a historical period and corresponding fault types;
S2, inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part;
S3, constructing a random forest model by taking main change characteristics of the internal components as explanatory variables and corresponding fault types as response variables.
In the embodiment, the main characteristic of the image is identified by shooting the image of the internal part of the ring main unit, and then the main characteristic is compared with the image without faults to obtain the main change characteristic of the internal part, so that the faulty part can be well positioned. Then, by constructing a random forest model to quantify the relation between the main change characteristics of the internal components and the corresponding fault types, the fault types can be rapidly judged after the fault components are positioned, so that the working efficiency of patrol personnel is improved.
Further, in step S2, the step of inputting the collected image into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal component without failure, and identifying main change features of the internal component, including the steps of:
s21, preprocessing the image to extract image characteristics and reduce noise, wherein the preprocessing comprises image scaling, clipping, graying and color conversion;
s22, constructing a convolutional neural network model, wherein the convolutional neural network model consists of a plurality of convolutional layers, a pooling layer and a full-connection layer, and the convolutional layers are used for extracting the characteristics of internal components in an image; the pooling layer is used for reducing the size of the feature map and retaining important features; the full connection layer is used for mapping the final characteristics into different prediction results;
S23, model training: inputting the prepared image data set into a convolutional neural network, and enabling the model to accurately identify the change characteristics of different internal components by adjusting parameters;
S24, feature extraction and comparison: and inputting the collected image data into a trained convolutional neural network model, extracting characteristics, comparing the characteristics with the difference between the standard images of the internal components without faults, and determining the internal components with the changes.
Random forests are a classical machine learning algorithm that can be used for feature extraction and variable importance ranking. Random forests are trained and predicted by building multiple decision trees, each modeled using only a portion of the training data and a portion of the features. A strong classification or regression model is finally obtained by constructing a plurality of decision trees, wherein each decision tree has weight contribution. The random forest may give a ranking of the importance of each input feature in the model, the importance scores of these features being calculated from their degree of influence in the random forest on the model's prediction results. Typically, feature importance scores in random forests are calculated based on out-of-bag errors.
In this embodiment, a fault type may be generated by a fault in one or more internal components, with each component having a different degree of impact on the fault type. Therefore, the importance of the main change features of the internal components causing each fault type is ordered through the random forest, and the main change features of the first few internal components with the importance ordering are used as variables for predicting the fault type of the ring main unit.
Further, in step S3, the construction of the random forest model using the main change feature of the internal component as an interpretation variable and the corresponding fault type as a response variable includes the following steps:
s31, randomly extracting L samples from a data set to serve as a training set;
s32, randomly and repeatedly extracting N main change features of the internal components as partition points, and determining and dividing the optimal partition points of the fault type by utilizing the coefficient of the Kerning so as to generate a decision tree;
S33, repeating the operations of the steps S31-S32 for M times to obtain M decision trees, and generating a random forest;
S34, calculating a prediction error of each decision tree in the random forest on the out-of-bag data;
S35, adding random disturbance of main change characteristics of internal components in the out-of-bag data, and calculating a prediction error of each decision tree of the random forest on the random disturbance;
s36, sorting the importance of main change features of the internal components according to the prediction error of the random forest on the out-of-bag data;
s37, selecting main change characteristics of n internal components before importance ranking as prediction variables, and constructing a final random forest model.
It should be noted that in this embodiment, n internal component main change features before the importance ranking, n may depend on the value of the model that the prediction error starts to become larger after adding the nth internal component main change feature.
Further, in step S33, the determination of the M values of the M decision trees is specifically as follows:
generating random forests with different decision tree numbers by taking O decision trees as step sizes;
Calculating a prediction error of the random forest on the test sample;
and selecting a random forest with the minimum prediction error, and determining the number M of decision trees.
Further, in step S36, the importance of the main change features of the internal components is ordered according to the prediction error of the random forest on the out-of-bag data, and the calculation formula is as follows:
，
Wherein: PIM represents the degree of importance of the classification rules; m is the number of decision trees in the random forest; Representing the prediction error of the kth decision tree on the data outside the bag added with the random disturbance of the main change characteristics of the ith internal part; Representing the prediction error of the kth decision on the out-of-bag data without random disturbance.
Further, in the data acquisition module, the internal components include a switch, a bus, a cable, and a cable connector.
Further, in the fault analysis module, the step of inputting the collected image into a preset fault analysis model and outputting a corresponding fault position and fault type includes the following steps:
preprocessing the acquired image of the internal part of the ring main unit, inputting the image into a trained convolutional neural network model to extract image features, comparing the image features with a standard image of the internal part without faults, and determining main change features of the internal part;
When the internal part change characteristics do not exist, judging that the ring main unit has no fault;
when the internal part change characteristics exist, the internal part main change characteristics are input into a trained random forest model, and the fault type of the ring main unit is judged.
The invention has the beneficial effects that:
Collecting images of faults of internal components of the ring main unit in a historical period and corresponding fault types; inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part; and constructing a random forest model by taking main change characteristics of the internal components as explanatory variables and corresponding fault types as response variables. The invention solves the problems that the state of the internal parts of the ring main unit is difficult to detect, the corresponding fault type is determined, and the fault detection efficiency is low.
The present invention is not limited to the above embodiments, but is capable of modification and variation in detail, and other modifications and variations can be made by those skilled in the art without departing from the scope of the present invention.
Claims (5)
1. A looped netowrk cabinet fault detection system, its characterized in that: the system comprises a data acquisition module, a fault analysis module and a fault alarm module, wherein the data acquisition module, the fault analysis module and the fault alarm module are in communication connection, and the system comprises the following components:
the data acquisition module is used for shooting and acquiring images of the internal components of the ring main unit;
The fault analysis module is used for inputting the acquired images into a preset fault analysis model and outputting corresponding fault positions and fault types;
The fault alarm module is used for sending out corresponding fault alarms according to the output fault positions and fault types;
the preset fault analysis model comprises the following construction steps:
s1, collecting images of faults of internal components of a ring main unit in a historical period and corresponding fault types;
S2, inputting the collected images into a convolutional neural network model to extract image features, comparing the extracted image features with a standard image of an internal part without faults, and identifying main change features of the internal part;
S3, constructing a random forest model by taking main change characteristics of internal components as explanatory variables and corresponding fault types as response variables, wherein the method comprises the following steps of:
s31, randomly extracting L samples from a data set to serve as a training set;
s32, randomly and repeatedly extracting N main change features of the internal components as partition points, and determining and dividing the optimal partition points of the fault type by utilizing the coefficient of the Kerning so as to generate a decision tree;
S33, repeating the operations of the steps S31-S32 for M times to obtain M decision trees, and generating a random forest;
S34, calculating a prediction error of each decision tree in the random forest on the out-of-bag data;
S35, adding random disturbance of main change characteristics of internal components in the out-of-bag data, and calculating a prediction error of each decision tree of the random forest on the random disturbance;
s36, sorting the importance of main change features of the internal components according to the prediction error of the random forest on the out-of-bag data;
s37, selecting main change characteristics of n internal parts before importance ranking as prediction variables, and constructing a final random forest model;
in the fault analysis module, the collected image is input into a preset fault analysis model, and the corresponding fault position and fault type are output, and the method comprises the following steps:
preprocessing the acquired image of the internal part of the ring main unit, inputting the image into a trained convolutional neural network model to extract image features, comparing the image features with a standard image of the internal part without faults, and determining main change features of the internal part;
When the internal part change characteristics do not exist, judging that the ring main unit has no fault;
when the internal part change characteristics exist, the internal part main change characteristics are input into a trained random forest model, and the fault type of the ring main unit is judged.
2. The ring main unit fault detection system of claim 1, wherein: in step S2, the collected image is input into a convolutional neural network model to extract image features, the extracted image features are compared with a standard image of an internal component without faults, and main change features of the internal component are identified, including the following steps:
s21, preprocessing the image to extract image characteristics and reduce noise, wherein the preprocessing comprises image scaling, clipping, graying and color conversion;
s22, constructing a convolutional neural network model, wherein the convolutional neural network model consists of a plurality of convolutional layers, a pooling layer and a full-connection layer, and the convolutional layers are used for extracting the characteristics of internal components in an image; the pooling layer is used for reducing the size of the feature map and retaining important features; the full connection layer is used for mapping the final characteristics into different prediction results;
S23, model training: inputting the prepared image data set into a convolutional neural network, and enabling the model to accurately identify the change characteristics of different internal components by adjusting parameters;
S24, feature extraction and comparison: and inputting the collected image data into a trained convolutional neural network model, extracting characteristics, comparing the characteristics with the difference between the standard images of the internal components without faults, and determining the internal components with the changes.
3. The ring main unit fault detection system of claim 1, wherein: in step S33, the determination of the M values of the M decision trees is specifically as follows:
generating random forests with different decision tree numbers by taking O decision trees as step sizes;
Calculating a prediction error of the random forest on the test sample;
and selecting a random forest with the minimum prediction error, and determining the number M of decision trees.
4. The ring main unit fault detection system of claim 1, wherein: in step S36, the importance of the main change features of the internal components is ordered according to the prediction error of the random forest on the data outside the bag, and the calculation formula is as follows:
，
Wherein: PIM represents the degree of importance of the classification rules; m is the number of decision trees in the random forest; Representing the prediction error of the kth decision tree on the data outside the bag added with the random disturbance of the main change characteristics of the ith internal part; and/> denotes the prediction error of the kth decision on the out-of-bag data without random perturbation added.
5. The ring main unit fault detection system of claim 1, wherein: in the data acquisition module, the internal components include a switch, a bus, a cable, and a cable connector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410279069.6A CN117893955B (en) | 2024-03-12 | 2024-03-12 | Ring main unit fault detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410279069.6A CN117893955B (en) | 2024-03-12 | 2024-03-12 | Ring main unit fault detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117893955A true CN117893955A (en) | 2024-04-16 |
| CN117893955B CN117893955B (en) | 2024-06-04 |
Family
ID=90652005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410279069.6A Active CN117893955B (en) | 2024-03-12 | 2024-03-12 | Ring main unit fault detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117893955B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015062209A1 (en) * | 2013-10-29 | 2015-05-07 | 华为技术有限公司 | Visualized optimization processing method and device for random forest classification model |
| AU2020100709A4 (en) * | 2020-05-05 | 2020-06-11 | Bao, Yuhang Mr | A method of prediction model based on random forest algorithm |
| US20200200648A1 (en) * | 2018-02-12 | 2020-06-25 | Dalian University Of Technology | Method for Fault Diagnosis of an Aero-engine Rolling Bearing Based on Random Forest of Power Spectrum Entropy |
| CN111458144A (en) * | 2020-03-04 | 2020-07-28 | 华北电力大学 | Wind driven generator fault diagnosis method based on convolutional neural network |
| CN112949714A (en) * | 2021-03-02 | 2021-06-11 | 北京城建设计发展集团股份有限公司 | Fault possibility estimation method based on random forest |
| CN116150604A (en) * | 2023-02-08 | 2023-05-23 | 正泰电气股份有限公司 | Transformer fault diagnosis method and device and electronic equipment |
| CN116633023A (en) * | 2023-07-05 | 2023-08-22 | 希格玛电气(珠海)有限公司 | Isolation switch control system and method |
-
2024
- 2024-03-12 CN CN202410279069.6A patent/CN117893955B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015062209A1 (en) * | 2013-10-29 | 2015-05-07 | 华为技术有限公司 | Visualized optimization processing method and device for random forest classification model |
| US20200200648A1 (en) * | 2018-02-12 | 2020-06-25 | Dalian University Of Technology | Method for Fault Diagnosis of an Aero-engine Rolling Bearing Based on Random Forest of Power Spectrum Entropy |
| CN111458144A (en) * | 2020-03-04 | 2020-07-28 | 华北电力大学 | Wind driven generator fault diagnosis method based on convolutional neural network |
| AU2020100709A4 (en) * | 2020-05-05 | 2020-06-11 | Bao, Yuhang Mr | A method of prediction model based on random forest algorithm |
| CN112949714A (en) * | 2021-03-02 | 2021-06-11 | 北京城建设计发展集团股份有限公司 | Fault possibility estimation method based on random forest |
| CN116150604A (en) * | 2023-02-08 | 2023-05-23 | 正泰电气股份有限公司 | Transformer fault diagnosis method and device and electronic equipment |
| CN116633023A (en) * | 2023-07-05 | 2023-08-22 | 希格玛电气(珠海)有限公司 | Isolation switch control system and method |
Non-Patent Citations (1)
| Title |
|---|
| 舒服华;: "基于随机森林的湖北省地下水资源预测", 武汉电力职业技术学院学报, no. 02, 15 June 2020 (2020-06-15), pages 70 - 74 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117893955B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| WO2017191872A1 (en) | Plant abnormality detection method and system | |
| CN111412579B (en) | Air conditioning unit fault type diagnosis method and system based on big data | |
| CN106407589B (en) | Fan state evaluation and prediction method and system | |
| CN104573850A (en) | Method for evaluating state of thermal power plant equipment | |
| CN105846780A (en) | Decision tree model-based photovoltaic assembly fault diagnosis method | |
| CN109858140B (en) | Fault diagnosis method for water chilling unit based on information entropy discrete Bayesian network | |
| CN109766952A (en) | Photovoltaic array fault detection method based on Partial Least Squares and extreme learning machine | |
| CN107844067A (en) | A kind of gate of hydropower station on-line condition monitoring control method and monitoring system | |
| CN110580492A (en) | Track circuit fault precursor discovery method based on small fluctuation detection | |
| CN114519923A (en) | Intelligent diagnosis and early warning method and system for power plant | |
| CN117612345A (en) | Power equipment state monitoring and alarming system and method | |
| CN113763667A (en) | Fire early warning and state monitoring device and method based on 5G edge calculation | |
| CN114487705A (en) | Power grid equipment fault positioning detection method | |
| CN116796261B (en) | Closed switch equipment mechanical characteristic prediction method based on artificial intelligence | |
| CN117556347A (en) | Power equipment fault prediction and health management method based on industrial big data | |
| CN117893955B (en) | Ring main unit fault detection system | |
| CN109872511B (en) | Self-adaptive two-stage alarm method for monitoring axial displacement sudden change | |
| CN111638416A (en) | Fault monitoring device and method for power distribution cabinet of power distribution room | |
| CN114997375A (en) | Insulator surface metal pollution model building system in air type switch cabinet | |
| CN115130731A (en) | Method, equipment and medium for detecting fault of wind driven generator | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| Li et al. | Transformer State Data Cleaning Method Based on DBSCAN and ESN | |
| CN118191682A (en) | Transformer running state detection system and method | |
| CN116047237A (en) | Online detection method and device for series arc faults of three-phase frequency converter circuit |
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 |