CN113642244A - Power metering equipment fault prediction method based on artificial intelligence - Google Patents
Power metering equipment fault prediction method based on artificial intelligence Download PDFInfo
- Publication number
- CN113642244A CN113642244A CN202110969054.9A CN202110969054A CN113642244A CN 113642244 A CN113642244 A CN 113642244A CN 202110969054 A CN202110969054 A CN 202110969054A CN 113642244 A CN113642244 A CN 113642244A
- Authority
- CN
- China
- Prior art keywords
- power metering
- metering equipment
- fault prediction
- prediction model
- equipment fault
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 17
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000012360 testing method Methods 0.000 claims abstract description 29
- 230000009467 reduction Effects 0.000 claims abstract description 28
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Water Supply & Treatment (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
Abstract
The invention provides an artificial intelligence-based power metering equipment fault prediction method, which comprises the steps of obtaining historical operating data of power metering equipment, constructing a power metering equipment fault prediction model by utilizing a deep neural network after preprocessing, and then performing iterative training and testing by utilizing a stack noise reduction automatic encoder to obtain a power metering equipment fault prediction model with higher identification precision. According to the invention, as the electric power metering equipment fault prediction model is trained and optimized through the deep neural network and the stack noise reduction automatic encoder, the prediction accuracy of the model can be ensured by utilizing a large amount of historical operating data, the automatic and accurate prediction of the electric power equipment fault is realized, and the problems of large workload and low fault discovery rate caused by the conventional manual electric power metering equipment fault prediction are solved.
Description
Technical Field
The invention relates to the technical field of electric power overhaul, in particular to an artificial intelligence-based electric power metering equipment fault prediction method.
Background
At present, the collection coverage rate of electric meters reaches 92.2 percent in national power grid systems, 3.98 hundred million intelligent electric energy meters are installed, and a large amount of data of metering equipment is accumulated in the operation of about 7 years. The reliability of the power equipment is the basis for guaranteeing the safe and economic operation of the power grid, and the reliability and the maintenance effect of the equipment are necessary conditions for guaranteeing the survival of enterprises.
At present, electric power metering device's maintenance is kept and is adopted technical staff to go to the on-the-spot mode that expandes the detection regularly and go on, relies on the manual work to discover the defect or inspect the trouble on the spot, has that field work volume is big, the fault discovery probability is low shortcoming to because lack the real-time supervision early warning ability to equipment, often still can cause the maintenance plan incomplete, worsen the consequence that is big trouble by little trouble. On the other hand, along with the increase of power consumption demand and equipment service life, the probability that equipment breaks down is also higher and higher, relies on simply to shorten the maintenance cycle and will cause very big burden for the electric power enterprise.
Disclosure of Invention
In view of this, the invention aims to solve the problems of large workload and low fault discovery rate in manual maintenance of the electric power metering device.
In order to solve the technical problems, the invention provides the following technical scheme:
the invention provides an artificial intelligence-based power metering equipment fault prediction method, which comprises the following steps:
collecting historical operation data of the power metering equipment, and converting the historical operation data;
performing type marking on the converted historical operating data, and dividing the marked historical operating data into a training set and a test set;
constructing a fault prediction model of the electric power metering equipment based on the deep neural network;
inputting the training set into a power metering equipment fault prediction model, and training the power metering equipment fault prediction model through a stack noise reduction automatic encoder;
inputting the test set into the trained power metering equipment fault prediction model, performing precision test on the trained power metering equipment fault prediction model, and stopping the test when the test precision meets a preset precision threshold.
Further, the converting the historical operating data specifically includes:
carrying out standardization processing on historical operation data;
and normalizing the normalized historical operating data.
Further, the power metering equipment fault prediction model comprises a plurality of layers of input layers, a plurality of layers of hidden layers and a plurality of layers of output layers.
Further, the expression of the output layer is as follows:
wherein Y is an output layer,
representing input as Xn+1H is a hidden layer, n is the number of input layers, Xn+1Representing a training set of historical operating data when the input is at layer n + 1.
Further, the stack denoising auto encoder specifically includes: input layer, output layer, hidden layer, encoding network, and decoding network.
Further, the expression of the coding network is specifically as follows:
F(W,b)(X)＝sF(WX+b)
in the formula, F(W,b)For coding the network, W is the network weight matrix between the input layer and the output layer, b is the offset vector, sFA function is activated for a neuron node of the coding network.
Further, the expression of the decoding network is specifically:
D(W,b′)(F)＝sD(WF+b′)
in the formula, D(W,b′)For decoding the network, W is the network weight matrix between the input layer and the output layer, b' is the bias matrix, sDA function is activated for a neuron node of the decoding network.
Further, training the fault prediction model of the electric power metering equipment through the stack noise reduction automatic encoder specifically comprises:
reconstructing an output layer of a power metering equipment fault prediction model through a stack noise reduction automatic encoder to obtain a reconstructed output layer, wherein an expression of the reconstructed output layer specifically comprises the following steps:
in the formula, Y' is a reconstructed output layer,
representing the corrupted training set obtained after gaussian noise is added to the training set X of historical run data.
Further, reconstructing an output layer of the power metering device fault prediction model by using the stack noise reduction automatic encoder, and obtaining the reconstructed output layer further comprises:
setting a reconstruction error threshold;
and iteratively training the fault prediction model of the power metering equipment by using a stack noise reduction automatic encoder until the reconstruction error of the input layer and the output layer of the fault prediction model of the power metering equipment is less than or equal to the reconstruction error threshold value, and stopping training.
Further, the preset precision threshold is specifically 0.95.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an artificial intelligence-based power metering equipment fault prediction method, which comprises the steps of obtaining historical operating data of power metering equipment, constructing a power metering equipment fault prediction model by utilizing a deep neural network after preprocessing, and then performing iterative training and testing by utilizing a stack noise reduction automatic encoder to obtain a power metering equipment fault prediction model with higher identification precision. According to the invention, as the electric power metering equipment fault prediction model is trained and optimized through the deep neural network and the stack noise reduction automatic encoder, the prediction accuracy of the model can be ensured by utilizing a large amount of historical operating data, the automatic and accurate prediction of the electric power equipment fault is realized, and the problems of large workload and low fault discovery rate caused by the conventional manual electric power metering equipment fault prediction are solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of a method for predicting a fault of an electric power metering device based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, the collection coverage rate of electric meters reaches 92.2 percent in national power grid systems, 3.98 hundred million intelligent electric energy meters are installed, and a large amount of data of metering equipment is accumulated in the operation of about 7 years. The reliability of the power equipment is the basis for guaranteeing the safe and economic operation of the power grid, and the reliability and the maintenance effect of the equipment are necessary conditions for guaranteeing the survival of enterprises.
At present, electric power metering device's maintenance is kept and is adopted technical staff to go to the on-the-spot mode that expandes the detection regularly and go on, relies on the manual work to discover the defect or inspect the trouble on the spot, has that field work volume is big, the fault discovery probability is low shortcoming to because lack the real-time supervision early warning ability to equipment, often still can cause the maintenance plan incomplete, worsen the consequence that is big trouble by little trouble. On the other hand, along with the increase of power consumption demand and equipment service life, the probability that equipment breaks down is also higher and higher, relies on simply to shorten the maintenance cycle and will cause very big burden for the electric power enterprise.
An embodiment of the method for predicting the fault of the electric power metering equipment based on the artificial intelligence is explained in detail below.
Referring to fig. 1, the present embodiment provides a method for predicting a fault of an electric power metering device based on artificial intelligence, including:
s101: collecting historical operation data of the power metering equipment, and converting the historical operation data;
it should be noted that the collected historical operation data includes historical operation data of the electric energy meter, the voltage transformer and the current transformer.
And the transformation processing of the historical operating data comprises standardization processing and normalization processing.
Specifically, the historical operating data is standardized according to the following formula:
in the formula, x0In order to be able to record the historical operating data,
for historical operating data x0Average value of (1), xsIs the standard deviation of the historical operating data x.
The normalized historical operating data x is normalized to limit its range to [0, 1] as follows:
wherein x is the normalized historical operating data and x0max、x0minRespectively historical operating data x0Maximum and minimum values of.
Because the standards of the data collected by different power metering devices are different, the interval difference and the calculation error between the data can be reduced by normalizing and normalizing the data.
S102: performing type marking on the converted historical operating data, and dividing the marked historical operating data into a training set and a test set;
it should be noted that the types of the marks include a transformer polarity, a current value, and a voltage value. The marked historical operating data is divided into a training set and a test set in a ratio of 3: 7.
S103: constructing a fault prediction model of the electric power metering equipment based on the deep neural network;
it should be noted that Deep Neural Networks (DNNs) are extensions based on perceptron, and are a Neural network with many hidden layers.
The power metering equipment fault prediction model constructed based on the deep neural network comprises a plurality of layers of input layers, a plurality of layers of hidden layers and a plurality of layers of output layers.
Wherein, the expression of the output layer is:
wherein Y is an output layer,
representing input as Xn+1H is a hidden layer, n is the number of input layers, Xn+1Representing a training set of historical operating data when the input is at layer n + 1.
In this embodiment, sigmoid function may be selected as the activation function
The specific expression is as follows:
sigmoid has an advantage in that an output range is limited, so data is not easily diverged during transfer. In addition, sigmoid has an advantage that the output range is (0,1), so that it can be used as an output layer, and the output represents probability.
S104: inputting the training set into a power metering equipment fault prediction model, and training the power metering equipment fault prediction model through a stack noise reduction automatic encoder;
after the power metering device fault prediction model is constructed through the deep neural network, the historical operating data training set needs to be input into an input layer of the model to train the model.
In the present embodiment, a stack noise reduction Auto-Encoder is constructed using a noise reduction Auto-Encoder (DAE), which is composed of a plurality of noise reduction Auto-encoders. The noise reduction automatic encoder adds noise which follows a certain statistical rule into a training sample to make the training sample become a damaged sample. And then reconstructing the damaged sample through the encoding and decoding processes, so that the model can gradually eliminate noise interference from the damaged sample in the training process, more key characteristic information of data is reserved, and the encoding characteristic has stronger robustness.
Gaussian noise refers to a type of noise whose probability density function follows a gaussian distribution (i.e., a normal distribution). Thus, gaussian noise can be added to the historical data training set to train the model.
In this embodiment, the stack noise reduction automatic encoder constructed based on the noise reduction automatic encoder is composed of an input layer, an output layer, a hidden layer, an encoding network and a decoding network.
The expression of the coding network is specifically as follows:
F(W,b)(X)＝sF(WX+b)
in the formula, F(W,b)For coding the network, W is the network weight matrix between the input layer and the output layer, b is the offset vector, sFA function is activated for a neuron node of the coding network.
The expression of the decoding network is specifically:
D(W,b′)(F)＝sD(WF+b′)
in the formula, D(W,b′)For decoding the network, W is the network weight matrix between the input layer and the output layer, b' is the bias matrix, sDA function is activated for a neuron node of the decoding network.
After the stack noise reduction automatic encoder is built, training a fault prediction model of the electric power metering equipment, reconstructing an output layer of the electric power metering equipment, and obtaining a reconstructed output layer after reconstruction, wherein the method specifically comprises the following steps:
in the formula, Y' is a reconstructed output layer,
representing the corrupted data set obtained after gaussian noise is added to the training set X of historical operating data.
S105: inputting the test set into the trained power metering equipment fault prediction model, performing precision test on the trained power metering equipment fault prediction model, and stopping the test when the test precision meets a preset precision threshold.
It should be noted that the test accuracy may be set according to actual requirements, which is set to 0.95 in this embodiment, the test set is input into the trained power metering device fault prediction model, and the test is stopped until the test accuracy reaches 0.95 through continuous iterative testing.
In this case, the accuracy of identifying the meter data by the electric power meter failure prediction model trained based on the historical operating data of a large number of electric power meters is high.
The embodiment provides an artificial intelligence-based power metering equipment fault prediction method, which includes the steps of obtaining historical operating data of power metering equipment, constructing a power metering equipment fault prediction model by using a deep neural network after preprocessing, and performing iterative training and testing by using a stack noise reduction automatic encoder to obtain a power metering equipment fault prediction model with high recognition accuracy. According to the invention, as the electric power metering equipment fault prediction model is trained and optimized through the deep neural network and the stack noise reduction automatic encoder, the prediction accuracy of the model can be ensured by utilizing a large amount of historical operating data, the automatic and accurate prediction of the electric power equipment fault is realized, and the problems of large workload and low fault discovery rate caused by the conventional manual electric power metering equipment fault prediction are solved.
The above is a detailed description of an embodiment of the method for predicting faults of an electric power metering device based on artificial intelligence, and another embodiment of the method for predicting faults of an electric power metering device based on artificial intelligence is described in detail below.
The embodiment provides an artificial intelligence-based power metering equipment fault prediction method, which comprises the following steps:
s201: collecting historical operation data of the power metering equipment, and converting the historical operation data;
s202: performing type marking on the converted historical operating data, and dividing the marked historical operating data into a training set and a test set;
s203: constructing a fault prediction model of the electric power metering equipment based on the deep neural network;
it should be noted that the specific implementation of steps S201 to S203 is the same as the specific implementation of the corresponding steps in the previous embodiment, and is not described herein again.
S204: inputting the training set into a power metering equipment fault prediction model, and training the power metering equipment fault prediction model through a stack noise reduction automatic encoder;
as can be seen from the foregoing implementation, the output layer of the power metering device failure prediction model can be reconstructed by using the stack noise reduction auto encoder, so as to obtain a reconstructed output layer.
However, in the power metering device failure prediction model constructed based on the deep neural network, when the number of neurons is large enough, the number of required weight parameters is also large. Setting the weight parameters manually each time reduces efficiency, so the weight parameters, i.e. the network weight matrix W, the bias vector b and the bias matrix b', can be optimized by a Back-Propagation (BP) strategy, and the specific optimization process refers to the following formula:
where r is the learning rate of the power metering equipment failure prediction model, which is set to 0.01 in the present embodiment,
the output layer vector of the encoded and decoded historical operation data X is the normalized historical operation data.
Through the error back propagation and fine tuning of the network weight and the offset, the reconstruction error P of the input vector and the output vector can be minimized, and simultaneously the coding characteristics of the hidden layer can furthest reserve the main information of the original input data.
In this embodiment, the reconstruction error P is expressed as:
in the formula, xiFor the ith original input vector, yiFor the ith reconstruction vector, U is the number of samples.
S205: setting a reconstruction error threshold value to be 0.1;
s206: iteratively training a fault prediction model of the electric power metering equipment by utilizing a stack noise reduction automatic encoder until the reconstruction error of an input layer and an output layer of the fault prediction model of the electric power metering equipment is less than or equal to a reconstruction error threshold value, and stopping training;
s207: inputting the test set into the trained power metering equipment fault prediction model, performing precision test on the trained power metering equipment fault prediction model, and stopping the test when the test precision meets a preset precision threshold.
The embodiment provides an artificial intelligence-based electric power metering equipment fault prediction method, which is characterized in that on the basis of a large amount of historical operating data of electric power metering equipment, a deep neural network is used for constructing a fault prediction model of the electric power metering equipment, and the fault prediction model is trained and optimized by utilizing a stack noise reduction automatic encoder and an error back propagation algorithm, so that the model is more accurate in data recognition of the electric power metering equipment, and the problem that recognition errors or recognition omission possibly exist in current artificial recognition is solved.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A power metering equipment fault prediction method based on artificial intelligence is characterized by comprising the following steps:
collecting historical operating data of the power metering equipment, and converting the historical operating data;
performing type marking on the converted historical operating data, and dividing the marked historical operating data into a training set and a test set;
constructing a fault prediction model of the electric power metering equipment based on the deep neural network;
inputting the training set into the power metering equipment fault prediction model, and training the power metering equipment fault prediction model through a stack noise reduction automatic encoder;
inputting the test set into the trained fault prediction model of the electric power metering equipment, performing precision test on the trained fault prediction model of the electric power metering equipment, and stopping the test when the test precision meets a preset precision threshold.
2. The method for predicting the fault of the electric power metering equipment based on the artificial intelligence as claimed in claim 1, wherein the converting the historical operation data specifically comprises:
carrying out standardization processing on the historical operating data;
and normalizing the normalized historical operating data.
3. The artificial intelligence based power metering equipment fault prediction method according to claim 1, wherein the power metering equipment fault prediction model comprises a plurality of layers of input layers, a plurality of layers of hidden layers and a plurality of layers of output layers.
4. The method according to claim 3, wherein the expression of the output layer is as follows:
wherein Y is an output layer,
representing input as Xn+1H is the hidden layer, n is the number of input layers, Xn+1Representing a training set of historical operating data when the input is at layer n + 1.
5. The method according to claim 4, wherein the stack denoising auto-encoder specifically comprises: input layer, output layer, hidden layer, encoding network, and decoding network.
6. The method according to claim 5, wherein the expression of the coding network is specifically as follows:
F(W,b)(X)＝sF(WX+b)
in the formula, F(W,b)For coding a network, W is a network weight matrix between the input layer and the output layer, b is a bias vector, sFA function is activated for a neuron node of the coding network.
7. The method according to claim 6, wherein the decoding network has an expression as follows:
D(W,b′)(F)＝sD(WF+b′)
in the formula, D(W,b′)For decoding the network, W is between the input layer and the output layerB' is a bias matrix, sDA function is activated for a neuron node of the decoding network.
8. The method according to claim 7, wherein the training of the electric power metering device fault prediction model by the stack noise reduction auto-encoder specifically comprises:
reconstructing an output layer of the power metering equipment fault prediction model through a stack noise reduction automatic encoder to obtain a reconstructed output layer, wherein an expression of the reconstructed output layer specifically comprises:
in the formula, Y' is a reconstructed output layer,
representing the corrupted training set obtained after gaussian noise is added to the training set X of historical run data.
9. The method of claim 8, wherein reconstructing an output layer of the power metering device failure prediction model by a stack noise reduction auto-encoder to obtain a reconstructed output layer further comprises:
setting a reconstruction error threshold;
and iteratively training the electric power metering equipment fault prediction model by using the stack noise reduction automatic encoder until the reconstruction error of the input layer and the output layer of the electric power metering equipment fault prediction model is less than or equal to the reconstruction error threshold value, and stopping training.
10. The method according to claim 1, wherein the predetermined accuracy threshold is 0.95.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110969054.9A CN113642244A (en) | 2021-08-23 | 2021-08-23 | Power metering equipment fault prediction method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110969054.9A CN113642244A (en) | 2021-08-23 | 2021-08-23 | Power metering equipment fault prediction method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113642244A true CN113642244A (en) | 2021-11-12 |
Family
ID=78423526
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110969054.9A Pending CN113642244A (en) | 2021-08-23 | 2021-08-23 | Power metering equipment fault prediction method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113642244A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115600695A (en) * | 2022-09-06 | 2023-01-13 | 北京航天计量测试技术研究所（Cn） | Fault diagnosis method of metering equipment |
| CN117556963A (en) * | 2023-12-05 | 2024-02-13 | 广东欣顿电源科技有限公司 | Intelligent prediction system for operation data of electric energy metering equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
| CN112183591A (en) * | 2020-09-15 | 2021-01-05 | 上海电机学院 | Transformer fault diagnosis method based on stack sparse noise reduction automatic coding network |
-
2021
- 2021-08-23 CN CN202110969054.9A patent/CN113642244A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059357A (en) * | 2019-03-19 | 2019-07-26 | 中国电力科学研究院有限公司 | A kind of intelligent electric energy meter failure modes detection method and system based on autoencoder network |
| CN112183591A (en) * | 2020-09-15 | 2021-01-05 | 上海电机学院 | Transformer fault diagnosis method based on stack sparse noise reduction automatic coding network |
Non-Patent Citations (1)
| Title |
|---|
| 朱超岩: "基于深度学习的变压器故障诊断方法的研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115600695A (en) * | 2022-09-06 | 2023-01-13 | 北京航天计量测试技术研究所（Cn） | Fault diagnosis method of metering equipment |
| CN115600695B (en) * | 2022-09-06 | 2023-10-17 | 北京航天计量测试技术研究所 | Fault diagnosis method for metering equipment |
| CN117556963A (en) * | 2023-12-05 | 2024-02-13 | 广东欣顿电源科技有限公司 | Intelligent prediction system for operation data of electric energy metering equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2023042527A (en) | Data drive active power distribution network abnormal state sensing method and system | |
| CN113642244A (en) | Power metering equipment fault prediction method based on artificial intelligence | |
| CN102478584B (en) | Wind power station wind speed prediction method based on wavelet analysis and system thereof | |
| CN112232404B (en) | Reliability calculation method and system based on historical abnormality and operation and maintenance information of railway power supply equipment | |
| US20230112749A1 (en) | Transformer state evaluation method based on echo state network and deep residual neural network | |
| CN116679211B (en) | Lithium battery health state prediction method | |
| CN116579768B (en) | Power plant on-line instrument operation and maintenance management method and system | |
| CN115222104A (en) | Intelligent substation secondary equipment state evaluation method based on extreme learning machine | |
| CN116562114A (en) | Power transformer fault diagnosis method based on graph convolution neural network | |
| CN112115636A (en) | Method and system for predicting insulation aging life of power cable in advance | |
| Dong | Combining unsupervised and supervised learning for asset class failure prediction in power systems | |
| CN115146739A (en) | Power transformer fault diagnosis method based on stacked time series network | |
| CN116840765A (en) | Voltage transformer error state evaluation method based on multivariate time sequence analysis | |
| CN117347796B (en) | Intelligent gateway-based switching equipment partial discharge diagnosis system and method | |
| CN116070140B (en) | Power distribution substation safe operation state monitoring system and method | |
| CN113283546A (en) | Furnace condition abnormity alarm method and system of heating furnace integrity management centralized control device | |
| CN110348489B (en) | Transformer partial discharge mode identification method based on self-coding network | |
| CN115564075B (en) | Main and auxiliary integrated fault collaborative diagnosis method and system for urban power grid | |
| CN115834406A (en) | Power grid transient stability prediction method based on convolutional neural network | |
| CN116404637A (en) | Short-term load prediction method and device for electric power system | |
| CN115906520A (en) | Low-voltage transformer health degree evaluation method based on Mahalanobis distance and self-encoder | |
| CN115577854A (en) | Quantile regression wind speed interval prediction method based on EEMD-RBF combination | |
| CN115392384A (en) | Cable fault diagnosis method, system and equipment based on Stacking learning | |
| CN113487062A (en) | Power load prediction method based on periodic automatic encoder | |
| CN112949936A (en) | Short-term photovoltaic power prediction method based on similar-day wavelet transform and multilayer perceptron |
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 |