CN115712865A - Power grid fault identification method and system based on neural network model and computer readable storage medium - Google Patents
Power grid fault identification method and system based on neural network model and computer readable storage medium Download PDFInfo
- Publication number
- CN115712865A CN115712865A CN202211307268.0A CN202211307268A CN115712865A CN 115712865 A CN115712865 A CN 115712865A CN 202211307268 A CN202211307268 A CN 202211307268A CN 115712865 A CN115712865 A CN 115712865A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- grid fault
- hidden layer
- layer
- 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
Images
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
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method, a system and a computer readable storage medium for identifying a power grid fault based on a neural network model, wherein the method comprises the following steps: constructing a neural network model; acquiring at least one power parameter representing the running state of a power grid in the power grid to be subjected to fault identification as a characteristic value; classifying the acquired power parameters into a test set and a training set; carrying out optimization training on the constructed neural network model through a training set; testing the optimally trained neural network model through a test set; and after the test is passed, a power grid fault identification model is established, and the power grid fault is identified. According to the grid fault identification method based on the neural network model, the constructed neural network model is trained and optimized, the actual operation state of the grid is obtained according to the actual power parameters representing the operation state of the grid, fault diagnosis can be performed quickly and accurately, and a foundation is laid for subsequent fault isolation and electric energy recovery.
Description
Technical Field
The invention belongs to the technical field of power grid operation and control, and particularly relates to a method and a system for identifying a power grid fault based on a neural network model and a computer readable storage medium.
Background
Parameters of the power distribution network have a vital significance for control and analysis of the power distribution network, the parameters of the power distribution network are influenced by factors such as temperature, operating environment and skin effect, and are difficult to directly measure through an instrument, and particularly after the power distribution network fails, if the related parameters change too much, the safe operation of the power distribution network is not utilized. The power distribution network comprises a plurality of nodes, and the power distribution network parameters comprise line resistance, line reactance, transformer resistance, transformer conductance, transformer reactance and transformer susceptance.
After an accident occurs in the distribution network, rapid and accurate fault diagnosis is required to isolate the faulty element and restore the power supply. Now, then, fault diagnosis is particularly difficult in the case of malfunctioning or multiple faults of the protection and circuit breaker.
Disclosure of Invention
The invention provides a method and a system for identifying a power grid fault based on a neural network model and a computer readable storage medium, which can more effectively solve the problem of low fault diagnosis efficiency.
The invention is realized by the following technical scheme:
in one aspect, the invention provides a grid fault identification method based on a neural network model, which comprises the following steps: constructing a neural network model; acquiring at least one power parameter representing the running state of a power grid in the power grid to be subjected to fault identification as a characteristic value; classifying the acquired power parameters into a test set and a training set; carrying out optimization training on the constructed neural network model through a training set; testing the optimally trained neural network model through a test set; after the test is passed, a power grid fault identification model is established, and the power grid fault is identified;
the neural network model comprises an input layer, a hidden layer and an output layer; identifying the grid fault includes: transmitting the power parameter to the hidden layer through the input layer; calculating the distance between the input vector of the input parameter and the weight vector of the input parameter by the neuron in the hidden layer; taking the calculated value of the neuron in the hidden layer as the input of a calculation model in the hidden layer to obtain an output value of the hidden layer; the output layer acquires the output value of the hidden layer and outputs the final identification result.
In some of these embodiments, the computational model is as follows:
wherein the content of the first and second substances,
is the output value of the hidden layer, n 1 Is the number of hidden layer neurons, x is the input vector, a i And σ i Respectively the weight and the probability divergence of the function.
In some embodiments, the calculation method for acquiring, by the output layer, the output value of the hidden layer and outputting the final recognition result includes:
wherein d is j Is the output of the jth neuron of the output layer, v ij The weight from the ith hidden layer neuron to the jth output neuron.
In some embodiments, the number of the neurons in the input layer is equal to the number of the power parameters which characterize the power grid operation state in the power grid to be subjected to fault identification; the number of neurons in the output layer is equal to the number of elements in the power grid.
In some embodiments, the mapping relationship between the input layer and the hidden layer is:
wherein, the matrix has l columns and t rows
Is the output of the l hidden layer neuron in the network with respect to the t input vector x (t);
the mapping relation corresponding to the hidden layer and the output layer is as follows:
V(n 1 ×n 2 ) (4)
the expected outputs of the training samples are:
the deviation between the calculated output of the neural network and the expected output D of the training sample is:
in some of these embodiments, the ratio of the test set to the training set is 2:8 or 3.
In some embodiments, after the test is passed, a power grid fault identification model is established, in the process of identifying the power grid fault, the identification rate reaches 95%, and the test is determined to be passed.
In some embodiments, after the power grid fault is tested to pass, a power grid fault identification model is established, and after the power grid fault is identified, if the identification rate does not reach 95%, the steps are repeated until the identification rate reaches 95%.
In another aspect, the present embodiment provides a grid fault identification system based on a neural network model, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the grid fault identification method based on the neural network model as in any one of the above embodiments by calling the computer program stored in the memory.
The present embodiment also provides a computer-readable storage medium, in which a computer program is stored, where the computer program is suitable for being loaded by a processor to execute the method for identifying a power grid fault based on a neural network model in any one of the foregoing embodiments.
Compared with the prior art, the invention has the following advantages and beneficial effects:
the method for identifying the power grid fault based on the neural network model provided by the invention trains and optimizes the built neural network model by taking the known electric power parameters representing the power grid running state as a training set and a test set, and then obtains the actual running state of the power grid according to the actual electric power parameters representing the power grid running state through the optimized neural network model. After the power grid fails, the fault diagnosis can be rapidly and accurately carried out through the method, and a foundation is laid for subsequent fault isolation and electric energy recovery.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
Fig. 1 is a schematic flow diagram of a method for identifying a grid fault based on a neural network model according to the present invention;
fig. 2 is a schematic flow chart of the grid fault identification step provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention.
On one hand, the embodiment provides a grid fault identification method based on a neural network model, as shown in fig. 1 and fig. 2, including the following steps:
and S10, constructing a neural network model. In S10, the constructed neural network model includes an input layer, a hidden layer, and an output layer. The hidden layer is provided with a calculation model, and the calculation model in the hidden layer comprises an initial model and a calculation model. The initial model is an untrained model, and forms a mature calculation model after being input into a training set, trained for multiple times and tested by a test set. And inputting power parameters representing the power grid running state in the power grid to be subjected to fault identification as characteristic values through a calculation model, reaching the hidden layer through the input layer, and finally outputting the power parameters through the output layer to obtain a fault identification result. On the other hand, when the electric parameters representing the power grid operation state in the power grid to be subjected to fault identification are identified and the fault identification result is obtained, the electric parameters representing the power grid operation state which are input correspondingly and unknown and the identification result which is output finally are actually compared, the calculation model can still continuously keep learning according to the data sets, and the calculation model is continuously improved.
S20, acquiring at least one electric power parameter representing the operation state of the power grid in the power grid to be subjected to fault identification as a characteristic value. In S20, according to the requirement of the security level of the power grid, in different actual scenes, different power parameters representing the operation state of the power grid are obtained. Correspondingly, the calculation model and the training set are also correspondingly provided with different neurons of the power parameters representing the power grid operation state. Exemplary power parameters that characterize the operating state of the grid include, but are not limited to, the total number and status of relays, circuit breakers, transmission lines, buses, and transformers.
And S30, classifying the acquired power parameters, and specifically dividing the acquired power parameters into a test set and a training set. In S30, the obtained power parameters are mainly known power parameters corresponding to different power grid operating states and power parameters thereof, where the test set and the training set respectively have corresponding power parameters and power grid operating states corresponding to the power parameters. And (3) preparing for the optimization training of the neural network model in a training mode through known power parameters and corresponding power grid operation state input values.
And S40, carrying out optimization training on the constructed neural network model through a training set. In S40, training the constructed neural network model by inputting known corresponding different power grid operation states and power parameters thereof to obtain a calculation model after the neural network model is optimized.
And S50, after the calculation model after the neural network model is optimized is trained and optimized, inputting a test set, namely known power parameters corresponding to different power grid operation states, comparing the output result of the neural network model with the actual power grid operation state corresponding to the power parameters, and judging the identification accuracy of the neural network model after the optimization training.
S60, after the test is passed, namely the neural network model after the optimization training is higher than a preset threshold value, the test is considered to be passed. And then establishing a power grid fault identification model, namely a trained neural network model, and carrying out specific identification operation on the power grid fault by adopting the neural network model.
The neural network model comprises an input layer, a hidden layer and an output layer. The hidden layer is built up of computational model neurons, the input signal is transmitted to the hidden layer via the input layer, the ith neuron in the hidden layer will compute an input vector x and its weight vector a i And the distance is used as the subsequent calculation model
And thus the output of the hidden layer.
In the step S60, identifying the grid fault specifically includes the following steps:
and S601, transmitting the power parameters to the hidden layer through the input layer. According to the safety level requirements of different power grids and the construction of the neural network model, corresponding to different safety standards required by the neural network model, corresponding power parameters are input and transmitted to the hidden layer through the input layer.
S602, inputting the power parameters into the hidden layer, and calculating the distance between the input vector of the input parameters and the weight vector of the input parameters by the neurons in the hidden layer.
S603, taking the calculated value of the neuron in the hidden layer in S602 (i.e. the distance between the input vector of the input parameter and the weight vector of the input parameter) as the input of the computation model in the hidden layer, and obtaining the output value of the hidden layer.
And S604, the output layer acquires the output value of the hidden layer, and finally the output layer outputs the final identification result of the power grid system.
In the embodiment, different power parameters representing the operation state of the power grid are selected as characteristic values by constructing the neural network model and according to the safety level requirement of the actual power grid. After the characteristic values are selected, corresponding characteristic values are input, and the neural network model is continuously trained and tested according to different classifications (a training set and a testing set) of the characteristic values, so that the optimization training of the neural network model is realized. After the neural network model is optimally trained, a mature calculation identification model is formed and applied for use. In the using process, corresponding actual power parameters representing the power grid running state when specific time nodes are input are calculated by the calculation identification model, and finally, a power grid fault identification result is obtained. Through the arrangement in the embodiment, the power grid fault identification method provided by the embodiment of the application can realize rapid and accurate power grid fault diagnosis and prepare for subsequent power grid fault isolation and electric energy recovery.
In some of these embodiments, the computational model mentioned in S603 is as follows:
in the formula (1), the reaction mixture is,
is the output value of the hidden layer, n 1 Is the number of hidden layer neurons, x is the input vector, a i And σ i Respectively the weight and the probability divergence of the function.
In the above embodiment, the neuron i in the hidden layer is used for detection when the vector x and the weight a are inputted i When the same, the output value is 1. Probability divergence sigma i Represents the input space x-a corresponding to the neuron in the hidden layer i The range in | is, in general, not greater than the maximum distance possible between the input vector and the center of the computational model, with the particular numerical value determined experimentally.
In some embodiments, in S604, the calculation method for acquiring, by the output layer, the output value of the hidden layer and outputting the final identification result includes the following steps:
in the formula (2), d j Is the output of the jth neuron of the output layer, v ij The weight from the ith hidden layer neuron to the jth output neuron.
In some embodiments, the number of neurons in the input layer is equal to the number of power parameters characterizing the operation state of the power grid in the power grid to be fault-identified. The number of the neurons of the output layer is equal to the number of elements in the power grid.
In the embodiment, in the process of constructing the neural network model, the set number of the neurons in the input layer is equal to the number of the power parameters representing the power grid operation state in the power grid to be subjected to fault identification; illustratively, the number of neurons in the input layer is equal to the total number of all protection relays and circuit breakers in the power network, the states of which are the inputs to the neural network model. On the other hand, the number of the neurons of the output layer is equal to the number of elements in the power grid; illustratively, the sum of the number of elements in the power network, such as transmission lines, busbars, transformers, etc., is equal to the number of neurons in the output layer.
The mapping relation between the input layer and the hidden layer is as follows:
in equation (3), the matrix has l columns and t rows
Is the output of the l hidden layer neuron in the network with respect to the t input vector x (t);
the mapping relation between the hidden layer and the output layer is as follows:
V(n 1 ×n 2 ) (4)
the expected outputs of the training samples are:
the deviation between the calculated output of the neural network and the expected output D of the training sample is:
in the above embodiment, two mappings (i.e. input layer to hidden layer, cause layer to output layer) in the neural network model can be represented in matrix form as:
D＝Φ·V+E (7)
in equation (7), the matrix Φ corresponds to the first mapping relationship in the network, and the specific content is as described in equation (3), where l columns and t rows of elements of the matrix are
Is the output of the l-th hidden layer neuron in the network with respect to the t-th input vector x (t). Matrix V (n) 1 ×n 2 ) The second mapping relationship in the corresponding network is the weight matrix in equation (2). Matrix D (N × N) 2 ) Is the expected output of all training samples, the result of which is similar to the matrix phi.
In some of these embodiments, the ratio of the test set to the training set is 2:8 or 3. In multiple experiments, the ratio of the test set to the training set is set according to the above, so that the neural network model can be better learned.
In some embodiments, after the power grid fault is to be tested, a power grid fault identification model is established, in the process of identifying the power grid fault, the identification rate reaches 95%, and the power grid fault is determined to be tested to be passed. And taking 95% as an identification threshold, and after the identification threshold is reached, considering that the established power grid fault identification model is qualified, immediately putting the power grid fault identification model into use, and starting to identify the power grid fault.
In some embodiments, after the power grid fault is tested to pass, a power grid fault identification model is established, and after the power grid fault is identified, if the identification rate does not reach 95%, the steps are repeated until the identification rate reaches 95%.
In the above embodiment, when the grid fault identification rate reaches 95%, the grid fault identification operation may be performed. And when the grid fault identification rate does not reach 95%, repeating the steps from S20 to S60, selecting different data samples with the same power parameters in the step S20, and continuing training and testing the neural network model until the grid fault identification rate is not lower than 95%, and performing grid fault identification operation.
In another aspect, the present embodiment provides a grid fault identification system based on a neural network model, which includes a memory and a processor, where the memory stores a computer program, and the processor executes the grid fault identification method based on the neural network model in any one of the above embodiments by calling the computer program stored in the memory.
The present embodiment also provides a computer-readable storage medium, in which a computer program is stored, where the computer program is suitable for being loaded by a processor to execute the method for identifying a power grid fault based on a neural network model in any one of the foregoing embodiments.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. used herein refer to the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the present invention is used, and are used for convenience of description and simplicity of description, but do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore should not be construed as limiting the present invention.
Furthermore, the terms "horizontal", "vertical" and the like when used in the description of the present invention do not require that the components be absolutely horizontal or overhanging, but may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the present invention, it should be further noted that unless otherwise explicitly stated or limited, the terms "disposed," "mounted," "connected," and "connected" should be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The terms "comprising" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or modules is not limited to the listed steps or modules but may alternatively include other steps or modules not listed or inherent to such process, method, article, or apparatus.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications and equivalent variations of the above embodiments according to the technical spirit of the present invention are included in the scope of the present invention.
Claims (10)
1. A grid fault identification method based on a neural network model is characterized by comprising the following steps:
constructing a neural network model;
acquiring at least one power parameter representing the running state of a power grid in the power grid to be subjected to fault identification as a characteristic value;
classifying the acquired power parameters into a test set and a training set;
performing optimization training on the constructed neural network model through the training set;
testing the neural network model after the optimization training through the test set;
after the test is passed, a power grid fault identification model is established, and the power grid fault is identified;
the neural network model comprises an input layer, a hidden layer and an output layer;
the identifying of the grid fault comprises:
transmitting the power parameter to the hidden layer through the input layer;
calculating the distance between an input vector of the input parameter and a weight vector of the input parameter by the neuron in the hidden layer;
taking the calculation value of the neuron in the hidden layer as the input of a calculation model in the hidden layer to obtain an output value of the hidden layer;
and the output layer acquires the output value of the hidden layer and outputs a final identification result.
2. The grid fault identification method based on the neural network model as claimed in claim 1, wherein the calculation model is as follows:
wherein the content of the first and second substances,
is the output value of the hidden layer, n 1 Is the number of hidden layer neurons, x is the input vector, a i And σ i Respectively the weight and the probability divergence of the function.
3. The grid fault identification method based on the neural network model according to claim 2, wherein the calculation method for acquiring the output value of the hidden layer by the output layer and outputting the final identification result comprises the following steps:
wherein d is j Is the output of the jth neuron of the output layer, v ij The weight of the ith hidden layer neuron to the jth output neuron.
4. The grid fault identification method based on the neural network model as claimed in claim 1, wherein the number of neurons in the input layer is equal to the number of power parameters representing the operation state of the grid in the grid to be fault identified; the number of the neurons of the output layer is equal to the number of elements in the power grid.
5. The method for identifying the grid fault based on the neural network model as claimed in claim 4, wherein the mapping relationship between the input layer and the hidden layer is as follows:
wherein, the matrix has l columns and t rows
Is the output of the l hidden layer neuron in the network with respect to the t input vector x (t);
the mapping relation corresponding to the hidden layer and the output layer is as follows:
V(n 1 ×n 2 ) (4)
the expected outputs of the training samples are:
D(N×n 2 )＝[d 1 ...d m ...d n2 ]＝[d(1)...d(t)...d(N)] T (5)
the deviation between the calculated output of the neural network and the expected output D of the training sample is:
6. the neural network model-based grid fault identification method according to claim 1, wherein the ratio of the test set to the training set is 2:8 or 3:7.
7. the method for identifying the grid fault based on the neural network model as claimed in claim 1, wherein the grid fault identification model is established after the grid fault is tested to pass, the identification rate reaches 95% in the identification of the grid fault, and the test is determined to pass.
8. The method for identifying the grid fault based on the neural network model as claimed in claim 1, wherein a grid fault identification model is established after the grid fault is tested, and after the grid fault is identified, if the identification rate does not reach 95%, the above steps are repeated until the identification rate reaches 95%.
9. A grid fault identification system based on a neural network model, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the grid fault identification method based on the neural network model according to any one of claims 1 to 8 by calling the computer program stored in the memory.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program adapted to be loaded by a processor to perform the method for neural network model based grid fault identification according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307268.0A CN115712865A (en) | 2022-10-24 | 2022-10-24 | Power grid fault identification method and system based on neural network model and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211307268.0A CN115712865A (en) | 2022-10-24 | 2022-10-24 | Power grid fault identification method and system based on neural network model and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115712865A true CN115712865A (en) | 2023-02-24 |
Family
ID=85231553
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211307268.0A Pending CN115712865A (en) | 2022-10-24 | 2022-10-24 | Power grid fault identification method and system based on neural network model and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115712865A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117200203A (en) * | 2023-09-07 | 2023-12-08 | 航电所(成都)科技有限公司 | Operation optimization method and system applied to power system |
-
2022
- 2022-10-24 CN CN202211307268.0A patent/CN115712865A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117200203A (en) * | 2023-09-07 | 2023-12-08 | 航电所(成都)科技有限公司 | Operation optimization method and system applied to power system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Afrasiabi et al. | Integration of accelerated deep neural network into power transformer differential protection | |
| Castro et al. | Knowledge discovery in neural networks with application to transformer failure diagnosis | |
| Tang et al. | An evidential reasoning approach to transformer condition assessments | |
| US11967823B2 (en) | Method for monitoring short-term voltage stability of power system | |
| CN110829417B (en) | Electric power system transient stability prediction method based on LSTM double-structure model | |
| CN111598166B (en) | Single-phase earth fault classification method and system based on principal component analysis and Softmax function | |
| CN107807860B (en) | Power failure analysis method and system based on matrix decomposition | |
| CN110672905A (en) | CNN-based self-supervision voltage sag source identification method | |
| KR102564407B1 (en) | A method and system for diagnosing the operating state of an electrochemical system in real time, and an electrochemical system including the diagnostic system | |
| CN115712865A (en) | Power grid fault identification method and system based on neural network model and computer readable storage medium | |
| CN114355240A (en) | Power distribution network ground fault diagnosis method and device | |
| CN111967620A (en) | Photovoltaic module diagnosis method, device, equipment and readable storage medium | |
| El Chamie et al. | Physics-based features for anomaly detection in power grids with micro-pmus | |
| CN116432112A (en) | Arc fault detection method based on wavelet packet transformation and residual convolution neural network | |
| CN116572747A (en) | Battery fault detection method, device, computer equipment and storage medium | |
| CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
| CN113782113A (en) | Method for identifying gas fault in transformer oil based on deep residual error network | |
| CN112284704A (en) | Rotating equipment fault diagnosis method and system based on test matrix and readable storage medium | |
| CN112380763A (en) | System and method for analyzing reliability of in-pile component based on data mining | |
| CN116578922A (en) | Valve cooling system fault diagnosis method and device based on multichannel convolutional neural network | |
| CN112085083B (en) | Transformer fault diagnosis method based on similarity analysis strategy | |
| CN113092934B (en) | Single-phase earth fault judgment method and system based on clustering and LSTM | |
| CN115311509A (en) | Power system transient stability evaluation method and system based on imaging data driving | |
| CN112446430A (en) | Fault identification method for direct-current power transmission system | |
| CN114239636A (en) | Defect type identification method and device, computer equipment and storage medium |
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 |