CN110794243A - Fault diagnosis method, system and equipment for direct current system - Google Patents
Fault diagnosis method, system and equipment for direct current system Download PDFInfo
- Publication number
- CN110794243A CN110794243A CN201911113599.9A CN201911113599A CN110794243A CN 110794243 A CN110794243 A CN 110794243A CN 201911113599 A CN201911113599 A CN 201911113599A CN 110794243 A CN110794243 A CN 110794243A
- Authority
- CN
- China
- Prior art keywords
- fault
- waveform
- fault diagnosis
- diagnosis model
- neural network
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 23
- 238000012360 testing method Methods 0.000 claims abstract description 21
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 20
- 230000009471 action Effects 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 3
- 230000008859 change Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000013024 troubleshooting Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009422 external insulation Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000009421 internal insulation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The invention discloses a method, a system and equipment for diagnosing faults of a direct current system, wherein the method comprises the following steps: acquiring a fault waveform and a fault type; establishing a corresponding table of fault waveforms and fault types; dividing fault waveforms into a training set and a test set; training the fault diagnosis model by adopting a training set, and testing by adopting a test set; and inputting the real-time fault waveform into a fault diagnosis model, and outputting the fault category of the corresponding fault waveform graph by the fault diagnosis model according to the corresponding table. According to the invention, the corresponding fault type is identified by analyzing the fault waveform through the convolutional neural network, the whole fault identification process is automatically carried out without human intervention, the calculation process is efficient and accurate, the problem that a large amount of time cost and labor cost are consumed due to manual fault diagnosis is avoided, and the working efficiency is greatly improved.
Description
Technical Field
The invention relates to the technical field of power diagnosis, in particular to a method, a system and equipment for diagnosing faults of a direct current system.
Background
At present, in a converter station, when an abnormality occurs in a direct current system, relevant information is reported in a sequence event record of a workstation, and then a waveform is called by a fault recording device for manual analysis and a fault type is found by field investigation.
However, as more and more direct current systems are put into operation, the power grid structure is more and more complex, and a mode of manually checking fault categories has certain disadvantages. Such as: the method has the advantages that the multi-fault troubleshooting effect is poor, the requirements on analysis capability and field experience of troubleshooting personnel are high, and the like, so that the technical problem of low diagnosis efficiency exists in the existing diagnosis of the fault type of the direct current system.
Disclosure of Invention
The invention provides a method, a system and equipment for diagnosing faults of a direct current system, and solves the technical problems of long diagnosis time and low diagnosis efficiency in the conventional fault diagnosis of the direct current system.
The invention provides a fault diagnosis method of a direct current system, which comprises the following steps:
acquiring a fault waveform and a fault type;
establishing a corresponding table of fault waveforms and fault types;
dividing fault waveforms into a training set and a test set;
establishing a fault diagnosis model, training the fault diagnosis model by adopting a training set, and testing by adopting a test set;
and inputting the real-time fault waveform into a fault diagnosis model, and outputting the fault category of the fault waveform by the fault diagnosis model according to a correspondence table of the fault waveform and the fault type.
Preferably, each fault waveform is marked with a protection action type, a protection action type-fault type correspondence table is established and input into the fault diagnosis model, and the fault diagnosis model directly outputs the fault category according to the protection action type.
Preferably, the fault waveform is normalized to a picture with uniform pixels, and the picture is grayed and then converted to a binary picture.
Preferably, the fault diagnosis model is composed of a convolutional neural network, the convolutional neural network is composed of a convolutional layer, a pooling layer and an output layer, cross entropy errors are established in the convolutional neural network as loss functions, a random gradient descent method is adopted, and weight parameters of the convolutional neural network are corrected through reverse transfer errors.
Preferably, the convolutional neural network uses a relu function as an activation function, and the output layer uses a softmax function.
Preferably, the fault waveforms are divided into training sets and test sets in an 8:2 ratio.
Preferably, the fault waveform is periodically examined and used as a sample set, an existing fault diagnosis model is periodically trained by using the sample set, and the weight parameters of the convolutional neural network in the existing fault diagnosis model are updated.
Preferably, the protection action types include: valve short circuit protection, direct current low voltage protection, commutation failure protection and valve bank differential protection.
A dc system fault diagnostic system comprising: the fault diagnosis system comprises a fault waveform acquisition module, a fault waveform correspondence table generation module, a fault waveform division module and a fault diagnosis module;
the fault waveform acquisition module is used for acquiring a fault waveform and a fault type;
the fault waveform corresponding table generating module is used for generating a corresponding table of fault waveforms and fault types;
the fault waveform dividing module is used for dividing fault waveforms into a training set and a test set;
the fault diagnosis module is used for constructing a fault diagnosis model and identifying fault types through fault waveforms.
A direct current system fault diagnosis device comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the direct current system fault diagnosis method according to the instructions in the program codes.
According to the technical scheme, the invention has the following advantages:
according to the embodiment of the invention, the corresponding fault type is identified by acquiring the fault waveform, establishing the corresponding table of the fault waveform and the fault type and analyzing the fault waveform file through the fault diagnosis model, the fault identification process is automatically carried out, the fault category can be directly output through the fault waveform without human intervention, the calculation process is efficient and accurate, the problem that the fault diagnosis needs to be carried out manually on the power network, so that a large amount of time cost and labor cost are consumed is avoided, and the working efficiency is greatly improved.
Another embodiment of the invention also has the following advantages:
according to the embodiment of the invention, the fault waveform is examined regularly and the fault name is marked as a sample set to train the existing fault diagnosis model, and the fault diagnosis model continuously learns different fault types, so that the weight parameters in the fault diagnosis model are further updated, and the fault diagnosis model can be continuously optimized so as to be suitable for most fault types.
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 flowchart of a method, a system, and a device for diagnosing a fault of a dc system according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a short circuit (87SCY) of a Y-bridge valve and a change in a digital VSCPY _ TR signal of a dc system fault diagnosis method, system and device according to an embodiment of the present invention, which corresponds to a three-phase line voltage, a three-phase line current waveform, a dc pole bus and a change in digital quantity.
Fig. 3 is a schematic diagram of a DC low voltage TRIP (27DC) and a digital UVP _ TRIP signal of a DC system fault diagnosis method, system and device according to an embodiment of the present invention, which correspond to a three-phase line voltage, a three-phase line current waveform, a DC pole bus and a digital quantity change.
Detailed Description
The embodiment of the invention provides a method, a system and equipment for diagnosing faults of a direct current system, which are used for solving the technical problems of long diagnosis time and low diagnosis efficiency in the current fault diagnosis of the direct current system.
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 obvious 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.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method, a system and a device for diagnosing a fault of a dc system according to an embodiment of the present invention.
The invention provides a fault diagnosis method of a direct current system, which comprises the following steps:
acquiring various fault waveforms and fault types in a converter station;
taking the fault waveform as a learning sample, and establishing a corresponding table of the fault waveform and the fault type;
dividing fault waveforms into a training set and a test set according to a certain proportion;
establishing a fault diagnosis model, training the fault diagnosis model by adopting a training set so that the fault diagnosis model can identify the fault category through a fault waveform, testing the fault diagnosis model by adopting a testing set, and searching for the optimal parameters of the fault diagnosis model, thereby obtaining the trained fault diagnosis model.
And inputting the real-time fault waveform into a fault diagnosis model, and outputting the fault category of the corresponding fault waveform by the fault diagnosis model according to a correspondence table of the fault waveform and the fault type to provide reference for field maintainers.
As a preferred embodiment, a protection action type is marked for each fault waveform, a protection action type-fault type correspondence table is established and input into a fault diagnosis model, and the fault diagnosis model directly outputs a fault category according to the protection action type. For example, the fault category corresponding to the valve short-circuit protection action is the insulation damage inside or outside the converter valve; the fault category corresponding to the commutation failure protection action is the voltage drop of the alternating current system and the control pulse fault, and a protection action type-fault category correspondence table is established according to the characteristics, so that fault troubleshooting is performed quickly.
As a preferred embodiment, the fault waveform is standardized to be a picture with uniform pixels, and since color features in the picture do not need to be paid attention to, the picture is grayed and then converted into a binary picture, so that the convolutional neural network can conveniently extract the binary image features of the fault waveform from the fault waveform, wherein the binary picture is a simplified version of 0-255 of a gray image, wherein 0 represents white, and 1 represents black.
As a preferred embodiment, the fault diagnosis model is composed of a convolutional neural network, the convolutional neural network is composed of a convolutional layer, a pooling layer and an output layer, and the convolutional neural network corrects the weight parameters by establishing cross entropy errors as loss functions and adopting a random gradient descent method and reversely transmitting the errors.
As a preferred embodiment, the convolutional neural network uses a relu function as an activation function, the output layer uses a softmax function, and the precision of the convolutional neural network is improved through continuous iterative training so as to achieve the purpose of image recognition.
As a preferred embodiment, the fault waveforms are divided into training and test sets on an 8:2 scale.
As a preferred embodiment, the fault waveform is periodically examined and the fault name is marked as a sample set, and the existing fault diagnosis model is periodically trained by using the sample set, so as to update the weight parameters of the existing fault diagnosis model. The fault diagnosis model can continuously learn by updating the weight parameters, and is finally suitable for most fault types.
As a preferred embodiment, the protection action types include: valve short circuit protection, direct current low voltage protection, commutation failure protection and valve bank differential protection.
A dc system fault diagnostic system comprising: the fault diagnosis system comprises a fault waveform acquisition module, a fault waveform correspondence table generation module, a fault waveform division module and a fault diagnosis module;
the fault waveform acquisition module is used for acquiring a fault waveform and a fault type;
the fault waveform corresponding table generating module is used for generating a corresponding table of fault waveforms and fault types;
the fault waveform dividing module is used for dividing fault waveforms into a training set and a test set;
the fault diagnosis module is used for constructing a fault diagnosis model and identifying fault types through fault waveforms.
A direct current system fault diagnosis device comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the direct current system fault diagnosis method according to instructions in the program codes.
Another embodiment provided by the present invention is as follows:
step 1: various fault waveforms and associated fault types of the converter station are collected.
Step 2: and taking the fault waveform as a learning sample set, and establishing a corresponding table of the fault waveform and the fault type.
Taking fig. 2 and 3 as an example, fig. 2 represents a short circuit (87SCY) of the Y-bridge valve, and the digital value VSCPY _ TR signal changes, which corresponds to a schematic diagram of changes in three-phase line voltage, three-phase line current waveform, dc pole bus and digital value.
Fig. 3 is a schematic diagram showing a DC low voltage TRIP (27DC), a change in the digital UVP _ TRIP signal, a corresponding three-phase line voltage, a three-phase line current waveform, a DC bus, and a change in the digital quantity.
Table 1 lists the fault types corresponding to the partial digital value variation, and when the protection is operated, the pulse signal corresponding to the digital value of the protection is changed from 0 to 1, and the pulse signal is shown as a dark cross in the corresponding waveform diagram.
TABLE 1 failure types corresponding to digital quantity variations
Marking the protection action type of each fault waveform, respectively marking valve short-circuit protection, direct-current low-voltage protection, commutation failure protection, valve group differential protection and the like as { VSCPY _ TR, UVP _ TRIP, CFP _ IND, CGDP _ IND,. } and establishing a fault reason corresponding table according to known protection actions, wherein the fault reason corresponding to the valve short-circuit protection action is the internal or external insulation damage of a converter valve, and the like; the fault reasons corresponding to the commutation failure protection action are alternating current system voltage drop, control pulse fault and the like, and fault troubleshooting can be rapidly carried out. Therefore, the type of the fault can be judged by identifying letters such as VSCPY _ TR, UVP _ TRIP and the like in the waveform image and the corresponding waveform image with voltage, current and digital quantity changes.
As can be seen from fig. 2, when the valve Y bridge short circuit (87SCY) protection is activated, as shown in fig. 2(1), the ac grid side three-phase line voltages UAC _ L1, UAC _ L2, UAC _ L3 change from 500kV to 0kV in waveform; as shown in fig. 2(2), the waveforms of the three-phase currents IVY _ L1, IVY _ L2 and IVY _ L3 on the star side are suddenly changed from 500A to about 1000A and gradually changed to 0A; as shown in fig. 2(3), the dc current IDLH on the dc bus line side and the dc current IDLN on the dc neutral bus grounding line side suddenly increase from 500A to about 2300A and gradually fall back to 0A; as shown in fig. 2(4), when digital value VSCPY _ TR representing valve Y bridge short circuit (87SCY) changes from 0 to 1 in the digital value operation signal, 87SCY protection is performed, and the inverter ac side switch operation is tripped, and signal ACB _ TRIP changes from 0 to 1.
As can be seen from fig. 3, when the DC low voltage trip (27DC) is made, as shown in fig. 3(1), the ac grid side three-phase line voltages UAC _ L1, UAC _ L2, UAC _ L3 change from 500kV to 0 kV; as shown in fig. 3(2), the waveforms of the three-phase currents IVY _ L1, IVY _ L2 and IVY _ L3 on the star side are suddenly changed from 500A to 0A; as shown in fig. 3(3), the dc current IDLH on the dc bus line side and the dc current IDLN on the dc neutral bus ground line side suddenly drop from 500A to 0A; as shown in fig. 3(4), the digital UVP _ TRIP representing the DC low voltage TRIP (27DC) changes from 0 to 1 in the digital operation signal, indicating that 27DC protection is performed, and the inverter ac side switch operates to TRIP, and the signal ACB _ TRIP changes from 0 to 1.
And step 3: a large number of fault waveforms are divided into training waveforms and test waveforms in a certain ratio (e.g., 8: 2).
And 4, step 4: and constructing a fault diagnosis model, and training the fault diagnosis model by using the fault waveform so that the fault diagnosis model can accurately identify the fault category through the fault waveform. In this step, the fault waveform is normalized to a picture of uniform pixels, and since there is no need to pay attention to the color of the waveform, the picture is grayed and then converted to a binary picture (binary, i.e., 0 and 1, which are substantially simple versions of 0 to 255 of a grayscale image, 0 representing white, and 1 representing black), the amount of calculation is reduced, and binary image features of the fault waveform, such as feature quantities such as VSCPY _ TR and UVP _ TRIP, and corresponding features of voltage, current waveform, and digital quantity changes, are extracted from the training fault waveform through a convolutional neural network in the fault diagnosis model.
The fault waveform is converted into a binary image, and the python code of the binary image pixel matrix (in data 3) is extracted as follows (taking the 87SCY waveform image as an example, the other images are similar):
and 5: and testing the fault diagnosis model by using the test set and optimizing the model parameters to obtain the trained optimal fault diagnosis model.
Step 6: and inputting the new fault waveform into a trained fault diagnosis model, outputting the fault type of the corresponding fault waveform graph, and providing reference for field maintainers.
And 7: and periodically manually checking a new fault waveform, marking a fault name, storing the fault name into a sample set, periodically training the existing model by using new data, and updating the weight parameters of the existing fault diagnosis model, so that the fault diagnosis model can be continuously learned and is finally suitable for most fault types.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; 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 fault diagnosis method for a direct current system is characterized by comprising the following steps:
acquiring a fault waveform and a fault type;
establishing a corresponding table of the fault waveform and the fault type;
dividing the fault waveform into a training set and a test set;
establishing a fault diagnosis model, training the fault diagnosis model by adopting the training set, and testing by adopting the test set;
and inputting a real-time fault waveform into the fault diagnosis model, and outputting the fault category of the fault waveform by the fault diagnosis model according to the fault waveform and the corresponding table of the fault types.
2. The method according to claim 1, wherein a protection action type is marked for each fault waveform, a protection action type-fault type correspondence table is established and input into a fault diagnosis model, and the fault diagnosis model directly outputs a fault type according to the protection action type.
3. The method according to claim 1, wherein the fault waveform is normalized to a picture with uniform pixels, and the picture is grayed and then converted to a binary picture.
4. The method according to claim 1, wherein the fault diagnosis model is composed of a convolutional neural network, the convolutional neural network is composed of convolutional layers, pooling layers and output layers, cross entropy errors are established in the convolutional neural network as loss functions, and weight parameters of the convolutional neural network are corrected by inverse transfer errors by a stochastic gradient descent method.
5. The method according to claim 4, wherein the convolutional neural network uses a relu function as an activation function, and the output layer uses a softmax function.
6. The method according to claim 5, wherein the fault waveform is periodically examined and used as a sample set, an existing fault diagnosis model is periodically trained using the sample set, and the weight parameters of the convolutional neural network in the existing fault diagnosis model are updated.
7. The method according to claim 1, wherein the fault waveform is divided into a training set and a test set in a ratio of 8: 2.
8. The method according to claim 2, wherein the protection action types include: valve short circuit protection, direct current low voltage protection, commutation failure protection and valve bank differential protection.
9. A dc system fault diagnostic system, comprising: the fault diagnosis system comprises a fault waveform acquisition module, a fault waveform correspondence table generation module, a fault waveform division module and a fault diagnosis module;
the fault waveform acquisition module is used for acquiring a fault waveform and a fault type;
the fault waveform corresponding table generating module is used for generating a corresponding table of fault waveforms and fault types;
the fault waveform dividing module is used for dividing fault waveforms into a training set and a test set;
the fault diagnosis module is used for constructing a fault diagnosis model and identifying fault types through fault waveforms.
10. A dc system fault diagnosis device, characterized in that the device comprises a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the dc system fault diagnosis method according to any one of claims 1 to 8 according to instructions in the program code.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113599.9A CN110794243A (en) | 2019-11-14 | 2019-11-14 | Fault diagnosis method, system and equipment for direct current system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911113599.9A CN110794243A (en) | 2019-11-14 | 2019-11-14 | Fault diagnosis method, system and equipment for direct current system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110794243A true CN110794243A (en) | 2020-02-14 |
Family
ID=69444813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911113599.9A Pending CN110794243A (en) | 2019-11-14 | 2019-11-14 | Fault diagnosis method, system and equipment for direct current system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110794243A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476374A (en) * | 2020-04-14 | 2020-07-31 | 重庆工业职业技术学院 | Pure electric vehicle electric appliance fault diagnosis training method and device based on neural network |
| CN112461289A (en) * | 2020-10-27 | 2021-03-09 | 国网山东省电力公司昌邑市供电公司 | Ring main unit fault monitoring method, system, terminal and storage medium |
| CN113110389A (en) * | 2021-04-21 | 2021-07-13 | 东方电气自动控制工程有限公司 | Fault recording data processing method based on intelligent power plant monitoring system |
| CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
| CN113433856A (en) * | 2021-06-17 | 2021-09-24 | 浙江齐安信息科技有限公司 | Equipment state monitoring method, device, system and storage medium |
| CN115311493A (en) * | 2022-08-04 | 2022-11-08 | 国网江苏省电力有限公司电力科学研究院 | Method, system, memory and equipment for judging direct current circuit state |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106526400A (en) * | 2016-11-28 | 2017-03-22 | 株洲中车时代电气股份有限公司 | Grounding fault diagnosing method and apparatus of DC 600V train power supply system |
| CN107450016A (en) * | 2017-07-24 | 2017-12-08 | 西安工程大学 | Fault Diagnosis for HV Circuit Breakers method based on RST CNN |
| CN109116203A (en) * | 2018-10-31 | 2019-01-01 | 红相股份有限公司 | Power equipment partial discharges fault diagnostic method based on convolutional neural networks |
| CN109917205A (en) * | 2019-03-13 | 2019-06-21 | 中南大学 | A kind of solenoid valve failure diagnostic device and method based on feature extraction and multi-layer perception (MLP) |
| CN110223195A (en) * | 2019-05-22 | 2019-09-10 | 上海交通大学 | Distribution network failure detection method based on convolutional neural networks |
-
2019
- 2019-11-14 CN CN201911113599.9A patent/CN110794243A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106526400A (en) * | 2016-11-28 | 2017-03-22 | 株洲中车时代电气股份有限公司 | Grounding fault diagnosing method and apparatus of DC 600V train power supply system |
| CN107450016A (en) * | 2017-07-24 | 2017-12-08 | 西安工程大学 | Fault Diagnosis for HV Circuit Breakers method based on RST CNN |
| CN109116203A (en) * | 2018-10-31 | 2019-01-01 | 红相股份有限公司 | Power equipment partial discharges fault diagnostic method based on convolutional neural networks |
| CN109917205A (en) * | 2019-03-13 | 2019-06-21 | 中南大学 | A kind of solenoid valve failure diagnostic device and method based on feature extraction and multi-layer perception (MLP) |
| CN110223195A (en) * | 2019-05-22 | 2019-09-10 | 上海交通大学 | Distribution network failure detection method based on convolutional neural networks |
Non-Patent Citations (1)
| Title |
|---|
| 刘学东: "基于图像分形的故障特征提取方法", 《北华航天工业学院学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111476374A (en) * | 2020-04-14 | 2020-07-31 | 重庆工业职业技术学院 | Pure electric vehicle electric appliance fault diagnosis training method and device based on neural network |
| CN111476374B (en) * | 2020-04-14 | 2022-09-27 | 重庆工业职业技术学院 | Pure electric vehicle electric appliance fault diagnosis training method and device based on neural network |
| CN112461289A (en) * | 2020-10-27 | 2021-03-09 | 国网山东省电力公司昌邑市供电公司 | Ring main unit fault monitoring method, system, terminal and storage medium |
| CN113110389A (en) * | 2021-04-21 | 2021-07-13 | 东方电气自动控制工程有限公司 | Fault recording data processing method based on intelligent power plant monitoring system |
| CN113189448A (en) * | 2021-04-29 | 2021-07-30 | 广东电网有限责任公司清远供电局 | Method and device for detecting fault type of power transmission line |
| CN113433856A (en) * | 2021-06-17 | 2021-09-24 | 浙江齐安信息科技有限公司 | Equipment state monitoring method, device, system and storage medium |
| CN115311493A (en) * | 2022-08-04 | 2022-11-08 | 国网江苏省电力有限公司电力科学研究院 | Method, system, memory and equipment for judging direct current circuit state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110794243A (en) | Fault diagnosis method, system and equipment for direct current system | |
| US20210319156A1 (en) | Method and system for fault diagnosis with small samples of power equipment based on virtual and real twin spaces | |
| CN111986172A (en) | Infrared image fault detection method and device for power equipment | |
| CN110909035B (en) | Method and device for generating personalized complex problem set, electronic equipment and storage medium | |
| CN114414942B (en) | Power transmission line fault identification classifier, identification method and system based on transient waveform image identification | |
| CN111967620B (en) | Photovoltaic module diagnosis method, device, equipment and readable storage medium | |
| CN110533064A (en) | A kind of the shelf depreciation map mode identification method and system of GIS device | |
| CN115047322B (en) | Method and system for identifying fault chip of intelligent medical equipment | |
| CN114359619A (en) | Incremental learning-based power grid defect detection method, device, equipment and medium | |
| CN113947746A (en) | Distribution network safety quality control method based on feedback mechanism supervision | |
| CN113406439B (en) | Fault positioning method for power distribution network | |
| CN116008731A (en) | Power distribution network high-resistance fault identification method and device and electronic equipment | |
| CN112113638B (en) | Water meter function self-checking device and method | |
| Nandi et al. | Diagnosis of induction motor faults using frequency occurrence image plots—a deep learning approach | |
| CN109711434A (en) | Obtain and assess method, apparatus, equipment and the medium of the training data of VQA system | |
| CN113406437A (en) | Power transmission line fault detection method for generating countermeasure network based on auxiliary classification | |
| CN112465358A (en) | Voltage quality classification method and device based on support vector machine | |
| CN110399911A (en) | A kind of transformer mechanical failure diagnostic method based on sound-filed simulation cloud atlas | |
| CN114662394B (en) | High-voltage alternating-current line protection behavior evaluation method and system based on YOLO V3 | |
| CN116165478A (en) | Small-current single-phase grounding fault line selection method and device under small sample condition | |
| CN116338545A (en) | Method, system, equipment and medium for identifying metering error state of current transformer | |
| CN108802512B (en) | Power distribution system test method and device | |
| CN111597957B (en) | Transformer winding fault diagnosis method based on morphological image processing | |
| CN114113909A (en) | Power distribution network single-phase earth fault line selection method and system | |
| CN113822288B (en) | Method and system for quickly checking white heads of secondary line cables |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |
|
| RJ01 | Rejection of invention patent application after publication |