CN115587312A - Fault point positioning method and system based on multi-dimensional big data analysis - Google Patents
Fault point positioning method and system based on multi-dimensional big data analysis Download PDFInfo
- Publication number
- CN115587312A CN115587312A CN202211145211.5A CN202211145211A CN115587312A CN 115587312 A CN115587312 A CN 115587312A CN 202211145211 A CN202211145211 A CN 202211145211A CN 115587312 A CN115587312 A CN 115587312A
- Authority
- CN
- China
- Prior art keywords
- fault
- module
- environmental
- power grid
- data collection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G01R31/08—Locating faults in cables, transmission lines, or networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Abstract
The invention discloses a fault point positioning method and a fault point positioning system based on multidimensional big data analysis, which relate to the technical field of power grid fault positioning, and are characterized in that the causes of power grid faults and the environmental conditions of each cause are collected in advance; then collecting the point locations with faults in the history of the power grid and the current environmental conditions of each point location; dividing fault causes into two categories; generating a machine learning model for judging whether a fault occurs according to environmental condition data for historical fault-like reasons; and installing environmental data collection equipment at the fault point; for the historical non-fault-like reasons, searching a proper position in the power grid to install environmental data collection equipment; finally, analyzing fault point positions according to real-time data collected by the environmental data collection equipment; the problem of seeking the power grid fault point location is solved.
Description
Technical Field
The invention belongs to the field of power grids, relates to a power grid fault positioning technology, and particularly relates to a fault point positioning method and system based on multi-dimensional big data analysis.
Background
At present, both urban and industrial networks need to rely on power grid technology; therefore, the arrangement of the power grid is often large and complicated; when a fault occurs in the operation process of the power grid, the fault point position is difficult to be timely and accurately positioned; moreover, the process of checking is often manual checking, which consumes huge manpower and material resources; in fact, the reason for the grid fault is usually due to some fixed environmental factors, and the location with the environmental factors is often fixed; therefore, a method for analyzing the power grid fault point location based on the historical power grid fault condition is needed;
therefore, a fault point positioning method and a fault point positioning system based on multi-dimensional big data analysis are provided.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. The fault point positioning method and the system based on the multi-dimensional big data analysis collect the reasons of the power grid fault and the environmental conditions of each reason in advance; collecting the point locations with faults in the history of the power grid and the environmental conditions of each point location at that time; dividing fault causes into two categories; generating a machine learning model for judging whether a fault occurs according to environmental condition data for historical fault-like reasons; and installing environmental data collection equipment at the fault point; for the historical non-fault-like reasons, searching a proper position in the power grid to install environmental data collection equipment; finally, analyzing fault point positions according to real-time data collected by the environmental data collection equipment; the problem of seeking the power grid fault point location is solved.
In order to achieve the above object, an embodiment according to a first aspect of the present invention provides a fault point locating method based on multidimensional big data analysis, including the following steps:
the method comprises the following steps: the fault reason collection module collects the reasons which can cause the grid fault and the corresponding typical environmental conditions in advance; and making a fault reason table;
step two: the fault data collection module collects historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid;
step three: the fault classification module classifies fault reasons in the fault reason table into history occurrence and history non-occurrence; judging the category of each fault reason in the fault reason table; if the fault is a historical fault, turning to the fourth step; if the historical failure causes do not occur, turning to the fifth step;
step four: the model training module classifies historical fault point locations according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; setting environmental data collection equipment corresponding to the failure occurrence reason at each historical failure point position through a first real-time data collection module;
step five: the second real-time data collection module is used for setting environmental data collection equipment corresponding to the failure occurrence reason at different positions in the power grid; the placement position of the environmental data collection equipment is set according to the actual condition of the power grid;
step six: all data collection equipment is started when a power grid runs, and collected environmental data are sent to a fault analysis module in real time;
step seven: when the power grid fails, the fault analysis module analyzes the environmental data of each position of the power grid, which are sent by the environmental data collection equipment; acquiring a point position where a fault occurs in a power grid;
wherein the failure cause collection module marks the collected failure cause set as R; each failure cause is marked as r; for each fault reason r, acquiring an environmental condition corresponding to the fault reason according to actual experience; marking the environmental condition set corresponding to the fault reason r as Er; for example, the environmental condition set Er may include temperature data, ventilation data, grid equipment usage, and the like due to a grid fault caused by a high temperature;
the fault data collection module collects each fault point position of a power grid fault in the history of the power grid, a fault reason r of each fault power grid and a corresponding environment condition set Er;
the historical occurrence of the similar faults is caused by the power grid faults caused by the fault reasons which have occurred in the operation history of the power grid; the historical non-fault-occurrence reasons are fault reasons which do not occur in the operation history of the power grid, namely fault reasons which are in the fault reason set R but do not occur in the historical fault point positions;
the model training module generates a machine learning model for judging whether a fault occurs according to the environmental condition data, and comprises the following steps of:
step S1: the model training module classifies all fault point positions according to fault reasons r; marking a fault point location set contained in each type of fault reason as Pr; for each fault point position set Pr, collecting data of an environmental condition set Er of each fault point position in the set when a fault occurs;
step S2: digitizing and normalizing the data of the environment condition set Er, and expressing the data into a form of a feature vector;
and step S3: inputting the characteristic vector set of each environment condition set Er into a machine learning model by taking the characteristic vector set of each environment condition set Er as input, and taking whether a fault occurs as output; the machine learning model takes the prediction accuracy as a training target to train; stopping training until the prediction accuracy reaches 95%; marking a machine learning model generated by the environment condition set Er as Mr;
the first real-time data collection module is provided with environmental data collection equipment at each historical fault point, and the data collected by the environmental data collection equipment comprises environmental condition data contained in fault reasons which have occurred historically at the fault point;
the second real-time data collection module searches a point location which accords with the environmental condition data in the power grid according to the environmental condition data of the historical non-occurrence-type fault reasons, and installs environmental data collection equipment which collects corresponding environmental data at the point location;
when a power grid fails, the equipment failure analysis module firstly analyzes the environmental data sent by the environmental data collection equipment of each failure point position in the first real-time data collection module, and analyzes whether the environmental data has the possibility of failure or not by using a machine learning model Mr according to the failure reason r of the corresponding failure point position; if the fault is possible, determining a fault point location; if no fault is possible, analyzing the environmental data sent by each environmental data collection device of the second real-time data collection module, and manually detecting whether each environmental data is abnormal; verifying the abnormal point positions; until the actual point location of the fault is found.
The embodiment of the second aspect of the invention provides a fault point positioning system based on multi-dimensional big data analysis, which comprises a fault reason collecting module, a fault data collecting module, a fault classification module, a model training module, a first real-time data collecting module, a second real-time data collecting module and a fault analysis module; wherein, the modules are connected in a wireless and/or electrical mode;
the fault reason collection module is used for collecting reasons which can cause the power grid fault and corresponding typical environmental conditions in advance; and making a fault reason table; the fault reason collection module sends the collected fault reason table to a fault classification module;
the fault data collection module is used for collecting historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid; and sending a collection receipt to the fault classification module;
the fault classification module is used for classifying the grid faults into two types of historical occurrence and historical non-occurrence; sending the classification result to a first real-time data collection module and a second real-time data collection module;
the model training module is used for classifying historical fault point positions according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; sending the generated machine learning model to a fault analysis module;
the first real-time data collection module is used for collecting environmental condition data of historical fault point locations in real time; sending the collected environmental conditions to a fault analysis module in real time;
the second real-time data collection module is used for setting environmental data collection equipment corresponding to failure occurrence reasons at different positions in the power grid; sending the collected environmental conditions to a fault analysis module in real time;
and the fault analysis module analyzes the point location of the point location fault in real time according to the environmental condition data.
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of collecting the reasons of power grid faults and the environmental conditions of each reason in advance; then collecting the point locations with faults in the history of the power grid and the current environmental conditions of each point location; dividing fault causes into two categories; generating a machine learning model for judging whether a fault occurs according to environmental condition data for historical fault-like reasons; and installing environmental data collection equipment at the fault point; for the historical non-fault-like reasons, searching a proper position in the power grid to install environmental data collection equipment; finally, analyzing fault point positions according to real-time data collected by the environmental data collection equipment; the problem of searching for the fault point position of the power grid is solved.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments 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.
As shown in fig. 1, a fault point positioning method based on multidimensional big data analysis includes the following steps:
the method comprises the following steps: the fault reason collection module collects the reasons which can cause the grid fault and the corresponding typical environmental conditions in advance; and making a fault reason table;
step two: the fault data collection module collects historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid;
step three: the fault classification module classifies fault causes in the fault cause table into history occurrence and history non-occurrence; judging the category of each fault reason in the fault reason table; if the fault is a historical fault, turning to the fourth step; if the historical failure causes do not occur, turning to the fifth step;
step four: the model training module classifies historical fault point locations according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; setting environmental data collection equipment corresponding to the failure occurrence reason at each historical failure point position through a first real-time data collection module;
step five: the second real-time data collection module is used for setting environmental data collection equipment corresponding to the failure occurrence reason at different positions in the power grid; the placement position of the environmental data collection equipment is set according to the actual condition of the power grid;
step six: all data collection equipment is started when a power grid runs, and collected environmental data are sent to a fault analysis module in real time;
step seven: when the power grid fails, the fault analysis module analyzes the environmental data of each position of the power grid, which are sent by the environmental data collection equipment; acquiring a point position where a fault occurs in a power grid;
it will be appreciated that there are many possible causes of faults in the power grid, including but not limited to excessive temperature, electrodynamic forces, poor contact, excessive humidity, supply voltage excursions, arcing, etc.; obviously, each cause of grid power failure is in different environmental conditions; for example, a power failure caused by excessive temperature is due to the ambient temperature at which the point of failure is located being above a certain temperature threshold; furthermore, in the actual operation process of the power grid, a certain point position is influenced by environmental conditions, so that the power grid fails; in the subsequent operation process, the probability of the fault point position having the fault again is higher than that of other positions; thus, monitoring the environmental conditions of each historically failed point location may help determine the failed point location;
wherein the failure cause collection module marks the collected failure cause set as R; each failure cause is marked as r; for each fault reason r, acquiring an environmental condition corresponding to the fault reason according to actual experience; marking the environmental condition set corresponding to the fault reason r as Er; for example, the environmental condition set Er may include temperature data, ventilation data, grid equipment usage, and the like due to a grid fault caused by a high temperature;
the fault data collection module collects each fault point position of a power grid fault in the history of the power grid, a fault reason r of each fault power grid and an environmental condition set Er corresponding to the fault reason r;
the historical fault-like reason is the reason of the grid fault caused by the fault reason which occurs in the operation history of the grid; the historical non-fault-occurrence reasons are fault reasons which do not occur in the operation history of the power grid, namely fault reasons which are in the fault reason set R but do not occur in the historical fault point positions;
the model training module generates a machine learning model for judging whether a fault occurs according to environmental condition data, and comprises the following steps of:
step S1: the model training module classifies all fault point positions according to fault reasons r; marking a fault point location set contained in each type of fault reason as Pr; for each fault point position set Pr, collecting data of an environmental condition set Er of each fault point position in the set when a fault occurs;
step S2: digitizing and normalizing the data of the environment condition set Er, and expressing the data into a characteristic vector form;
and step S3: inputting the characteristic vector set of each environment condition set Er into a machine learning model by taking the characteristic vector set of each environment condition set Er as input, and taking whether a fault occurs as output; the machine learning model takes the prediction accuracy as a training target to train; stopping training until the prediction accuracy reaches 95%; marking a machine learning model generated by the environment condition set Er as Mr;
the first real-time data collection module is provided with environmental data collection equipment at each historical fault point, and the data collected by the environmental data collection equipment comprises environmental condition data contained in fault reasons which have occurred historically at the fault point;
the second real-time data collection module searches a point location which accords with the environmental condition data in the power grid according to the environmental condition data of the historical non-occurrence-type fault reasons, and installs environmental data collection equipment which collects corresponding environmental data at the point location;
when a power grid fails, the equipment failure analysis module firstly analyzes the environmental data sent by the environmental data collection equipment of each failure point position in the first real-time data collection module, and analyzes whether the environmental data has the possibility of failure or not by using a machine learning model Mr according to the failure reason r of the corresponding failure point position; if the fault is possible, determining a fault point location; if no fault is possible, analyzing the environmental data sent by each environmental data collection device of the second real-time data collection module, and manually detecting whether each environmental data is abnormal; verifying the abnormal point positions; until the actual fault point location is found.
As shown in fig. 2, a fault point locating system based on multidimensional big data analysis includes a fault cause collecting module, a fault data collecting module, a fault classification module, a model training module, a first real-time data collecting module, a second real-time data collecting module, and a fault analyzing module; wherein, the modules are connected in a wireless and/or electrical mode;
the fault reason collection module is used for collecting reasons which can cause grid faults and corresponding typical environmental conditions in advance; and making a fault reason table; the fault reason collection module sends the collected fault reason table to a fault classification module;
the fault data collection module is used for collecting historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid; and sending a collection receipt to the fault classification module;
the fault classification module is used for classifying the grid faults into two types of historical occurrence and historical non-occurrence; sending the classification result to a first real-time data collection module and a second real-time data collection module;
the model training module is used for classifying historical fault point positions according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; sending the generated machine learning model to a fault analysis module;
the first real-time data collection module is used for collecting environmental condition data of historical fault point locations in real time; sending the collected environmental conditions to a fault analysis module in real time;
the second real-time data collection module is used for setting environmental data collection equipment corresponding to failure occurrence reasons at different positions in the power grid; sending the collected environmental conditions to a fault analysis module in real time;
and the fault analysis module analyzes the point location of the point location fault in real time according to the environmental condition data.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the scope of the present invention.
Claims (8)
1. A fault point positioning method based on multi-dimensional big data analysis is characterized by comprising the following steps:
the method comprises the following steps: the fault reason collection module collects the reasons which can cause the grid fault and the corresponding typical environmental conditions in advance; and making a fault reason table;
step two: the fault data collection module collects historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid;
step three: the fault classification module classifies fault reasons in the fault reason table into history occurrence and history non-occurrence; judging which category the fault reason belongs to for each fault reason in the fault reason table;
step four: the model training module classifies historical fault point locations according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; setting environmental data collection equipment corresponding to the failure occurrence reason at each historical failure point position through a first real-time data collection module;
step five: the second real-time data collection module is used for setting environment data collection equipment corresponding to failure occurrence reasons at different positions in the power grid; the placement position of the environmental data collection equipment is set according to the actual condition of the power grid;
step six: all data collection equipment is started when a power grid runs, and collected environmental data are sent to a fault analysis module in real time;
step seven: when the power grid fails, the fault analysis module analyzes the environmental data of each position of the power grid, which is sent by the environmental data collection equipment; and acquiring the point position of the fault in the power grid.
2. The method for locating a fault point based on multidimensional big data analysis according to claim 1, wherein the fault cause collection module labels the collected set of fault causes as R; each failure cause is marked as r; for each fault reason r, acquiring an environmental condition corresponding to the fault reason according to actual experience; and marking the environmental condition set corresponding to the fault reason r as Er.
3. The method for locating the fault point based on the multi-dimensional big data analysis as claimed in claim 1, wherein the fault data collection module collects each fault point where a power grid fault occurs in the history of the power grid, a fault reason r of each fault power grid and a corresponding environmental condition set Er.
4. The fault point positioning method based on multi-dimensional big data analysis according to claim 1, wherein the historical fault-like cause is a cause of a power grid fault caused by the fault cause, which has occurred in the power grid operation history; the historical non-fault-like reason is a fault reason which has not occurred in the operation history of the power grid, namely a fault reason which is in the fault reason set R but does not appear in the historical fault point location.
5. The method for locating fault points based on multidimensional big data analysis according to claim 1, wherein the model training module generating a machine learning model for determining whether a fault occurs according to environmental condition data comprises the following steps:
step S1: the model training module classifies all fault point positions according to fault reasons r; marking a fault point location set contained in each type of fault reason as Pr; for each fault point position set Pr, collecting data of an environmental condition set Er of each fault point position in the set when a fault occurs;
step S2: digitizing and normalizing the data of the environment condition set Er, and expressing the data into a characteristic vector form;
and step S3: inputting the characteristic vector set of each environment condition set Er into a machine learning model by taking the characteristic vector set of each environment condition set Er as input, and taking whether a fault occurs as output; the machine learning model takes the prediction accuracy as a training target to train; stopping training until the prediction accuracy reaches 95%; the machine learning model generated by the set of environmental conditions Er is labeled Mr.
6. The fault point positioning method based on the multidimensional big data analysis as claimed in claim 1, wherein the first real-time data collection module is provided with an environmental data collection device at each historical fault point, and the data collected by the environmental data collection device includes environmental condition data included in fault reasons which have occurred in the history of the fault point;
the second real-time data collection module searches a point location which accords with the environmental condition data in the power grid according to the environmental condition data of the historical non-occurrence-type fault reasons, and installs environmental data collection equipment which collects corresponding environmental data at the point location.
7. The method for locating the fault point based on the multi-dimensional big data analysis according to claim 1, wherein when the power grid fails, the device fault analysis module firstly analyzes environmental data sent by the environmental data collection device of each fault point in the first real-time data collection module, and analyzes whether the environmental data is likely to fail or not by using a machine learning model Mr according to a fault reason r of the corresponding fault point; if the fault is possible, determining a fault point location; if no fault is possible, analyzing the environmental data sent by each environmental data collection device of the second real-time data collection module, and manually detecting whether each environmental data is abnormal; verifying the abnormal point positions; until the actual point location of the fault is found.
8. A fault point positioning system based on multi-dimensional big data analysis is characterized by comprising a fault reason collecting module, a fault data collecting module, a fault classification module, a model training module, a first real-time data collecting module, a second real-time data collecting module and a fault analyzing module; wherein, the modules are connected in a wireless and/or electrical mode;
the fault reason collection module is used for collecting reasons which can cause grid faults and corresponding typical environmental conditions in advance; and making a fault reason table; the fault reason collection module sends the collected fault reason table to a fault classification module;
the fault data collection module is used for collecting historical fault point positions, fault occurrence reasons and fault occurrence conditions in the power grid; sending a collection receipt to the fault classification module;
the fault classification module is used for classifying the grid faults into two types of historical occurrence and historical non-occurrence; sending the classification result to a first real-time data collection module and a second real-time data collection module;
the model training module is used for classifying historical fault point positions according to fault occurrence reasons; for each type of historical fault point location, generating a machine learning model for judging whether a fault occurs according to environmental condition data; sending the generated machine learning model to a fault analysis module;
the first real-time data collection module is used for collecting environmental condition data of historical fault point locations in real time; the collected environmental conditions are sent to a fault analysis module in real time;
the second real-time data collection module is used for setting environmental data collection equipment corresponding to failure occurrence reasons at different positions in the power grid; sending the collected environmental conditions to a fault analysis module in real time;
and the fault analysis module analyzes the point location of the point location fault in real time according to the environmental condition data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211145211.5A CN115587312B (en) | 2022-09-20 | 2022-09-20 | Fault point positioning method and system based on multidimensional big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211145211.5A CN115587312B (en) | 2022-09-20 | 2022-09-20 | Fault point positioning method and system based on multidimensional big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115587312A true CN115587312A (en) | 2023-01-10 |
| CN115587312B CN115587312B (en) | 2023-09-01 |
Family
ID=84777883
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211145211.5A Active CN115587312B (en) | 2022-09-20 | 2022-09-20 | Fault point positioning method and system based on multidimensional big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115587312B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116660672A (en) * | 2023-08-02 | 2023-08-29 | 国网四川省电力公司乐山供电公司 | Power grid equipment fault diagnosis method and system based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN111444240A (en) * | 2020-03-26 | 2020-07-24 | 北京国网富达科技发展有限责任公司 | Power transmission line fault early warning method and device |
| CN114705950A (en) * | 2022-04-11 | 2022-07-05 | 国网安徽省电力有限公司安庆供电公司 | Single-phase earth fault positioning system of power distribution network line |
-
2022
- 2022-09-20 CN CN202211145211.5A patent/CN115587312B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107766879A (en) * | 2017-09-30 | 2018-03-06 | 中国南方电网有限责任公司 | The MLP electric network fault cause diagnosis methods of feature based information extraction |
| CN109218114A (en) * | 2018-11-12 | 2019-01-15 | 西安微电子技术研究所 | A kind of server failure automatic checkout system and detection method based on decision tree |
| CN110018389A (en) * | 2019-02-21 | 2019-07-16 | 国网山东省电力公司临沂供电公司 | A kind of transmission line of electricity on-line fault monitoring method and system |
| CN111444240A (en) * | 2020-03-26 | 2020-07-24 | 北京国网富达科技发展有限责任公司 | Power transmission line fault early warning method and device |
| CN114705950A (en) * | 2022-04-11 | 2022-07-05 | 国网安徽省电力有限公司安庆供电公司 | Single-phase earth fault positioning system of power distribution network line |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116660672A (en) * | 2023-08-02 | 2023-08-29 | 国网四川省电力公司乐山供电公司 | Power grid equipment fault diagnosis method and system based on big data |
| CN116660672B (en) * | 2023-08-02 | 2023-10-10 | 国网四川省电力公司乐山供电公司 | Power grid equipment fault diagnosis method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115587312B (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210512B (en) | Automatic log anomaly detection method and system | |
| CN112492567B (en) | Fault analysis and solution method and device in emergency command communication | |
| CN110687473B (en) | Fault positioning method and system for relay protection test of intelligent substation | |
| CN111582235A (en) | Alarm method, system and equipment for monitoring abnormal events in station in real time | |
| CN116028887B (en) | Analysis method of continuous industrial production data | |
| CN115587312B (en) | Fault point positioning method and system based on multidimensional big data analysis | |
| CN111666978B (en) | Intelligent fault early warning system for IT system operation and maintenance big data | |
| CN113285358A (en) | Power distribution cabinet accident monitoring and alarming method and system | |
| CN105321039B (en) | Online monitoring data management system and method for isolating switch | |
| CN113487051B (en) | Power distribution network fault first-aid repair maintenance data processing method and equipment and computer storage medium | |
| CN112949874B (en) | Power distribution terminal defect characteristic self-diagnosis method and system | |
| CN114895634A (en) | Product production line automatic control system based on machine vision | |
| CN114460439A (en) | Digital integrated circuit test system | |
| CN117150418B (en) | Transformer operation detection period formulation method and system based on state characteristic fault tree | |
| CN114487705A (en) | Power grid equipment fault positioning detection method | |
| CN114215705A (en) | Wind turbine generator fault early warning method and system | |
| CN113688987A (en) | Training method of photovoltaic monitoring model, monitoring method of photovoltaic equipment and equipment | |
| CN113471864A (en) | Transformer substation secondary equipment field maintenance device and method | |
| CN113010394A (en) | Machine room fault detection method for data center | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN112803587A (en) | Intelligent inspection method for state of automatic equipment based on diagnosis decision library | |
| CN115171242B (en) | Industrial vehicle remote fault detection system | |
| CN111831862A (en) | High-quality insulation evaluation system | |
| CN113659709B (en) | Switching station operation monitoring system and method based on voice recognition | |
| CN114740343B (en) | Real-time detection system for circuit breaker |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |