CN113869444A - Transformer substation fault detection method and device, computer equipment and storage medium - Google Patents
Transformer substation fault detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113869444A CN113869444A CN202111176423.5A CN202111176423A CN113869444A CN 113869444 A CN113869444 A CN 113869444A CN 202111176423 A CN202111176423 A CN 202111176423A CN 113869444 A CN113869444 A CN 113869444A
- Authority
- CN
- China
- Prior art keywords
- fault
- target
- matrix
- state data
- transformer substation
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 86
- 238000012544 monitoring process Methods 0.000 claims abstract description 89
- 238000000034 method Methods 0.000 claims abstract description 40
- 239000011159 matrix material Substances 0.000 claims description 152
- 238000005070 sampling Methods 0.000 claims description 93
- 239000013598 vector Substances 0.000 claims description 52
- 238000012549 training Methods 0.000 claims description 41
- 238000004590 computer program Methods 0.000 claims description 13
- 230000008447 perception Effects 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 6
- 241001465754 Metazoa Species 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 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
- 230000005236 sound signal Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application relates to a transformer substation fault detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring target state data obtained by a target sensor monitoring a transformer substation in a target time period; acquiring fault state data corresponding to the target sensor and the historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition of substation fault; and performing similarity comparison on the target state data and the fault state data to obtain a comparison result, and determining whether the transformer substation has faults or not according to the comparison result. By adopting the method, the efficiency of the fault detection of the transformer substation can be improved.
Description
Technical Field
The present application relates to the field of power systems, and in particular, to a method and an apparatus for detecting a fault in a substation, a computer device, and a storage medium.
Background
In an electric power system, ensuring the safety and stability of a transformer substation is an important link for realizing the normal work of the electric power system, so that the method has very important significance for fault detection of the transformer substation.
In the related art, inspection is usually performed manually, and an inspector judges whether a fault exists in a substation according to information such as appearance phenomena or indicating instruments of substation equipment.
However, the variety of electrical devices in the substation is large, and if the fault detection of the substation is realized only by manpower, a large amount of manpower and material resources are consumed, and the efficiency of the fault detection of the substation is low.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a substation fault detection method, a substation fault detection apparatus, a computer device, and a storage medium, which can improve the substation fault detection efficiency.
In a first aspect, a substation fault detection method is provided, and the method includes:
acquiring target state data obtained by a target sensor monitoring a transformer substation in a target time period;
acquiring fault state data corresponding to the target sensor and the historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition of substation fault;
and performing similarity comparison on the target state data and the fault state data to obtain a comparison result, and determining whether the transformer substation has faults or not according to the comparison result.
In one embodiment, the comparing the similarity between the target status data and the fault status data to obtain a comparison result includes:
constructing a fault monitoring matrix according to the target state data;
constructing a historical fault matrix according to the fault state data;
mutual information of the fault monitoring matrix and the historical fault matrix is obtained, and a comparison result is obtained according to the mutual information.
In one embodiment, the target state data includes position information of a target sensor and target sensing data corresponding to at least one sampling time in a target time period, and the fault monitoring matrix is constructed according to the target state data, including:
for each sampling moment, determining a matrix row vector according to the position information of the target sensor, and determining a matrix column vector according to target sensing data corresponding to the target sensor and the sampling moment;
and constructing a target fault monitoring matrix corresponding to the sampling time based on the matrix row vector and the matrix column vector, and taking the target fault monitoring matrix corresponding to each sampling time as a fault monitoring matrix.
In one embodiment, the obtaining of the mutual information between the fault monitoring matrix and the historical fault matrix and the obtaining of the comparison result according to the mutual information includes:
for each sampling moment, determining a target fault moment corresponding to the sampling moment, and calculating target mutual information of a target fault monitoring matrix corresponding to the sampling moment and a target historical fault matrix corresponding to the target fault moment;
calculating a mutual information difference value of target mutual information corresponding to two adjacent sampling moments in each sampling moment;
comparing each target mutual information with a first threshold value respectively to obtain a first comparison result, and comparing each mutual information difference value with a second threshold value respectively to obtain a second comparison result;
and taking each first comparison result and each second comparison result as comparison results.
In one embodiment, the target sensor is deployed in a substation wirelessly; the number of the target sensors is multiple, and the multiple target sensors are distributed in the transformer substation in a tree-shaped network topological structure or a multi-hop network topological structure.
In one embodiment, the method further comprises:
if the transformer substation has faults, target state data is input into a fault detection model, and fault occurrence positions and fault types of the transformer substation are obtained;
matching the fault occurrence position and the fault type of the transformer substation with fault information in a fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
In one embodiment, the training process of the fault detection model includes:
acquiring training data, wherein the training data comprises position information of a target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment;
and performing iterative training on the initial fault detection model by using the training data to obtain a fault detection model.
In a second aspect, a substation fault detection device is provided, the device comprising:
the acquisition module is used for acquiring target state data obtained by monitoring the transformer substation by the target sensor in a target time period; acquiring fault state data corresponding to the target sensor and a historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation is in fault;
and the judging module is used for comparing the similarity of the target state data and the fault state data to obtain a comparison result and determining whether the transformer substation has faults or not according to the comparison result.
In one embodiment, the determining module is specifically configured to:
constructing a fault monitoring matrix according to the target state data;
constructing a historical fault matrix according to the fault state data;
mutual information of the fault monitoring matrix and the historical fault matrix is obtained, and a comparison result is obtained according to the mutual information.
In one embodiment, the target state data includes position information of a target sensor and target sensing data corresponding to at least one sampling time in a target time period, and the determining module is further configured to:
for each sampling moment, determining a matrix row vector according to the position information of the target sensor, and determining a matrix column vector according to target sensing data corresponding to the target sensor and the sampling moment;
and constructing a target fault monitoring matrix corresponding to the sampling time based on the matrix row vector and the matrix column vector, and taking the target fault monitoring matrix corresponding to each sampling time as a fault monitoring matrix.
In one embodiment, the historical failure matrix includes a target historical failure matrix corresponding to at least one failure time in the historical time period, and the determining module is further configured to:
for each sampling moment, determining a target fault moment corresponding to the sampling moment, and calculating target mutual information of a target fault monitoring matrix corresponding to the sampling moment and a target historical fault matrix corresponding to the target fault moment;
calculating a mutual information difference value of target mutual information corresponding to two adjacent sampling moments in each sampling moment;
comparing each target mutual information with a first threshold value respectively to obtain a first comparison result, and comparing each mutual information difference value with a second threshold value respectively to obtain a second comparison result;
and taking each first comparison result and each second comparison result as comparison results.
In one embodiment, the target sensor is deployed in a substation wirelessly; the number of the target sensors is multiple, and the multiple target sensors are distributed in the transformer substation in a tree-shaped network topological structure or a multi-hop network topological structure.
In one embodiment, the apparatus further comprises:
the output module is used for inputting the target state data to the fault detection model under the condition that the fault exists in the transformer substation, and obtaining the fault occurrence position and the fault type of the transformer substation;
and the solution module is used for matching the fault occurrence position and the fault type of the transformer substation with the fault information in the fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
In one embodiment, the training process of the fault detection model includes:
acquiring training data, wherein the training data comprises position information of a target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment;
and performing iterative training on the initial fault detection model by using the training data to obtain a fault detection model.
In a third aspect, a computer device is provided, comprising a memory and a processor, the memory storing a computer program which, when executed by the processor, implements the substation fault detection method according to the first aspect described above.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the substation fault detection method according to the first aspect as described above.
According to the transformer substation fault detection method, the transformer substation fault detection device, the computer equipment and the storage medium, the target state data obtained by monitoring the transformer substation by the target sensor in the target time period and the fault state data corresponding to the target sensor in the historical time period are obtained, the similarity comparison is carried out on the target state data and the fault state data to obtain the comparison result, whether the transformer substation has a fault or not is determined according to the comparison result, and the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation has a fault, so that the fault state data can represent the state characteristics of the target sensor under the condition that the transformer substation has a fault, the similarity comparison is carried out on the target state data and the fault state data, and if the similarity between the target state data and the fault state data is high, the target state data is represented to have the state characteristics of the target sensor under the condition that the transformer substation has a fault, therefore, the transformer substation fault can be determined, and if the similarity between the target state data and the fault state data is smaller, the representation target state data does not have the state characteristics of the target sensor under the condition of the transformer substation fault, so that the transformer substation can be determined not to have the fault, the automatic judgment of the transformer substation fault and the real-time performance of the fault judgment are realized, and the transformer substation fault detection efficiency is improved.
Drawings
Fig. 1 is a schematic flow chart of a substation fault detection method in one embodiment;
FIG. 2 is a schematic flow chart of step 103 in one embodiment;
FIG. 3 is a flow chart illustrating step 201 in one embodiment;
FIG. 4 is a schematic flow chart of step 203 in one embodiment;
FIG. 5 is a schematic illustration of the topological distribution of target sensors in one embodiment;
FIG. 6 is a schematic flow chart of a substation fault detection method in one embodiment;
FIG. 7 is a schematic flow chart diagram illustrating the training process for the fault detection model in one embodiment;
FIG. 8 is a schematic flow chart of a method for substation fault detection in one embodiment;
FIG. 9 is a block diagram of a substation fault detection device in one embodiment;
FIG. 10 is a block diagram of a substation fault detection device in one embodiment;
FIG. 11 is a diagram illustrating an internal structure of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an electric power system, ensuring the safety and stability of a transformer substation is an important link for realizing the normal work of the electric power system, so that the method has very important significance for fault detection of the transformer substation.
In the related art, inspection is usually performed manually, and an inspector judges whether a fault exists in a substation according to information such as appearance phenomena or indicating instruments of substation equipment.
However, as the scale of the power grid becomes larger, more and more electrical devices are arranged in the substation, and manual detection items are required to be increased, and the detection items are various, for example, whether a reactor and a resistor of the ice melting filter are burnt, whether the temperature and humidity in the operation box are too high, whether a main pump is abnormal, whether a small animal is present in the substation, and the like. If the transformer substation fault detection is realized only by manpower, the transformer substation fault detection efficiency is low, and the ever-changing requirements cannot be met.
In view of this, the embodiment of the present application provides a method for detecting a fault of a transformer substation, so as to automatically determine whether the transformer substation has a fault.
It should be noted that, in the substation fault detection method provided in the embodiment of the present application, an execution main body may be a substation fault detection device, and the substation fault detection method may be implemented as part or all of a terminal in a software, hardware, or a combination of software and hardware.
In the following method embodiments, the execution subject is a terminal, where the terminal may be a personal computer, a notebook computer, a media player, a smart television, a smart phone, a tablet computer, a portable wearable device, and the like, and it is understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented through interaction between the terminal and the server.
Please refer to fig. 1, which shows a flowchart of a substation fault detection method provided in an embodiment of the present application. As shown in fig. 1, the substation fault detection method may include the following steps:
The target sensor can be deployed in the transformer substation, and after the target sensor is electrified, the target sensor senses a monitored object and the environment in the transformer substation to obtain target state data.
For example, the target state data may include deployment location information of the target sensor, target perception data, and location information of a monitoring object of the target sensor, and the like. The monitoring object can be equipment in a transformer substation, small animals in the transformer substation, and the like.
Hereinafter, the content included in the target perception data will be described.
In an embodiment of the present application, the target sensor includes at least one of a humidity sensor, a temperature sensor, a vibration sensor, a displacement sensor, an infrared sensor, and a sound sensor. The humidity sensor is used for monitoring whether the humidity of the mechanism box exceeds the standard or not; the temperature sensor is used for monitoring whether the humidity of the monitoring mechanism box exceeds the standard or not; the vibration sensor is used for monitoring whether the vibration acceleration of the valve cooling main pump exceeds the standard or not; the displacement sensor is used for monitoring the displacement of the GIS or GIL equipment telescopic joint; the infrared sensor is used for detecting whether the small animals are present or not in the transformer substation; the sound sensor is used for detecting whether the operation sound of the transformer is abnormal or not.
In this way, the target sensing data may include humidity data in the mechanism box obtained by sensing by the humidity sensor and temperature data in the mechanism box obtained by sensing by the temperature sensor; the vibration sensor senses at least one of vibration acceleration data of the valve cooling main pump, GIS or GIL equipment telescopic joint displacement data sensed by the displacement sensor, thermography data of the surface temperature of the small animal sensed by the infrared sensor and transformer operation sound signals sensed by the sound sensor.
Optionally, the terminal is provided with a sampling period, for example, the sampling period may be set to 20 min. Optionally, the target time period is a time period that takes the current time as an end point in time sequence. The length of the target time period is proportional to the sampling period. And determining the sampling time corresponding to the target time according to the sampling period, wherein the target sensing data comprises target sensing data obtained by monitoring the transformer substation by the target sensor at each sampling time.
Optionally, when the sampling time is reached, the terminal sends a request instruction of target sensing data to the target sensor, and the target sensing data uploads the target sensing data obtained by the monitoring substation to the terminal after receiving the request. The terminal receives the target perception data for substation fault detection.
102, acquiring fault state data corresponding to the target sensor and the historical time period, wherein the fault state data are obtained by monitoring the target sensor under the condition that the transformer substation is in fault.
The historical time period is any time period before the target time period in time sequence. The number of the history time period may be 1 or more. The length of the history time period may be the same as or different from the length of the target time period.
When the terminal monitors that the transformer substation has a fault, the terminal determines the moment as a fault moment, and stores state data monitored by a target sensor corresponding to the fault moment as fault state data into a corresponding storage path.
Wherein the number of samples of fault status data is related to the number of target sensors. The fault state data may be fault state data at a plurality of fault times corresponding to the same historical time period, or may be fault state data at a certain fault time at different time periods. When the number of the target sensors is plural, the fault state data at least includes fault state data of each target sensor in the case where the monitored object is abnormal. Taking the number of the target sensors as 2 as an example, the monitoring objects of the target sensors are respectively equipment a and equipment B, and the fault state data includes fault state data of the target sensors when only the equipment a has a fault, fault state data of the target sensors when only the equipment B has a fault, and fault state data of the equipment a and the equipment B.
Optionally, the terminal divides the fault state data into a plurality of object types according to the target sensor corresponding to the monitored abnormality. When the terminal stores the fault state data, the object type, the historical time period and the fault time corresponding to the fault state data are correspondingly stored.
And 103, performing similarity comparison on the target state data and the fault state data to obtain a comparison result, and determining whether the transformer substation has faults or not according to the comparison result.
Optionally, the terminal selects one fault status data under each object type. And for each sampling moment, carrying out similarity comparison on the target state data corresponding to the sampling moment and each fault state data. Optionally, a similarity calculation method is used to calculate a similarity value between the target state data corresponding to the sampling time and each fault state data, so as to obtain a plurality of similarity values. The terminal can preset a threshold value, each similarity value is compared with the threshold value, then the multiple similarities are summed or weighted and summed to obtain a final similarity value, if the final similarity value exceeds the threshold value, the transformer substation is indicated to have a fault, otherwise, the transformer substation does not have the fault.
Optionally, the terminal determines the data at the time when the target time period ends as the target state data, and determines the data at the time when the historical time period ends as the historical fault data. And calculating the similarity value between the target state data and the fault state data by using a similarity calculation method to obtain the similarity value. The terminal can preset a threshold value, the similarity value is compared with the threshold value, if the similarity value exceeds the threshold value, the transformer substation is indicated to have a fault, otherwise, the transformer substation does not have the fault.
Optionally, when the length of the historical time period is the same as that of the target time period, the terminal makes each sampling time of the target time period correspond to each fault time in the historical time period one to one, calculates a similarity value between the target state data corresponding to each sampling time and the fault state data corresponding to the corresponding fault time to obtain a plurality of similarity values, and then sums or weights and sums the plurality of similarity values to obtain a final similarity value. The terminal can preset a threshold value, the final similarity value is compared with the threshold value, if the final similarity value exceeds the threshold value, the transformer substation is indicated to have a fault, otherwise, the transformer substation does not have the fault.
The embodiment obtains target state data obtained by a target sensor monitoring a transformer substation in a target time period and fault state data of the target sensor corresponding to a historical time period, compares the similarity of the target state data and the fault state data to obtain a comparison result, and determines whether the transformer substation has a fault according to the comparison result, because the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation has a fault, the fault state data can represent the state characteristics of the target sensor under the condition that the transformer substation has a fault, thus, the similarity of the target state data and the fault state data is compared, if the similarity of the target state data and the fault state data is larger, the represented target state data has the state characteristics of the target sensor under the condition that the transformer substation has a fault, so that the transformer substation can be determined to have a fault, and if the similarity between the target state data and the fault state data is smaller, the representation target state data does not have the state characteristics of the target sensor under the condition of the fault of the transformer substation, so that the fact that the transformer substation has no fault can be determined, the automatic judgment of the fault of the transformer substation and the real-time performance of the fault judgment are realized, and the efficiency of the fault detection of the transformer substation is improved.
In the implementation of the present application, referring to fig. 2, based on the embodiment shown in fig. 1, the present embodiment relates to a step 103 of comparing similarity between target state data and fault state data to obtain a comparison result, and determining whether a fault exists in a substation according to the comparison result, including steps 201, 202, and 203:
The target state data comprises position information of a target sensor and target perception data; wherein the position information is deployment position information of the target sensor or position information of a monitoring object of the target sensor.
The deployment position information of the target sensor and the position information of the monitoring object of the target sensor are in one-to-one correspondence, and optionally, the terminal stores a mapping relation table of the deployment position information of the target sensor and the position information of the monitoring object of the target sensor.
In an optional implementation manner, the terminal determines a matrix row vector according to the position information of the target sensor, determines a matrix column vector according to the target sensing data of the target sensor, and constructs a fault monitoring matrix X, where X ═ X (X ═ X)i,j)M×N，xi,jAnd the target sensing data of a certain target sensor at certain position information is represented, wherein M is the number of the position information, and N is the number of the target sensors. In another optional implementation manner, the terminal determines a matrix row vector according to target sensing data of the target sensor, determines a matrix column vector according to position information of the target sensor, and constructs a fault monitoring matrix X, where X ═ X (X ═ X)i,j)N×M，xi,jAnd the target perception data of a certain target sensor at a certain position information is represented, M is the number of the position information, and N is the number of the target sensors.
The fault state data comprises position information of the target sensor and target historical sensing data monitored by the target sensor in the fault state of the transformer substation.
Optionally, the matrix row vector is determined according to the position information of the target sensor, and the matrix column vector structure is determined according to the target sensing data of the target sensorUnder the condition of establishing a fault monitoring matrix X, the terminal determines a matrix row vector according to the position information of the target sensor, determines a matrix column vector according to the target historical sensing data of the target sensor and establishes a historical fault matrix Y, wherein Y is (Y ═ Yi,j)M×N，yi,jAnd the historical sensing data of the target of a certain target sensor at certain position information is shown, M is the number of the position information, and N is the number of the target sensors.
Optionally, in the case that a matrix row vector is determined according to the target sensing data of the target sensor, and a matrix column vector is determined according to the position information of the target sensor to construct the fault monitoring matrix X, the terminal determines the matrix row vector according to the target historical sensing data of the target sensor, and determines the matrix column vector according to the position information of the target sensor to construct the historical fault matrix Y, where Y ═ (Y ═ Yi,j)N×M，yi,jThe method includes the steps that target historical sensing data of a certain target sensor at certain position information are shown, M is the number of the position information, and N is the number of the target sensors.
And step 203, acquiring mutual information of the fault monitoring matrix and the historical fault matrix, and acquiring a comparison result according to the mutual information.
Optionally, mutual information MI (X, Y) of the fault monitoring matrix X and the historical fault matrix Y is calculated:
wherein, PX(i)＝∑jPX,Y(i,j)、PY(j)＝∑iPX,Y(i, j) are respectively the marginal probability distribution, P, of the fault monitoring matrix X and the historical fault matrix YX,Y(i, j) is the joint probability distribution of the fault monitoring matrix X and the historical fault matrix Y.
According to the method and the device, the fault monitoring matrix is built according to the target state data, the historical fault matrix is built according to the fault state data, mutual information of the fault monitoring matrix and the historical fault matrix is obtained, the comparison result is obtained according to the mutual information, whether the current monitoring data are abnormal or not is judged quickly, and the difficulty of transformer substation fault detection is reduced.
In this application example, the target state data includes position information of the target sensor and target sensing data corresponding to at least one sampling time in a target time period, and the fault state data includes target historical sensing data corresponding to at least one fault time in a historical time period, referring to fig. 3, based on the embodiment shown in fig. 2, the implementation process of the above step 201 and step 202 includes step 301, step 302, step 303, and step 304:
Wherein the position information is deployment position information of the target sensor or position information of a monitoring object of the target sensor.
Optionally, the terminal is provided with a sampling period, for example, the sampling period may be set to 20 min. And determining the sampling time according to the sampling period.
Optionally, the terminal obtains a plurality of position points according to the position information of the target sensor, and sets numbers for the plurality of position points according to a certain sequence, where the number i of each position point is 1,2, … N, where N represents the number of the position points; and the terminal sets numbers for the target sensors according to the number of the target sensors, wherein the number j of each target sensor is 1,2 and … M, wherein M represents the number of the position points.
And the terminal takes the position point number i as a matrix row vector and takes the target sensing data of the target sensor corresponding to the number j as a matrix column vector.
The target fault monitoring matrix is used for representing the monitored target state condition of the corresponding target sensor at each position point.
Optionally, for each sampling time, the terminal obtains target state data of the target sensor corresponding to each position point at the sampling time, takes the corresponding position point number i as a matrix row vector, takes the target sensing data of the target sensor corresponding to the number j as a matrix column vector, and constructs a target fault monitoring matrix X, which is expressed as follows:
wherein x isi,jRepresenting the target perception data of sensor j at the ith position point.
The target fault time refers to the acquisition time of the target historical sensing data of the corresponding target sensor when the substation fault is monitored in the non-target time period.
Optionally, the terminal stores a data table of target failure time and target historical sensing data. Determining a target fault moment, acquiring corresponding target historical sensing data, and then constructing a target historical fault matrix according to the position information of the target sensor and the target historical sensing data.
Optionally, obtaining a plurality of position points according to the position information of the target sensor, and setting numbers for the plurality of position points according to a certain sequence, where the number i of each position point is 1,2, … N, where N represents the number of the position points; according to the number of the target sensors, numbers are set for the target sensors, and the number j of each target sensor is 1,2, … M, wherein M represents the number of the position points.
And taking the position point number i as a matrix row vector, and taking the target historical sensing data of the target sensor corresponding to the number j as a matrix column vector.
And 304, constructing a target historical fault matrix corresponding to the fault time based on the second matrix row vector and the second matrix column vector, and taking the target historical fault matrix corresponding to each fault time as a historical fault matrix.
The target historical fault matrix is used for representing the monitored fault state condition of the corresponding target sensor at each position point.
Optionally, for each fault time, obtaining target historical sensing data acquired by a target sensor corresponding to each position point at the fault time, taking a corresponding position point number i as a matrix row vector, taking target historical sensing data of the target sensor corresponding to a number j as a matrix column vector, and constructing a target historical fault matrix Y to represent as follows:
wherein, yi,jRepresenting the target historical perception data of sensor j at the ith location.
According to the fault detection method and the fault detection device, the fault monitoring matrix is constructed according to the position information of the target sensor and the target sensing data corresponding to the target sensor at each sampling moment, and the historical fault matrix is constructed according to the position information of the target sensor and the corresponding target historical sensing data of the target sensor at each fault moment.
In this embodiment, referring to fig. 4, based on the embodiment shown in fig. 3, the step 203 of obtaining mutual information between the fault monitoring matrix and the historical fault matrix, and obtaining a comparison result according to the mutual information includes steps 401, 402, 403, and 404:
Optionally, the target fault time corresponding to the sampling time is one or more.
Optionally, for each sampling time, when the target fault time corresponding to the sampling time is multiple, the mutual information of the target fault monitoring matrix corresponding to the sampling time and the target historical fault matrix corresponding to each target fault time is respectively calculated to obtain multiple mutual information, and then the multiple mutual information of the targets is summed or weighted summed to obtain final mutual information, that is, the final mutual information is the target mutual information.
Optionally, target mutual information of the target fault monitoring matrix corresponding to the sampling time and the target historical fault matrix corresponding to the target fault time is calculated, and a mutual information sequence S ═ MI is obtained1,MI2,…,MIn]Wherein MIiAnd representing the target mutual information corresponding to the ith sampling time point.
Optionally, the mutual information difference is calculated as λ ═ MIi-MIi-1Or λ ═ MIi-MIi-1|。
Optionally, the latest sampling time point corresponds to the target mutual information, and the target mutual information is compared with the first threshold. And then acquiring target mutual information corresponding to the last sampling time point of the latest sampling time point, calculating a mutual information difference value between the target mutual information corresponding to the latest sampling time point and the target mutual information corresponding to the last sampling time point, and comparing the mutual information difference value with a second threshold value.
And step 404, taking each first comparison result and each second comparison result as a comparison result.
Optionally, when the target mutual information is greater than the first threshold and the mutual information difference is greater than the second threshold, the substation has a fault.
Optionally, when the transformer substation is detected to have a fault, an alarm signal is sent to a terminal device of a transformer substation worker or a maintainer.
According to the embodiment, the target mutual information is compared with the first threshold value respectively to obtain the first comparison result, the mutual information difference value is compared with the second threshold value respectively to obtain the second comparison result, and the first comparison result and the second comparison result are used as the comparison result to judge whether the transformer substation has faults or not, so that the accuracy of rapidly judging the faults is improved.
In the embodiment of the application, based on the embodiment shown in fig. 1, the target sensor is deployed in the substation wirelessly; the number of the target sensors is multiple, and the multiple target sensors are distributed in the transformer substation in a tree-shaped network topological structure or a multi-hop network topological structure.
Optionally, the wireless sensor network is constructed based on the target sensor, the power wireless private network base station and the local area network server. As shown in fig. 5, the topology structure of the wireless sensor network is a tree network topology structure or a multi-hop network topology structure. In another optional implementation manner, a wireless sensor network is constructed based on the target sensor, the electric power wireless private network base station and the cloud server.
Optionally, the wireless sensor network is constructed by using a wireless ad hoc network technology.
Optionally, the target sensor transmits the acquired target state data to the electric power wireless private network base station through the LIE-a wireless communication interface, and the electric power wireless private network base station transmits the received target sensing data to the local area network server or the cloud server through the internet. The terminal collects target sensing data from a local area network server or a cloud server. And the terminal monitors the abnormal state in real time according to the acquired target sensing data and judges whether the transformer substation has faults or not.
According to the embodiment, the target sensor is deployed in the transformer substation in a wireless mode, the problem that the target sensor is inconvenient to deploy due to the fact that the target sensor is connected in a wired communication mode is solved, and flexible deployment of the target sensor is achieved.
In the embodiment of the present application, referring to fig. 6, based on the embodiment shown in fig. 1, the substation fault detection method further includes steps 501 and 502:
Wherein, the fault detection model is a convolution neural network model.
Optionally, the target state data is input into the fault detection model, abnormal data in the target sensing data is located, a corresponding target sensor is determined according to the abnormal data, and the position information of the monitored object of the target sensor is determined according to the target sensor, that is, the fault occurrence position is obtained. The type of the fault is determined according to the type of the target sensing data of the target sensor, such as temperature, humidity, sound, displacement, vibration acceleration, and thermographic data.
Optionally, the target sensors and the position information of the monitored objects of the target sensors are in one-to-one correspondence, and optionally, the terminal stores a mapping relation table of the position information of the monitored objects of the target sensors and the target sensors. And determining the position information of the monitored object of the target sensor according to the target sensor by means of a table look-up mode.
And 502, matching the fault occurrence position and the fault type of the transformer substation with fault information in a fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
The fault knowledge base stores a large amount of fault information in advance, wherein each fault information comprises fault description information, a corresponding solution and a fraction value of a solution effect, and the fault information comprises a fault occurrence position, a fault type and the like of a certain fault. Wherein, the score value of the solution reflects the quality of the solution, and the higher the score value is, the better the solution is.
Optionally, the matching degree between the fault occurrence position and the fault type of the substation and the fault description information in the fault knowledge base is calculated, and the fault solution corresponding to the fault description information with the high matching degree is determined as the fault solution corresponding to the fault occurrence position and the fault type.
Optionally, the fault occurrence position and the fault type of the substation are matched with fault description information in the fault knowledge base to obtain a plurality of fault solutions corresponding to the fault description information, and a final solution is determined according to the fraction value of the solution effect.
According to the embodiment, the target state data is input to the fault detection model under the condition that the fault exists in the transformer substation, so that the fault occurrence position and the fault type of the transformer substation are obtained, the accuracy of fault positioning is improved, and the real-time performance and the accuracy of fault diagnosis are considered at the same time. In addition, the fault occurrence position and the fault type of the transformer substation are matched with the fault information in the fault knowledge base, so that a fault solution corresponding to the fault occurrence position and the fault type is obtained, and the fault solution efficiency is improved.
In the embodiment of the present application, referring to fig. 7, based on the embodiment shown in fig. 6, the training process of the fault detection model includes:
The training data comprises position information of the target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment.
Optionally, when the terminal monitors that the substation has a fault, the sensor sensing data, the fault location information and the fault type monitored by the target sensor corresponding to the moment are stored in the corresponding storage path as fault state data. The storage path may be located on the terminal or on the server.
Alternatively, the fault detection model may be self-trained by the terminal; optionally, in order to save the computing resources of the terminal, the fault detection model may also be trained by the server, and sent to the terminal after the training is completed.
Optionally, the terminal or the server may call the stored fault state data when training the fault detection model.
Optionally, for expanding the number of data samples of the fault state data, the number of data samples of the fault state data may be expanded by a sample expansion method such as a random oversampling algorithm, a SMOTE algorithm, an ADASYN algorithm, a generation countermeasure network method, and the like.
And step 602, performing iterative training on the initial fault detection model by using the training data to obtain a fault detection model.
Optionally, the position information of the target sensor and the sensor sensing data corresponding to the multiple historical fault times are used as the input of an initial fault detection model, the fault position information corresponding to each historical fault time and the fault type corresponding to each historical fault time are used as the initial fault detection model, and the initial fault detection model is subjected to iterative training by using a back propagation algorithm.
Optionally, the terminal may further divide the training data set into a training set and a test set, obtain the fault detection model through training in the training set, verify the model effect of the fault detection model through the test set, and determine that training is completed if the fault detection model passes the verification, so as to obtain the final fault detection model.
According to the embodiment, the initial fault detection model is iteratively trained by acquiring the training data and utilizing the training data to obtain the fault detection model, so that the reliability of the fault detection model is improved.
In the embodiment of the present application, as shown in fig. 8, a transformer substation fault detection method is provided, and the method includes the following steps:
And 703, determining a matrix row vector according to the position information of the target sensor at each sampling moment, and determining a matrix column vector according to the target sensor and target sensing data corresponding to the sampling moment.
The fault state data comprise target historical sensing data corresponding to at least one fault moment in a historical time period.
The historical fault matrix comprises a target historical fault matrix corresponding to each fault moment, and for each fault moment, a second matrix row vector is determined according to the position information of the target sensor, and a second matrix column vector is determined according to the target sensor and target historical sensing data corresponding to the fault moment; and constructing a target historical fault matrix corresponding to the fault time based on the second matrix row vector and the second matrix column vector, and taking the target historical fault matrix corresponding to each fault time as a historical fault matrix.
And 707, determining a target fault time corresponding to the sampling time for each sampling time, and calculating target mutual information of the target fault monitoring matrix corresponding to the sampling time and the target historical fault matrix corresponding to the target fault time.
And 709, comparing the target mutual information with a first threshold respectively to obtain a first comparison result, and comparing the difference value of the target mutual information with a second threshold respectively to obtain a second comparison result.
And step 710, taking each first comparison result and each second comparison result as a comparison result, and determining whether the transformer substation has faults or not according to the comparison result.
And 711, if the transformer substation has a fault, inputting the target state data to the fault detection model to obtain the fault occurrence position and the fault type of the transformer substation.
Wherein, the fault detection model is a convolution neural network model.
Wherein, the training process of the fault detection model comprises the following steps: acquiring training data, wherein the training data comprises position information of a target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment; and performing iterative training on the initial fault detection model by using the training data to obtain a fault detection model.
And 712, matching the fault occurrence position and the fault type of the transformer substation with the fault information in the fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
According to the embodiment, the target sensors are deployed in the transformer substation in a wireless mode, so that flexible deployment of the target sensors is achieved; the method comprises the steps of calculating target mutual information of a target fault monitoring matrix corresponding to a sampling moment and a target historical fault matrix corresponding to a target fault moment and mutual information difference values of the target mutual information corresponding to two adjacent sampling moments in each sampling moment, comparing each target mutual information with a first threshold value respectively to obtain a first comparison result, comparing each mutual information difference value with a second threshold value respectively to obtain a second comparison result, and determining whether the transformer substation has a fault according to the first comparison result and the second comparison result, so that the fault judgment difficulty is reduced, and the fault judgment speed is increased. In addition, the target state data is input to the fault detection model under the condition that the fault exists in the transformer substation, so that the fault occurrence position and the fault type of the transformer substation are obtained, the accuracy of fault positioning is improved, and the real-time performance and the accuracy of fault diagnosis are considered at the same time.
It should be understood that although the various steps in the flowcharts of fig. 1-4 and 6-8 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 1-4 and 6-8 may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or at least partially with other steps or with at least some of the other steps.
In an embodiment of the present application, as shown in fig. 9, there is provided a substation fault detection device, including: the device comprises an acquisition module and a judgment module, wherein:
the acquisition module is used for acquiring target state data obtained by monitoring the transformer substation by the target sensor in a target time period; acquiring fault state data corresponding to the target sensor and a historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation is in fault;
and the judging module is used for comparing the similarity of the target state data and the fault state data to obtain a comparison result and determining whether the transformer substation has faults or not according to the comparison result.
In one embodiment, the determining module is specifically configured to:
constructing a fault monitoring matrix according to the target state data;
constructing a historical fault matrix according to the fault state data;
mutual information of the fault monitoring matrix and the historical fault matrix is obtained, and a comparison result is obtained according to the mutual information.
In one embodiment, the target state data includes position information of the target sensor and target sensing data corresponding to at least one sampling time within a target time period, and the determining module is further configured to:
for each sampling moment, determining a matrix row vector according to the position information of the target sensor, and determining a matrix column vector according to target sensing data corresponding to the target sensor and the sampling moment;
and constructing a target fault monitoring matrix corresponding to the sampling time based on the matrix row vector and the matrix column vector, and taking the target fault monitoring matrix corresponding to each sampling time as a fault monitoring matrix.
In one embodiment, the historical failure matrix includes a target historical failure matrix corresponding to at least one failure time in the historical time period, and the determining module is further configured to:
for each sampling moment, determining a target fault moment corresponding to the sampling moment, and calculating target mutual information of a target fault monitoring matrix corresponding to the sampling moment and a target historical fault matrix corresponding to the target fault moment;
calculating a mutual information difference value of target mutual information corresponding to two adjacent sampling moments in each sampling moment;
comparing each target mutual information with a first threshold value respectively to obtain a first comparison result, and comparing each mutual information difference value with a second threshold value respectively to obtain a second comparison result;
and taking each first comparison result and each second comparison result as comparison results.
In one embodiment, the target sensor is deployed wirelessly in a substation; the number of the target sensors is multiple, and the multiple target sensors are distributed in the transformer substation in a tree-shaped network topological structure or a multi-hop network topological structure.
In one embodiment, as shown in fig. 10, the apparatus further includes an output module and a resolution module, specifically:
the output module is used for inputting the target state data to the fault detection model under the condition that the fault exists in the transformer substation, and obtaining the fault occurrence position and the fault type of the transformer substation;
and the solution module is used for matching the fault occurrence position and the fault type of the transformer substation with the fault information in the fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
In one embodiment, the training process of the fault detection model includes:
acquiring training data, wherein the training data comprises position information of a target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment;
and performing iterative training on the initial fault detection model by using the training data to obtain a fault detection model.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 11. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a substation fault detection method. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the architecture shown in fig. 11 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the above-described method embodiments when executing the computer program.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database or other medium used in the embodiments provided herein can include at least one of non-volatile and volatile memory. Non-volatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical storage, or the like. Volatile Memory can include Random Access Memory (RAM) or external cache Memory. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A transformer substation fault detection method is characterized by comprising the following steps:
acquiring target state data obtained by a target sensor monitoring a transformer substation in a target time period;
acquiring fault state data corresponding to the target sensor and a historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation is in fault;
and performing similarity comparison on the target state data and the fault state data to obtain a comparison result, and determining whether the transformer substation has faults or not according to the comparison result.
2. The method of claim 1, wherein comparing the similarity between the target status data and the fault status data to obtain a comparison result comprises:
constructing a fault monitoring matrix according to the target state data;
constructing a historical fault matrix according to the fault state data;
and acquiring mutual information of the fault monitoring matrix and the historical fault matrix, and acquiring the comparison result according to the mutual information.
3. The method of claim 2, wherein the target status data comprises position information of the target sensor and target perception data corresponding to at least one sampling time within the target time period; constructing a fault monitoring matrix according to the target state data, wherein the method comprises the following steps:
for each sampling moment, determining a matrix row vector according to the position information of the target sensor, and determining a matrix column vector according to the target sensor and the target perception data corresponding to the sampling moment;
and constructing a target fault monitoring matrix corresponding to the sampling time based on the matrix row vector and the matrix column vector, and taking the target fault monitoring matrix corresponding to each sampling time as the fault monitoring matrix.
4. The method of claim 3, wherein the historical fault matrix comprises a target historical fault matrix corresponding to at least one fault time within the historical time period; the acquiring mutual information of the fault monitoring matrix and the historical fault matrix, and acquiring the comparison result according to the mutual information, includes:
for each sampling moment, determining a target fault moment corresponding to the sampling moment, and calculating target mutual information of the target fault monitoring matrix corresponding to the sampling moment and the target historical fault matrix corresponding to the target fault moment;
calculating a mutual information difference value of the target mutual information corresponding to two adjacent sampling moments in each sampling moment;
comparing each target mutual information with a first threshold value respectively to obtain a first comparison result, and comparing each mutual information difference value with a second threshold value respectively to obtain a second comparison result;
and taking each first comparison result and each second comparison result as the comparison result.
5. The method of claim 1, wherein the target sensor is deployed wirelessly in the substation; the number of the target sensors is multiple, and the multiple target sensors are distributed in the transformer substation in a tree-shaped network topological structure or a multi-hop network topological structure.
6. The method of claim 1, further comprising:
if the transformer substation has faults, inputting the target state data to a fault detection model to obtain the fault occurrence position and the fault type of the transformer substation;
matching the fault occurrence position and the fault type of the transformer substation with fault information in a fault knowledge base to obtain a fault solution corresponding to the fault occurrence position and the fault type.
7. The method of claim 6, wherein the training process of the fault detection model comprises:
acquiring training data, wherein the training data comprises position information of the target sensor, sensor sensing data corresponding to a plurality of historical fault moments, fault position information corresponding to each historical fault moment and fault types corresponding to each historical fault moment;
and performing iterative training on the initial fault detection model by using the training data to obtain the fault detection model.
8. A substation fault detection device, the device comprising:
the acquisition module is used for acquiring target state data obtained by monitoring the transformer substation by the target sensor in a target time period; acquiring fault state data corresponding to the target sensor and a historical time period, wherein the fault state data is obtained by monitoring the target sensor under the condition that the transformer substation is in fault;
and the judging module is used for comparing the similarity of the target state data and the fault state data to obtain a comparison result and determining whether the transformer substation has faults or not according to the comparison result.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111176423.5A CN113869444A (en) | 2021-10-09 | 2021-10-09 | Transformer substation fault detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111176423.5A CN113869444A (en) | 2021-10-09 | 2021-10-09 | Transformer substation fault detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113869444A true CN113869444A (en) | 2021-12-31 |
Family
ID=79002270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111176423.5A Pending CN113869444A (en) | 2021-10-09 | 2021-10-09 | Transformer substation fault detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113869444A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114994451A (en) * | 2022-08-08 | 2022-09-02 | 山东交通职业学院 | Ship electrical equipment fault detection method and system |
| CN115409210A (en) * | 2022-08-22 | 2022-11-29 | 中国南方电网有限责任公司超高压输电公司昆明局 | Control method and device of monitoring equipment, computer equipment and storage medium |
-
2021
- 2021-10-09 CN CN202111176423.5A patent/CN113869444A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114994451A (en) * | 2022-08-08 | 2022-09-02 | 山东交通职业学院 | Ship electrical equipment fault detection method and system |
| CN114994451B (en) * | 2022-08-08 | 2022-10-11 | 山东交通职业学院 | Ship electrical equipment fault detection method and system |
| CN115409210A (en) * | 2022-08-22 | 2022-11-29 | 中国南方电网有限责任公司超高压输电公司昆明局 | Control method and device of monitoring equipment, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10817394B2 (en) | Anomaly diagnosis method and anomaly diagnosis apparatus | |
| CN113869444A (en) | Transformer substation fault detection method and device, computer equipment and storage medium | |
| US10976729B2 (en) | Method of generating plant normal state prediction data and apparatus using the same | |
| CN113792453A (en) | Partial discharge monitoring system, method and device based on digital twins | |
| CN109143094B (en) | Abnormal data detection method and device for power battery | |
| CN107924184A (en) | The control method of monitoring arrangement and monitoring arrangement | |
| CN110850233A (en) | Cable fault positioning method and device | |
| JP2019121162A (en) | Monitoring device, monitoring method, and monitoring program | |
| CN116164843A (en) | Cable monitoring and early warning method and system based on Internet of things | |
| JP6989398B2 (en) | Failure diagnostic device, failure diagnosis method, and failure diagnosis program | |
| CN114254879A (en) | Multi-sensor information fusion power equipment safety diagnosis method and device | |
| CN113762391A (en) | State detection method and device of cooling system, computer equipment and storage medium | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| CN115469178A (en) | Monitoring method and device for power transmission line, computer equipment and storage medium | |
| CN113295399B (en) | Converter valve element state evaluation method, device, electronic equipment and storage medium | |
| CN112508137B (en) | Transformer abnormality detection method and device, computer equipment and storage medium | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN114198863B (en) | Fault detection method and device for air conditioner in machine room, computer equipment and storage medium | |
| JP6044739B2 (en) | Equipment state analysis device, equipment state analysis method, storage medium and equipment management system | |
| JPWO2018043232A1 (en) | Temperature estimation system, temperature estimation method, and recording medium recording temperature estimation program | |
| CN113284600A (en) | Fault prediction method, device, computer equipment and storage medium | |
| CN114444776A (en) | Neural network-based hazard source analysis method and device | |
| JP2020166819A (en) | Method and system for creating model to discriminate state of structure | |
| CN113344137B (en) | SOM-based data fusion method and device, storage medium and electronic equipment | |
| CN113660107B (en) | Fault locating method, system, 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 |