CN115598457A - Electrical equipment abnormality detection method and device, computer equipment and storage medium - Google Patents
Electrical equipment abnormality detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115598457A CN115598457A CN202211513411.1A CN202211513411A CN115598457A CN 115598457 A CN115598457 A CN 115598457A CN 202211513411 A CN202211513411 A CN 202211513411A CN 115598457 A CN115598457 A CN 115598457A
- Authority
- CN
- China
- Prior art keywords
- data
- electrical equipment
- mode
- power
- operation data
- 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 188
- 230000005856 abnormality Effects 0.000 title claims abstract description 87
- 230000002159 abnormal effect Effects 0.000 claims abstract description 102
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000004590 computer program Methods 0.000 claims abstract description 22
- 230000000630 rising effect Effects 0.000 claims description 33
- 230000015654 memory Effects 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 12
- 230000001174 ascending effect Effects 0.000 claims description 9
- 230000000087 stabilizing effect Effects 0.000 claims description 8
- 230000011664 signaling Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000003247 decreasing effect Effects 0.000 description 3
- 230000007787 long-term memory Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 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
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to the technical field of electric power, and provides an electrical equipment abnormality detection method, an electrical equipment abnormality detection device, computer equipment, a storage medium and a computer program product. According to the method and the device, the accuracy and the efficiency of determining the abnormal detection result of the electrical equipment can be improved. The method comprises the following steps: acquiring operation data of the electrical equipment to be detected; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
Description
Technical Field
The present application relates to the field of power technologies, and in particular, to a method and an apparatus for detecting an abnormality of an electrical device, a computer device, a storage medium, and a computer program product.
Background
With the development of power technology, electrical equipment plays an extremely important role in a power system, and if the electrical equipment breaks down, local power failure of a power grid or even large-area power failure can be caused, so that immeasurable loss is caused to the society. Therefore, how to detect the abnormality of the electrical device is an important research direction.
The conventional technology is generally to manually collect data of the electrical equipment, so that an expert determines an abnormal detection result of the electrical equipment through the data, but the method is mainly based on subjective judgment, so that the accuracy of determining the abnormal detection result of the electrical equipment is low.
Disclosure of Invention
In view of the foregoing, it is necessary to provide an electrical device abnormality detection method, apparatus, computer device, computer-readable storage medium, and computer program product for solving the above technical problems.
In a first aspect, the present application provides a method for detecting an abnormality of an electrical device. The method comprises the following steps:
acquiring operation data of the electrical equipment to be detected;
dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode;
inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode;
and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
In one embodiment, the pre-trained electrical equipment abnormality detection model is trained by the following steps:
obtaining sample operation data;
according to the working modes, the sample operation data is divided to obtain sample operation subdata of each working mode;
and training the electrical equipment abnormity detection model to be trained by utilizing the sample operation subdata to obtain a pre-trained electrical equipment abnormity detection model.
In one embodiment, obtaining sample operational data comprises:
acquiring first original operation data;
inputting the first original operation data into an abnormal data identification model, and identifying abnormal data contained in the first original operation data through the abnormal data identification model;
deleting abnormal data in the first original operation data to obtain second original operation data;
inputting the second original operation data into a missing data identification model, and identifying the missing data of the second original operation data through the missing data identification model;
and adding the missing data into the second original operation data to obtain sample operation data.
In one embodiment, before the sample operation data is divided according to the working modalities to obtain the sample operation subdata of each working modality, the method further includes:
taking a preset working mode as a working mode; the preset working modes comprise a low-power ascending mode, a low-power descending mode, a high-power ascending mode, a high-power descending mode, a medium-power ascending mode, a medium-power descending mode and a power stabilizing mode;
according to the working modes, the sample operation data is divided to obtain the sample operation subdata of each working mode, and the method comprises the following steps:
and according to the working mode, dividing the sample operation data to obtain sample operation subdata of a low-power rising mode, a low-power falling mode, a high-power rising mode, a high-power falling mode, a medium-power rising mode, a medium-power falling mode and a power stable mode.
In one embodiment, inputting the operation sub data into a pre-trained electrical equipment abnormality detection model to obtain an abnormality detection sub-result of each working mode, including:
inputting the operation subdata into a pre-trained electrical equipment abnormity detection model, and identifying whether the operation subdata meets a dynamic numerical value interval condition through the pre-trained electrical equipment abnormity detection model to obtain an identification result; the dynamic numerical value interval is determined according to the working mode;
and determining the abnormal detection sub-result of each working mode according to the identification result.
In one embodiment, the electrical equipment to be detected is a converter transformer;
acquiring the operation data of the electrical equipment to be detected, comprising the following steps:
acquiring remote measuring information and remote signaling information of the converter transformer;
and taking the telemetering information and the remote signaling information as operation data.
In one embodiment, after determining the abnormality detection result of the electrical device to be detected according to the abnormality detection sub-result, the method further includes:
displaying an abnormal detection result;
and when the abnormal detection result is abnormal, alarming according to the abnormal detection result.
In a second aspect, the application further provides an electrical equipment abnormality detection device. The device comprises:
the data acquisition module is used for acquiring the operation data of the electrical equipment to be detected;
the data dividing module is used for dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode;
the data input module is used for inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain an abnormality detection subdue result of each working mode;
and the result determining module is used for determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
In a third aspect, the application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
acquiring operation data of the electrical equipment to be detected; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
acquiring operation data of the electrical equipment to be detected; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
acquiring operation data of the electrical equipment to be detected; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormity detection model to obtain abnormity detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
The electrical equipment abnormity detection method, the electrical equipment abnormity detection device, the computer equipment, the storage medium and the computer program product are used for acquiring the operation data of the electrical equipment to be detected; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result. According to the scheme, the acquired operation data of the electrical equipment to be detected are divided to obtain operation subdata of each working mode of the electrical equipment to be detected, the operation subdata of each working mode is input into an electrical equipment abnormity detection model, different abnormity detections are automatically carried out on the operation subdata of different working modes respectively by using the electrical equipment abnormity detection model, more accurate abnormity detection subdata of different working modes are obtained, and the abnormity detection result of the electrical equipment to be detected is rapidly determined, so that the accuracy and the efficiency of determining the abnormity detection result of the electrical equipment are improved.
Drawings
FIG. 1 is a schematic flow chart of a method for detecting an anomaly in an electrical device according to an embodiment;
FIG. 2 is a schematic flow chart diagram of the model training step in one embodiment;
FIG. 3 is a schematic flowchart of a method for detecting an abnormality in an electrical device according to another embodiment;
FIG. 4 is a block diagram showing the structure of an abnormality detection device for electrical equipment according to an embodiment;
FIG. 5 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.
In an embodiment, as shown in fig. 1, there is provided an electrical device abnormality detection method, which is exemplified by applying the method to a terminal, and includes the following steps:
and S101, acquiring the operation data of the electrical equipment to be detected.
In this step, the electrical equipment to be detected may be a converter transformer, or may be multiple converter transformers under the same working condition; the operational data may be telemetry data (telemetry information), televised data (televised information), and/or Sequence Events Recorder (SER).
Specifically, the terminal acquires real-time operation data of the electrical equipment to be detected in real time.
And S102, dividing the operation data according to the working modes of the electrical equipment to be detected to obtain the operation subdata of each working mode.
In this step, the operation mode may be an operation mode, for example, the operation mode includes a low power increasing mode, a low power decreasing mode, a high power increasing mode, a high power decreasing mode, a medium power increasing mode, a medium power decreasing mode, and a power smoothing mode.
Specifically, the terminal divides the operation data according to the preset operation modes and power levels to obtain operation sub-data of each operation mode (for example, obtaining operation sub-data of a low-power rising mode, a low-power falling mode, a high-power rising mode, a high-power falling mode, a medium-power rising mode, a medium-power falling mode, and a power stabilizing mode, respectively).
And step S103, inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain an abnormality detection subdue result of each working mode.
In this step, the pre-trained anomaly detection model of the electrical equipment can be a pre-trained Bayes long and short term memory network model; the anomaly detection sub-result may be a result of whether it is in a dynamic value interval of data of the current power level.
Specifically, the terminal inputs the operation subdata into a pre-trained electrical equipment abnormality detection model, and detects (or identifies) each operation subdata through the pre-trained electrical equipment abnormality detection model to obtain an abnormality detection subdue result of each working mode.
And step S104, determining the abnormal detection result of the to-be-detected electrical equipment according to the abnormal detection sub-result.
In this step, the abnormality detection result may be a detection result of whether the electrical device to be detected is abnormal.
Specifically, the terminal judges whether the abnormal detection sub-results are normal or pass, if so, the abnormal detection result of the electrical equipment to be detected is determined to be normal, and if not, the abnormal detection result of the electrical equipment to be detected is determined to be abnormal, and an alarm is given.
In the electrical equipment abnormality detection method, operation data of electrical equipment to be detected is acquired; dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode; inputting the operation subdata into a pre-trained electrical equipment abnormality detection model to obtain abnormality detection subducts of each working mode; and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result. According to the scheme, the acquired operation data of the electrical equipment to be detected are divided to obtain operation subdata of each working mode of the electrical equipment to be detected, the operation subdata of each working mode is input into an electrical equipment abnormality detection model, different abnormality detections are automatically carried out on the operation subdata of different working modes by using the electrical equipment abnormality detection model respectively, more accurate abnormality detection subdues of different working modes are obtained, and the abnormality detection result of the electrical equipment to be detected is rapidly determined, so that the accuracy and the efficiency of determining the abnormality detection result of the electrical equipment are improved.
In one embodiment, the pre-trained electrical device anomaly detection model is obtained by training in the following way, specifically including: acquiring sample operation data; according to the working modes, the sample operation data is divided to obtain sample operation subdata of each working mode; and training the electrical equipment abnormity detection model to be trained by utilizing the sample operation subdata to obtain a pre-trained electrical equipment abnormity detection model.
In this embodiment, the sample operation data may be sample data of operation data, for example, sample data such as telemetry data (telemetry information), trust data (trust information), and/or mass event sequence recording data of the sample electrical device.
Specifically, the terminal acquires sample operation data (such as historical power data) such as telemetry data (telemetry information), shaking information data (shaking information) and/or massive event sequence recording data related to the converter transformer from a plurality of data sources, divides the sample operation data according to working modes (for example, the historical power data is divided according to seven modes of low-power rising, low-power falling, high-power rising, high-power falling, medium-power rising, medium-power falling and stable power by using a mode division algorithm), obtains sample operation subdata of each working mode, trains an electrical equipment abnormality detection model to be trained by using the sample operation subdata, and obtains a pre-trained electrical equipment abnormality detection model.
According to the technical scheme, the electrical equipment abnormity detection model to be trained is trained through the sample operation data, so that the electrical equipment abnormity detection model which is more accurate and efficient to pre-train can be obtained, and the accuracy and the efficiency of determining the abnormity detection result of the electrical equipment can be improved subsequently.
In an embodiment, the method may further include the following steps of obtaining sample operation data, specifically including: acquiring first original operation data; inputting the first original operation data into an abnormal data identification model, and identifying abnormal data contained in the first original operation data through the abnormal data identification model; deleting abnormal data in the first original operation data to obtain second original operation data; inputting the second original operation data into a missing data identification model, and identifying the missing data of the second original operation data through the missing data identification model; and adding the missing data into the second original operation data to obtain sample operation data.
In this embodiment, the first original operating data may be directly obtained unprocessed sample data (original data); the abnormal data identification model may be a model for detecting an abnormal value (abnormal data) and deleting the abnormal value (abnormal data); the missing data identification model may be a model that determines missing data according to a preset rule and performs padding.
Specifically, the terminal acquires first original operation data, inputs the first original operation data into an abnormal data identification model, identifies abnormal data contained in the first original operation data through the abnormal data identification model, deletes the abnormal data in the first original operation data to obtain second original operation data, inputs the second original operation data into a missing data identification model, identifies missing data of the second original operation data through the missing data identification model, and adds the missing data into the second original operation data to obtain sample operation data.
According to the technical scheme, the original operation data are preprocessed through the abnormal data recognition model and the missing data recognition model, so that the more accurate sample operation data which are more suitable for model training can be obtained, and the more accurate pre-trained electrical equipment abnormality detection model can be obtained.
In an embodiment, the method may further include obtaining the sample run sub-data by the following steps: taking a preset working mode as a working mode; and according to the working mode, dividing the sample operation data to obtain sample operation subdata of a low-power rising mode, a low-power falling mode, a high-power rising mode, a high-power falling mode, a medium-power rising mode, a medium-power falling mode and a power stable mode.
In this embodiment, the preset operation modes include a low power up mode, a low power down mode, a high power up mode, a high power down mode, a medium power up mode, a medium power down mode, and a power steady mode, wherein each preset operation mode may be an operation mode generated by power (load) adjustment.
Specifically, the terminal uses preset working modes including a low-power rising mode, a low-power falling mode, a high-power rising mode, a high-power falling mode, a medium-power rising mode, a medium-power falling mode and a power stabilizing mode as working modes, and divides sample running data according to the working modes to obtain multiple (seven) modes of sample running sub-data, such as the low-power rising mode, the low-power falling mode, the high-power rising mode, the high-power falling mode, the medium-power rising mode, the medium-power falling mode and the power stabilizing mode.
According to the technical scheme, the sample operation sub-data of the low-power rising mode, the low-power descending mode, the high-power rising mode, the high-power descending mode, the medium-power rising mode, the medium-power descending mode and the power stable mode are obtained by dividing the sample operation data, so that the accurate division of the sample operation data is facilitated, the accuracy and the efficiency of the obtained sample operation data are improved, the more accurate and more efficient pre-trained electrical equipment abnormality detection model is facilitated, and the accuracy and the efficiency of determining the abnormality detection result of the electrical equipment are improved.
In an embodiment, the inputting the operation sub data into the pre-trained electrical equipment abnormality detection model in step S103 to obtain the abnormality detection sub-result of each working mode specifically includes: inputting the operation subdata into a pre-trained electrical equipment abnormity detection model, and identifying whether the operation subdata meets the condition of a dynamic numerical value interval through the pre-trained electrical equipment abnormity detection model to obtain an identification result; and determining the abnormal detection sub-result of each working mode according to the identification result.
In the embodiment, the dynamic numerical interval is determined according to the working mode; the dynamic numerical interval condition may be a condition of a numerical interval or a data interval corresponding to different working modes.
Specifically, the terminal inputs the operation subdata into a pre-trained electrical equipment abnormality detection model, identifies whether each operation subdata meets each dynamic value interval condition through the pre-trained electrical equipment abnormality detection model to obtain an identification result for each operation subdata, and determines an abnormality detection sub-result of each working mode (or each operation subdata) according to the identification result for each operation subdata.
According to the technical scheme, whether the operation subdata meets the dynamic numerical value interval condition is identified through the pre-trained electrical equipment abnormality detection model, so that the abnormality detection sub-results of each working mode are determined, the abnormality detection sub-results can be obtained more accurately and rapidly, and the accuracy and the efficiency of determining the abnormality detection results of the electrical equipment can be improved subsequently.
In an embodiment, the acquiring the operation data of the electrical device to be detected in step S101 specifically includes: acquiring remote measuring information and remote signaling information of the converter transformer; and taking the telemetering information and the remote signaling information as operation data.
In this embodiment, the electrical device to be detected is a converter transformer.
Specifically, the terminal collects telemetering data (telemetering information), letter shaking data (letter shaking information) and/or massive event sequence recording data related to the detection electrical equipment (converter transformer) from a plurality of data sources, and the telemetering data (telemetering information), letter shaking data (letter shaking information) and/or massive event sequence recording data are used as operation data.
According to the technical scheme, the specific data corresponding to the operation data are determined, and the specific data are obtained to serve as the operation data, so that the accurate operation data can be obtained, and the accuracy of the abnormal detection result of the electrical equipment can be improved.
In an embodiment, the method may further perform an alarm for the abnormal detection result through the following steps, specifically including: displaying an abnormal detection result; and when the abnormal detection result is abnormal, alarming is carried out according to the abnormal detection result.
In this embodiment, the abnormality detection result may be abnormal or normal.
Specifically, the terminal displays an abnormality detection result on a front-end interface for a worker to refer to, and when the abnormality detection result is abnormal, the terminal gives an alarm for the abnormality detection result to indicate the worker to perform maintenance and other processing on the electrical equipment to be detected.
According to the technical scheme of the embodiment, the abnormality detection result is displayed, and the alarm is given when the abnormality detection result is abnormal, so that the feedback instantaneity, the functionality and the safety of the abnormality detection result of the electrical equipment can be improved.
The method for detecting the abnormality of the electrical device provided by the present application is described as an embodiment below, and the embodiment is described by applying the method to a terminal for example, and includes the following main steps:
in the first step, the terminal acquires first original operation data.
And secondly, the terminal inputs the first original operation data into an abnormal data identification model, and abnormal data contained in the first original operation data are identified through the abnormal data identification model.
And thirdly, deleting the abnormal data in the first original operation data by the terminal to obtain second original operation data.
And fourthly, the terminal inputs the second original operation data into the missing data identification model, and the missing data of the second original operation data is identified through the missing data identification model.
And fifthly, adding the missing data into the second original operation data by the terminal to obtain sample operation data.
And sixthly, the terminal takes a preset working mode as a working mode.
And seventhly, the terminal divides the sample operation data according to the working mode to obtain sample operation subdata of a low-power rising mode, a low-power descending mode, a high-power rising mode, a high-power descending mode, a medium-power rising mode, a medium-power descending mode and a stable-power mode respectively.
And eighthly, training the electrical equipment abnormity detection model to be trained by the terminal by using the sample operation subdata to obtain a pre-trained electrical equipment abnormity detection model.
And step nine, the terminal acquires the telemetering information and the remote signaling information of the converter transformer.
And step ten, the terminal takes the telemetering information and the telemetering information as operation data.
And step eleven, the terminal divides the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode.
Step ten, the terminal inputs the operation subdata into a pre-trained electrical equipment abnormity detection model, and identifies whether the operation subdata meets the condition of a dynamic numerical value interval through the pre-trained electrical equipment abnormity detection model to obtain an identification result; the dynamic numerical interval is determined according to the working mode.
And step thirteen, the terminal determines the abnormal detection sub-result of each working mode according to the identification result.
And fourteenth, the terminal determines the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
And fifteenth, displaying an abnormal detection result by the terminal.
Sixthly, the terminal gives an alarm aiming at the abnormal detection result when the abnormal detection result is abnormal.
The electrical equipment to be detected is a converter transformer; the preset operation modes include a low power up mode, a low power down mode, a high power up mode, a high power down mode, a medium power up mode, a medium power down mode, and a power plateau mode.
According to the technical scheme of the embodiment, the acquired operation data of the electrical equipment to be detected is divided to obtain the operation subdata of each working mode of the electrical equipment to be detected, the operation subdata of each working mode is input into the electrical equipment abnormality detection model, different abnormality detections are automatically performed on the operation subdata of different working modes by using the electrical equipment abnormality detection model respectively, more accurate abnormality detection subducts of different working modes are obtained, and the abnormality detection result of the electrical equipment to be detected is rapidly determined, so that the accuracy and the efficiency of determining the abnormality detection result of the electrical equipment are improved.
The method for detecting the abnormality of the electrical device provided by the present application is described below with an application example, and the application example is illustrated by applying the method to a terminal, as shown in fig. 2 and 3, the main steps include:
first, as shown in fig. 2, the model training step is performed, and the terminal acquires data (acquires historical data): the required data is collected from a plurality of data sources, including telemetry, SER (mass event sequence recording) data related to the converter transformer.
And secondly, the terminal performs data preprocessing (including abnormal value deletion and missing value filling): and preprocessing the data, detecting abnormal values by using an abnormal detection model, removing the abnormal values, and filling the abnormal values by using a missing filling model according to rules.
Thirdly, the terminal divides working modes: and dividing the historical power data according to seven modes of low power rising, low power falling, high power rising, high power falling, medium power rising, medium power falling and power stabilizing by using a modal division algorithm.
Fourthly, the terminal trains an abnormal detection model: and respectively inputting the divided data into a Bayesian long-term and short-term memory network to obtain a trained space-time consistency detection algorithm model.
Fifthly, as shown in fig. 3, the terminal performs real-time data acquisition and real-time data division: a section of data set is input, and the data are divided according to power levels by using a modal division algorithm.
Sixthly, the terminal performs abnormity detection (detection is performed by using an abnormity detection model): and detecting the state of the section of data by using a trained space-time consistency detection algorithm, judging whether the section of data is in a dynamic numerical value interval of the data of the current power level, and if not, giving an alarm.
According to the technical scheme of the application example, the operation data is divided according to 7 types of working modes by using a mode division algorithm, and then abnormal detection is carried out on the data according to different working modes, so that the problem of model false alarm caused by load (power) adjustment can be effectively reduced, and the problem of excessive abnormal detection model false alarm caused by load adjustment can be effectively avoided by dividing different working modes according to historical data, so that the reliability of system output is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the present application further provides an electrical equipment abnormality detection apparatus for implementing the electrical equipment abnormality detection method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so that the specific limitations in the embodiment of one or more electrical device abnormality detection apparatuses provided below may refer to the limitations on the electrical device abnormality detection method in the above description, and are not described herein again.
In one embodiment, as shown in fig. 4, there is provided an electrical equipment abnormality detection apparatus, and the apparatus 400 may include:
the data acquisition module 401 is used for acquiring the operation data of the electrical equipment to be detected;
the data dividing module 402 is configured to divide the operation data according to the working modes of the electrical device to be detected, so as to obtain operation subdata of each working mode;
a data input module 403, configured to input the operation sub data into a pre-trained electrical device anomaly detection model, so as to obtain an anomaly detection sub-result of each working mode;
a result determining module 404, configured to determine, according to the abnormal detection sub-result, an abnormal detection result of the to-be-detected electrical device.
In one embodiment, the apparatus 400 further comprises: the model training module is used for acquiring sample operation data; according to the working modes, the sample operation data are divided to obtain sample operation subdata of each working mode; and training an electrical equipment abnormity detection model to be trained by using the sample operation subdata to obtain the pre-trained electrical equipment abnormity detection model.
In one embodiment, the model training module is further configured to obtain first raw operational data; inputting the first original operation data into an abnormal data identification model, and identifying abnormal data contained in the first original operation data through the abnormal data identification model; deleting the abnormal data in the first original operation data to obtain second original operation data; inputting the second original operation data into a missing data identification model, and identifying the missing data of the second original operation data through the missing data identification model; and adding the missing data into the second original operation data to obtain the sample operation data.
In one embodiment, the apparatus 400 further comprises: the working mode is used as a module for taking a preset working mode as the working mode; the preset working modes comprise a low-power ascending mode, a low-power descending mode, a high-power ascending mode, a high-power descending mode, a medium-power ascending mode, a medium-power descending mode and a power stabilizing mode; and the model training module is further configured to perform division processing on the sample operation data according to the working mode to obtain sample operation sub-data of the low-power rising mode, the low-power falling mode, the high-power rising mode, the high-power falling mode, the medium-power rising mode, the medium-power falling mode and the power stabilizing mode, respectively.
In an embodiment, the data input module 403 is further configured to input the operation sub data into the pre-trained electrical device abnormality detection model, and identify, by using the pre-trained electrical device abnormality detection model, whether the operation sub data meet a dynamic numerical value interval condition, so as to obtain an identification result; the dynamic numerical value interval is determined according to the working mode; and determining the abnormal detection sub-result of each working mode according to the identification result.
In one embodiment, the electrical equipment to be detected is a converter transformer; the data acquisition module 401 is further configured to acquire telemetry information and remote signaling information of the converter transformer; and taking the telemetering information and the telecommand information as the operation data.
In one embodiment, the apparatus 400 further comprises: the result warning module is used for displaying the abnormal detection result; and when the abnormal detection result is abnormal, alarming according to the abnormal detection result.
Each module in the above-described electrical equipment abnormality detection apparatus may be entirely or partially implemented by software, hardware, or a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 5. The computer apparatus includes a processor, a memory, an input/output interface, a communication interface, a display unit, and an input device. The processor, the memory and the input/output interface are connected by a system bus, and the communication interface, the display unit and the input device are connected by the input/output interface to the system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile 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 input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for communicating with an external terminal in a wired or wireless manner, and the wireless manner can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement an electrical device anomaly detection method. The display unit of the computer device is used for forming a visual picture and can be a display screen, a projection device or a virtual reality imaging device. The display screen 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.
It will be appreciated by those skilled in the art that the configuration shown in fig. 5 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device 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 further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above 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.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, carries out the steps in the method embodiments described above.
It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant countries and regions.
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, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. 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 databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.
All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure 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 present application. 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, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.
Claims (10)
1. An electrical equipment abnormality detection method characterized by comprising:
acquiring operation data of the electrical equipment to be detected;
dividing the operation data according to the working modes of the to-be-detected electrical equipment to obtain operation subdata of each working mode;
inputting the operation subdata into a pre-trained electrical equipment abnormity detection model to obtain abnormity detection subducts of each working mode;
and determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-result.
2. The method of claim 1, wherein the pre-trained electrical equipment anomaly detection model is trained by:
acquiring sample operation data;
dividing the sample operation data according to the working modes to obtain sample operation subdata of each working mode;
and training an electrical equipment abnormity detection model to be trained by using the sample operation subdata to obtain the pre-trained electrical equipment abnormity detection model.
3. The method of claim 2, wherein said obtaining sample operational data comprises:
acquiring first original operation data;
inputting the first original operation data into an abnormal data identification model, and identifying abnormal data contained in the first original operation data through the abnormal data identification model;
deleting the abnormal data in the first original operation data to obtain second original operation data;
inputting the second original operation data into a missing data identification model, and identifying the missing data of the second original operation data through the missing data identification model;
and adding the missing data into the second original operation data to obtain the sample operation data.
4. The method according to claim 2, before dividing the sample operation data according to the working modalities to obtain sample operation sub-data of each working modality, further comprising:
taking a preset working mode as the working mode; the preset working modes comprise a low-power ascending mode, a low-power descending mode, a high-power ascending mode, a high-power descending mode, a medium-power ascending mode, a medium-power descending mode and a power stabilizing mode;
the dividing and processing the sample operation data according to the working modes to obtain the sample operation subdata of each working mode includes:
according to the working mode, the sample operation data is divided to obtain sample operation subdata of the low-power rising mode, the low-power descending mode, the high-power rising mode, the high-power descending mode, the medium-power rising mode, the medium-power descending mode and the power stable mode.
5. The method of claim 1, wherein the inputting the operation sub-data into a pre-trained electrical equipment abnormality detection model to obtain an abnormality detection sub-result of each of the operation modes comprises:
inputting the operation subdata into the pre-trained electrical equipment abnormity detection model, and identifying whether the operation subdata meets dynamic numerical value interval conditions through the pre-trained electrical equipment abnormity detection model to obtain an identification result; the dynamic numerical value interval is determined according to the working mode;
and determining the abnormal detection sub-result of each working mode according to the identification result.
6. The method according to claim 1, characterized in that the electrical equipment to be tested is a converter transformer;
the acquiring of the operation data of the electrical equipment to be detected comprises the following steps:
acquiring telemetering information and telesignaling information of the converter transformer;
and taking the telemetering information and the remote signaling information as the operation data.
7. The method according to claim 1, further comprising, after determining an abnormality detection result of the electrical device to be detected based on the abnormality detection sub-result:
displaying the abnormal detection result;
and when the abnormal detection result is abnormal, alarming is carried out aiming at the abnormal detection result.
8. An electrical equipment abnormality detection apparatus, characterized in that the apparatus comprises:
the data acquisition module is used for acquiring the operation data of the electrical equipment to be detected;
the data dividing module is used for dividing the operation data according to the working modes of the electrical equipment to be detected to obtain operation subdata of each working mode;
the data input module is used for inputting the operation subdata into a pre-trained electrical equipment abnormity detection model to obtain abnormity detection subducts of each working mode;
and the result determining module is used for determining the abnormal detection result of the electrical equipment to be detected according to the abnormal detection sub-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 |
|---|---|---|---|
| CN202211513411.1A CN115598457A (en) | 2022-11-30 | 2022-11-30 | Electrical equipment abnormality detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211513411.1A CN115598457A (en) | 2022-11-30 | 2022-11-30 | Electrical equipment abnormality detection method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115598457A true CN115598457A (en) | 2023-01-13 |
Family
ID=84853081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211513411.1A Pending CN115598457A (en) | 2022-11-30 | 2022-11-30 | Electrical equipment abnormality detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115598457A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110961A (en) * | 2021-04-30 | 2021-07-13 | 平安国际融资租赁有限公司 | Equipment abnormality detection method and device, computer equipment and readable storage medium |
| CN113533910A (en) * | 2021-06-10 | 2021-10-22 | 中国电力科学研究院有限公司 | Method and system suitable for converter transformer partial discharge early warning |
-
2022
- 2022-11-30 CN CN202211513411.1A patent/CN115598457A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113110961A (en) * | 2021-04-30 | 2021-07-13 | 平安国际融资租赁有限公司 | Equipment abnormality detection method and device, computer equipment and readable storage medium |
| CN113533910A (en) * | 2021-06-10 | 2021-10-22 | 中国电力科学研究院有限公司 | Method and system suitable for converter transformer partial discharge early warning |
Non-Patent Citations (1)
| Title |
|---|
| 柯志敏 主编, 北京：北京交通大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112306835B (en) | User data monitoring and analyzing method, device, equipment and medium | |
| KR102315580B1 (en) | Fire predictive analysis device and method of building | |
| CN114398354A (en) | Data monitoring method and device, electronic equipment and storage medium | |
| CN115238831A (en) | Fault prediction method, apparatus, computer device, storage medium and program product | |
| CN115878958A (en) | Transformer oil temperature prediction method, device, equipment and storage medium | |
| CN116414815A (en) | Data quality detection method, device, computer equipment and storage medium | |
| CN114446019A (en) | Alarm information processing method, device, equipment, storage medium and product | |
| CN109308225A (en) | A kind of virtual machine method for detecting abnormality, device, equipment and storage medium | |
| CN114254864A (en) | Power utilization data processing method and device, computer equipment and storage medium | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN116628564B (en) | Model training method and system for detecting generator state | |
| CN115639327B (en) | Sleeve fault detection method and device based on oil-immersed sleeve gas detection | |
| CN115598457A (en) | Electrical equipment abnormality detection method and device, computer equipment and storage medium | |
| CN115601013A (en) | Nuclear reactor failure determination method, device, apparatus, storage medium, and product | |
| CN115617634A (en) | Nuclear power equipment abnormity diagnosis method and device based on 5G and computer equipment | |
| CN115098326A (en) | System anomaly detection method and device, storage medium and electronic equipment | |
| CN115358336A (en) | Power utilization abnormity detection method and device and electronic equipment | |
| CN115169155A (en) | Engine fault prediction method and device, computer equipment and storage medium | |
| CN114239639A (en) | Feature selection method and device, computer equipment and storage medium | |
| CN113888061A (en) | Method and device for evaluating running state of converter transformer | |
| CN113887676A (en) | Equipment fault early warning method, device, equipment, medium and computer program product | |
| CN113689042A (en) | Fault source prediction method for monitoring node | |
| CN117875945B (en) | Power grid equipment maintenance prediction method, system and medium | |
| CN114993455A (en) | Transformer fault diagnosis method and device, computer equipment, medium and product | |
| CN118054397A (en) | Regional power outage method, regional power outage device, regional power outage equipment, regional power outage storage medium and regional power outage computer product |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230113 |