CN118134462A - Operation and maintenance method and device of power transformation equipment, electronic equipment and storage medium - Google Patents

Abstract

The invention discloses an operation and maintenance method and device of power transformation equipment, electronic equipment and a storage medium. The method comprises the following steps: acquiring target operation data of target power transformation equipment; inputting target operation data into a pre-trained classification model to determine a target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm; and determining an operation and maintenance scheme according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme. The scheme provided by the invention can detect the target operation data by using the classification model, so that the operation and maintenance scheme is determined according to the detected type of the target fault, the manual intervention is reduced, the error judgment of the abnormal operation data caused by the non-fault of the equipment is reduced, and the detection efficiency is improved.

Description

Operation and maintenance method and device of power transformation equipment, electronic equipment and storage medium

Technical Field

The present invention relates to the field of power systems, and in particular, to an operation and maintenance method and apparatus for a power transformation device, an electronic device, and a storage medium.

Background

In a power system, various faults are likely to occur in power transformation equipment such as transformers and circuit breakers. These faults may cause interruption of the power supply, which has a serious influence on production and life.

At present, operation and maintenance of a power system can only be carried out according to data collected around power transformation equipment to judge whether the equipment has faults. When a fault exists in the equipment, an maintainer is arranged to go to the equipment to check what fault exists in the equipment, and an operation and maintenance scheme is determined according to experience of the maintainer.

However, the device responsible for collecting the data may have errors in the data at a certain time or within a certain period of time, resulting in anomalies in the operational data caused by non-device failures. In this way, the workload of the operation and maintenance personnel for judging the current operation state of the equipment is increased, and even the normal operation of the power system can be influenced.

Disclosure of Invention

The invention provides an operation and maintenance method, an operation and maintenance device, electronic equipment and a storage medium of power transformation equipment, which can detect target operation data by using a classification model, so that an operation and maintenance scheme is determined according to the detected target fault type, manual intervention is reduced, meanwhile, error judgment of operation data abnormality caused by equipment non-fault is reduced, and detection efficiency is improved.

According to an aspect of the present invention, there is provided an operation and maintenance method of a power transformation device, the method comprising:

acquiring target operation data of target power transformation equipment;

inputting target operation data into a pre-trained classification model to determine a target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm;

And determining an operation and maintenance scheme according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme.

According to another aspect of the present invention, there is provided an operation and maintenance apparatus of a power transformation device, the apparatus comprising:

the acquisition module is used for acquiring target operation data of the target power transformation equipment;

the determining module is used for inputting the target operation data into a pre-trained classification model to determine the target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm;

And the operation and maintenance module is used for determining an operation and maintenance scheme according to the target fault type so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme.

According to another aspect of the present invention, there is provided an electronic apparatus including:

at least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of operating the power conversion device of any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute an operation and maintenance method of a power transformation device according to any one of the embodiments of the present invention.

According to the operation and maintenance method of the power transformation equipment, the target operation data of the target power transformation equipment are acquired, the target operation data are input into the pre-trained classification model, the target fault type is determined, and the operation and maintenance scheme is determined according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme. According to the technical scheme, on one hand, operation data of the target power transformation equipment are acquired through various equipment to obtain target operation data, and the target operation data are input into a pre-trained classification model to automatically determine the target fault type. The target operation data is detected by using the classification model, so that the error judgment of the operation data abnormality caused by the non-fault of the equipment is reduced while the manual intervention is reduced, and the detection efficiency is improved. Meanwhile, continuous self-adaptive optimization of the classification model can be utilized, and the maintenance accuracy is gradually improved. On the other hand, according to the target fault type of the target power transformation equipment, the operation and maintenance scheme of the time is determined, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme, intelligent management is realized, and the operation and maintenance efficiency of the target fault type of the target power transformation equipment is improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a schematic flow chart of an operation and maintenance method of a power transformation device according to the present invention;

Fig. 2 is another flow chart of the operation and maintenance method of the power transformation device provided by the invention;

fig. 3 is an exemplary diagram of an operation and maintenance system of the power transformation device provided by the invention;

Fig. 4 is a schematic structural diagram of an operation and maintenance device of the power transformation equipment provided by the invention;

Fig. 5 is a schematic structural diagram of an electronic device provided by the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Fig. 1 is a schematic flow chart of an operation and maintenance method of a power transformation device according to the present invention, where the method may be performed by an operation and maintenance device of the power transformation device, the operation and maintenance device of the power transformation device may be implemented in hardware and/or software, and the operation and maintenance device of the power transformation device may be configured in an electronic device. As shown in fig. 1, the method includes:

s101, acquiring target operation data of target substation equipment.

The target power transformation equipment refers to power transformation equipment which needs to be subjected to operation, maintenance and overhaul. Illustratively, the target power transformation device includes a transformer, a circuit breaker, and the like. The target operation data is operation data of the target power transformation device. By way of example, the operational data of the target power transformation device may be monitored using devices such as a current sensor, a voltage sensor, a temperature sensor, a discharge detection monitoring system, and a circuit breaker status monitoring system.

Specifically, the target operation data of the target power transformation device may be obtained according to the needs of the user. In one implementation, if the user needs to monitor the target power transformation device in real time, real-time operation data of the target power transformation device is obtained and used as target operation data. In another implementation manner, if the user requests to monitor the operation data of the target power transformation device according to the set time period, the operation data of the target power transformation device in each preset time period can be obtained and used as the target operation data.

Optionally, if the user needs to process the collected data after monitoring and collecting the operation data of the target power transformation device by using various devices, the collected data may be processed according to the user's requirement to obtain the target operation data of the target power transformation device.

S102, inputting target operation data into a pre-trained classification model, and determining a target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm.

The target fault type is the fault type of the target power transformation equipment corresponding to the target operation data obtained by using the classification model.

Specifically, the obtained target operation data are input into a pre-trained classification model, and the target fault type can be determined after the classification model analyzes the target operation data. The classification model is a model obtained by training the classifier by using a machine learning algorithm or a deep learning algorithm. Illustratively, the classifier may be trained using at least one of algorithms such as a logistic regression algorithm, a naive bayes algorithm, a nearest neighbor algorithm, a decision tree algorithm, a support vector machine algorithm, and the like, to obtain the classification model.

In this embodiment, operation data of the target power transformation device is collected through various devices to obtain target operation data, and the target operation data is input into a pre-trained classification model to automatically determine a target fault type. The target operation data is detected by using the classification model, so that the error judgment of the operation data abnormality caused by the non-fault of the equipment is reduced while the manual intervention is reduced, and the detection efficiency is improved.

S103, determining an operation and maintenance scheme according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme.

The operation and maintenance scheme comprises a user identification, an overhaul step and overhaul resources. The user identification is personal identification information of maintenance personnel, the maintenance step is a maintenance step proposal of the target power transformation equipment, and the maintenance resource is resource allocation and scheduling of maintenance tools and/or maintenance materials.

Specifically, according to the target fault type, an operation and maintenance scheme corresponding to the target power transformation equipment is determined, so that a user can overhaul the target power transformation equipment according to the operation and maintenance scheme.

For example, in one implementation, information of all users may be entered into the operation and maintenance device of the power transformation device in advance. For example, the user name, the user adept field, the user contact information and the like are input into the operation and maintenance device of the substation equipment in advance, when the target fault type is determined, all users are ranked according to the processing experience of the current target fault type and the belonging field, and the user with the higher ranking is preferentially selected. Meanwhile, users with fewer tasks which are not processed currently can be selected from the users with earlier sequences according to tasks which are not processed currently by each user, and the users are used as maintenance personnel. In another implementation, relevant operation data, corresponding fault types and operation and maintenance schemes for a power system or a target power transformation device in the industrial internet are collected, and historical operation data, corresponding fault types and operation and maintenance schemes of the target power transformation device are saved. And taking the devices, the corresponding operation data, the corresponding fault types and the operation and maintenance schemes as reference information. When the target fault type is determined, an operation and maintenance scheme corresponding to the target power transformation equipment with the target fault type can be determined according to the reference information. The representation of the reference information may be an image, a data table or other various forms. In still another implementation manner, related information of the target power transformation device, such as an operation method, a maintenance method under different conditions, information of tools and materials which may be used, and the like, may be input into an operation and maintenance device of the power transformation device in advance, and when the target fault type is determined, distribution and scheduling of the maintenance tool and/or maintenance material are determined according to the related information of the target power transformation device corresponding to the current target fault type.

In this embodiment, the operation and maintenance scheme of this time is determined according to the target fault type of the target power transformation device, so that a user overhauls the target power transformation device according to the operation and maintenance scheme, intelligent management is realized, and operation and maintenance overhauling efficiency of the target fault type of the target power transformation device is improved.

According to the operation and maintenance method of the power transformation equipment, the target operation data of the target power transformation equipment are acquired, the target operation data are input into the pre-trained classification model, the target fault type is determined, and the operation and maintenance scheme is determined according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme. According to the technical scheme, on one hand, operation data of the target power transformation equipment are acquired through various equipment to obtain target operation data, and the target operation data are input into a pre-trained classification model to automatically determine the target fault type. The target operation data is detected by using the classification model, so that the error judgment of the operation data abnormality caused by the non-fault of the equipment is reduced while the manual intervention is reduced, and the detection efficiency is improved. Meanwhile, continuous self-adaptive optimization of the classification model can be utilized, and the maintenance accuracy is gradually improved. On the other hand, according to the target fault type of the target power transformation equipment, the operation and maintenance scheme of the time is determined, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme, intelligent management is realized, and the operation and maintenance efficiency of the target fault type of the target power transformation equipment is improved.

Fig. 2 is another flow chart of the operation and maintenance method of the power transformation device according to the present invention, and the step of determining the operation and maintenance scheme according to the target fault type is described in detail in the preprocessing step before obtaining the target operation data based on the above embodiment. In order to make the operation and maintenance method of the power transformation device shown in fig. 2 clearer, the operation and maintenance system of the power transformation device provided by the invention is first described. Fig. 3 is an exemplary diagram of an operation and maintenance system of the power transformation device provided by the present invention. As shown in fig. 3, the system includes: the system comprises a data acquisition unit 10, a data processing unit 20, a fault diagnosis unit 30 and an operation and maintenance overhaul release unit 40. The data acquisition unit 10 is configured to acquire operation data of the target power transformation device, and send the acquired operation data to the data processing unit 20. The data processing unit 20 is configured to perform preprocessing, such as sorting, storing, etc., on the collected operation data, so as to normalize the collected operation data, and send the normalized operation data to the fault diagnosis unit 30. Meanwhile, the data processing unit 20 may perform preliminary analysis on the collected operation data, for example, in a certain period of time, if the data at a certain moment is obviously missing or exceeds a preset threshold, the abnormal operation data may be directly fed back to the operation maintenance and repair issuing unit 40. The fault diagnosis unit 30 is configured to perform fault diagnosis on the operation data or the abnormal operation data, determine a fault type corresponding to the operation data, and feed back the fault type to the operation and maintenance service issuing unit 40. After receiving the fault type, the operation and maintenance overhaul publishing unit 40 determines a corresponding operation and maintenance overhaul scheme, namely an operation and maintenance scheme, according to the fault type so as to realize overhaul of the target power transformation equipment by a user according to the operation and maintenance scheme. Meanwhile, when the operation and maintenance service issuing unit 40 receives the abnormal operation data fed back by the data processing unit 20, the operation and maintenance service issuing unit 40 alarms to the user, and after receiving the feedback information of the user for the alarm, the abnormal operation data is sent back to the data processing unit 20 for marking and processing.

After the operation and maintenance system of the power transformation equipment provided by the invention is introduced, the operation and maintenance method of the power transformation equipment provided by the invention is introduced in detail.

As shown in fig. 2, the method includes:

s201, collecting original operation data of target power transformation equipment.

The original operation data are original operation data of the target power transformation equipment.

Specifically, various sensors and/or devices can be utilized to collect the operation data of the target power transformation device, so as to obtain the original operation data.

S202, normalizing the original operation data.

Wherein the normalization process includes the arrangement and generalization of the raw operational data. Illustratively, the normalization process includes establishing a data management flow and formulating a data specification.

Specifically, establishing a data management flow includes data collection, data storage, data access, data maintenance, and data management. Illustratively, the data collection includes determining the type of data and the source of the data to be collected, such as the current, voltage, and temperature values collected by the target substation device a; a data acquisition scheme is designed, such as acquiring a current value, a voltage value and a temperature value of the target power transformation device a at a frequency of 30 times/minute, and storing the values into a cloud storage. The data storage includes determining a data storage format, a storage path, and a storage backup scheme. The data access comprises setting data access authority and access mode, and providing data inquiry interface and data export function. Data maintenance includes periodic sorting of data, such as deleting obsolete data and merging duplicate data. The data management refers to selecting a proper data management system or data management platform to assist in realizing the data management flow, and performing data mining and data analysis according to the collected data.

Formulating the data specification includes formulating a data naming specification, a data format specification and a data security specification. Illustratively, the data naming convention is to define a unified data naming convention, for example using hump nomenclature or underline nomenclature, etc. The data format specification is to determine the storage format and transmission format of the data, and to formulate the data precision and unit specification, for example, using CSV, JSON, XML and other storage and transmission formats, and to formulate the data precision to be 0.01 and the like. The data security specification is the policy establishment for backup and recovery of data.

In this embodiment, the original operation data is normalized, so that the consistency and safety of the collected data are ensured. Meanwhile, a stronger comparability foundation is provided for the follow-up fault analysis by using normalized data.

S203, determining whether abnormal operation data exist in the normalized original operation data according to the normalized original operation data and the acquisition time sequence thereof, and executing S204-S205 if the abnormal operation data exist in the normalized original operation data; if not, S206 is performed.

The acquisition time sequence is a sequence obtained by sequencing data according to the acquisition time.

Specifically, establishing the data management flow may further include data verification. Data verification illustratively includes checking for missing or anomalies in the collected data, i.e., the raw operational data. In one implementation manner, the acquired original operation data includes the identifier of the acquisition device and the acquisition time, so that the original operation data with the same identifier of the acquisition device can be ordered according to the acquisition time to obtain an acquisition time sequence. If the data at a certain time point in the acquisition time sequence is empty, the original operation data can be determined to be missing. In another implementation manner, the numerical range of the original operation parameters may be preset, and if the data at a certain time point in the original operation data exceeds the numerical range, the abnormality of the original operation data is determined. Besides the acquisition time sequence, a preset algorithm and a model can be used for determining whether abnormal operation data exist in the normalized original operation data, such as a standard score method, an isolated forest algorithm, a self-encoder neural network or a support vector machine algorithm.

If the original operation data after normalization processing and the acquisition time sequence are determined to have the original operation data missing and/or abnormal in the original operation data after normalization processing, the abnormal operation data can be determined to have. At this time, abnormal operation data may be displayed and an abnormal alarm may be triggered. If it is determined that there is no abnormal operation data, all the original operation data may be determined as target operation data.

S204, displaying abnormal operation data and triggering an abnormal alarm.

Specifically, when abnormal operation data exists in the normalized original operation data, the abnormal operation data is displayed to a user, and an abnormal alarm is triggered, so that the user can know the abnormal operation data in time.

S205, when feedback information of a user for abnormal alarm is received, marking and processing the abnormal operation data.

The method for processing the abnormal operation data comprises at least one of removing error data, filling missing data and modifying the error data.

Specifically, after triggering the abnormal alarm, the user can timely learn the condition of the abnormal operation data and feed back the abnormal alarm. At this time, feedback information of the user for abnormal alarm can be received, and abnormal data can be marked and processed. Illustratively, upon receiving feedback information from the user regarding the anomaly alarm, the user inputs "process the anomaly operation data", for example. At this time, the abnormal operation data can be marked and processed according to the abnormal problems of the abnormal operation data. In one implementation, the abnormal problem of the abnormal running data is that the abnormal running data is missing at a certain moment, the abnormal running data can be marked as 'missing abnormal running data', and 'filling the missing data' is carried out. In another implementation, the abnormal problem of the abnormal running data is that if the data exceeds the preset numerical range at a certain moment, the abnormal running data can be marked as "abnormal running data", and the abnormal running data is processed by "eliminating error data" and "modifying error data".

In this embodiment, according to the normalized raw operation data and the acquisition time sequence thereof, whether the normalized raw operation data has abnormal operation data or not is determined, when the abnormal operation data exists, the abnormal operation data is displayed, and an abnormal alarm is triggered, so that a user can timely learn the condition of the abnormal operation data. And the feedback information of the user aiming at the abnormal alarm is received, and the abnormal operation data is correspondingly marked and processed, so that the primary standardization and processing of the acquired data are realized, and the problem that the operation data is abnormal possibly caused by the temporary fault of the acquisition equipment is solved, thereby increasing the workload of the user.

S206, obtaining target operation data.

Specifically, the target operation data is original operation data after normalization processing, namely, the original operation data which does not have abnormal operation data after normalization processing and the operation data after marking and processing the abnormal operation data.

S207, inputting the target operation data into a pre-trained classification model, and determining the target fault type.

The training method of the classification model can be as follows:

Acquiring a training set, wherein the training set comprises at least one operation data sample, and one operation data sample is provided with a standard fault type label; inputting the current operation data sample into a classifier, and determining an actual fault type label of the current operation data sample; determining a loss function according to the standard fault type label and the actual fault type label; setting training ending conditions, wherein the training ending conditions comprise: the value of the loss function is smaller than or equal to a preset threshold value; converging a loss function; the current training times are equal to the maximum training times; if the training ending condition is met, determining the classifier as a classification model; and if the training ending condition is not met, adjusting parameters of the classifier according to the loss function, taking the next operation data sample as the current operation data sample, and returning to execute the step of inputting the current operation data sample into the classifier to determine the actual fault type label of the current operation data sample.

Illustratively, historical operation data is obtained, and the corresponding standard fault type is determined according to the historical operation data; inputting historical operation data carrying standard fault type labels into a classifier to obtain actual fault type labels; calculating a loss function of the current classifier according to the standard fault type label and the actual fault type label; if the current training ending condition is that the value of the loss function is smaller than or equal to a preset threshold value, determining whether the value of the loss function of the current classifier is smaller than or equal to the preset threshold value; if the training time is less than or equal to the preset threshold value, training is finished; if the value of the loss function of the classifier is smaller than or equal to the preset threshold value, the next historical operation data sample is continuously input into the classifier.

Specifically, after the target operation data are obtained, the target operation data are input into a pre-trained classification model, and the target fault type is determined.

In the embodiment, the target operation data is input into the pre-trained classification model to automatically determine the target fault type, namely, the classification model is utilized to detect the target operation data, so that the manual intervention is reduced, meanwhile, the error judgment of the operation data abnormality caused by the non-fault of the equipment is reduced, and the detection efficiency is improved. Meanwhile, continuous self-adaptive optimization of the classification model can be utilized, and the maintenance accuracy is gradually improved.

S208, basic corpus data of each transformation device is obtained, and an initial map is constructed according to the basic corpus data.

The basic corpus data of each power transformation device can be obtained through a power knowledge website or various power overhaul manuals. The basic corpus data comprises categories, names, component names, other electric power vocabularies, electric power industry terms and the like of the power transformation equipment.

Specifically, basic corpus data of each transformation device can be obtained, and an initial map is constructed according to the basic corpus data. For example, a knowledge-graph framework may be constructed from the base corpus data, and model elements such as entities, attributes, relationships, etc. may be determined to construct an initial graph.

S209, acquiring a historical operation fault analysis report of the target power transformation equipment, and determining an overhaul knowledge graph according to the historical operation fault analysis report and the initial graph.

Wherein the historical operational failure analysis report includes: substation equipment parameters such as specifications, performance indicators, operating conditions, etc.; the possible fault types of the power transformation equipment, the corresponding maintenance steps, methods, required tools, materials and the like; related power system documents such as historical maintenance records, expert experience, operating manuals, and maintenance guidelines.

Specifically, the historical operation fault analysis report is converted into a map format, and the construction of the overhaul knowledge map is completed based on the initial map. Illustratively, the historical operational failure analysis report is converted into a resource description framework or a graph database format, etc., and the construction of the overhaul knowledge graph can be accomplished using a graph construction tool or various programming languages. Meanwhile, after the overhaul knowledge graph is determined, the quality of the overhaul knowledge graph can be evaluated. For example, the integrity, accuracy and consistency of the data in the overhaul knowledge-graph are checked using automated testing or manual inspection. Meanwhile, other data can be utilized to verify the validity and practicability of the overhaul knowledge graph. After verification, optimizing the overhaul knowledge graph according to the result, correcting error content, supplementing missing information, and updating and expanding data in the overhaul knowledge graph at any time.

S210, determining a fault analysis report according to the target fault type.

The fault analysis report is a report obtained by analyzing the target fault type. The fault analysis report includes the specific type of fault, the possible cause of the fault, and the scope of impact of the fault.

Specifically, after determining the target fault type, a basic fault analysis report may be determined based on the target fault type. The fault analysis report records the specific type of fault, the possible cause of the fault and the scope of impact of the fault.

S211, determining an operation and maintenance scheme according to the fault analysis report and the pre-configured overhaul knowledge graph.

Specifically, according to the fault analysis report and a pre-configured overhaul knowledge graph, an operation and maintenance scheme can be determined. Illustratively, the fault analysis report is used as a query condition, and in a pre-configured overhaul knowledge graph, an operation and maintenance scheme matched with the target fault analysis report is searched based on parameters such as the specific type of the fault, the possible cause of the fault and the influence range of the fault. Since there may be multiple operation and maintenance schemes matching the target failure analysis report, the retrieved operation and maintenance schemes may also be screened and ranked, e.g., according to information such as applicability, feasibility, and historical success rate of the scheme. And finally determining a better operation and maintenance scheme or an operation and maintenance scheme determined according to the selection of a user.

Illustratively, in a template of an operation and maintenance scheme, the operation and maintenance scheme can be customized according to actual requirements and scenes. Which may include maintenance steps, tools required, materials required, personnel configuration, safety precautions, etc. And matching the maintenance knowledge graph with a better operation and maintenance scheme, or after determining the operation and maintenance scheme according to the selection of a user, filling the operation and maintenance scheme according to the content in a template of the operation and maintenance scheme to obtain the operation and maintenance scheme corresponding to the target power transformation equipment with the target fault type.

S212, inputting the target fault type into the overhaul model, and determining an operation and maintenance scheme.

Wherein, overhaul knowledge patterns are arranged in the overhaul model. Illustratively, the overhaul knowledge map may be configured in a model such as a large language model to form an overhaul model.

Specifically, in addition to the method as S210 to S211, it is also possible to select to directly input the target fault type into the overhaul model configured with the overhaul knowledge map, and determine an operation and maintenance scheme corresponding to the target power transformation device having the target fault type.

It should be noted that S210-S211 and S212 are parallel steps, i.e. during the practical application, S210-S211 and S212 may be alternatively executed.

In this embodiment, the fault analysis obtained by the target fault type is reported in the overhaul knowledge graph for retrieval, or the target fault type is directly input into the overhaul model configured with the overhaul knowledge graph, so as to obtain the operation and maintenance scheme, thereby solving the problem in the prior art that the user needs to determine the operation and maintenance scheme according to the target fault type, saving a great amount of time, realizing rapid determination of the better operation and maintenance scheme according to the target fault type, realizing intelligent management, reducing manual intervention, and improving the working efficiency.

According to the operation and maintenance method of the power transformation equipment, original operation data of the target power transformation equipment are collected, and normalized processing is carried out on the original operation data; determining whether abnormal operation data exists in the normalized original operation data according to the normalized original operation data and the acquisition time sequence thereof, displaying the abnormal operation data to a user if the abnormal operation data exists, triggering an abnormal alarm, and marking and processing the abnormal operation data when feedback information of the user for the abnormal alarm is received; if no abnormal operation data exists, the normalized original operation data can be directly used as target operation data; after the target operation data are obtained, inputting the target operation data into a pre-trained classification model, and determining the type of the target fault; basic corpus data of each transformation device is obtained, and an initial map is constructed according to the basic corpus data; acquiring a historical operation fault analysis report of the target power transformation equipment, and determining an overhaul knowledge graph according to the historical operation fault analysis report and the initial graph; after the overhaul knowledge graph is determined, a fault analysis report is determined according to the target fault type, and an operation and maintenance scheme is determined according to the fault analysis report and the pre-configured overhaul knowledge graph; or directly inputting the target fault type into the overhaul model to determine the operation and maintenance scheme. According to the technical scheme, on one hand, the original operation data is subjected to standardization processing, so that the consistency and the safety of the collected data are ensured. Meanwhile, a stronger comparability foundation is provided for the follow-up fault analysis by using normalized data. On the other hand, according to the original operation data after normalization processing and the acquisition time sequence thereof, determining whether the original operation data after normalization processing has abnormal operation data, displaying the abnormal operation data when the abnormal operation data exists, and triggering an abnormal alarm so that a user can know the condition of the abnormal operation data in time. And the feedback information of the user aiming at the abnormal alarm is received, and the abnormal operation data is correspondingly marked and processed, so that the primary standardization and processing of the acquired data are realized, and the problem that the operation data is abnormal possibly caused by the temporary fault of the acquisition equipment is solved, thereby increasing the workload of the user. On the other hand, the target operation data is input into the pre-trained classification model, so that the target fault type is automatically determined, namely, the target operation data is detected by using the classification model, so that the manual intervention is reduced, meanwhile, the error judgment of the operation data abnormality caused by the non-fault of the equipment is reduced, and the detection efficiency is improved. Meanwhile, continuous self-adaptive optimization of the classification model can be utilized, and the maintenance accuracy is gradually improved. Finally, the fault analysis obtained by the target fault type is reported in the overhaul knowledge graph for retrieval, or the target fault type is directly input into an overhaul model configured with the overhaul knowledge graph, so that an operation and maintenance scheme is obtained, the problem that a user needs to determine the operation and maintenance scheme according to the target fault type in the prior art is solved, a great amount of time is saved, and a better operation and maintenance scheme is quickly determined according to the target fault type, so that intelligent management is realized, manual intervention is reduced, and work efficiency is improved.

Fig. 4 is a schematic structural diagram of an operation and maintenance device of the power transformation equipment provided by the invention. As shown in fig. 4, the apparatus includes:

An obtaining module 401, configured to obtain target operation data of a target power transformation device;

the determining module 402 is configured to input the target operation data into a pre-trained classification model, and determine a target fault type, where the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm;

and the operation and maintenance module 403 is configured to determine an operation and maintenance scheme according to the target fault type, so that a user overhauls the target power transformation device according to the operation and maintenance scheme.

Optionally, the obtaining module 401 is specifically configured to:

Collecting original operation data of target power transformation equipment;

And carrying out standardization processing on the original operation data to obtain target operation data.

Optionally, the device further includes a preprocessing module, where after normalization processing is performed on the original operation data, the preprocessing module is configured to:

Determining whether abnormal operation data exists in the normalized original operation data according to the normalized original operation data and the acquisition time sequence thereof;

If abnormal operation data exist, displaying the abnormal operation data and triggering an abnormal alarm;

When feedback information of a user aiming at abnormal alarm is received, marking and processing the abnormal operation data, wherein the mode of processing the abnormal operation data comprises at least one of removing error data, filling the missing data and modifying the error data.

Optionally, the device further includes a classification model training module, and the classification model training module is specifically configured to:

Acquiring a training set, wherein the training set comprises at least one operation data sample, and one operation data sample is provided with a standard fault type label;

inputting the current operation data sample into a classifier, and determining an actual fault type label of the current operation data sample;

Determining a loss function according to the standard fault type label and the actual fault type label;

if the training ending condition is met, determining the classifier as a classification model;

If the training ending condition is not met, according to the loss function, adjusting parameters of the classifier, taking a next operation data sample as a current operation data sample, and returning to execute the step of inputting the current operation data sample into the classifier to determine an actual fault type label of the current operation data sample; wherein the training end condition includes at least one of: the value of the loss function is smaller than or equal to a preset threshold value; converging a loss function; the current training number is equal to the maximum training number.

Optionally, the operation and maintenance module 403 is specifically configured to:

determining a fault analysis report according to the target fault type;

And determining an operation and maintenance scheme according to the fault analysis report and the pre-configured overhaul knowledge graph, wherein the operation and maintenance scheme comprises user identification, overhaul steps and overhaul resources.

Optionally, the operation and maintenance module 403 is specifically configured to:

and inputting the target fault type into an overhaul model, and determining an operation and maintenance scheme, wherein an overhaul knowledge graph is arranged in the overhaul model, and the operation and maintenance scheme comprises a user identifier, overhaul steps and overhaul resources.

Optionally, the device further includes a maintenance knowledge graph construction module, before determining the fault analysis report according to the target fault type, or before inputting the target fault type into the maintenance model, the maintenance knowledge graph construction module is configured to:

Basic corpus data of each transformation device is obtained, and an initial map is constructed according to the basic corpus data;

And acquiring a historical operation fault analysis report of the target power transformation equipment, and determining an overhaul knowledge graph according to the historical operation fault analysis report and the initial graph.

The operation and maintenance device of the power transformation equipment provided by the embodiment of the invention can execute the operation and maintenance method of the power transformation equipment provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Fig. 5 is a schematic structural diagram of the electronic device 5 provided by the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 5 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 5 can also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

The various components in the electronic device 5 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 5 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the respective methods and processes described above, for example, the operation and maintenance method of the power transformation device.

In some embodiments, the method of operation and maintenance of the power transformation device may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 5 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the above-described operation and maintenance method of the power transformation device may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the method of operation of the substation device in any other suitable way (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. A method of operation and maintenance of a power transformation device, the method comprising:

acquiring target operation data of target power transformation equipment;

Inputting the target operation data into a pre-trained classification model to determine the target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm;

And determining an operation and maintenance scheme according to the target fault type, so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme.

2. The operation and maintenance method of a power transformation device according to claim 1, wherein the obtaining the target operation data of the target power transformation device includes:

collecting original operation data of the target power transformation equipment;

And carrying out standardization processing on the original operation data to obtain the target operation data.

3. The operation and maintenance method of the power transformation device according to claim 2, further comprising, after normalizing the raw operation data:

Determining whether abnormal operation data exists in the normalized original operation data according to the normalized original operation data and the acquisition time sequence thereof;

If the abnormal operation data exist, displaying the abnormal operation data and triggering an abnormal alarm;

And when feedback information of a user aiming at the abnormal alarm is received, marking and processing the abnormal operation data, wherein the mode of processing the abnormal operation data comprises at least one of removing error data, filling in missing data and modifying the error data.

4. The method of operation and maintenance of a power transformation device according to claim 1, wherein the method of training the classification model comprises:

acquiring a training set, wherein the training set comprises at least one operation data sample, and one operation data sample is provided with a standard fault type label;

inputting the current operation data sample into the classifier, and determining an actual fault type label of the current operation data sample;

determining a loss function according to the standard fault type tag and the actual fault type tag;

if the training ending condition is met, determining the classifier as the classification model;

If the training ending condition is not met, adjusting parameters of the classifier according to the loss function, taking a next operation data sample as a current operation data sample, and returning to execute the step of inputting the current operation data sample into the classifier to determine an actual fault type label of the current operation data sample;

Wherein the training end condition includes at least one of: the value of the loss function is smaller than or equal to a preset threshold value; the loss function converges; the current training number is equal to the maximum training number.

5. The method for operating and maintaining the power transformation device according to claim 1, wherein the determining an operation and maintenance scheme according to the target fault type comprises:

Determining a fault analysis report according to the target fault type;

And determining the operation and maintenance scheme according to the fault analysis report and a pre-configured overhaul knowledge graph, wherein the operation and maintenance scheme comprises a user identifier, an overhaul step and an overhaul resource.

6. The method for operating and maintaining the power transformation device according to claim 1, wherein the determining an operation and maintenance scheme according to the target fault type comprises:

inputting the target fault type into an overhaul model, and determining the operation and maintenance scheme, wherein an overhaul knowledge graph is arranged in the overhaul model, and the operation and maintenance scheme comprises a user identifier, an overhaul step and an overhaul resource.

7. The operation and maintenance method of a power transformation device according to claim 5 or 6, further comprising, before determining a fault analysis report according to the target fault type, or before inputting the target fault type into a overhaul model:

Basic corpus data of each transformation device is obtained, and an initial map is constructed according to the basic corpus data;

And acquiring a historical operation fault analysis report of the target power transformation equipment, and determining the overhaul knowledge graph according to the historical operation fault analysis report and the initial graph.

8. An operation and maintenance device for a power transformation device, comprising:

the acquisition module is used for acquiring target operation data of the target power transformation equipment;

The determining module is used for inputting the target operation data into a pre-trained classification model to determine the target fault type, wherein the classification model is a model obtained by training a classifier by using a machine learning algorithm or a deep learning algorithm;

and the operation and maintenance module is used for determining an operation and maintenance scheme according to the target fault type so that a user overhauls the target power transformation equipment according to the operation and maintenance scheme.

9. An electronic device, comprising:

One or more processors;

A memory for storing one or more programs,

The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of operation and maintenance of the power transformation device of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the operation and maintenance method of a power transformation device as claimed in any one of claims 1 to 7.