Zone area electric energy quality abnormity positioning method based on expert rules

Abstract

The invention discloses an expert rule-based transformer area electric energy quality abnormity positioning method. The method comprises the steps of obtaining electric energy quality data of a transformer area; preprocessing the obtained power quality data of the transformer area to generate a power quality database; generating an electric energy quality anomaly detection expert rule base based on the electric energy quality database and the electric energy quality anomaly expert experience; learning the historical electric energy quality database and the real-time electric energy quality data, and adaptively updating the expert rule base through a feedback mechanism; and in combination with the real-time electric energy quality database and the updated expert rule base, carrying out electric energy quality abnormity positioning and processing decision making, and carrying out electric energy quality abnormity positioning display. According to the invention, through updating the meta-learning algorithm and the dynamic rule base, novel and complex abnormal conditions can be rapidly adapted, and efficient power quality management is realized. According to the invention, the detection precision and the response speed of the system are improved, and important technical support is provided for the development of a future smart power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality anomaly positioning, and in particular to a method for positioning power quality anomaly in a substation based on expert rules. Background Art

[0002] With the development of modern power systems and the continuous increase in user electricity demand, power quality issues have become increasingly prominent, especially in distribution networks. The stability of power quality is directly related to the safe operation of the power system and the life of the user's power equipment. Power quality issues are mainly manifested in voltage deviation, frequency deviation, harmonic pollution, voltage fluctuation and flicker, etc. These problems may cause equipment damage, reduced operating efficiency, and even cause large-scale power outages. Therefore, the monitoring and management of power quality has become an important task in the operation of power systems.

[0003] At present, the detection and location of power quality anomalies mainly rely on expert experience and traditional machine learning algorithms. For example, methods such as random forests have been widely used in power quality anomaly detection. By learning from historical data, common power quality problems can be identified and located more accurately. However, these methods have certain limitations, especially when facing new or complex power quality anomalies. The generalization ability and adaptability of the model are poor, and it is impossible to respond to new power quality problems quickly and effectively. In addition, with the continuous expansion of the power system and the complexity of the power consumption environment, traditional methods often need to frequently adjust model parameters or retrain models when dealing with dynamic and diverse power quality anomalies, resulting in a decrease in system response speed and increased complexity of operation and maintenance. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a method for locating power quality anomalies in a substation based on expert rules, which overcomes the above problems or at least partially solves the above problems.

[0005] In order to solve the above technical problems, the embodiments of the present application disclose the following technical solutions:

[0006] In a first aspect, an embodiment of the present invention discloses a method for locating power quality anomalies in a substation based on expert rules, comprising:

[0007] Obtain the power quality data of the substation based on the power quality monitoring equipment, user-end equipment and historical database of the substation;

[0008] Pre-process the power quality data of the substation to generate a power quality database;

[0009] Generate an expert rule base for power quality anomaly detection based on the power quality database and power quality anomaly expert experience;

[0010] Using an irrelevant meta-learning algorithm to learn the historical power quality database and the real-time power quality data, and adaptively updating the expert rule base through a feedback mechanism;

[0011] Combined with the real-time power quality database and the updated expert rule base, power quality anomaly positioning and processing decisions are carried out, and the power quality anomaly positioning is displayed through a visualization tool.

[0012] Furthermore, according to the power quality monitoring equipment, user-end equipment and historical database of the substation, the power quality data of the substation is obtained, and the power quality data at least includes voltage, current, power factor, harmonics and voltage fluctuation.

[0013] Furthermore, the power quality data of the acquired substation is preprocessed to generate a power quality database; the preprocessing of the power quality data at least includes data cleaning, data filling, normalization processing and power quality abnormality feature extraction; wherein, the specific method of data cleaning includes: deduplication of data by identifying and deleting duplicate data; detecting abnormal values ​​by identifying abnormal values ​​through statistical analysis algorithms, and determining whether the abnormal values ​​are erroneous data, and if they are erroneous data, deleting or replacing the abnormal values ​​with reasonable values; and processing missing values ​​by using mean interpolation, median interpolation or most frequent value interpolation methods to determine missing data in the power quality data.

[0014] Furthermore, the specific methods of data filling, normalization processing and power quality abnormality feature extraction include: for numerical data, calculating the mean of the feature column and replacing the missing values ​​with the mean; for categorical data, using the mode of the column to fill the missing values; for time series data, using a linear interpolation method to fill in the linear relationship between the previous and next values ​​to obtain the power quality data after data filling; using Min-Max normalization or Z-score standardization method to normalize the filled power quality data; using time domain and frequency domain analysis methods to extract power quality abnormality features from the normalized power quality data.

[0015] Furthermore, the abnormal power quality characteristics include at least abnormal voltage characteristics, abnormal frequency characteristics, harmonic characteristics, transient characteristics, current characteristics and power characteristics.

[0016] Furthermore, based on the power quality database and the expert experience of power quality anomalies, an expert rule base for power quality anomaly detection is generated. The specific method includes: based on the power quality database and the expert experience of power quality anomalies, a preliminary expert rule base for power quality anomaly detection is created, and the rules formulated in the expert rule base judge the type of power quality anomaly through threshold judgment, waveform recognition, and harmonic analysis methods, including at least voltage anomaly, current anomaly, and frequency anomaly; the rule base contains multiple rules, each rule corresponds to a type of power quality anomaly, and the rules in the rule base should have clear names, descriptions, detection conditions and processing methods.

[0017] Furthermore, an irrelevant meta-learning algorithm is used to learn the historical power quality database and the real-time power quality data, and the expert rule base is adaptively updated through a feedback mechanism. The specific method includes:

[0018] Divide the historical power quality database into multiple training tasks, each of which contains a set of power anomaly features and power quality levels; initialize the training model, and for each training task, use a small amount of data to perform gradient updates to fine-tune the model parameters; repeat this process on all tasks to optimize the overall performance of the model;

[0019] Real-time power quality data is acquired through power quality monitoring equipment and user-end equipment, and the data is preprocessed, including cleaning, feature extraction and standardization; the initial parameters obtained by training with an irrelevant meta-learning algorithm are used to quickly adapt the real-time power quality data to obtain an updated training model; new real-time power quality data is continuously collected and used to update the training model, and the performance of the training model is regularly evaluated and the model is fine-tuned as needed to obtain the optimal training model.

[0020] Furthermore, the training model update strategy at least includes regularly checking existing rules, replacing invalid rules, adding new rules, and optimizing existing rules; wherein:

[0021] Regularly check existing rules: The system regularly checks each rule in the rule base to evaluate whether it is still applicable to the current environment. If it is found that some rules are no longer valid under the existing data conditions, the system will mark these rules as invalid;

[0022] Replace invalid rules: For rules marked as invalid, the system will automatically generate new rules to replace them based on the output of the adaptive learning module. The new rules will overwrite the old rules to ensure that the rule base is updated with the times;

[0023] Add new rules: When the system detects a new abnormal power quality pattern or a new feature, it will automatically generate and add the corresponding rules to the rule base to expand the coverage of the rule base;

[0024] Optimize existing rules: For existing rules, the system will adjust thresholds or optimize conditions based on actual operating conditions and data analysis results, so that these rules can more accurately describe the power quality status of the substation.

[0025] Furthermore, in combination with the real-time power quality database and the updated expert rule base, power quality anomaly positioning and processing decisions are carried out. The specific method includes: inputting the real-time collected power quality data into the rule base, performing power quality anomaly detection, judging whether there is power quality anomaly according to the rules in the rule base, and if power quality anomaly is detected, taking corresponding processing measures according to the processing method in the rule base; the processing measures at least include reducing the impact of abnormal sources, optimizing power quality, and implementing power quality improvement projects; providing feedback on the processing results, evaluating the effectiveness of the rule base, and making necessary adjustments and improvements to the rule base according to the feedback results.

[0026] In a second aspect, an embodiment of the present invention discloses an electronic device, including:

[0027] one or more processors;

[0028] A memory for storing one or more programs;

[0029] When the one or more programs are executed by the one or more processors, the one or more processors implement the power quality anomaly locating method.

[0030] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0031] The present invention discloses a method for locating power quality anomalies in a substation based on expert rules, including: obtaining power quality data of the substation according to the power quality monitoring equipment, user-end equipment and historical database of the substation; preprocessing the power quality data of the substation to generate a power quality database; generating a power quality anomaly detection expert rule base based on the power quality database and the power quality anomaly expert experience; using an irrelevant meta-learning algorithm to learn the historical power quality database and real-time power quality data, and adaptively updating the expert rule base through a feedback mechanism; combining the real-time power quality database and the updated expert rule base to locate power quality anomalies and make processing decisions, and display the power quality anomaly location through a visualization tool. The present invention can quickly adapt to new and complex abnormal situations and realize efficient power quality management through the update of the meta-learning algorithm and the dynamic rule base. The present invention not only improves the detection accuracy and response speed of the system, but also provides important technical support for the development of future smart grids.

[0032] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0034] Figure 1 This is a flow chart of a method for locating power quality anomalies in a substation based on expert rules in Embodiment 1 of the present invention;

[0035] Figure 2 This is a schematic diagram of the structure of an electronic device in Embodiment 2 of the present invention. DETAILED DESCRIPTION

[0036] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0037] In order to solve the problems existing in the prior art, an embodiment of the present invention provides a method for locating power quality anomalies in a substation based on expert rules.

[0038] Example 1

[0039] The present invention discloses a method for locating power quality anomalies in a substation based on expert rules, such as Figure 1 ,include:

[0040] S100.According to the power quality monitoring equipment, user-end equipment and historical database of the substation, the power quality data of the substation is obtained; wherein, the substation is an important concept in the power system. The substation refers to the power supply range or area of ​​(one or more) transformers. It is a special term for power economic operation management and one of the important basic data for distribution information integration. In the power system, the substation usually refers to the area where the transformer supplies power to the user, and the user is connected through low-voltage lines to form a power supply network radiating to the surrounding areas.

[0041] Specifically, the power quality data of the substation is obtained based on the power quality monitoring equipment, user-end equipment and historical database of the substation, and the power quality data at least includes voltage, current, power factor, harmonics and voltage fluctuation. Power quality-related data is obtained from various sensors and historical databases to ensure data diversity and timeliness.

[0042] S200. Preprocess the power quality data of the acquired substation to generate a power quality database; specifically, preprocess the power quality data of the acquired substation to generate a power quality database; the preprocessing of the power quality data at least includes data cleaning, data filling, normalization processing and power quality abnormality feature extraction; by preprocessing the power quality data of the acquired substation, the quality of data input into the training model is ensured.

[0043] In this embodiment, the specific method of data cleaning includes: deduplicating data by identifying and deleting duplicate data; detecting outliers by identifying outliers through a statistical analysis algorithm to determine whether the outliers are erroneous data, and if they are erroneous data, deleting or replacing the outliers with reasonable values; processing missing values ​​using mean interpolation, median interpolation, or most frequent value interpolation methods to determine missing data in the power quality data.

[0044] In this embodiment, the specific methods of data filling, normalization processing and power quality abnormality feature extraction include: for numerical data, calculating the mean of the feature column and replacing the missing values ​​with the mean; for categorical data, using the mode of the column to fill the missing values; for time series data, using a linear interpolation method to fill according to the linear relationship between the previous and next values ​​to obtain the power quality data after data filling; using Min-Max normalization or Z-score standardization method to normalize the filled power quality data; using time domain and frequency domain analysis methods to extract power quality abnormality features from the normalized power quality data.

[0045] In this embodiment, power quality refers to the quality of electric energy in the power system, which is related to the stability and reliability of the power system, as well as the safety and economy of electricity use by users. In a strict sense, the main indicators for measuring the quality of power quality include voltage, frequency and waveform. Voltage quality involves voltage deviation, voltage fluctuation and flicker, three-phase imbalance, etc.; frequency quality mainly examines frequency deviation; and waveform quality focuses on waveform distortion (such as harmonics), voltage sag, interruption, temporary rise, etc. These indicators together constitute the evaluation system of power quality. In this embodiment, the abnormal power quality characteristics include at least abnormal voltage characteristics, abnormal frequency characteristics, harmonic characteristics, transient characteristics, current characteristics and power characteristics. By collecting and analyzing these characteristics, important basis and guidance can be provided for early warning and troubleshooting of abnormal power quality. According to the results of data analysis, it may be necessary to establish a model for prediction and classification to improve the intelligent level of power quality monitoring.

[0046] S300. Based on the power quality database and the power quality anomaly expert experience, generate the power quality anomaly detection expert rule base; In this embodiment, based on the power quality database and the power quality anomaly expert experience, generate the power quality anomaly detection expert rule base, the specific method includes: based on the power quality database and the power quality anomaly expert experience, create a preliminary power quality anomaly detection expert rule base, the rules formulated by the expert rule base judge the power quality anomaly type through threshold judgment, waveform recognition, harmonic analysis method, at least including voltage anomaly, current anomaly, frequency anomaly; the rule base contains multiple rules, each rule corresponds to a power quality anomaly type, the rules in the rule base should have a clear name, description, detection conditions and processing methods. For example, when the voltage fluctuation amplitude exceeds ±10%, it is determined to be a voltage anomaly, when the current harmonic content exceeds 5%, it is determined to be a current harmonic anomaly, and when the frequency deviates from the standard frequency by more than ±0.5Hz, it is determined to be a frequency anomaly.

[0047] Among them, the rule generation method includes creating a set of initial rules based on the extracted features and expert experience. These rules are usually expressed in logical expressions, decision trees or other forms, defining the actions that should be taken (such as triggering an alarm) when certain conditions (such as voltage below a certain threshold) are met. The rule base construction method includes storing the generated rules in a rule base, which can be stored in the form of a JSON file or a database to facilitate subsequent calls and updates.

[0048] Through the above steps, a comprehensive, accurate and effective power quality anomaly detection expert rule base can be generated based on the power quality database and power quality anomaly expert experience. This rule base will help improve the accuracy and efficiency of power quality monitoring and provide a strong guarantee for the stable operation of the power system.

[0049] S400. Using an irrelevant meta-learning algorithm to learn the historical power quality database and the real-time power quality data, and adaptively updating the expert rule base through a feedback mechanism;

[0050] Specifically, model-agnostic meta-learning (MAML) is a meta-learning algorithm that trains an initialization model so that it can quickly learn and adapt when faced with new tasks. Specifically, MAML trains on multiple tasks so that the initial parameters of the model can quickly adapt to new tasks through a small amount of gradient updates. Therefore, this method is very suitable for adaptive learning in power quality anomaly detection. In this embodiment, the input data includes power quality parameters such as voltage, frequency, total harmonic distortion (THD), power factor, etc. The model training tasks are different power quality anomaly detection tasks, such as voltage sag, frequency anomaly, etc.; model output: predicted label of power quality status.

[0051] In this embodiment, an irrelevant meta-learning algorithm is used to learn the historical power quality database and the real-time power quality data, and the expert rule base is adaptively updated through a feedback mechanism. The specific method includes:

[0052] Divide the historical power quality database into multiple training tasks, each of which contains a set of power anomaly features and power quality levels; initialize the training model, and for each training task, use a small amount of data to perform gradient updates to fine-tune the model parameters; repeat this process on all tasks to optimize the overall performance of the model;

[0053] Real-time power quality data is acquired through power quality monitoring equipment and user-end equipment, and the data is preprocessed, including cleaning, feature extraction and standardization; the initial parameters obtained by training with an irrelevant meta-learning algorithm are used to quickly adapt the real-time power quality data to obtain an updated training model; new real-time power quality data is continuously collected and used to update the training model, and the performance of the training model is regularly evaluated and the model is fine-tuned as needed to obtain the optimal training model.

[0054] By adopting the irrelevant meta-learning algorithm of this embodiment, it is possible to quickly adapt to new tasks. By pre-training on multiple related tasks, the model can quickly adapt to new tasks with only a small amount of gradient updates. The model trained by the irrelevant meta-learning algorithm has stronger generalization ability and can better handle unseen power quality anomalies. The irrelevant meta-learning algorithm can quickly adjust the model according to real-time data to achieve dynamic updates of the expert rule base.

[0055] In this embodiment, the training model update strategy at least includes regularly checking existing rules, replacing invalid rules, adding new rules, and optimizing existing rules; wherein:

[0056] Regularly check existing rules: The system regularly checks each rule in the rule base to evaluate whether it is still applicable to the current environment. If it is found that some rules are no longer valid under the existing data conditions, the system will mark these rules as invalid;

[0057] Replace invalid rules: For rules marked as invalid, the system will automatically generate new rules to replace them based on the output of the adaptive learning module. The new rules will overwrite the old rules to ensure that the rule base is updated with the times;

[0058] Add new rules: When the system detects a new abnormal power quality pattern or a new feature, it will automatically generate and add the corresponding rules to the rule base to expand the coverage of the rule base;

[0059] Optimize existing rules: For existing rules, the system will adjust thresholds or optimize conditions based on actual operating conditions and data analysis results, so that these rules can more accurately describe the power quality status of the substation.

[0060] S500. Combine the real-time power quality database and the updated expert rule base to locate power quality anomalies and make processing decisions, and display the power quality anomaly location through a visualization tool.

[0061] In this embodiment, the real-time power quality database and the updated expert rule base are combined to locate power quality anomalies and make processing decisions. The specific method includes: inputting the real-time collected power quality data into the rule base, performing power quality anomaly detection, judging whether there is power quality anomaly according to the rules in the rule base, and if the power quality anomaly is detected, taking corresponding processing measures according to the processing method in the rule base; the processing measures at least include reducing the impact of the abnormal source, optimizing the power quality, and implementing power quality improvement projects; feedback is given to the processing results, the effectiveness of the rule base is evaluated, and the rule base is adjusted and improved as necessary according to the feedback results. Combining the real-time power quality database and the updated expert rule base to locate power quality anomalies and make processing decisions is a complex and systematic process that requires efforts and collaboration from many aspects. Through continuous optimization and improvement, rapid response and effective processing of power quality problems can be achieved to ensure the stable operation of the power grid and the power quality of users.

[0062] The present embodiment discloses a method for locating power quality anomalies in a substation based on expert rules, including: obtaining power quality data of the substation according to the power quality monitoring equipment, user-end equipment and historical database of the substation; preprocessing the power quality data of the substation to generate a power quality database; generating a power quality anomaly detection expert rule base based on the power quality database and the power quality anomaly expert experience; using an irrelevant meta-learning algorithm to learn the historical power quality database and real-time power quality data, and adaptively updating the expert rule base through a feedback mechanism; combining the real-time power quality database and the updated expert rule base to locate and process power quality anomalies, and displaying the power quality anomaly location through a visualization tool. The present invention can quickly adapt to new and complex abnormal situations and realize efficient power quality management through the update of the meta-learning algorithm and the dynamic rule base. The present invention not only improves the detection accuracy and response speed of the system, but also provides important technical support for the development of future smart grids.

[0063] Example 2

[0064] Based on the same inventive concept, an embodiment of the present disclosure also provides an electronic device. Figure 2 FIG. 1 is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. Figure 2 As shown, an embodiment of the present disclosure provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement any optimization method in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, and are configured to implement information interaction between the processor and the memory.

[0065] Among them, the processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus), etc.

[0066] In some embodiments, the processor 101 , the memory 102 , and the I / O interface 103 are connected to each other via a bus 104 , and further connected to other components of the computing device.

[0067] In some embodiments, the one or more processors 101 include a field programmable gate array.

[0068] According to an embodiment of the present disclosure, a computer-readable medium is further provided, wherein a computer program is stored on the computer-readable medium, wherein when the program is executed by a processor, the steps in any optimization method in the above-mentioned embodiment are implemented.

[0069] It should be understood that the specific order or hierarchy of steps in the disclosed process is an example of an exemplary method. Based on design preferences, it should be understood that the specific order or hierarchy of steps in the process can be rearranged without departing from the scope of protection of the present disclosure. The attached method claims present the elements of the various steps in an exemplary order and are not intended to be limited to the specific order or hierarchy described.

[0070] In the above detailed description, various features are grouped together in a single embodiment to simplify the disclosure. This method of disclosure should not be interpreted as reflecting an intention that the embodiments of the claimed subject matter require more features than are clearly stated in each claim. On the contrary, as reflected in the appended claims, the invention is in a state of having less than all the features of the disclosed individual embodiments. Therefore, the appended claims are hereby expressly incorporated into the detailed description, with each claim standing on its own as a separate preferred embodiment of the invention.

[0071] Those skilled in the art will also appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments herein can all be implemented as electronic hardware, computer software, or a combination thereof. In order to clearly illustrate the interchangeability between hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above around their functions. Whether such functions are implemented as hardware or software depends on specific applications and the design constraints imposed on the entire system. A skilled person can implement the described functions in an alternative manner for each specific application, but such implementation decisions should not be interpreted as departing from the scope of protection of the present disclosure.

[0072] The steps of the method or algorithm described in conjunction with the embodiments herein may be directly embodied as hardware, a software module executed by a processor, or a combination thereof. The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a mobile disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is connected to the processor so that the processor can read information from the storage medium and can write information to the storage medium. Of course, the storage medium may also be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The ASIC may be located in a user terminal. Of course, the processor and the storage medium may also be present in a user terminal as discrete components.

[0073] For software implementation, the techniques described in this application can be implemented with modules (e.g., procedures, functions, etc.) that perform the functions described in this application. These software codes can be stored in a memory unit and executed by a processor. The memory unit can be implemented within the processor or outside the processor. In the latter case, it is coupled to the processor in a communication manner via various means, which are well known in the art.

[0074] The above description includes examples of one or more embodiments. Of course, it is impossible to describe all possible combinations of components or methods for the purpose of describing the above embodiments, but it should be recognized by those skilled in the art that the various embodiments may be further combined and arranged. Therefore, the embodiments described herein are intended to cover all such changes, modifications and variations that fall within the scope of protection of the appended claims. In addition, with respect to the term "comprising" used in the specification or claims, the word is covered in a manner similar to the term "including", just as "including," is explained as a transitional word in the claims. In addition, any term "or" used in the specification of the claims is intended to mean "non-exclusive or".

Claims

1. A method for locating power quality anomalies in a substation based on expert rules, characterized in that: include: Obtain the power quality data of the substation based on the power quality monitoring equipment, user-end equipment and historical database of the substation; Pre-process the power quality data of the substation to generate a power quality database; Generate an expert rule base for power quality anomaly detection based on the power quality database and power quality anomaly expert experience; Using an irrelevant meta-learning algorithm to learn the historical power quality database and the real-time power quality data, and adaptively updating the expert rule base through a feedback mechanism; Combined with the real-time power quality database and the updated expert rule base, power quality anomaly positioning and processing decisions are carried out, and the power quality anomaly positioning is displayed through a visualization tool.

2. The method for locating power quality anomalies in a substation based on expert rules according to claim 1, characterized in that: The power quality data of the substation is obtained according to the power quality monitoring equipment, user-end equipment and historical database of the substation, and the power quality data at least includes voltage, current, power factor, harmonics and voltage fluctuation.

3. The method for locating power quality anomalies in a substation based on expert rules according to claim 1, characterized in that: Pre-process the power quality data of the substation to generate a power quality database; The preprocessing of the power quality data at least includes data cleaning, data filling, normalization processing and power quality abnormality feature extraction; wherein, the specific method of data cleaning includes: deduplication of data by identifying and deleting duplicate data; detecting outliers by identifying outliers through statistical analysis algorithms, and determining whether the outliers are erroneous data. If they are erroneous data, deleting or replacing the outliers with reasonable values; processing missing values ​​by using mean interpolation, median interpolation or most frequent value interpolation methods to determine missing data in the power quality data.

4. The method for locating power quality anomalies in a substation based on expert rules as claimed in claim 3, characterized in that: The specific methods of data filling, normalization processing and power quality abnormality feature extraction include: for numerical data, calculating the mean of the feature column and replacing the missing values ​​with the mean; for categorical data, using the mode of the column to fill the missing values; for time series data, using a linear interpolation method to fill the data according to the linear relationship between the previous and next values ​​to obtain the power quality data after data filling; using Min-Max normalization or Z-score standardization method to normalize the filled power quality data; using time domain and frequency domain analysis methods to extract power quality abnormality features from the normalized power quality data.

5. The method for locating power quality anomalies in a substation based on expert rules as claimed in claim 4, characterized in that: The abnormal power quality characteristics include at least abnormal voltage characteristics, abnormal frequency characteristics, harmonic characteristics, transient characteristics, current characteristics and power characteristics.

6. The method for locating power quality anomalies in a substation based on expert rules according to claim 1, characterized in that: Based on the power quality database and the expert experience of power quality anomalies, an expert rule base for power quality anomaly detection is generated. The specific method includes: based on the power quality database and the expert experience of power quality anomalies, a preliminary expert rule base for power quality anomaly detection is created, and the rules formulated by the expert rule base judge the type of power quality anomaly through threshold judgment, waveform recognition, and harmonic analysis methods, including at least voltage anomaly, current anomaly, and frequency anomaly; the rule base contains multiple rules, each rule corresponds to a type of power quality anomaly, and the rules in the rule base should have clear names, descriptions, detection conditions and processing methods.

7. The method for locating power quality anomalies in a substation based on expert rules according to claim 1, characterized in that: The irrelevant meta-learning algorithm is used to learn the historical power quality database and the real-time power quality data, and the expert rule base is adaptively updated through a feedback mechanism. The specific method includes: Divide the historical power quality database into multiple training tasks, each of which contains a set of power anomaly features and power quality levels; initialize the training model, and for each training task, use a small amount of data to perform gradient updates to fine-tune the model parameters; repeat this process on all tasks to optimize the overall performance of the model; Real-time power quality data is acquired through power quality monitoring equipment and user-end equipment, and the data is preprocessed, including cleaning, feature extraction and standardization; the initial parameters obtained by training with an irrelevant meta-learning algorithm are used to quickly adapt the real-time power quality data to obtain an updated training model; new real-time power quality data is continuously collected and used to update the training model, and the performance of the training model is regularly evaluated and the model is fine-tuned as needed to obtain the optimal training model.

8. The method for locating power quality anomalies in a substation based on expert rules as claimed in claim 7, characterized in that: The training model update strategy at least includes regularly checking existing rules, replacing invalid rules, adding new rules, and optimizing existing rules; wherein: Regularly check existing rules: The system regularly checks each rule in the rule base to evaluate whether it is still applicable to the current area environment. If it is found that some rules are no longer valid under the existing data conditions, the system will mark these rules as invalid; Replace invalid rules: For rules marked as invalid, the system will automatically generate new rules to replace them based on the output of the adaptive learning module. The new rules will overwrite the old rules to ensure that the rule base is updated with the times; Add new rules: When the system detects a new abnormal power quality pattern or a new feature, it will automatically generate and add the corresponding rules to the rule base to expand the coverage of the rule base; Optimize existing rules: For existing rules, the system will adjust thresholds or optimize conditions based on actual operating conditions and data analysis results, so that these rules can more accurately describe the power quality status of the substation.

9. The method for locating power quality anomalies in a substation based on expert rules according to claim 1, characterized in that: Combined with the real-time power quality database and the updated expert rule base, power quality anomaly positioning and processing decision are carried out. The specific method includes: inputting the real-time collected power quality data into the rule base, performing power quality anomaly detection, judging whether there is power quality anomaly according to the rules in the rule base, and if power quality anomaly is detected, taking corresponding processing measures according to the processing method in the rule base; the processing measures at least include reducing the impact of abnormal sources, optimizing power quality, and implementing power quality improvement projects; providing feedback on the processing results, evaluating the effectiveness of the rule base, and making necessary adjustments and improvements to the rule base according to the feedback results.

10. An electronic device comprising: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method for locating power quality anomalies as described in any one of claims 1 to 9.

Images