Automatic fault early warning method for reactive power compensation device

Abstract

The invention discloses a reactive power compensation device fault automatic early warning method, and belongs to the technical field of reactive power compensation device power grid power factor correction. According to the method, various operation data are collected, early warning analysis is carried out on electric quantity data and the operation data, and abnormal early warning is generated. According to the method, a fault analysis and diagnosis model is constructed and trained according to historical fault data and a fault case library, early warning information is subjected to multi-source data fusion and then input into the model, and a final diagnosis result is obtained. And finally, calling a reactive compensation strategy and a disposal suggestion from a database according to a diagnosis result. According to the method, multi-source data fusion and intelligent diagnosis are adopted, comprehensive and deep early warning and diagnosis can be realized, the power quality of the power grid and the fault handling efficiency are remarkably improved, and the operation and maintenance cost is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of reactive power compensation device power factor correction, in particular to a reactive power compensation device fault automatic early warning method. BACKGROUND

[0002] The reactive power compensation device is a key equipment in the power system for improving the power factor of the power grid, reducing line loss and improving voltage quality. It provides capacitive reactive power to the power grid through the switching of capacitor banks or the adjustment of static reactive power generators, to balance the reactive power consumed by inductive loads. Real-time monitoring of the operating state of the reactive power compensation device and timely detection of potential faults are crucial for ensuring the safe, stable and economic operation of the power system. Existing reactive power compensation device fault warning methods usually rely on simple threshold monitoring of the device's own operating parameters. For example, when the current of the capacitor exceeds the set value or the temperature is too high, the system will issue an alarm. Some methods also monitor the power factor of the power grid, and trigger an alarm when the power factor is below the set lower limit. These methods are mainly based on static threshold judgment of a single data source, and use a pre-set fixed rule base to issue fault alarms.

[0003] However, the above-mentioned prior art has obvious technical defects. Since only a single data source is used for judgment, when the power grid load fluctuates normally, it may also cause the power factor to decrease temporarily or the device parameters to jump instantaneously, thus causing frequent false alarms. Conversely, for some early-stage faults that develop slowly and have no obvious characteristics, such as slight dielectric aging of the capacitor or gradual contact failure of the connection point, the parameter changes may be within the normal range for a long time, making it difficult for existing methods to effectively detect them, resulting in missed alarms until the fault is discovered. SUMMARY

[0004] To solve the above problems, the present application provides a reactive power compensation device fault automatic early warning method, which combines multi-source data fusion analysis with a time series diagnosis model, and can realize early and accurate warning and self-adaptive disposal of the faults of the reactive power compensation device.

[0005] The above-mentioned object can be achieved by the following scheme: The application discloses a kind of reactive power compensation device failure automatic early warning method, comprising: collecting the real-time operation data of reactive power compensation device, real-time power data of power grid, historical data, failure data and failure case base;Real-time power data is carried out early warning analysis, when the real-time power data of power grid exceeds preset threshold, power data abnormal early warning is obtained;Real-time operation data is analyzed with key parameter change trend, and the equipment failure early warning of early failure hidden danger is obtained;According to the failure data and failure case base, time series algorithm is used to construct and train failure analysis diagnosis model, and the trained failure analysis diagnosis model is obtained;The power data abnormal early warning and equipment failure early warning are fused by multi-source data, and the final failure diagnosis result is generated by generating comprehensive failure diagnosis and inputting into failure analysis diagnosis model;According to the final failure diagnosis result, corresponding reactive power compensation strategy and failure disposal suggestion are retrieved from the database that is stored with multiple reactive power compensation strategies and failure disposal suggestions, to realize the correction of power factor in power data.

[0006] Optionally, the method further comprises: according to the output reactive power compensation strategy, automatically adjusting the operating parameters of the reactive power compensation device through a closed-loop control mechanism to realize the correction of the power factor;Obtain the operating effect data after adjusting the operating parameters of the reactive power compensation device, and update the final failure diagnosis result, the executed reactive power compensation strategy and the operating effect data to the failure case base as new failure cases.

[0007] Optionally, the collection of real-time operation data of reactive power compensation device, real-time power data of power grid, historical data, failure data and failure case base comprises: the real-time operation data includes temperature, vibration and noise when the reactive power compensation device is running;The real-time power data of power grid includes reactive power, active power, power factor, harmonic current, negative sequence current and three-phase voltage of power grid;The historical data includes historical operation data and historical power data of reactive power compensation device;The failure data is the historical failure of reactive power compensation device, including power data abnormal failure and equipment failure;The failure case base is constructed based on analysis and mining of the failure data, and has failure type label, evolution law and verified historical disposal strategy corresponding to different failure types in an associated form.

[0008] Optionally, the early warning analysis on the real-time power data comprises: setting the preset threshold of power factor, reactive power, harmonic current, negative sequence current and three-phase voltage according to the historical data;Determine whether the power factor of power grid continuously exceeds the preset threshold or any one of the reactive power, harmonic current, negative sequence current and three-phase voltage exceeds the safety limit value specified by the related standard or continuously exceeds the respective preset threshold, yes, generate power data abnormal early warning, wherein the early warning is used to indicate that the power factor of power grid is abnormal or the power quality is decreased, no, continuously monitor the power data.

[0009] Optionally, the real-time operation data is analyzed for early fault warning by a key parameter change trend to obtain an early fault hidden danger device fault warning, comprising: constructing a machine learning model for anomaly detection, unsupervised training the machine learning model with the historical operation data to obtain a normal operation baseline model; inputting the real-time operation data into the normal operation baseline model for analysis, calculating a deviation value between the real-time operation data and the normal operation baseline, wherein the deviation value is used to represent the degree of deviation of the real-time operation data from the normal state; when the deviation value continuously exceeds a normal fluctuation range, obtaining an early fault hidden danger device fault warning, the normal fluctuation range being obtained from the historical operation data and a fault case library.

[0010] Optionally, the machine learning model for anomaly detection is constructed, and the machine learning model is unsupervised trained with the historical operation data, comprising: statistically analyzing the historical operation data, and extracting statistical features of the historical operation data, wherein the statistical features include mean, variance, standard deviation and kurtosis of the operation data; unsupervised training the machine learning model with the statistical features to obtain a normal baseline model capable of calculating a deviation value between the operation data and the normal operation baseline.

[0011] Optionally, the fault analysis diagnosis model is constructed and trained by using a time series algorithm according to the fault data and the fault case library to obtain a trained fault analysis diagnosis model, comprising: constructing an initial fault analysis diagnosis model capable of learning time series dependency relationship by using a long short-term memory network algorithm; mapping the fault data and corresponding fault type labels in the fault case library to form a training sample set; iteratively training the initial fault analysis diagnosis model using the training sample set, and optimizing model parameters until its diagnosis performance converges to obtain the trained fault analysis diagnosis model.

[0012] Optionally, the power data anomaly warning and the device fault warning are fused for multi-source data to generate a comprehensive fault diagnosis and input into the fault analysis diagnosis model to generate a final fault diagnosis result, comprising: assigning corresponding confidence and priority weight to the power data anomaly warning and the device fault warning, performing weighted decision processing to generate fusion data; formatting the fusion data to generate a comprehensive fault diagnosis capable of being received by the trained fault analysis diagnosis model; inputting the comprehensive fault diagnosis into the fault analysis diagnosis model, and the fault analysis diagnosis model outputting a final fault diagnosis result.

[0013] Optionally, according to the final fault diagnosis result, corresponding reactive power compensation strategy and fault handling suggestion are retrieved and output from a preset database storing a plurality of reactive power compensation strategies and fault handling suggestions, including: using the fault type label contained in the final fault diagnosis result as a retrieval index; matching and retrieving corresponding reactive power compensation strategy and fault handling suggestion in the database storing a plurality of reactive power compensation strategies and fault handling suggestions through the retrieval index; combining the reactive power compensation strategy and the fault handling suggestion into a structured handling scheme and outputting.

[0014] Based on the same inventive concept, the present application also provides an automatic early warning system for reactive power compensation device faults, which comprises: a data acquisition module for acquiring real-time operation data of a reactive power compensation device, real-time power data of a power grid, historical data, fault data and a fault case library; a warning analysis module for performing warning analysis on the real-time power data to generate power data anomaly warning and performing key parameter change trend analysis on the real-time operation data to generate device fault warning; a model construction module for constructing and training a fault analysis diagnosis model based on the fault data and the fault case library by using a time series algorithm to obtain a trained fault analysis diagnosis model; a data fusion module for performing multi-source data fusion on the power data anomaly warning and the device fault warning to generate comprehensive fault diagnosis; a diagnosis analysis module for inputting the comprehensive fault diagnosis into the trained fault analysis diagnosis model to obtain a final fault diagnosis result; and a handling output module for retrieving and outputting corresponding reactive power compensation strategy and fault handling suggestion from a preset database storing a plurality of reactive power compensation strategies and fault handling suggestions according to the final fault diagnosis result.

[0015] Compared with the prior art, the present application has the following advantages: 1. The present application realizes the cooperative judgment from macro power quality fluctuation to micro device state anomaly by analyzing power grid power data and device operation data in parallel and inputting the resulting double warning signals into a diagnosis model. This multi-dimensional and multi-level analysis method effectively distinguishes external power grid disturbance from device self-fault, significantly improves the accuracy of fault warning, and avoids false alarms or missed alarms caused by misjudgment of a single data source.

[0016] 2. The fault analysis diagnosis model constructed by the present application utilizes the deep learning capability of the time series algorithm to autonomously explore and understand the dynamic fault evolution pattern hidden behind complex operation data. This makes the diagnosis result no longer limited to simple "yes" or "no" judgment, but can accurately identify the specific fault type, laying a solid foundation for subsequent targeted and efficient handling measures, realizing the intelligent upgrade from "finding problems" to "locating roots".

[0017] 3、The present application establishes a complete closed loop from intelligent diagnosis to automatic disposal and self-optimization. Not only can the optimal reactive power compensation strategy be automatically retrieved and executed to quickly stabilize the power grid according to the accurate diagnosis result, but also the experience of each fault handling can be fed back to the fault case library for continuous learning and iteration of the model. This adaptive and self-evolutionary capability ensures that the system can maintain high efficiency and reliability for a long time and continuously adapt to changes in the power grid environment.

[0018] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0020] Figure 1 is a flowchart of a fault automatic early warning method of a reactive power compensation device according to an embodiment of the present application.

[0021] Figure 2 is a fault early warning logic flowchart according to an embodiment of the present application.

[0022] Figure 3 is a model training and diagnosis flowchart according to an embodiment of the present application.

[0023] Figure 4 is a structure diagram of a fault automatic early warning system of a reactive power compensation device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the following will combine the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0025] Reference Figure 1One embodiment of the present application proposes a reactive power compensation device failure automatic early warning method. The method combines multi-source data fusion analysis and time series diagnosis model, can realize early and accurate warning and self-adaptive disposal of reactive power compensation device failure, significantly improves the power quality and failure disposal efficiency of the power grid, and reduces the operation and maintenance cost and the professional ability requirement of the operation personnel.

[0026] The method of the embodiment specifically includes: Collecting real-time operation data of the reactive power compensation device, real-time power data of the power grid, historical data, failure data and a failure case library; Specifically, the data collection acquires physical parameters of the reactive power compensation device during operation, such as thermal state, vibration amplitude and acoustic characteristics. At the same time, the power quality parameters of the power grid are obtained from real-time monitoring, such as reactive power, harmonic content and voltage level, which can reflect the overall power quality of the power grid. In addition, long-term historical operation data, historical failure data and a case library storing different failure type labels, evolution rules and historical disposal experience of the reactive power compensation device are also obtained.

[0027] Performing early warning analysis on the real-time power data, and obtaining a power data abnormal early warning when the real-time power data of the power grid exceeds a preset threshold value; Specifically, the collected real-time power data of the power grid is continuously analyzed and compared with the preset threshold value. When any data of the power factor, reactive power, harmonic content and voltage level of the power grid exceeds the safety limit value or continuously exceeds the respective preset threshold value, an abnormal power data early warning signal is generated. The early warning is used to indicate abnormal power factor or power quality decline of the power grid. If all power data is within the normal range, continuous monitoring will be performed. Figure 2 As shown, the power data abnormal early warning and the equipment failure early warning in the method are intuitively displayed, and how they jointly generate comprehensive failure diagnosis through multi-source data fusion.

[0028] Performing failure early warning analysis on the real-time operation data and the change trend of the key parameters, and obtaining an early failure hidden danger equipment failure early warning; Specifically, the collected real-time operation data of the reactive power compensation device is continuously analyzed, a mathematical model capable of identifying abnormal data patterns is constructed to learn the data characteristics of the equipment in the normal operation state, and a mathematical baseline model is established. The real-time operation data is input into the mathematical baseline model for analysis, and the deviation value between the real-time operation data and the mathematical baseline model is calculated. When the deviation value continuously exceeds the normal fluctuation range, an early failure hidden danger equipment failure early warning is generated.

[0029] According to the fault data and the fault case library, a fault analysis diagnosis model is constructed and trained by using a time series algorithm, and a trained fault analysis diagnosis model is obtained; Specifically, based on the fault data and the fault case library, an initial fault analysis diagnosis model is constructed by using a time series algorithm capable of learning dynamic dependencies in time series data. The fault data is mapped with the corresponding fault type labels in the fault case library to form a structured training sample set. The initial fault analysis diagnosis model is iteratively trained using the training sample set, and the model parameters are continuously optimized until the diagnostic performance converges, and finally a trained model capable of accurately diagnosing faults is obtained. As shown in Figure 3 illustrates how the fault data and the fault case library work together to construct and train the fault analysis diagnosis model, and finally receive comprehensive fault diagnosis input and output diagnostic results.

[0030] The power data anomaly warning and the equipment fault warning are fused to generate a comprehensive fault diagnosis and input into the fault analysis diagnosis model to generate the final fault diagnosis result; Specifically, the power data anomaly warning and the equipment fault warning, which are two different sources of warning information, are fused to form a comprehensive fault diagnosis. The fusion process assigns appropriate weights to different warnings to generate a fusion data that represents the comprehensive degree of faults. The fusion data is input into the trained fault analysis diagnosis model, and the model outputs the final fault diagnosis result based on the input.

[0031] According to the final fault diagnosis result, the corresponding reactive power compensation strategy and fault handling suggestion are retrieved from a database that stores a plurality of reactive power compensation strategies and fault handling suggestions, and the correction of the power factor in the power data is output.

[0032] Specifically, the fault type information contained in the final fault diagnosis result is used as a retrieval index. In the database that stores a plurality of reactive power compensation strategies and fault handling suggestions, the corresponding reactive power compensation strategy and fault handling suggestion are matched and retrieved by the retrieval index. The reactive power compensation strategy and the fault handling suggestion are combined into a structured handling scheme, and output through a visual interface or a remote communication method to guide the operation and maintenance personnel to correct the power factor, so that the power grid operation returns to normal.

[0033] The combination of multi-source data fusion analysis and time series diagnosis model can realize early and accurate warning and self-adaptive handling of reactive power compensation device faults, significantly improve the power quality and fault handling efficiency of the power grid, and reduce the operation and maintenance cost and the professional ability requirement of the operation personnel.

[0034] Optionally, the method further comprises: According to the output reactive power compensation strategy, the operation parameters of the reactive power compensation device are automatically adjusted through a closed-loop control mechanism to correct the power factor; Specifically, when the reactive power compensation strategy is output, a closed-loop control unit receives the strategy and automatically sends control instructions to the reactive power compensation device according to the content of the strategy. These control instructions can accurately adjust the switching state of the reactive power compensation device or adjust its output power to correct the power factor of the power grid in real time. For example, if the final diagnosis result is that the capacitor group capacity is insufficient, the control unit will instruct the reactive power compensation device to switch more capacitor groups to increase the reactive power output. Conversely, if the power grid voltage is detected to be too high, the control unit will reduce the reactive power output of the reactive power compensation device by adjusting its operation parameters.

[0035] After obtaining the operation effect data of the adjusted operation parameters of the reactive power compensation device, the final fault diagnosis result, the executed reactive power compensation strategy, and the operation effect data are used as a new fault case to update the fault case library.

[0036] Specifically, real-time operation data of the reactive power compensation device and real-time power data of the power grid are continuously obtained after the execution of the reactive power compensation strategy, and these data constitute the adjusted operation effect data. The final fault diagnosis result, the executed reactive power compensation strategy, and these operation effect data are associated and packaged. The packaged data is used as a new fault case to update the fault case library. The updating process realizes self-learning and continuous optimization, so that the accuracy of fault diagnosis and disposal can be continuously improved over time.

[0037] Optionally, the collection of real-time operation data of the reactive power compensation device, real-time power data of the power grid, historical data, fault data, and the fault case library comprises: The real-time operation data includes temperature, vibration, and noise of the reactive power compensation device during operation; Specifically, various sensors are arranged on the key components of the reactive power compensation device to collect real-time temperature, vibration, and noise signals during device operation. These sensors can be wired or use wireless communication to ensure flexibility in data collection. For example, optical fiber temperature measurement technology or wireless temperature measurement sensors are used to obtain temperature data of high-voltage cable connection points and coils; vibration sensors are used to monitor the vibration of transformer bases and casings; sound sensors are used to monitor abnormal noise, and these data can comprehensively reflect the physical health status of the device.

[0038] The real-time power data of the power grid includes reactive power, active power, power factor, harmonic current, negative sequence current, and three-phase voltage of the power grid; Specifically, by configuring multifunctional electric meters or intelligent electric quantity acquisition terminals at the low-voltage side outlet of the distribution transformer and the grid connection point of the reactive power compensation device, key electric quantity parameters of the power grid are obtained in real time. These parameters can comprehensively reflect the power quality status of the power grid and the compensation effect of the reactive power compensation device. The acquisition frequency can be adjusted according to actual needs to ensure the real-time and accuracy of the data. These electric quantity data are not only used for immediate warning, but also serve as historical data to support subsequent model training.

[0039] The historical data includes historical operation data and historical electric quantity data of the reactive power compensation device; Specifically, by storing real-time operation data and real-time electric quantity data in the database of the cloud platform or local server for a long time, a complete historical database is formed. These data constitute an important basis for trend analysis, baseline model training, and fault mode identification, which can help understand the long-term operation rules of the equipment, so as to more accurately judge potential fault risks. The collection frequency of historical data can be lower than that of real-time data to save storage resources.

[0040] The fault data are historical faults of the reactive power compensation device, including electric quantity data abnormal faults and equipment faults; Specifically, when the reactive power compensation device fails in the past, the relevant historical fault information is recorded and automatically or manually uploaded. These historical fault records include two main types of information: one is the electric quantity data abnormal fault, which records the abnormal situation of the power factor, harmonic current or voltage of the power grid at a certain time point; the other is the equipment fault, which records the damage of the capacitor bank, the tripping of the switch cabinet or the over-temperature of the equipment itself. These fault data constitute the key raw materials for building the fault case library.

[0041] The fault case library is built based on the analysis and mining of the fault data, and stores the fault type labels, evolution rules and verified historical treatment strategies corresponding to different fault types in an associated form.

[0042] Specifically, the collected fault data are analyzed and mined to extract the characteristics of the fault signals, and combined with expert experience and historical maintenance records. The analysis and mining process associates different types of faults, such as capacitor dielectric aging, poor contact of cable joints or protection misoperation, with specific fault type labels and evolution rules. Finally, these information together with the verified historical treatment strategies are stored in the fault case library in a structured manner, providing a knowledge base for diagnosis and treatment.

[0043] Optionally, the warning analysis on the real-time electric quantity data includes: According to the historical data, preset threshold values of power factor, reactive power, harmonic current, negative sequence current and three-phase voltage are set; Specifically, by analyzing the historical power data of the reactive power compensation device during normal operation, statistical methods are used to statistically analyze various parameters. For example, the mean and standard deviation of each parameter can be calculated, and its dynamic fluctuation range is determined according to the criteria to serve as preset thresholds. These thresholds can be stored in a configuration table and called during early warning analysis.

[0044] If the power factor of the power grid continuously exceeds the preset threshold or any of the reactive power, harmonic current, negative sequence current, and three-phase voltage exceeds the safety limit specified by the relevant standard or continuously exceeds the respective preset threshold, an abnormal power data early warning is generated, wherein the early warning is used to indicate abnormal power factor of the power grid or power quality degradation. Otherwise, the power data is continuously monitored.

[0045] Specifically, the real-time collected power data is continuously monitored. First, it is determined whether the power factor of the power grid continuously exceeds or is lower than the set threshold within a preset time period. At the same time, it also determines each of the other key parameters such as reactive power, harmonic current, negative sequence current, and three-phase voltage to check whether these data exceed the safety limit specified by the national or industry standard. As long as any of the above conditions is met, an abnormal power data early warning signal is generated. The early warning signal will be marked as abnormal power factor or power quality degradation for subsequent analysis. If all parameters do not exceed the limit, continuous monitoring will be performed.

[0046] Optionally, the real-time operation data is analyzed for fault early warning based on the trend of the key parameters to obtain an early fault warning of the device including: A machine learning model for anomaly detection is constructed, and the machine learning model is unsupervised trained using the historical operation data to obtain a normal operation baseline model. Specifically, a machine learning model for anomaly detection can be constructed, which can be an unsupervised learning model, such as an isolation forest model or an autoencoder model. The historical operation data of the reactive power compensation device is used for training. The training process aims to learn and identify the internal patterns and data distribution characteristics of the device in the normal operation state. The purpose of training is to establish a mathematical model that can represent the normal operation behavior of the device, i.e., a normal operation baseline model.

[0047] The real-time operation data is input into the normal operation baseline model for analysis, and the deviation value between the real-time operation data and the normal operation baseline is calculated, wherein the deviation value is used to represent the degree of deviation of the real-time operation data from the normal state. Specifically, the real-time data collected from the reactive compensation device operation is continuously input into the trained normal operation baseline model. Based on the input real-time data, the model calculates the deviation between the real-time data and the normal operation baseline. This deviation can be calculated using a variety of methods, such as Euclidean distance or Mahalanobis distance. Taking Euclidean distance as an example, if the real-time operation data vector is , the normal operation baseline data vector is , then the deviation value The calculation formula is: , in, represents the dimension of the data vector, and Indicates real-time operation data and normal operation baseline data in the The values ​​in the dimensions.

[0048] When the deviation value continues to exceed the normal fluctuation range, an early warning of equipment failure potential is obtained. The normal fluctuation range is obtained from historical operation data and a fault case library.

[0049] Specifically, the deviation value is continuously monitored and compared with a normal fluctuation range determined by historical data analysis. This normal fluctuation range is determined by statistically analyzing the historical operating data of the reactive power compensation device and combining it with known failure modes in a fault case library to establish an objective threshold. If the deviation value continuously exceeds the normal fluctuation range for a period of time, an early warning of equipment failure is generated, indicating a potential fault.

[0050] Optionally, the constructing of a machine learning model for anomaly detection and performing unsupervised training on the machine learning model using the historical operating data includes: Performing statistical analysis on the historical operation data to extract statistical features of the historical operation data, wherein the statistical features include mean, variance, standard deviation, and kurtosis of the operation data; Specifically, the historical operating data of the reactive power compensation device is retrieved from the database, including multiple time series data such as temperature, vibration, and noise. Then, statistical analysis is performed on each type of operating data to extract its key statistical features. For example, for a set of historical operating data samples }, mean The calculation formula is: , variance The calculation formula is: , in, represents the total number of samples, Indicates the The statistical features can comprehensively reflect the behavior pattern of the equipment in the normal state.

[0051] The statistical features are used for unsupervised training of a machine learning model to obtain a normal baseline model capable of calculating a deviation value between running data and a normal running baseline.

[0052] Specifically, the extracted statistical features are used as input to train an unsupervised machine learning model. The model is a clustering model, and the training target is to cluster data points in the historical running data that belong to the normal state. The training process aims to enable the model to learn the distribution rule of the normal data points, thereby forming a mathematical model representing the normal running state of the equipment, i.e., the normal baseline model. The model can calculate a deviation value from the normal baseline according to the input real-time running data.

[0053] Optionally, according to the fault data and the fault case library, a time series algorithm is used to construct and train a fault analysis and diagnosis model to obtain the trained fault analysis and diagnosis model, which includes: An initial fault analysis and diagnosis model capable of learning time series dependency is constructed using a long short-term memory network algorithm; Specifically, an initial fault analysis and diagnosis model capable of learning and memorizing long-term time dependency in the fault data is constructed using a long short-term memory network algorithm. The model mainly consists of an input gate, a forget gate, an output gate, and a memory unit, and the core is to effectively process and analyze time series data. When constructing the model, the feature sequence of the fault data is used as the input of the model, and the purpose is to provide an initial structure with basic learning ability for the subsequent training process.

[0054] The fault data are mapped to corresponding fault type labels in the fault case library to form a training sample set; Specifically, the fault data are sorted and preprocessed, and are one-to-one associated with the corresponding fault type labels in the fault case library. The association process maps the fault data, such as temperature, vibration, or current abnormal records of the equipment in a certain time period, to a unique fault type label. Through this mapping, a structured training sample set is formed, in which each sample contains a fault data and a corresponding fault type label, which provides necessary training materials for supervised learning.

[0055] The initial fault analysis and diagnosis model is iteratively trained using the training sample set, and the model parameters are optimized until the diagnostic performance converges, to obtain the trained fault analysis and diagnosis model.

[0056] Specifically, the initial fault analysis and diagnosis model is iteratively trained using the training sample set. During the training process, the training samples are input into the model for forward propagation to obtain predicted outputs, which are then compared with the true fault type labels to calculate the prediction error. Based on the prediction error, the backpropagation algorithm is used to adjust the model's weights and biases and other parameters. The training process will continue, and by continuously optimizing the model parameters, the diagnostic performance of the model will no longer be significantly improved until it reaches a state of convergence, and finally a trained fault analysis and diagnosis model with accurate diagnostic capabilities is obtained.

[0057] Optionally, the power data anomaly warning and equipment fault warning are subjected to multi-source data fusion to generate a comprehensive fault diagnosis and input into the fault analysis and diagnosis model to generate the final fault diagnosis result, which includes: The power data anomaly warning and the equipment fault warning are assigned corresponding confidence and priority weights for weighted decision processing to generate fusion data. Specifically, when receiving both the power data anomaly warning and the equipment fault warning, a confidence and priority weight are assigned to each warning. The confidence can be determined based on the reliability of the data source and the severity of the warning, for example, the confidence of the warning caused by instantaneous jump is low, while the confidence of the warning caused by continuous over-limit is high. The priority weight can be pre-set according to the operation and maintenance experience, for example, the priority of the power data anomaly warning directly related to the power quality of the power grid is higher than that of the equipment fault warning. These confidence and priority weights are used as inputs for weighted decision processing to generate a fusion data, which can reflect the comprehensive severity and nature of the current fault.

[0058] The fusion data is formatted to generate a comprehensive fault diagnosis that can be received by the trained fault analysis and diagnosis model. Specifically, the fusion data is formatted to conform to the input format required by the trained fault analysis and diagnosis model. The formatting process includes uniform processing and encoding of warning information from different sources to generate a comprehensive fault diagnosis vector that can be understood by the model. The comprehensive fault diagnosis vector serves as the input for the final diagnosis of the model.

[0059] The comprehensive fault diagnosis is input into the fault analysis and diagnosis model, and the fault analysis and diagnosis model outputs the final fault diagnosis result.

[0060] Specifically, the formatted comprehensive fault diagnosis vector is input into the trained fault analysis and diagnosis model. The model performs in-depth analysis on the input and outputs the final fault diagnosis result. The final fault diagnosis result can be a specific fault type, such as "capacitor bank aging" or "switch cabinet overheating", or a probability of fault occurrence, which provides accurate guidance for subsequent disposal.

[0061] Optionally, according to the final fault diagnosis result, corresponding reactive power compensation strategy and fault handling suggestion are retrieved from a preset database storing a plurality of reactive power compensation strategies and fault handling suggestions, including: The fault type label contained in the final fault diagnosis result is used as a retrieval index; Specifically, when outputting the final fault diagnosis result, the result contains one or more fault type labels, such as "capacitor bank aging" or "switch cabinet overheating". The result is automatically parsed to extract these unique fault type labels, and these labels are used as indexes for retrieval in the handling scheme database.

[0062] In the database storing a plurality of reactive power compensation strategies and fault handling suggestions, corresponding reactive power compensation strategy and fault handling suggestion are retrieved by matching the retrieval index; Specifically, the obtained retrieval index is used to quickly match in the handling scheme database. The database is a structured storage system, in which different reactive power compensation strategies and fault handling suggestions are associated with corresponding fault type labels. When the entry matching the retrieval index is found, the associated reactive power compensation strategy and fault handling suggestion are retrieved.

[0063] The reactive power compensation strategy and the fault handling suggestion are combined into a structured handling scheme and output.

[0064] Specifically, the retrieved reactive power compensation strategy and fault handling suggestion are integrated to form a complete and structured handling scheme. The handling scheme can be a step-by-step guide that details the specific handling steps, required tools, and estimated completion time. The handling scheme is output in the form of a visual interface, SMS, or email, etc. to guide the maintenance and repair of the reactive power compensation device by the operation and maintenance personnel.

[0065] Based on the same inventive concept, as shown in Figure 4 The present application also provides an automatic early warning system for reactive power compensation device faults, which comprises: A data acquisition module for acquiring real-time operation data of the reactive power compensation device, real-time power data of the power grid, historical data, fault data, and a fault case library; A warning analysis module for performing warning analysis on the real-time power data to generate power data abnormality warning, and performing key parameter change trend analysis on the real-time operation data to generate device fault warning; A model construction module for constructing and training a fault analysis and diagnosis model based on the fault data and the fault case library using a time series algorithm to obtain a trained fault analysis and diagnosis model; a data fusion module, configured to perform multi-source data fusion on the power data anomaly warning and the device fault warning to generate a comprehensive fault diagnosis; a diagnostic analysis module, configured to input the comprehensive fault diagnosis into the trained fault analysis diagnosis model to obtain a final fault diagnosis result; a treatment output module, configured to, according to the final fault diagnosis result, retrieve and output corresponding reactive power compensation strategies and fault treatment suggestions from a database preset to store a plurality of reactive power compensation strategies and fault treatment suggestions.

[0066] Embodiment 1 In order to verify the feasibility of the present application in implementation, the present application is applied to a certain large steel rolling mill. Due to the use of large motors and electric arc furnaces and other impact loads, the power factor of the power grid of the rolling mill fluctuates violently, and is often lower than the requirement of the power supply department, resulting in electricity fee penalty; at the same time, the reactive power compensation device in the factory area occasionally has accidental faults due to long-term high-load operation, causing production interruption and safety hazards. The traditional alarm method based on fixed threshold has a high false alarm rate, and cannot provide effective early warning before the fault occurs. The rolling mill hopes to use the method of the present application to intelligently perform fault warning and closed-loop management on the reactive power compensation device cluster of its main substation.

[0067] In this embodiment, the rolling mill deploys the method of the present application in its reactive power compensation system. Real-time operation data of each capacitor bank is comprehensively collected, such as capacitor switching state, temperature, branch current, real-time power data of the power grid access point such as voltage, current, power factor, and historical operation data and archived fault maintenance records of the past year are integrated to form a multi-source data set. Before inputting into analysis, all data are subjected to time alignment and normalization preprocessing. The experimental comparison period is 6 months, and the operation effect of the present application is compared with the traditional management method used before.

[0068] In November 2024, it was monitored that the real-time power factor of the power grid frequently dropped during the afternoon production peak period. Under the traditional method, a fixed threshold of 0.90 would generate a large number of false alarms during this period. However, through dynamic threshold warning analysis, the present application calculates the dynamic power factor threshold of this period as 0.88 based on the historical data of the past seven days. When the real-time power factor drops to 0.87, it is determined to be a real anomaly, and a "power data anomaly warning" is generated, effectively avoiding false alarms caused by normal load fluctuations.

[0069] In early December 2024, when analyzing the trend of key parameters of the real-time operation data of capacitor group No. 5, an early fault hidden danger was identified. Through the sliding window algorithm, the change trend of the body temperature in multiple consecutive time windows was calculated as a small positive value, indicating that the capacitor had an abnormal heating trend, even though its absolute temperature value had not reached the traditional alarm fixed threshold of 65°C. Accordingly, a "device fault warning" was generated.

[0070] Subsequently, the above-mentioned "electricity data anomaly warning" and "device fault warning" were subjected to multi-source data fusion processing. Through weighted decision-making, a high-risk score fusion data was generated, which was integrated as a new feature with temperature, current and other time series data to form a comprehensive fault diagnosis input. This input was sent to the long short-term memory network fault analysis and diagnosis model which had been trained. The final fault diagnosis result output by the model was: "capacitor overheating aging".

[0071] According to the diagnosis result of "capacitor overheating aging", the corresponding treatment scheme was immediately retrieved from the fault disposal suggestion database. The reactive power compensation strategy was: "immediately remove capacitor group No. 5 through control and automatically put the standby capacitor group No. 8 into operation". The fault disposal suggestion was: "generate a high-level maintenance work order and notify the operation and maintenance personnel to check the state of the cooling fan of capacitor group No. 5 and prepare to replace the capacitor".

[0072] The closed-loop control mechanism automatically parses the reactive power compensation strategy into a control signal and issues it to the device controller, completing the removal and operation of the capacitor group within 1 minute. The subsequent monitoring data shows that the power factor of the power grid quickly rises above 0.95, and the correction effect is significant. The complete fault warning, diagnosis, disposal and effect verification data are packaged into a new case and updated to the fault case library for future incremental learning and optimization of the model.

[0073] Through 6 months of data comparison, the present application shows significant advantages in warning accuracy, diagnosis and disposal efficiency, and power quality improvement.

[0074] Table 1 Comparison table of warning accuracy of reactive power compensation device

[0075] Table 2 Comparison table of key fault diagnosis and disposal efficiency

[0076] Table 3 Comparison table of power quality (power factor) improvement effect

[0077] From the data in Table 1 above, it can be seen that the application can achieve an average early warning accuracy of more than 90% through dynamic threshold and trend analysis, which is much higher than the accuracy of less than 15% of the traditional method, greatly reducing the number of false positives and enabling operation and maintenance personnel to focus on real fault risks.

[0078] In Table 2, the rapidity and intelligence of the system in fault diagnosis and response are demonstrated. For early risks such as capacitor overheating and aging, the application can complete diagnosis and automatic disposal within a few minutes, avoiding the production interruption and equipment damage risks caused by traditional manual troubleshooting for several hours, and realizing predictive maintenance.

[0079] The data results in Table 3 fully prove the excellent effect of the application in improving power quality. Through rapid and accurate fault disposal and closed-loop control, the system improves the average power factor from 0.89 to more than 0.96, and the power factor compliance rate from about 75% to more than 99%, saving a large amount of electricity fee penalties for enterprises and ensuring the stable and reliable operation of the power grid.

[0080] It should be noted that the electrical connection between the above-mentioned units does not necessarily represent the direct connection of the line, and the indirect connection mode can also be applied to the embodiments of the application as long as the purpose of the application is achieved. The above-described is only an exemplary embodiment of the application, and cannot limit the scope of the application.

[0081] That is, any equivalent changes and modifications made according to the teachings of the application are still within the scope of the application. Other embodiments of the application will be readily apparent to those skilled in the art upon considering the disclosure herein. The present application is intended to cover any variations, uses, or adaptive changes of the application following the general principles of the application and including common knowledge or conventional technical means in the art not disclosed by the application.

Claims

1. A method for automatic early warning of faults in reactive power compensation devices, characterized in that: The method comprises: Collect real-time operating data of reactive power compensation devices, real-time power data of the power grid, historical data, fault data and fault case database; Performing early warning analysis on the real-time power data, and obtaining an abnormal power data warning when the real-time power data of the power grid exceeds a preset threshold; Perform fault warning analysis on the real-time operation data and key parameter change trends to obtain equipment fault warnings with early-stage potential fault hazards; Based on the fault data and the fault case library, a fault analysis and diagnosis model is constructed and trained using a time series algorithm to obtain a trained fault analysis and diagnosis model; Perform multi-source data fusion on the power data abnormality warning and equipment failure warning to generate a comprehensive fault diagnosis and input it into the fault analysis and diagnosis model to generate the final fault diagnosis result; According to the final fault diagnosis result, corresponding reactive power compensation strategies and fault handling suggestions are retrieved from a preset database storing a variety of reactive power compensation strategies and fault handling suggestions, and output to achieve correction of the power factor in the electrical quantity data.

2. The method for automatic warning of reactive power compensation device failure according to claim 1, characterized in that: The method further comprises: According to the output reactive power compensation strategy, the operating parameters of the reactive power compensation device are automatically adjusted through a closed-loop control mechanism to achieve power factor correction; The operating effect data after adjusting the operating parameters of the reactive power compensation device is obtained, and the final fault diagnosis result, the executed reactive power compensation strategy and the operating effect data are used as new fault cases and updated to the fault case library.

3. The method for automatic warning of reactive power compensation device failure according to claim 1, characterized in that: The acquisition of real-time operating data of the reactive power compensation device, real-time power data of the power grid, historical data, fault data and a fault case library includes: The real-time operation data includes temperature, vibration and noise when the reactive compensation device is in operation; The real-time power data of the power grid includes reactive power, active power, power factor, harmonic current, negative sequence current and three-phase voltage of the power grid; The historical data includes historical operation data and historical power data of the reactive power compensation device; The fault data is historical faults of the reactive power compensation device, including abnormal power data faults and equipment faults; The fault case library is constructed based on the analysis and mining of the fault data, and stores fault type labels, evolution rules, and verified historical handling strategies corresponding to different fault types in an associated form.

4. The method for automatic warning of reactive power compensation device failure according to claim 3, characterized in that: Performing early warning analysis on the real-time power data includes: setting preset thresholds for power factor, reactive power, harmonic current, negative sequence current, and three-phase voltage, respectively, based on the historical data; Determine whether the power factor of the power grid continues to exceed a preset threshold or any of the reactive power, harmonic current, negative sequence current and three-phase voltage exceeds the safety limit specified in the relevant standards or continues to exceed their respective preset thresholds. If so, generate an abnormal power data warning, wherein the warning is used to indicate that the power factor of the power grid is abnormal or the power quality is degraded. If not, continue to monitor the power data.

5. The method for automatic warning of reactive power compensation device failure according to claim 3, characterized in that: Fault early warning analysis of the real-time operating data and key parameter change trends to obtain early warning of equipment failure potentials includes: Building a machine learning model for anomaly detection, and performing unsupervised training on the machine learning model using the historical operating data to obtain a normal operating baseline model; Inputting the real-time operation data into a normal operation baseline model for analysis, and calculating a deviation value between the real-time operation data and the normal operation baseline, wherein the deviation value is used to represent the degree to which the real-time operation data deviates from a normal state; When the deviation value continues to exceed the normal fluctuation range, an early warning of equipment failure potential is obtained. The normal fluctuation range is obtained from historical operation data and a fault case library.

6. The method for automatic warning of reactive power compensation device failure according to claim 5, characterized in that: The step of constructing a machine learning model for anomaly detection and performing unsupervised training on the machine learning model using the historical operating data includes: Performing statistical analysis on the historical operation data to extract statistical features of the historical operation data, wherein the statistical features include mean, variance, standard deviation, and kurtosis of the operation data; The statistical features are used to perform unsupervised training on the machine learning model to obtain a normal baseline model that can calculate the deviation value between the operating data and the normal operating baseline.

7. The method for automatic warning of reactive power compensation device failure according to claim 1, characterized in that: Based on the fault data and the fault case library, a fault analysis and diagnosis model is constructed and trained using a time series algorithm. The trained fault analysis and diagnosis model includes: The long short-term memory network algorithm is used to build an initial fault analysis and diagnosis model that can learn time series dependencies; Mapping the fault data to the corresponding fault type labels in the fault case library to form a training sample set; The initial fault analysis and diagnosis model is iteratively trained using the training sample set, and the trained fault analysis and diagnosis model is obtained by optimizing model parameters until its diagnostic performance converges.

8. The method for automatic warning of reactive power compensation device failure according to claim 1, characterized in that: The power data anomaly warning and equipment failure warning are multi-sourced and integrated to generate a comprehensive fault diagnosis. The integrated fault diagnosis is then input into the fault analysis and diagnosis model to generate the final fault diagnosis results, including: Assign corresponding confidence levels and priority weights to the power data anomaly warning and the equipment failure warning, perform weighted decision processing, and generate fused data; Formatting the fused data to generate a comprehensive fault diagnosis that can be received by a trained fault analysis and diagnosis model; The comprehensive fault diagnosis is input into a fault analysis and diagnosis model, and the fault analysis and diagnosis model outputs a final fault diagnosis result.

9. The method for automatic warning of reactive power compensation device failure according to claim 1, characterized in that: According to the final fault diagnosis result, the corresponding reactive power compensation strategy and fault handling suggestion are retrieved from a preset database storing a plurality of reactive power compensation strategies and fault handling suggestions, including: Using the fault type label included in the final fault diagnosis result as a retrieval index; In the database storing a plurality of reactive power compensation strategies and fault handling suggestions, the corresponding reactive power compensation strategies and fault handling suggestions are retrieved by searching the index matching method; The reactive power compensation strategy and the fault handling suggestion are combined into a structured handling solution and outputted.

Images