Power equipment multi-level collaborative early warning method and system based on state monitoring

Abstract

The invention discloses a multi-level collaborative early warning method and system for power equipment based on state monitoring, and the method comprises the steps: collecting the real-time operation state data of the power equipment based on a time sequence form, carrying out the standardization processing of the real-time operation state data, and obtaining the standardization processing data; based on the standardized processing data, the operation state of the power equipment is evaluated through a multi-stage cooperative fault early warning model, and a state evaluation result of the power equipment is generated; determining a plurality of early warning levels of the power equipment based on the state evaluation result; based on the determined relevance between the multiple early warning levels and the multiple pieces of power equipment, collaborative analysis is carried out on the multiple pieces of power equipment, and whether the operation state of the power equipment is abnormal or not is judged; and when the operation state of the power equipment is judged to be abnormal, generating and sending an early warning signal of the abnormity of the power equipment.

Description

Technical Field

[0001] This invention relates to the field of power equipment monitoring and early warning technology, and more specifically, to a multi-level collaborative early warning method and system for power equipment based on condition monitoring. Background Technology

[0002] The multi-level collaborative early warning method and system for power equipment based on condition monitoring aims to provide multi-level collaborative fault early warning by collecting and analyzing the operating data of power equipment in real time, thereby reducing the risk of equipment failure and ensuring the stable operation of the power system. The basic structure of the early warning system includes several modules: Power equipment condition monitoring: Different power equipment collects various types of data, including voltage, current, temperature, and vibration, through sensors. This data is transmitted to a unified data platform for real-time aggregation and fusion processing. Through comprehensive data monitoring, the system can dynamically obtain the health status of the equipment, providing data support for subsequent fault early warning. Collaborative multi-device correlation analysis: Based on data collection, the system performs correlation analysis on the data between different power equipment to uncover potential connections and mutual influences between devices. For example, if the current in a transmission line increases abnormally, the system will immediately check the status of transformers, switches, and other equipment connected to that line, and combine their data analysis to determine whether there are overloads or short circuits. Through this multi-device collaborative analysis, the system can more accurately determine the cause and location of faults, improving the accuracy and effectiveness of early warning.

[0003] While existing early warning systems offer significant advantages in fault prediction through real-time monitoring and multi-device collaborative analysis, their reliance on data analysis algorithms is hampered by limitations. These algorithms struggle to handle complex power equipment fault modes, particularly when new fault types emerge, as existing models cannot be updated or adapted in a timely manner. This results in substantial judgment errors when dealing with uncommon faults, impacting the reliability of early warning systems.

[0004] Early warning systems rely on data analysis algorithms, but existing algorithms are unable to handle complex power equipment fault modes, especially when new fault types emerge, as existing models cannot be updated or adapted in a timely manner. This results in significant judgment errors when the system handles some uncommon faults, affecting the reliability of early warnings. Summary of the Invention

[0005] The present invention provides a method and system for multi-level collaborative early warning of power equipment based on condition monitoring, in order to solve the problem of how to perform multi-level collaborative early warning of power equipment based on condition monitoring.

[0006] To address the above problems, this invention provides a multi-level collaborative early warning method for power equipment based on condition monitoring, the method comprising: Real-time operating status data of power equipment is collected in the form of time series, and the real-time operating status data is standardized to obtain standardized data. Based on the standardized processed data, the operating status of power equipment is evaluated through a multi-level collaborative fault early warning model, and the status evaluation results of the power equipment are generated. Based on the status assessment results, multiple early warning levels for power equipment are determined; Based on the identified multiple warning levels and the correlation between multiple power devices, a collaborative analysis is performed on multiple power devices to determine whether the operating status of the power devices is abnormal. When the operating status of power equipment is determined to be abnormal, an early warning signal for power equipment abnormality is generated and sent.

[0007] Preferably, the multiple warning levels and the correlation between multiple power devices are determined by the following formula, including: Assuming electrical equipment and electrical equipment The degree of correlation between them is The formula for analyzing the correlation between power equipment is: in, For power equipment and electrical equipment covariance of the data and Power equipment and electrical equipment The standard deviation of the data, X i ( t For electrical equipment Standardized data processing, X j ( t ) represents the standardized processing data for power equipment j.

[0008] Preferably, the method further includes: updating the multi-level collaborative fault early warning model, including: Based on a preset time period, the multi-level collaborative fault early warning model is learned, and the model parameters of the multi-level collaborative fault early warning model are updated: in, For the updated model parameters, X new (t) represents the updated input characteristic data of the power equipment at time t, Y. new The output value is the result of the multi-level collaborative fault early warning model based on the updated parameters.

[0009] Preferably, the method further includes: updating the multi-level collaborative fault early warning model, including: When a new type of power equipment fault occurs, the multi-level collaborative fault early warning model is updated based on the new fault type data by adjusting the classifier, wherein the adjusted classifier is: in, To adjust the output of the classifier, X new ( t () represents the adjusted input feature data. Y new The predicted output is adjusted based on the adjusted input feature data. This represents the decision result of the classifier.

[0010] Preferably, the assessment of the operating status of power equipment through a multi-level collaborative fault early warning model includes: The evaluation results of power equipment are obtained through the multi-level collaborative fault early warning model. Through the early warning function Based on the evaluation results Determine the early warning level of power equipment : in, This is a warning function based on the evaluation results of power equipment. Output the corresponding warning level , Normal, Warning, Fault .

[0011] Preferably, after evaluating the operating status of the power equipment using a multi-level collaborative fault early warning model and generating the power equipment status evaluation results, the multi-level collaborative fault early warning model is modified by minimizing the objective function: in, These are the predicted values ​​from a multi-level collaborative fault early warning model. The actual value of the power equipment. To standardize the sample size of the data, t is a time variable representing the point in time when the data or state is processed.

[0012] According to another aspect of the present invention, the present invention provides a multi-level collaborative early warning system for power equipment based on condition monitoring, the system comprising: The acquisition unit is used to collect real-time operating status data of power equipment in the form of time series, and to standardize the real-time operating status data to obtain standardized data. The generation unit is used to evaluate the operating status of power equipment based on the standardized processed data and through a multi-level collaborative fault early warning model, and generate the status evaluation results of the power equipment. A determining unit is used to determine multiple warning levels for power equipment based on the status assessment results; The judgment unit is used to perform collaborative analysis on multiple power devices based on multiple determined warning levels and the correlation between multiple power devices, and to determine whether the operating status of the power devices is abnormal. The early warning unit is used to generate and send an early warning signal for power equipment abnormality when it is determined that the operating status of the power equipment is abnormal.

[0013] Preferably, the judgment unit is used to determine multiple warning levels and the correlation between multiple power devices through the following formula, and is also used to: Assuming electrical equipment and electrical equipment The degree of correlation between them is The formula for analyzing the correlation between power equipment is: in, For power equipment and electrical equipment covariance of the data and Power equipment and electrical equipment The standard deviation of the data, X i ( t For electrical equipment Standardized data processing, X j ( t ) represents the standardized processing data for power equipment j.

[0014] Preferably, it further includes an update unit, used to update the multi-level collaborative fault early warning model, and further used to: Based on a preset time period, the multi-level collaborative fault early warning model is learned, and the model parameters of the multi-level collaborative fault early warning model are updated: in, For the updated model parameters, X new (t) represents the updated input characteristic data of the power equipment at time t, Y. new The output value is the result of the multi-level collaborative fault early warning model based on the updated parameters.

[0015] Preferably, it further includes an update unit, used to update the multi-level collaborative fault early warning model, and further used to: When a new type of power equipment fault occurs, the multi-level collaborative fault early warning model is updated based on the new fault type data by adjusting the classifier, wherein the adjusted classifier is: in, To adjust the output of the classifier, X new ( t () represents the adjusted input feature data. Y new The predicted output is adjusted based on the adjusted input feature data. This represents the decision result of the classifier.

[0016] Preferably, the generation unit is used to evaluate the operating status of power equipment through a multi-level collaborative fault early warning model, and is also used to: The evaluation results of power equipment are obtained through the multi-level collaborative fault early warning model. Through the early warning function Based on the evaluation results Determine the early warning level of power equipment : in, This is a warning function based on the evaluation results of power equipment. Output the corresponding warning level , Normal, Warning, Fault .

[0017] Preferably, the updating unit is further configured to reduce the objective function to correct the multi-level collaborative fault early warning model: in, These are the predicted values ​​from a multi-level collaborative fault early warning model. The actual value of the power equipment. To standardize the sample size of the data, t is a time variable representing the point in time when the data or state is processed.

[0018] In another aspect, the present invention provides a computer-readable storage medium storing a computer program for executing a multi-level collaborative early warning method for power equipment based on condition monitoring.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: a processor and a memory; wherein, The memory is used to store the processor-executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement a multi-level collaborative early warning method for power equipment based on condition monitoring.

[0020] This invention provides a multi-level collaborative early warning method and system for power equipment based on condition monitoring. The method includes: collecting real-time operating status data of power equipment in time-series format and standardizing the real-time operating status data to obtain standardized data; evaluating the operating status of the power equipment based on the standardized data using a multi-level collaborative fault early warning model to generate a status assessment result; determining multiple early warning levels for the power equipment based on the status assessment result; performing collaborative analysis on the multiple early warning levels and the correlation between multiple power equipment to determine whether the operating status of the power equipment is abnormal; and generating and sending an early warning signal for power equipment abnormality when the operating status of the power equipment is determined to be abnormal. This invention solves the problem of existing early warning systems being unable to update in a timely manner when facing new fault types through a self-learning and model adjustment mechanism. The self-learning module in this invention can collect and label new fault type data in real time, and automatically update the prediction model through machine learning algorithms to adapt to new fault types. This adaptive mechanism ensures that the system can continuously optimize the fault classifier and improve the ability to identify unseen faults. Furthermore, through centralized processing and large-scale data analysis on the cloud computing platform, the system can efficiently process data from multiple devices and promptly monitor and respond to faults in large-scale power networks. Attached Figure Description

[0021] Exemplary embodiments of the present invention can be more fully understood by referring to the following figures: Figure 1 This is a flowchart of a multi-level collaborative early warning method for power equipment based on condition monitoring, according to a preferred embodiment of the present invention. Figure 2 This is a flowchart of a multi-level collaborative early warning method for power equipment based on condition monitoring, according to a preferred embodiment of the present invention. Figure 3 This is a schematic diagram illustrating the advantages of a multi-level collaborative early warning system for power equipment based on condition monitoring, according to a preferred embodiment of the present invention. Figure 4 This is a structural diagram of a multi-level collaborative early warning system for power equipment based on condition monitoring, according to a preferred embodiment of the present invention. Detailed Implementation

[0022] Exemplary embodiments of the invention will now be described with reference to the accompanying drawings. However, the invention may be embodied in many different forms and is not limited to the embodiments described herein. These embodiments are provided to fully and completely disclose the invention and to fully convey its scope to those skilled in the art. The terminology used in the exemplary embodiments illustrated in the drawings is not intended to limit the invention. In the drawings, the same units / elements are referred to by the same reference numerals.

[0023] Unless otherwise stated, the terms used herein (including technical terms) have their common meaning as understood by one of ordinary skill in the art. Furthermore, it is understood that terms defined in commonly used dictionaries should be understood to have a meaning consistent with the context of their relevant field, and not to be interpreted as having an idealized or overly formal meaning.

[0024] Figure 1 This is a flowchart of a multi-level collaborative early warning method for power equipment based on condition monitoring, according to a preferred embodiment of the present invention.

[0025] This invention provides a multi-level collaborative early warning method for power equipment based on condition monitoring, which solves the problem that when new fault types occur, the existing model cannot be updated or adapted in a timely manner, which may result in large judgment errors when the system handles some unconventional faults, affecting the reliability of the early warning.

[0026] like Figure 1 As shown, this invention provides a multi-level collaborative early warning method for power equipment based on condition monitoring, the method comprising: Step 101: Collect real-time operating status data of power equipment in time series form, and standardize the real-time operating status data to obtain standardized data; Step 102: Based on standardized data processing, the operating status of power equipment is assessed through a multi-level collaborative fault early warning model to generate the status assessment results of the power equipment; Step 103: Based on the condition assessment results, determine multiple warning levels for power equipment; Step 104: Based on the determined multiple warning levels and the correlation between multiple power devices, perform collaborative analysis on multiple power devices to determine whether the operating status of the power devices is abnormal; The multi-level collaborative early warning method for power equipment provided by the embodiments of the present invention includes: a. Acquire real-time operating status data of power equipment, wherein the real-time operating status data is collected in time series format; b. Perform data standardization processing on the acquired operating status data; c. Based on the data standardization processing... A multi-level collaborative fault early warning model is used to assess the operating status of the equipment and generate equipment status assessment results. d. Based on the evaluation results The power equipment is divided into multiple early warning levels; e. After the early warning level is determined, multi-equipment collaborative analysis is carried out based on the correlation between equipment to identify the cause and location of the fault, and to assume that the equipment... and equipment The degree of correlation between them is Equipment correlation analysis is performed using the following formula: in, For equipment and equipment covariance of the data and respectively equipment and equipment f. Standard deviation of data; if abnormal equipment status is detected, generate an early warning signal. And issue warnings to maintenance personnel, triggering the corresponding emergency response procedures; g. Regularly perform self-learning and adjustment of the existing fault prediction model to adapt to new fault types, and update the equipment association model; h. If a new equipment fault type occurs, collect and label the new data in real time, and automatically update the fault classification model using intelligent algorithms, adjusting the classifier according to the following update rules: in, The system provides the following functions: i. Feedback adjustments to the data and models within the system, correcting prediction errors during analysis by feeding them back into the model to improve early warning accuracy; j. Optimizing fault prediction accuracy through information sharing and collaborative computation among multiple devices during the early warning response process, ensuring timely and effective early warning results; k. Centralized processing and storage of fault data and equipment information using a cloud computing platform to ensure the efficiency and real-time nature of fault monitoring and early warning in large-scale power systems; I. Cross-level and cross-device collaborative correction during the feedback of early warning data to ensure the early warning mechanism can adapt to the complexity and variability of power equipment.

[0027] The multi-level collaborative fault early warning model of the present invention includes: S(t) = {S1(t), S2(t), ..., Sk(t)} A multi-level state analysis model for power equipment, in which the state of the equipment... Contains multiple sub-states Each sub-state corresponds to a specific health dimension of the device; the inter-device correlation analysis model is used to dynamically adjust the early warning strategy based on the interdependence between power devices and the fault propagation law.

[0028] The real-time operating status data of this invention includes, but is not limited to, voltage, current, temperature, and vibration data. The data standardization processing includes data cleaning, preprocessing, and fusion. The standardized dataset... And transmit it to the early warning platform.

[0029] This invention determines multiple early warning levels and the correlation between multiple power devices through the following formula, including: Assuming electrical equipment and electrical equipment The degree of correlation between them is The formula for analyzing the correlation between power equipment is: in, For power equipment and electrical equipment covariance of the data and Power equipment and electrical equipment The standard deviation of the data, X i ( t For electrical equipment Standardized data processing, X j ( t ) represents the standardized processing data for power equipment j.

[0030] Step 105: When it is determined that the operating status of the power equipment is abnormal, generate and send an early warning signal for the power equipment abnormality.

[0031] Preferably, the method is further used to update the multi-level collaborative fault early warning model, including: Based on a preset time period, the multi-level collaborative fault early warning model is trained, and the model parameters of the multi-level collaborative fault early warning model are updated: in, For the updated model parameters, X new (t) represents the updated input characteristic data of the power equipment at time t, Y. new The output value is the result of the multi-level collaborative fault early warning model based on the updated parameters.

[0032] This invention is based on an updated dataset and fault type labeling Through machine learning algorithms Update model parameters: in, These are the updated model parameters.

[0033] Preferably, the method is further used to update the multi-level collaborative fault early warning model, including: When a new type of power equipment fault occurs, the multi-level collaborative fault early warning model is updated based on the new fault type data by adjusting the classifier. The adjusted classifier is as follows: in, To adjust the output of the classifier, X new ( t () represents the adjusted input feature data. Y new The predicted output is adjusted based on the adjusted input feature data. This represents the decision result of the classifier.

[0034] Preferably, the operating status of power equipment is assessed using a multi-level collaborative fault early warning model, including: The evaluation results of power equipment are obtained through a multi-level collaborative fault early warning model. Through the early warning function Based on the evaluation results Determine the early warning level of power equipment : in, This is a warning function based on the evaluation results of power equipment. Output the corresponding warning level , Normal, Warning, Fault .

[0035] The present invention This indicates the health status of the equipment, with a value ranging from 0 to 1. It represents the degree of normal operation of the equipment, and the warning levels include normal, warning, and fault. The following warning function is used for judgment: in, This is an early warning function, based on the health status assessment results of the equipment. Output the corresponding warning level , Normal, Warning, Fault .

[0036] Preferably, the operating status of power equipment is evaluated using a multi-level collaborative fault early warning model. After generating the power equipment status evaluation results, the multi-level collaborative fault early warning model is modified by minimizing the objective function. in, These are the predicted values ​​from a multi-level collaborative fault early warning model. The actual value of the power equipment. To standardize the sample size of the data, t is a time variable representing the point in time when the data or state is processed.

[0037] The modification of this invention is achieved by minimizing the following objective function: in, The predicted value of the model. For the true value, This represents the number of data samples.

[0038] like Figure 2-3 As shown, this embodiment of the invention provides a multi-level collaborative early warning method for power equipment based on condition monitoring, including: a. Acquire real-time operating status data of power equipment. This data is collected in time-series format and includes, but is not limited to, voltage, current, temperature, and vibration data. Data standardization processing includes data cleaning, preprocessing, and fusion. The standardized dataset... a. Transmit the acquired operational status data to the early warning platform. b. Standardize the acquired operational status data. c. Based on the standardized data... A multi-level collaborative fault early warning model is used to assess the operating status of the equipment and generate equipment status assessment results. , This indicates the health status of the equipment, with a value ranging from 0 to 1. It represents the degree of normal operation of the equipment, and the warning levels include normal, warning, and fault. The following warning function is used for judgment: in, This is an early warning function, based on the health status assessment results of the equipment. Output the corresponding warning level , Normal, Warning, Fault The multi-level collaborative fault early warning model includes: a multi-level state analysis model for power equipment. S(t) = {S1(t), S2(t), ..., Sk(t)} Among them, the status of the equipment Contains multiple sub-states Each sub-state corresponds to a specific health dimension of the device. An inter-device correlation analysis model is used to dynamically adjust early warning strategies based on the interdependencies and fault propagation patterns among power equipment. d. Based on the evaluation results... The power equipment is divided into multiple warning levels. e. After the warning level is determined, based on the correlation between equipment, multi-equipment collaborative analysis is conducted to identify the cause and location of the fault, assuming the equipment... and equipment The degree of correlation between them is Equipment correlation analysis is performed using the following formula: in, For equipment and equipment covariance of the data and respectively equipment and equipment f. Standard deviation of the data. If an abnormal equipment condition is detected, a warning signal will be generated. And issue a warning to maintenance personnel, triggering the corresponding emergency response process. g. Regularly perform self-learning and adjustment on the existing fault prediction model to adapt to new fault types, and update the device association model and the updated dataset. and fault type labeling Through machine learning algorithms Update model parameters: in, The updated model parameters. h. If a new equipment fault type occurs, collect and label the new data in real time, and automatically update the fault classification model using intelligent algorithms. Adjust the classifier according to the following update rules: in, The output of the new classifier. i. Feedback adjustments are made to the data and model in the system. Prediction errors during the analysis process are fed back to the model for correction, improving the accuracy of early warnings. The correction is achieved by minimizing the following objective function: in, The predicted value of the model. For the true value, j. During the early warning response process, optimize the accuracy of fault prediction through the sharing and collaborative computing of information from multiple devices to ensure timely and effective early warning results. k. Utilize a cloud computing platform for centralized processing and storage of fault data and equipment information to ensure the efficiency and real-time nature of fault monitoring and early warning in large-scale power systems. I. During the feedback process of early warning data, conduct cross-level and cross-device collaborative corrections to ensure that the early warning mechanism can adapt to the complexity and variability of power equipment.

[0039] This invention aims to verify the effectiveness of a multi-level collaborative early warning method for power equipment based on condition monitoring. By collecting the condition data of power equipment in real time, a multi-level collaborative fault early warning model is used to evaluate the equipment condition, identify faults and issue early warnings, ultimately improving the accuracy and real-time performance of power equipment fault prediction.

[0040] Experimental equipment: Power transformers, transmission lines and switchgear (combinations of various power equipment) Power equipment condition monitoring sensors: voltage, current, temperature, vibration sensors Data acquisition and transmission system Data processing and early warning platform Cloud computing platform (used for storing and analyzing fault data) Experimental steps: Equipment status data acquisition: Sensors installed on electrical equipment collect status data including voltage, current, temperature, and vibration. The data acquisition process uses a time-series format. Assume the collected data for a certain time period (e.g., 1 hour) is as follows: Voltage Current temperature vibration Data standardization processing: The collected operational status data is standardized. Assume the standardized status data for each device is as follows: Standardized voltage Standardized current Standardized temperature Standardized vibration The multi-level collaborative fault early warning model of this invention uses a standardized dataset. As input, through pre-trained multi-level collaborative fault The early warning model assesses equipment status. This model generates equipment health status assessment results. Let's assume the result is: (Indicates the equipment is operating well and close to normal) Warning level determination: Use warning function Equipment health status assessment results This is mapped to an alert level. Assume the function is defined as: like If so, the device status is "normal".

[0041] like If so, the device status will be "warning".

[0042] like If so, the device status will be "faulty".

[0043] Based on this warning function, the device status... The corresponding warning level is "normal".

[0044] Experimental results: Equipment condition assessment results: Experimental data shows that the system can collect and standardize the status data of power equipment in real time. Based on the multi-level collaborative fault early warning model, the equipment health status assessment accurately reflects the operating condition of the equipment.

[0045] Warning level determination: Based on the health status assessment results, the warning level was correctly classified as "normal," which is consistent with the actual operating condition of the equipment.

[0046] Fault prediction accuracy: During the experiment, the system was able to identify potential equipment failure risks in a timely manner, provide early warnings, and effectively prevent equipment failures from occurring.

[0047] Self-learning and model updates: Through a periodic self-learning process, the system successfully adjusted its prediction model to adapt to newly emerging fault types, thereby improving the accuracy of fault classification.

[0048] This invention addresses the problem of existing early warning systems failing to update in a timely manner when faced with new fault types by employing a self-learning and model adjustment mechanism. The self-learning module in this invention can collect and label new fault type data in real time, automatically updating the prediction model through machine learning algorithms to adapt to new fault types. This adaptive mechanism ensures that the system can continuously optimize the fault classifier, improving its ability to identify unseen faults. Furthermore, through centralized processing and large-scale data analysis on a cloud computing platform, the system can efficiently process data from multiple devices and promptly monitor and respond to faults in large-scale power networks.

[0049] Figure 4 This is a structural diagram of a multi-level collaborative early warning system for power equipment based on condition monitoring, according to a preferred embodiment of the present invention.

[0050] like Figure 4 As shown, this invention provides a multi-level collaborative early warning system for power equipment based on condition monitoring. The system includes: The acquisition unit 401 is used to collect real-time operating status data of power equipment in the form of time series, and to perform standardized processing on the real-time operating status data to obtain standardized processed data. The generation unit 402 is used to evaluate the operating status of power equipment based on standardized processed data and through a multi-level collaborative fault early warning model, and generate the status evaluation results of the power equipment. The determination unit 403 is used to determine multiple early warning levels for power equipment based on the condition assessment results; The judgment unit 404 is used to perform collaborative analysis on multiple power devices based on the determined multiple warning levels and the correlation between multiple power devices, and to determine whether the operating status of the power devices is abnormal. The early warning unit 405 is used to generate and send an early warning signal for power equipment abnormality when it is determined that the operating status of the power equipment is abnormal.

[0051] This invention provides a multi-level collaborative early warning system for power equipment based on condition monitoring, comprising: The acquisition unit 401 is used to collect real-time operating status data of power equipment; to preprocess, standardize and fuse the collected operating data; the generation unit 402 is used to evaluate the operating status of the equipment and generate a status evaluation result based on the preprocessed data; the determination unit 403 is used to classify the equipment into different warning levels according to the evaluation result and generate a warning signal; the judgment unit 404 is used to analyze the interrelationship between the equipment and identify the cause and location of the fault. The early warning unit 405 is used to classify the equipment into different early warning levels based on the evaluation results and generate early warning signals; A cloud computing platform is used to store device data and fault information, and to support large-scale data analysis and processing.

[0052] The update unit is used to collect and label new fault type data in real time; and to dynamically update the fault prediction model to adapt to the newly emerging fault types. The model update unit is used to apply new data to the machine learning algorithm to optimize and update the fault prediction model.

[0053] Preferably, the judgment unit 404 is used to determine multiple warning levels and the correlation between multiple power devices through the following formula, and is also used to: Assuming electrical equipment and electrical equipment The degree of correlation between them is The formula for analyzing the correlation between power equipment is: in, For power equipment and electrical equipment covariance of the data and Power equipment and electrical equipment The standard deviation of the data, X i ( t For electrical equipment Standardized data processing, X j ( t ) represents the standardized processing data for power equipment j.

[0054] Preferably, the system further includes an update unit 406, used to update the multi-level collaborative fault early warning model, and also used for: Based on a preset time period, the multi-level collaborative fault early warning model is trained, and the model parameters of the multi-level collaborative fault early warning model are updated: in, For the updated model parameters, X new (t) represents the updated input characteristic data of the power equipment at time t, Y. new This is the output value predicted by the multi-level collaborative fault early warning model based on the updated parameters.

[0055] Preferably, the system further includes an update unit 406, used to update the multi-level collaborative fault early warning model, and also used for: When a new type of power equipment fault occurs, the multi-level collaborative fault early warning model is updated based on the new fault type data by adjusting the classifier. The adjusted classifier is as follows: in, To adjust the output of the classifier, X new ( t () represents the adjusted input feature data. Y new The predicted output is adjusted based on the adjusted input feature data. This represents the decision result of the classifier.

[0056] Preferably, the system further includes a generation unit 402, used to evaluate the operating status of power equipment through a multi-level collaborative fault early warning model, and also used for: The evaluation results of power equipment are obtained through a multi-level collaborative fault early warning model. Through the early warning function Based on the evaluation results Determine the early warning level of power equipment : in, This is a warning function based on the evaluation results of power equipment. Output the corresponding warning level , Normal, Warning, Fault .

[0057] Preferably, the system further includes an update unit 406, which is also used to reduce the objective function to correct the multi-level collaborative fault early warning model: in, These are the predicted values ​​from a multi-level collaborative fault early warning model. The actual value of the power equipment. To standardize the sample size of the data, t is a time variable representing the point in time when the data or state is processed.

[0058] This invention provides a multi-level collaborative early warning method and system for power equipment based on condition monitoring. By acquiring real-time operating status data of the equipment and performing standardized processing, it ensures high data consistency and stability, providing a reliable data foundation for subsequent fault assessment. Employing a multi-level condition analysis model, each equipment state is divided into multiple sub-states, more accurately reflecting the equipment's performance across different health dimensions. Simultaneously, through correlation analysis between equipment, it can deeply explore the mutual influences and fault propagation paths between devices, thereby dynamically adjusting the early warning strategy and reducing the possibility of false alarms and missed alarms. This solution can promptly identify the specific causes and locations of equipment faults, providing more accurate early warning results and significantly improving the reliability and security of the power system.

[0059] This invention addresses the problem of existing early warning systems failing to update in a timely manner when faced with new fault types by employing a self-learning and model adjustment mechanism. The self-learning module in this invention can collect and label new fault type data in real time, automatically updating the prediction model through machine learning algorithms to adapt to new fault types. This adaptive mechanism ensures that the system can continuously optimize the fault classifier, improving its ability to identify unseen faults. Furthermore, through centralized processing and large-scale data analysis on a cloud computing platform, the system can efficiently process data from multiple devices and promptly monitor and respond to faults in large-scale power networks.

[0060] The present invention provides a computer-readable storage medium storing a computer program for executing a multi-level collaborative early warning method for power equipment based on condition monitoring.

[0061] This invention provides an electronic device, which includes: a processor and a memory; wherein, Memory, used to store processor-executable instructions; A processor is used to read executable instructions from memory and execute the instructions to implement a multi-level collaborative early warning method for power equipment based on condition monitoring.

[0062] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0063] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0067] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0068] The invention has been described with reference to a few embodiments. However, as will be known to those skilled in the art, and as defined in the appended claims, other embodiments besides those disclosed above fall equivalently within the scope of the invention.

[0069] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the art, unless otherwise expressly defined herein. All references to “a / the / the [device, component, etc.]” ​​are openly interpreted as at least one instance of said device, component, etc., unless otherwise expressly stated. The steps of any method disclosed herein need not be performed in the exact order disclosed unless explicitly stated otherwise.

Claims

1. A multi-level cooperative early warning method for power equipment based on condition monitoring, characterized in that, The method comprises: Collecting real-time operation state data of power equipment in a time series form, and performing standardization processing on the real-time operation state data to obtain standardized processing data; Based on the standardized processing data, the operation state of the power equipment is evaluated by a multi-level cooperative fault early warning model to generate a state evaluation result of the power equipment; Based on the state evaluation result, a plurality of early warning levels of the power equipment are determined; Based on the determined plurality of early warning levels and the correlation between the plurality of power equipment, the plurality of power equipment are cooperatively analyzed to determine whether the operation state of the power equipment is abnormal; When it is determined that the operation state of the power equipment is abnormal, an early warning signal of the abnormal power equipment is generated and sent.

2. The method of claim 1, wherein, The plurality of early warning levels and the correlation between the plurality of power equipment are determined by the following formula: Assume the correlation degree between power equipment i and power equipment j is p ij (t), the correlation analysis formula between power equipment is: wherein cov(X i (t), X j (t)) is the covariance of the power device i and power device j data, σ(X i (t)) and σ(X j (t)) are the standard deviations of the power device i and power device j data, respectively, X i (t) is the normalized data of the power device i, and X j (t) is the normalized data of the power device j.

3. The method of claim 1, wherein, The multi-level cooperative fault early warning model is updated, and further comprises: Based on a preset time period, the multi-level cooperative fault early warning model is learned, and the model parameters of the multi-level cooperative fault early warning model are updated: wherein θ new is the updated model parameter, X new (t) is the input feature data of the power equipment at time t, Y new is the output value predicted by the multi-stage collaborative fault early warning model according to the updated parameter.

4. The method of claim 3, wherein, The multi-level cooperative fault early warning model is updated, and further comprises: When a new fault type of power equipment occurs, the multi-level cooperative fault early warning model is updated based on new fault type data by adjusting the classifier, wherein the adjusting classifier is: where P new is the adjusted classifier output, X new (t) is the adjusted input feature data, Y new is the predicted output adjusted according to the adjusted input feature data, and is the decision result of the classifier.

5. The method of claim 1, wherein, The operation state of the power equipment is evaluated by the multi-level cooperative fault early warning model, and further comprises: An evaluation result of the power equipment is acquired through the multi-stage cooperative fault early warning model Through the early warning function Based on the evaluation result The early warning level of the power equipment is determined wherein, is a pre-warning function, according to the evaluation result of the power equipment outputs the corresponding pre-warning level 6. The method of claim 1, wherein, After the operation state of the power equipment is evaluated by the multi-level cooperative fault early warning model to generate a state evaluation result of the power equipment, the multi-level cooperative fault early warning model is corrected by minimizing the objective function: wherein, Y is the prediction value of the multi-level cooperative fault early warning model, true (t) is the true value of the power equipment, N is the sample number of the normalized processed data, t is the time variable, indicating the time point of the data or state.

7. A multi-level cooperative warning system based on condition monitoring of power equipment, characterized in that, The system comprises: An acquisition unit is configured to collect real-time operation state data of power equipment in a time series form, and perform standardization processing on the real-time operation state data to obtain standardized processing data; A generation unit is configured to evaluate the operation state of the power equipment by a multi-level cooperative fault early warning model based on the standardized processing data to generate a state evaluation result of the power equipment; A determination unit is configured to determine a plurality of early warning levels of the power equipment based on the state evaluation result; A judgment unit is configured to cooperatively analyze the plurality of power equipment based on the determined plurality of early warning levels and the correlation between the plurality of power equipment, and determine whether the operation state of the power equipment is abnormal; An early warning unit is configured to generate and send an early warning signal of abnormal power equipment when it is determined that the operation state of the power equipment is abnormal.

8. The system of claim 7, wherein, The judgment unit is configured to determine the plurality of early warning levels and the correlation between the plurality of power equipment by the following formula, and is further configured to: Assuming the correlation degree between power equipment i and power equipment j is p ij (t), the correlation analysis formula between power equipment is: wherein cov(X i (t),X j (t)) is the covariance of the power device i and power device j data, σ(X i (t)) and σ(X j (t)) are the standard deviations of the power device i and power device j data, respectively, X i (t) is the normalized data of the power device i, and X j (t) is the normalized data of the power device j.

9. The system of claim 7, wherein, Further comprising an update unit configured to update the multi-level cooperative fault early warning model, and further configured to: Based on a preset time period, the multi-level cooperative fault early warning model is learned, and the model parameters of the multi-level cooperative fault early warning model are updated: wherein θ new is the updated model parameter, X new (t) is the input feature data of the power equipment at time t, Y new is the output value predicted by the multi-stage collaborative fault early warning model according to the updated parameter.

10. The system of claim 9, wherein, Further comprising an update unit configured to update the multi-level cooperative fault early warning model, and further configured to: When a new fault type of the power equipment occurs, the multi-stage cooperative fault early warning model is updated based on new fault type data by adjusting a classifier, wherein the adjusting classifier is: where P new is the adjusted classifier output, X new (t) is the adjusted input feature data, Y new is the predicted output adjusted according to the adjusted input feature data, is the decision result of the classifier.

11. The system of claim 7, wherein, The generating unit is configured to evaluate the operation state of the power equipment by using the multi-stage cooperative fault early warning model, and is further configured to: An evaluation result of the power equipment is acquired through the multi-stage cooperative fault early warning model Through the early warning function Based on the evaluation result A warning level of the power equipment is determined wherein, is a pre-warning function according to the evaluation result of the power equipment outputs the corresponding pre-warning level 12. The system of claim 7, wherein, The updating unit is further configured to correct the multi-stage cooperative fault early warning model by minimizing the objective function. wherein, Y is the prediction value of the multi-stage collaborative fault early warning model, true (t) is the true value of the power equipment, N is the sample number of the normalized processed data, t is the time variable, indicating the time point of the data or state.

13. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is configured to execute the method in any one of claims 1-6.

14. An electronic device, comprising: The electronic device comprises a processor and a memory; wherein, The memory is configured to store executable instructions of the processor. The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method in any one of claims 1-6.

Images