A method and system for evaluating the state of electrical equipment in a thermal power plant

Abstract

The application relates to the technical field of electrical equipment state evaluation, and particularly discloses a thermal power plant electrical equipment state evaluation method and system, which comprises the following steps: obtaining vibration signals of electrical equipment, clustering and partitioning each electrical equipment according to the vibration signals of the electrical equipment; obtaining historical fault data of the electrical equipment, and mining strong association rules of the historical fault data based on an association rule algorithm; obtaining current operation data of the electrical equipment, and determining operation state parameters of the current electrical equipment according to the current operation data of the electrical equipment, the cluster partition where the electrical equipment is located and the strong association rules of the historical fault data; obtaining an environmental temperature when the electrical equipment is running, correcting the operation state parameters according to the environmental temperature, and determining an evaluation grade of the electrical equipment according to the corrected operation state parameters. The application calculates the operation state parameters after clustering the electrical equipment, evaluates the state of the electrical equipment in the thermal power plant, and accurately evaluates the fault risk of the electrical equipment.

Description

Technical Field

[0001] This application relates to the field of electrical equipment condition assessment technology, and more specifically, to a method and system for assessing the condition of electrical equipment in thermal power plants. Background Technology

[0002] With the continuous expansion of thermal power plant power systems and the development of the electricity market, the safety and reliability of power systems have become increasingly prominent. Therefore, assessing the operational health status of power supply equipment is essential to address these issues. By combining real-time analysis of equipment monitoring data, the current operating status and health level of the equipment can be accurately grasped, allowing for the timely detection and resolution of potential safety hazards and faults. This ensures the safe and stable operation of the equipment, optimizes maintenance management, extends equipment lifespan, improves operating efficiency, and reduces equipment replacement and maintenance costs.

[0003] As the structure of equipment in thermal power plants becomes increasingly complex, the requirements for the precision of equipment maintenance also increase. The time and manpower costs required for fault repair are also rising, making the upgrading and iteration of electrical equipment fault monitoring systems imperative. Current technologies, which perform maintenance after equipment failure, result in losses of manpower and time, leading to significant delays in equipment maintenance. Summary of the Invention

[0004] This invention provides a method and system for evaluating the condition of electrical equipment in thermal power plants, to address the problem of significant lag in the maintenance of electrical equipment in existing technologies, including:

[0005] Acquire vibration signals from electrical equipment and cluster and partition the electrical equipment based on the vibration signals.

[0006] Acquire historical fault data of electrical equipment and mine strong association rules based on association rule algorithms;

[0007] Obtain the current operating data of electrical equipment, and determine the current operating status parameters of electrical equipment based on the current operating data of electrical equipment, its cluster partition, and the strong correlation rules of historical fault data;

[0008] The ambient temperature during the operation of electrical equipment is obtained, the operating status parameters are corrected based on the ambient temperature, and the evaluation level of the electrical equipment is determined based on the corrected operating status parameters.

[0009] Furthermore, the step of clustering and partitioning the electrical equipment based on its vibration signals includes:

[0010] The vibration signal of the electrical equipment is preprocessed, and the preprocessed vibration signal is subjected to a fast Fourier transform to obtain the vibration signal spectrum.

[0011] Fault parameters are determined based on the vibration signal spectrum of electrical equipment, and the electrical equipment is clustered according to the fault parameters to obtain the cluster partitions of each electrical equipment.

[0012] Furthermore, determining the fault parameters based on the vibration signal spectrum of the electrical equipment includes:

[0013] The peak points in the vibration signal spectrum are obtained, and the peak points in the vibration signal spectrum that are greater than the first preset threshold are selected. The first fault parameter is determined based on the average peak points that are greater than the first preset threshold.

[0014] Calculate the absolute value of the slope between the peak point and the adjacent valley point in the vibration signal spectrum, and determine the second fault parameter based on the variance of the absolute values ​​of all slopes in the vibration signal spectrum.

[0015] Obtain the preset standard vibration signal spectrum of the electrical equipment, calculate the area values ​​of the vibration signal spectrum and the preset standard vibration signal spectrum with respect to the coordinate axis during the operating cycle of the electrical equipment, and determine the third fault parameter based on the area difference between the vibration signal spectrum and the preset standard vibration signal spectrum.

[0016] The first fault parameter, the second fault parameter, and the third fault parameter are normalized, and the normalized first fault parameter, the second fault parameter, and the third fault parameter are set as the first length, the second length, and the third length according to a preset ratio.

[0017] The first and second lengths are used as the lower and upper bases, respectively, and the third length is used as the height. A frustum is constructed based on the lower base, upper base, and height, and the volume of the frustum is set as the comprehensive fault parameter of the electrical equipment.

[0018] Furthermore, the step of clustering electrical equipment based on fault parameters to obtain cluster partitions for each electrical equipment includes:

[0019] A comprehensive fault parameter dataset is established based on the comprehensive fault parameters of electrical equipment. An initial k value is set, and the initial cluster centers of the comprehensive fault parameter dataset are randomly selected based on the initial k value.

[0020] Calculate the Euclidean distance between each comprehensive fault parameter in the comprehensive fault parameter dataset and the k initial cluster centers, and cluster the comprehensive fault parameters into the cluster partitions with the closest Euclidean distance to the initial cluster centers;

[0021] Calculate the average value of the comprehensive fault parameters within each cluster partition, and set new cluster centers based on the average value of the comprehensive fault parameters within each cluster partition;

[0022] Repeat the process of creating new cluster centers until the cluster centers no longer change, resulting in the final cluster partitions of k electrical devices.

[0023] Furthermore, the strong association rules for mining historical fault data based on the association rule algorithm include:

[0024] Obtain historical operating data and corresponding fault types of electrical equipment, and discretize the historical operating data and corresponding fault types of electrical equipment to obtain a fault dataset;

[0025] Frequent itemsets in a fault dataset are mined using an association rule algorithm, and strong association rules are determined based on these frequent itemsets.

[0026] Furthermore, the step of mining frequent itemsets in the fault dataset based on the association rule algorithm and determining strong association rules based on the frequent itemsets in the fault dataset includes:

[0027] Set a minimum support threshold, and mine historical operating data with support greater than or equal to the minimum support threshold based on the historical operating data of electrical equipment and the corresponding fault types;

[0028] A minimum confidence threshold is set, and based on the historical operating data of electrical equipment and the corresponding fault types, historical operating data with confidence levels greater than or equal to the minimum confidence threshold are mined from the historical operating data with support greater than or equal to the minimum support threshold to obtain strong association rules.

[0029] Furthermore, based on the current operating data of the electrical equipment and its cluster partition, combined with strong association rules of historical fault data, the current operating status parameters of the electrical equipment are determined, including:

[0030] Obtain the cluster partition where the electrical equipment is located, normalize the cluster centers of the cluster partitions, and obtain the fault weight value of the electrical equipment.

[0031] Obtain the current operating data of the electrical equipment, and based on the confidence of the corresponding fault type in the strong association rule set, obtain the fault probability of each fault type of the current electrical equipment.

[0032] The operating status parameters of each electrical device are obtained by multiplying the fault weight value of the electrical device by the fault probability of each fault type and then adding them together.

[0033] Furthermore, the correction of operating status parameters based on ambient temperature includes:

[0034] Calculate the difference between the ambient temperature and the real-time internal temperature of the electrical equipment during operation, plot the temperature difference change curve based on the difference between the ambient temperature and the real-time internal temperature of the electrical equipment, and filter out the temperature difference values ​​in the temperature difference change curve that are greater than the fourth preset threshold.

[0035] Calculate the proportion of temperature differences greater than the second preset threshold in the temperature difference change curve, and use the ratio of the proportion of temperature differences greater than the second preset threshold in the temperature difference change curve to the preset standard proportion as the operating status correction coefficient.

[0036] The corrected operating status parameters are obtained by multiplying the operating status correction factor by the operating status parameters of the electrical equipment.

[0037] Furthermore, determining the evaluation level of electrical equipment based on the corrected operating status parameters includes:

[0038] Obtain the preset standard value of the operating state, calculate the difference between the operating state parameter of the electrical equipment and the preset standard value of the operating state, and determine whether the difference between the operating state parameter of the electrical equipment and the preset standard value of the operating state is greater than the third preset threshold.

[0039] If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the third preset threshold, then the first level will be used as the evaluation level of the electrical equipment.

[0040] If the difference between the operating status parameter of the electrical equipment and the preset operating status standard value is less than or equal to the third preset threshold, then determine whether the difference between the operating status parameter of the electrical equipment and the preset operating status standard value is greater than the fourth preset threshold.

[0041] If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the fourth preset threshold, then the second level will be used as the evaluation level of the electrical equipment.

[0042] If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is less than or equal to the fourth preset threshold, then the third level will be used as the evaluation level of the electrical equipment.

[0043] To achieve the above objectives, the present invention also provides a condition assessment system for electrical equipment in thermal power plants, comprising:

[0044] The clustering module is used to acquire vibration signals from electrical equipment and to cluster and partition the electrical equipment based on these vibration signals.

[0045] The data mining module is used to acquire historical fault data of electrical equipment and mine strong association rules in the historical fault data based on association rule algorithms.

[0046] The calculation module is used to obtain the current operating data of electrical equipment, and determine the current operating status parameters of electrical equipment based on the current operating data of electrical equipment, its cluster partition, and the strong correlation rules of historical fault data.

[0047] The evaluation module is used to obtain the ambient temperature during the operation of electrical equipment, correct the operating status parameters based on the ambient temperature, and determine the evaluation level of the electrical equipment based on the corrected operating status parameters.

[0048] The beneficial effects of this invention are as follows:

[0049] By applying the above technical solutions, this invention clusters electrical equipment using vibration signals and mines historical fault data. It effectively utilizes the massive, high-density historical operational monitoring data of thermal power plants. Based on the mining results and the clustering partitions of each electrical equipment, the operating status of the electrical equipment is evaluated, which can accurately assess the fault risk of the electrical equipment and facilitate timely maintenance when the electrical equipment is abnormal or may be abnormal. Attached Figure Description

[0050] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0051] Figure 1 A general flowchart of a method for evaluating the condition of electrical equipment in a thermal power plant, as proposed in an embodiment of the present invention, is shown.

[0052] Figure 2 A schematic diagram of the structure of a thermal power plant electrical equipment condition evaluation system proposed in an embodiment of the present invention is shown. Detailed Implementation

[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0054] This application provides a method for evaluating the condition of electrical equipment in a thermal power plant, such as... Figure 1 As shown, it includes:

[0055] S101, acquire the vibration signal of the electrical equipment, and cluster and partition each electrical equipment according to the vibration signal.

[0056] In some embodiments of this application, the step of clustering and partitioning electrical equipment based on vibration signals includes: preprocessing the vibration signals of the electrical equipment; performing a fast Fourier transform on the preprocessed vibration signals to obtain a vibration signal spectrum; determining fault parameters based on the vibration signal spectrum of the electrical equipment; and clustering the electrical equipment based on the fault parameters to obtain cluster partitions for each electrical equipment.

[0057] In this embodiment, vibration signals of various electrical equipment in a thermal power plant are detected by an accelerometer. After preprocessing the vibration signals to reduce noise, the preprocessed vibration signals are transformed from the time domain to the frequency domain based on the fast Fourier transform to obtain the vibration signal spectrum.

[0058] In some embodiments of this application, determining fault parameters based on the vibration signal spectrum of the electrical equipment includes: acquiring peak points in the vibration signal spectrum, filtering out peak points in the vibration signal spectrum that are greater than a first preset threshold, and determining a first fault parameter based on the average peak points greater than the first preset threshold; calculating the absolute value of the slope between the peak points and adjacent valley points in the vibration signal spectrum, and determining a second fault parameter based on the variance of the absolute values ​​of all slopes in the vibration signal spectrum; acquiring a preset standard vibration signal spectrum of the electrical equipment, and calculating the vibration signal spectrum within the operating cycle of the electrical equipment compared with the preset standard... The area values ​​of the quasi-vibration signal spectrum and the coordinate axes are used to determine the third fault parameter based on the area difference between the vibration signal spectrum and the preset standard vibration signal spectrum. The first, second, and third fault parameters are normalized, and the normalized first, second, and third fault parameters are set as the first length, second length, and third length according to a preset ratio. The first and second lengths are used as the lower and upper bases, respectively, and the third length is used as the height. A frustum is constructed based on the lower base, upper base, and height, and the volume value of the frustum is set as the comprehensive fault parameter of the electrical equipment.

[0059] In this embodiment, the first fault parameter is determined by the average peak point greater than the first preset threshold, the second fault parameter is determined by the variance of the absolute values ​​of all slopes in the vibration signal spectrum, and the third fault parameter is determined by the area difference between the vibration signal spectrum and the preset standard vibration signal spectrum. The first fault parameter, the second fault parameter and the third fault parameter are combined to construct a frustum, and the volume value of the frustum is set as the comprehensive fault parameter of the electrical equipment, so that the comprehensive fault parameter can more comprehensively represent the vibration state of the electrical equipment.

[0060] In some embodiments of this application, the step of clustering electrical equipment based on fault parameters to obtain cluster partitions for each electrical equipment includes: establishing a comprehensive fault parameter dataset based on the comprehensive fault parameters of the electrical equipment, setting an initial k value, and randomly selecting initial cluster centers for the comprehensive fault parameter dataset based on the initial k value; calculating the Euclidean distance between each comprehensive fault parameter in the comprehensive fault parameter dataset and the k initial cluster centers, and clustering the comprehensive fault parameters into the cluster partitions with the closest Euclidean distance to the initial cluster centers; calculating the average value of the comprehensive fault parameters in each cluster partition, and setting new cluster centers based on the average value of the comprehensive fault parameters in each cluster partition; repeatedly iterating the new cluster centers until the cluster centers no longer change, thereby obtaining the final cluster partitions for the k electrical equipment.

[0061] In this embodiment, the initial value of k is specifically 8. The comprehensive fault parameters are clustered based on the k-means clustering algorithm, which facilitates the subsequent calculation of operating status parameters of electrical equipment for different clustering partitions.

[0062] S102, Obtain historical fault data of electrical equipment, and mine strong association rules of historical fault data based on association rule algorithm.

[0063] In some embodiments of this application, the step of mining strong association rules based on association rule algorithms for historical fault data includes: obtaining historical operating data of electrical equipment and corresponding fault types; discretizing the historical operating data of electrical equipment and corresponding fault types to obtain a fault dataset; mining frequent itemsets of the fault dataset based on association rule algorithms; and determining strong association rules based on the frequent itemsets of the fault dataset.

[0064] In some embodiments of this application, the step of mining frequent itemsets of a fault dataset based on an association rule algorithm and determining strong association rules based on the frequent itemsets of the fault dataset includes: setting a minimum support threshold, mining historical operating data with support greater than or equal to the minimum support threshold based on historical operating data of electrical equipment and corresponding fault types; setting a minimum confidence threshold, mining historical operating data with confidence greater than or equal to the minimum confidence threshold from historical operating data with support greater than or equal to the minimum support threshold based on historical operating data of electrical equipment and corresponding fault types, thereby obtaining strong association rules.

[0065] In this embodiment, historical operating data and corresponding fault types of electrical equipment are determined by historical fault data, and a fault dataset is established. The historical operating data of electrical equipment includes voltage, current, power, speed, etc., and the fault types include electrical equipment fault types such as discharge faults and overheating faults. Based on the association rule algorithm, strong association rules are mined from the fault dataset to realize the effective utilization of the massive high-density historical operating data of thermal power plants.

[0066] S103, obtain the current operating data of the electrical equipment, and determine the current operating status parameters of the electrical equipment based on the current operating data of the electrical equipment, its cluster partition, and the strong correlation rules of historical fault data.

[0067] In some embodiments of this application, the operating status parameters of the electrical equipment are determined based on the current operating data of the electrical equipment and its cluster partition, combined with strong association rules of historical fault data. This includes: obtaining the cluster partition of the electrical equipment, normalizing the cluster center of the cluster partition to obtain the fault weight value of the electrical equipment; obtaining the current operating data of the electrical equipment, obtaining the fault probability of each fault type of the current electrical equipment based on the confidence level of the current operating data in the strong association rule set of the fault type; and multiplying the fault weight value of the electrical equipment by the fault probability of each fault type and then adding them together to obtain the operating status parameters of each electrical equipment.

[0068] In this embodiment, the cluster center of the cluster partition where the electrical equipment is located can represent the current vibration state of the electrical equipment. Therefore, the fault weight value of the electrical equipment is determined by the cluster center. The confidence of the fault type corresponding to the current operating data in the strong association rule set is used as the fault probability of each fault type of the current electrical equipment. The fault probability of each fault type of the electrical equipment is multiplied by the fault weight value and then added to obtain the operating state parameters of each electrical equipment.

[0069] S104: Obtain the ambient temperature during the operation of the electrical equipment, correct the operating status parameters based on the ambient temperature, and determine the evaluation level of the electrical equipment based on the corrected operating status parameters.

[0070] In some embodiments of this application, the step of correcting the operating status parameters based on ambient temperature includes: calculating the difference between the ambient temperature and the real-time internal temperature of the electrical equipment during operation; plotting a temperature difference change curve based on the difference between the ambient temperature and the real-time internal temperature of the electrical equipment; selecting temperature differences greater than a fourth preset threshold from the temperature difference change curve; calculating the proportion of temperature differences greater than a second preset threshold in the temperature difference change curve; using the ratio of the proportion of temperature differences greater than the second preset threshold in the temperature difference change curve to a preset standard proportion as the operating status correction coefficient; and multiplying the operating status correction coefficient by the operating status parameters of the electrical equipment to obtain the corrected operating status parameters.

[0071] In this embodiment, the fourth preset threshold is used as the maximum acceptable temperature difference of the electrical equipment. The operating status parameters are corrected by the ratio of the proportion of temperature differences greater than the fourth preset threshold in the temperature difference change curve to the preset standard proportion, so that the calculation of the operating status parameters of the electrical equipment is more accurate.

[0072] In some embodiments of this application, determining the evaluation level of electrical equipment based on the modified operating status parameters includes: obtaining a preset operating status standard value; calculating the difference between the operating status parameters of the electrical equipment and the preset operating status standard value; determining whether the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than a third preset threshold; if the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the third preset threshold, then the first level is taken as the evaluation level of the electrical equipment; if the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is less than or equal to the third preset threshold, then determining whether the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than a fourth preset threshold; if the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the fourth preset threshold, then the second level is taken as the evaluation level of the electrical equipment; if the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is less than or equal to the fourth preset threshold, then the third level is taken as the evaluation level of the electrical equipment.

[0073] In this embodiment, the operating status of electrical equipment is evaluated and a corresponding level is set by operating status parameters. This can accurately assess the failure risk of electrical equipment and facilitate timely maintenance when electrical equipment malfunctions or is likely to malfunction.

[0074] Based on the same technological concept, such as Figure 2 As shown, the present invention also provides a condition evaluation system for electrical equipment in thermal power plants, comprising: a clustering module for acquiring vibration signals of electrical equipment and clustering each piece of electrical equipment according to the vibration signals; a mining module for acquiring historical fault data of electrical equipment and mining strong association rules of historical fault data based on an association rule algorithm; a calculation module for acquiring current operating data of electrical equipment and determining the current operating status parameters of electrical equipment based on the current operating data of electrical equipment, its clustering partition, and the strong association rules of historical fault data; and an evaluation module for acquiring the ambient temperature during the operation of electrical equipment, correcting the operating status parameters according to the ambient temperature, and determining the evaluation level of electrical equipment based on the corrected operating status parameters.

[0075] By applying the above technical solutions, this invention acquires vibration signals from electrical equipment and clusters and partitions the equipment based on these signals; it acquires historical fault data of the equipment and mines strong association rules based on association rule algorithms; it acquires current operating data of the equipment and determines the current operating status parameters based on the current operating data, the equipment's cluster partition, and the strong association rules from historical fault data; it acquires the ambient temperature during equipment operation, corrects the operating status parameters based on the ambient temperature, and determines the evaluation level of the equipment based on the corrected operating status parameters. This invention performs condition evaluation on electrical equipment in thermal power plants by clustering electrical equipment and calculating operating status parameters, accurately assessing the failure risk of the electrical equipment.

[0076] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented in hardware or by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) and includes several instructions to cause a computer device (such as a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for evaluating the condition of electrical equipment in a thermal power plant, characterized in that, The method includes: Acquire vibration signals from electrical equipment and cluster and partition the electrical equipment based on the vibration signals. Acquire historical fault data of electrical equipment and mine strong association rules based on association rule algorithms; Obtain the current operating data of electrical equipment, and determine the current operating status parameters of electrical equipment based on the current operating data of electrical equipment, its cluster partition, and the strong correlation rules of historical fault data; The ambient temperature during the operation of electrical equipment is obtained, the operating status parameters are corrected based on the ambient temperature, and the evaluation level of the electrical equipment is determined based on the corrected operating status parameters. The process of clustering and partitioning electrical equipment based on its vibration signals includes: The vibration signal of the electrical equipment is preprocessed, and the preprocessed vibration signal is subjected to a fast Fourier transform to obtain the vibration signal spectrum. Fault parameters are determined based on the vibration signal spectrum of electrical equipment, and the electrical equipment is clustered based on the fault parameters to obtain the cluster partitions of each electrical equipment. The process of determining fault parameters based on the vibration signal spectrum of electrical equipment includes: The peak points in the vibration signal spectrum are obtained, and the peak points in the vibration signal spectrum that are greater than the first preset threshold are selected. The first fault parameter is determined based on the average peak points that are greater than the first preset threshold. Calculate the absolute value of the slope between the peak point and the adjacent valley point in the vibration signal spectrum, and determine the second fault parameter based on the variance of all absolute values ​​of the slope in the vibration signal spectrum. Obtain the preset standard vibration signal spectrum of the electrical equipment, calculate the area values ​​of the vibration signal spectrum and the preset standard vibration signal spectrum with respect to the coordinate axis during the operating cycle of the electrical equipment, and determine the third fault parameter based on the area difference between the vibration signal spectrum and the preset standard vibration signal spectrum. The first fault parameter, the second fault parameter, and the third fault parameter are normalized, and the normalized first fault parameter, the second fault parameter, and the third fault parameter are set as the first length, the second length, and the third length according to a preset ratio. The first and second lengths are used as the lower and upper bases, respectively, and the third length is used as the height. A frustum is constructed based on the lower base, upper base, and height, and the volume of the frustum is set as the comprehensive fault parameter of the electrical equipment.

2. The method for evaluating the condition of electrical equipment in thermal power plants according to claim 1, characterized in that, The process of clustering electrical equipment based on fault parameters to obtain cluster partitions for each electrical equipment includes: A comprehensive fault parameter dataset is established based on the comprehensive fault parameters of electrical equipment. An initial k value is set, and the initial cluster centers of the comprehensive fault parameter dataset are randomly selected based on the initial k value. Calculate the Euclidean distance between each comprehensive fault parameter in the comprehensive fault parameter dataset and the k initial cluster centers, and cluster the comprehensive fault parameters into the cluster partitions with the closest Euclidean distance to the initial cluster centers; Calculate the average value of the comprehensive fault parameters within each cluster partition, and set new cluster centers based on the average value of the comprehensive fault parameters within each cluster partition; Repeat the process of creating new cluster centers until the cluster centers no longer change, resulting in the final cluster partitions of k electrical devices.

3. The method for evaluating the condition of electrical equipment in thermal power plants according to claim 2, characterized in that, The strong association rules for mining historical fault data based on the association rule algorithm include: Obtain historical operating data and corresponding fault types of electrical equipment, and discretize the historical operating data and corresponding fault types of electrical equipment to obtain a fault dataset; Frequent itemsets in a fault dataset are mined using an association rule algorithm, and strong association rules are determined based on these frequent itemsets.

4. The method for evaluating the condition of electrical equipment in a thermal power plant according to claim 3, characterized in that, The method for mining frequent itemsets in a fault dataset based on association rule algorithms, and determining strong association rules based on the frequent itemsets in the fault dataset, includes: Set a minimum support threshold, and mine historical operating data with support greater than or equal to the minimum support threshold based on the historical operating data of electrical equipment and the corresponding fault types; A minimum confidence threshold is set, and based on the historical operating data of electrical equipment and the corresponding fault types, historical operating data with confidence levels greater than or equal to the minimum confidence threshold are mined from the historical operating data with support greater than or equal to the minimum support threshold to obtain strong association rules.

5. The method for evaluating the condition of electrical equipment in a thermal power plant according to claim 4, characterized in that, The current operating status parameters of the electrical equipment are determined based on its current operating data, its cluster partition, and strong correlation rules from historical fault data. These parameters include: Obtain the cluster partition where the electrical equipment is located, normalize the cluster centers of the cluster partitions, and obtain the fault weight value of the electrical equipment. Obtain the current operating data of the electrical equipment, and based on the confidence of the corresponding fault type in the strong association rule set, obtain the fault probability of each fault type of the current electrical equipment. The operating status parameters of each electrical device are obtained by multiplying the fault weight value of the electrical device by the fault probability of each fault type and then adding them together.

6. The method for evaluating the condition of electrical equipment in a thermal power plant according to claim 5, characterized in that, The correction of operating status parameters based on ambient temperature includes: Calculate the difference between the ambient temperature and the real-time internal temperature of the electrical equipment during operation, plot the temperature difference change curve based on the difference between the ambient temperature and the real-time internal temperature of the electrical equipment, and filter out the temperature difference values ​​in the temperature difference change curve that are greater than the fourth preset threshold. Calculate the proportion of temperature differences greater than the second preset threshold in the temperature difference change curve, and use the ratio of the proportion of temperature differences greater than the second preset threshold in the temperature difference change curve to the preset standard proportion as the operating status correction coefficient. The corrected operating status parameters are obtained by multiplying the operating status correction factor by the operating status parameters of the electrical equipment.

7. The method for evaluating the condition of electrical equipment in a thermal power plant according to claim 6, characterized in that, The process of determining the evaluation level of electrical equipment based on the corrected operating status parameters includes: Obtain the preset standard value of the operating state, calculate the difference between the operating state parameter of the electrical equipment and the preset standard value of the operating state, and determine whether the difference between the operating state parameter of the electrical equipment and the preset standard value of the operating state is greater than the third preset threshold. If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the third preset threshold, then the first level will be used as the evaluation level of the electrical equipment. If the difference between the operating status parameter of the electrical equipment and the preset operating status standard value is less than or equal to the third preset threshold, then determine whether the difference between the operating status parameter of the electrical equipment and the preset operating status standard value is greater than the fourth preset threshold. If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is greater than the fourth preset threshold, then the second level will be used as the evaluation level of the electrical equipment. If the difference between the operating status parameters of the electrical equipment and the preset operating status standard value is less than or equal to the fourth preset threshold, then the third level will be used as the evaluation level of the electrical equipment.

8. A condition assessment system for electrical equipment in a thermal power plant, characterized in that, include: The clustering module is used to acquire vibration signals from electrical equipment and to cluster and partition the electrical equipment based on these vibration signals. The data mining module is used to acquire historical fault data of electrical equipment and mine strong association rules in the historical fault data based on association rule algorithms. The calculation module is used to obtain the current operating data of electrical equipment, and determine the current operating status parameters of electrical equipment based on the current operating data of electrical equipment, its cluster partition, and the strong correlation rules of historical fault data. The evaluation module is used to obtain the ambient temperature during the operation of electrical equipment, correct the operating status parameters based on the ambient temperature, and determine the evaluation level of the electrical equipment based on the corrected operating status parameters. The clustering module clusters and partitions each electrical device based on its vibration signals, including: The vibration signal of the electrical equipment is preprocessed, and the preprocessed vibration signal is subjected to a fast Fourier transform to obtain the vibration signal spectrum. Fault parameters are determined based on the vibration signal spectrum of electrical equipment, and the electrical equipment is clustered based on the fault parameters to obtain the cluster partitions of each electrical equipment. The process of determining fault parameters based on the vibration signal spectrum of electrical equipment includes: The peak points in the vibration signal spectrum are obtained, and the peak points in the vibration signal spectrum that are greater than the first preset threshold are selected. The first fault parameter is determined based on the average peak points that are greater than the first preset threshold. Calculate the absolute value of the slope between the peak point and the adjacent valley point in the vibration signal spectrum, and determine the second fault parameter based on the variance of all absolute values ​​of the slope in the vibration signal spectrum. Obtain the preset standard vibration signal spectrum of the electrical equipment, calculate the area values ​​of the vibration signal spectrum and the preset standard vibration signal spectrum with respect to the coordinate axis during the operating cycle of the electrical equipment, and determine the third fault parameter based on the area difference between the vibration signal spectrum and the preset standard vibration signal spectrum. The first fault parameter, the second fault parameter, and the third fault parameter are normalized, and the normalized first fault parameter, the second fault parameter, and the third fault parameter are set as the first length, the second length, and the third length according to a preset ratio. The first and second lengths are used as the lower and upper bases, respectively, and the third length is used as the height. A frustum is constructed based on the lower base, upper base, and height, and the volume of the frustum is set as the comprehensive fault parameter of the electrical equipment.

Images