Management method and system of traction equipment for power grid

Abstract

The invention is suitable for the field of power grid equipment management, and provides a management method and system for traction equipment for a power grid, and the method comprises the steps: collecting the operation parameters of a target bearing in the traction equipment in real time, and the operation parameters comprise a vibration signal, a temperature signal and a rotating speed signal; the target bearing operation parameters are analyzed and processed, and the real-time state of the bearing is determined; measuring the loss factor of the targeted insulating medium in the traction equipment in real time, and predicting the real-time variation of the loss factor; evaluating the real-time operation state of the traction equipment based on the real-time state of the target bearing and the real-time variation of the loss factor of the target insulating medium; based on the evaluation result of the real-time operation state of the traction equipment, equipment early warning information is matched, corresponding maintenance suggestions are sent, real-time monitoring and accurate evaluation of the traction equipment can be achieved, and sudden faults of the equipment are effectively avoided. Power grid power supply interruption caused by equipment faults is reduced, and the stability of power transmission and distribution is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the field of power grid equipment management, and in particular relates to a management method and system for traction equipment used in a power grid. Background Art

[0002] With the continuous development of modern power grids, the efficiency and safety of power transmission have become increasingly important issues. Grid maintenance and operation involve a large number of devices. Traction equipment, as one of the most important components of the power system, plays a crucial role in ensuring the normal operation of the grid. Traditional traction equipment management methods rely on manual operations and record-keeping, which cannot meet the requirements of efficient, safe, and automated management.

[0003] With technological advancements, information-based and intelligent traction equipment management systems are gradually emerging. However, existing traction equipment management systems often lack effective automatic monitoring and real-time feedback mechanisms, cannot quickly respond to equipment failures or abnormalities, and lack information sharing, which affects equipment maintenance and management efficiency. Therefore, there is an urgent need for a new power grid traction equipment management method and system. Through efficient information collection, data processing, and intelligent analysis, this method can improve the management efficiency and operational safety of traction equipment, reduce equipment failure rates, and optimize power grid operating costs. Summary of the Invention

[0004] The purpose of the present invention is to provide a management method and system for traction equipment for a power grid, aiming to solve the problems raised in the above background technology.

[0005] The present invention is implemented as follows: on the one hand, a method for managing traction equipment for a power grid, the method comprising:

[0006] Real-time collection of operating parameters of targeted bearings in traction equipment, including vibration signals, temperature signals, and speed signals;

[0007] Analyze and process targeted bearing operating parameters to determine the real-time status of the bearing;

[0008] Real-time measurement of the loss factor of the targeted insulating medium in the traction equipment and prediction of the real-time change of the loss factor;

[0009] Evaluate the real-time operating status of traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor;

[0010] Based on the evaluation results of the real-time operating status of the traction equipment, match the equipment warning information and send corresponding maintenance suggestions.

[0011] As a further solution of the present invention, the analyzing and processing of the target bearing operating parameters to determine the real-time status of the bearing specifically includes:

[0012] If there are abnormal parameter values of the vibration signal, the vibration signal is converted to the frequency domain based on the frequency domain analysis method to generate a frequency domain vibration signal;

[0013] Analyze characteristic frequency components based on frequency domain vibration signals;

[0014] Correlate the target bearing temperature signal and speed signal to determine the target bearing fault type and fault location.

[0015] As a further embodiment of the present invention, the real-time measurement of the loss factor of the targeted insulating medium in the traction device and the prediction of the real-time change of the loss factor specifically include:

[0016] Measuring the targeted insulation dielectric loss factor at preset time intervals;

[0017] Compare two adjacent loss factor measurement values, calculate and generate real-time changes;

[0018] Perform trend analysis on several real-time changes.

[0019] As a further solution of the present invention, the trend analysis of the plurality of real-time changes specifically includes:

[0020] Calculate the Pearson correlation coefficient of several real-time changes;

[0021] If the Pearson correlation coefficient is greater than a preset coefficient threshold, several linear relationship models between real-time change and time are established;

[0022] Based on the linear relationship model, the linear model parameters are determined by the least square method to generate a linear equation of the real-time change over time;

[0023] Generate trend prediction model based on linear equation;

[0024] Based on the trend prediction model, a predicted value of the real-time change in loss factor is generated.

[0025] As a further solution of the present invention, the evaluation of the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor specifically includes:

[0026] Obtain the predicted values of abnormal vibration signal parameters and real-time changes in loss factor;

[0027] Fusion of abnormal vibration signal parameter values and predicted values of real-time loss factor changes to generate a targeted management feature vector;

[0028] Input the targeted management feature vector into the preset fault model;

[0029] If the targeted management feature vector matches the fault state pattern in the preset fault model, the fault type is determined and reported.

[0030] As a further embodiment of the present invention, in another aspect, a management system for traction equipment for a power grid is provided, the system comprising:

[0031] A real-time acquisition module is used to acquire the operating parameters of the targeted bearing in the traction equipment in real time, wherein the operating parameters include vibration signals, temperature signals, and speed signals;

[0032] An analysis module is used to analyze and process the operating parameters of the targeted bearing and determine the real-time status of the bearing;

[0033] A real-time measurement module for measuring the loss factor of a targeted insulating medium in traction equipment in real time;

[0034] Prediction module, used to predict the real-time change of loss factor;

[0035] An evaluation module for evaluating the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor;

[0036] The matching and sending module is used to match equipment warning information and send corresponding maintenance suggestions based on the evaluation results of the real-time operating status of the traction equipment.

[0037] As a further solution of the present invention, the analysis module specifically includes:

[0038] A first calculation unit is used to calculate and analyze the vibration signal based on a time domain analysis method;

[0039] A first acquiring unit is used to acquire an abnormal parameter value of the vibration signal;

[0040] a conversion unit, configured to convert the vibration signal into a frequency domain based on a frequency domain analysis method if an abnormal parameter value of the vibration signal exists;

[0041] A first generating unit, configured to generate a frequency domain vibration signal;

[0042] An analysis unit, configured to analyze characteristic frequency components based on the frequency domain vibration signal;

[0043] a correlation unit, configured to correlate a targeted bearing temperature signal and a speed signal;

[0044] The determination unit is used to determine the target bearing fault type and fault location.

[0045] As a further solution of the present invention, the real-time measurement module specifically includes:

[0046] A measuring unit, configured to measure a targeted insulation dielectric loss factor at preset time intervals;

[0047] A comparison unit, used to compare two adjacent loss factor measurement values;

[0048] A calculation and generation unit, used for calculating and generating real-time changes;

[0049] The trend analysis unit is used to perform trend analysis on a number of real-time change quantities.

[0050] As a further solution of the present invention, the trend analysis unit specifically includes:

[0051] The second calculation unit is used to calculate the Pearson correlation coefficient of several real-time change quantities;

[0052] A linear relationship model unit is used to establish a plurality of linear relationship models between real-time variation and time if the Pearson correlation coefficient is greater than a preset coefficient threshold;

[0053] The second generating unit is used to determine the linear model parameters by the least square method based on the linear relationship model, and generate a linear equation in which the real-time variation changes with time;

[0054] A third generating unit is used to generate a trend prediction model based on the linear equation;

[0055] The third generating unit is used to generate a predicted value of the real-time change of the loss factor according to the trend prediction model.

[0056] As a further solution of the present invention, the evaluation module specifically includes:

[0057] The second acquisition unit is used to obtain the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor;

[0058] A fusion unit is used to fuse the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor;

[0059] a fourth generating unit, configured to generate a targeted management feature vector;

[0060] An input unit, used for inputting a targeted management feature vector into a preset fault model;

[0061] The determination unit is configured to determine and report the fault type if the targeted management feature vector matches the fault state pattern in the preset fault model.

[0062] The present invention provides a method and system for managing traction equipment for power grids. This method and system enable real-time monitoring and precise assessment of traction equipment, proactively identifying potential bearing failures and insulation degradation, effectively preventing sudden equipment failures. This reduces power grid interruptions caused by equipment failures, ensures the stability of power transmission and distribution, minimizes economic losses, and improves the reliability and safety of power grid operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 The present invention is a main flow chart of a method for managing traction equipment for a power grid.

[0064] Figure 2 The invention discloses a flow chart for analyzing and processing target bearing operating parameters and determining the real-time status of bearings in a management method for traction equipment used in a power grid.

[0065] Figure 3 The invention discloses a flow chart for measuring the loss factor of a targeted insulating medium in the traction equipment in real time and predicting the real-time change of the loss factor in a management method of traction equipment for a power grid.

[0066] Figure 4 The present invention is a flow chart for trend analysis of real-time variation in a management method of traction equipment for a power grid.

[0067] Figure 5 The invention discloses a flow chart for evaluating the real-time operating status of traction equipment based on the real-time status of a targeted bearing and the real-time variation of a targeted insulation medium loss factor in a management method for traction equipment for a power grid.

[0068] Figure 6 This is a main structural diagram of a management system for traction equipment used in power grids.

[0069] Figure 7 The present invention is a structural block diagram of an analysis module in a management system for traction equipment used in a power grid.

[0070] Figure 8 The present invention is a structural block diagram of a real-time measurement module in a management system for traction equipment used in a power grid.

[0071] Figure 9 The present invention is a structural block diagram of a trend analysis unit in a management system for traction equipment used in a power grid.

[0072] Figure 10 The present invention is a structural block diagram of an evaluation module in a management system for traction equipment used in a power grid. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0074] The specific implementation of the present invention is described in detail below with reference to specific embodiments.

[0075] The present invention provides a method and system for managing traction equipment for a power grid, which solves the technical problems in the background technology.

[0076] like Figure 1 FIG. 1 is a main flow chart of a method for managing traction equipment for a power grid according to an embodiment of the present invention. The method for managing traction equipment for a power grid includes:

[0077] Step S100: collecting operating parameters of the targeted bearing in the traction equipment in real time;

[0078] The operating parameters include vibration signals, temperature signals, and speed signals;

[0079] Step S200: analyzing and processing the operating parameters of the targeted bearing to determine the real-time status of the bearing;

[0080] Step S300: measuring the loss factor of the targeted insulating medium in the traction device in real time, and predicting the real-time change of the loss factor;

[0081] Step S400: evaluating the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor;

[0082] Step S500: Based on the evaluation results of the real-time operating status of the traction equipment, match the equipment warning information and send corresponding maintenance suggestions;

[0083] When this embodiment is applied, high-precision sensors are first used to collect the vibration signal, temperature signal, and speed signal of the targeted bearing in real time. Time domain analysis is used to calculate parameters such as the mean and variance of the vibration signal, and frequency domain analysis is used to determine the fault characteristic frequency. The real-time status of the bearing is accurately determined by combining the temperature and speed signals. A professional dielectric loss meter is used to measure the loss factor of the targeted insulating medium at fixed time intervals. Time series analysis and other methods are used to predict the real-time change in the loss factor based on historical data and current measurements. The real-time status of the bearing and the real-time change in the insulation medium loss factor are used as key indicators. After normalization, features are extracted and fused. These features are input into a fault judgment model based on machine learning or deep learning, matched with normal and faulty state patterns, and the real-time operating status of the traction equipment is evaluated. Finally, based on the evaluation results, if there is a potential fault in the equipment, corresponding warning information is matched from the equipment maintenance knowledge base based on the type and severity of the fault, and sent via SMS, email, etc., with targeted maintenance measures and repair plan recommendations.

[0084] like Figure 2 As shown in FIG. 1 , as a preferred embodiment of the present invention, the analysis and processing of the target bearing operating parameters to determine the real-time state of the bearing specifically includes:

[0085] Step S201: Calculate and analyze the vibration signal based on the time domain analysis method to obtain abnormal parameter values of the vibration signal;

[0086] Step S202: If there is an abnormal parameter value of the vibration signal, convert the vibration signal into the frequency domain based on the frequency domain analysis method to generate a frequency domain vibration signal;

[0087] Step S203: Analyze characteristic frequency components based on the frequency domain vibration signal;

[0088] Step S204: Correlate the target bearing temperature signal and the speed signal to determine the target bearing fault type and fault location.

[0089] When applied, this embodiment uses a time domain analysis method to perform in-depth computational analysis on the collected vibration signal. Various parameters of the vibration signal are calculated using a preset algorithm to obtain abnormal parameter values of the vibration signal. Once an abnormal parameter value is detected, it indicates that the bearing has a potential operational failure. When an abnormal vibration signal is found, a frequency domain analysis method is used to convert the vibration signal from the time domain to the frequency domain to generate a frequency domain vibration signal. Frequency domain analysis can decompose complex vibration signals into different frequency components, providing richer information for fault diagnosis. Based on the generated frequency domain vibration signal, the characteristic frequency components are analyzed. Different fault types correspond to specific characteristic frequencies. By identifying the characteristic frequencies, the nature of the fault can be determined, and the temperature signal and speed signal of the targeted bearing are then included in the analysis scope. Abnormal temperature increases or unstable fluctuations in speed are closely related to bearing failures. By comprehensively considering the frequency domain analysis results of the vibration signal, the temperature signal, and the speed signal, and utilizing a pre-established algorithm model or expert knowledge base, the fault type and location of the targeted bearing can be accurately determined. Furthermore, for example, if a significant vibration peak is detected at a specific frequency and the bearing temperature exceeds the normal range, combined with the speed change, it can be determined whether it is bearing wear, fatigue cracks or other fault types, and the specific location of the fault can be determined.

[0090] like Figure 3 As shown, as a preferred embodiment of the present invention, the real-time measurement of the loss factor of the targeted insulating medium in the traction equipment and the prediction of the real-time change of the loss factor specifically include:

[0091] Step S301: measuring the targeted insulation dielectric loss factor at a preset time interval;

[0092] Step S302: comparing two adjacent loss factor measurement values, calculating and generating a real-time change;

[0093] Step S303: performing trend analysis on a number of real-time changes;

[0094] In this embodiment, specialized measuring instruments are used to measure the targeted insulation loss factor at preset intervals. Stable and regular measurement intervals ensure data continuity and comparability. Subsequently, the two consecutive loss factor measurements are compared to calculate and generate a real-time change in the loss factor. This real-time change intuitively reflects the dynamic changes in insulation performance over a short period of time. Finally, trend analysis is performed on these real-time changes.

[0095] like Figure 4 As shown in FIG. 1 , as a preferred embodiment of the present invention, the trend analysis of a plurality of real-time variation quantities specifically includes:

[0096] Step S3031: Calculate the Pearson correlation coefficient of several real-time changes;

[0097] Step S3032: If the Pearson correlation coefficient is greater than the preset coefficient threshold, establish a plurality of linear relationship models between the real-time change amount and time;

[0098] Step S3033: Based on the linear relationship model, the linear model parameters are determined by the least square method to generate a linear equation for the real-time variation over time;

[0099] Step S3034: generating a trend prediction model based on the linear equation;

[0100] Step S3035: Generate a predicted value of the real-time change of the loss factor according to the trend prediction model;

[0101] It should be understood that the Pearson correlation coefficients of several real-time changes are calculated. The Pearson correlation coefficient is used to measure the degree of linear correlation between two variables, and its value ranges from -1 to 1. In this technical process, we use a specific algorithm to calculate the Pearson correlation coefficient between each real-time change and time. If the Pearson correlation coefficient is greater than a preset coefficient threshold (such as 0.8), it indicates that there is a strong linear correlation between these real-time changes and time. At this point, based on this linear correlation, several linear relationship models between real-time changes and time are established. The linear model parameters are determined using the least squares method. The principle of the least squares method is to minimize the sum of squared errors between the observed values and the model predicted values, thereby finding the linear model parameters that best match the data trend. After the parameters are calculated, a linear equation is generated to show the change of the real-time change over time. Based on this linear equation, a trend prediction model is further generated. Using this trend prediction model, by inputting future time values, the predicted value of the real-time change of the loss factor can be calculated.

[0102] like Figure 5 As shown, as a preferred embodiment of the present invention, the evaluation of the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change of the targeted insulation dielectric loss factor specifically includes:

[0103] Step S401: Obtaining abnormal parameter values of vibration signals and predicted values of real-time changes in loss factor;

[0104] Step S402: Fusion of the abnormal vibration signal parameter value and the predicted value of the real-time change of the loss factor to generate a targeted management feature vector;

[0105] Step S403: inputting the targeted management feature vector into the preset fault model;

[0106] Step S404: If the targeted management feature vector matches the fault state pattern in the preset fault model, the fault type is determined and reported.

[0107] When this embodiment is applied, the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor are first obtained. These two key data reflect the operating conditions of the bearing and the insulating medium, respectively. The abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor are then integrated to generate a targeted management feature vector. The management feature vector integrates the status information of the key components of the equipment. The targeted management feature vector is then input into a preset fault model, which contains various known fault status patterns. If the targeted management feature vector matches the fault status pattern in the preset fault model, the system can quickly determine the fault type and report it in a timely manner.

[0108] Furthermore, the process of establishing the preset fault model is as follows: (1) Data collection: extensively collect a large amount of data on the traction equipment in normal operation and various known fault states, including vibration signals, temperature signals, speed signals of the target bearings, and loss factors and their variations of the target insulation medium; (2) Feature engineering: extract effective features from the collected data. At the same time, preprocess the data; (3) Model selection: select the appropriate model type, such as support vector machine (SVM), random forest, neural network, based on the data characteristics and fault diagnosis requirements; (4) Model training: divide the preprocessed and feature-extracted data into training sets and test sets, and use the training set to train the selected model. During the training process, by adjusting the model parameters, the model can accurately learn the characteristic patterns of the data in normal and fault states; (5) Model evaluation and optimization: use the test set to evaluate the trained model, and evaluate the performance of the model by calculating indicators such as accuracy, recall rate, and F1 value.

[0109] like Figure 6 As shown, as another preferred embodiment of the present invention, on the other hand, a management system for traction equipment for a power grid, the system includes:

[0110] A real-time acquisition module 100 is used to acquire operating parameters of a targeted bearing in a traction device in real time, wherein the operating parameters include vibration signals, temperature signals, and speed signals;

[0111] Analysis module 200, used to analyze and process the operating parameters of the targeted bearing to determine the real-time status of the bearing;

[0112] A real-time measurement module 300 is used to measure the loss factor of the targeted insulating medium in the traction equipment in real time;

[0113] Prediction module 400, used to predict the real-time change of loss factor;

[0114] An evaluation module 500 is used to evaluate the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor;

[0115] The matching and sending module 600 is used to match the equipment warning information and send corresponding maintenance suggestions based on the evaluation results of the real-time operating status of the traction equipment.

[0116] When this embodiment is applied, the real-time acquisition module 100 acquires the operating parameters of the targeted bearing in the traction equipment in real time, and the operating parameters include vibration signals, temperature signals, and speed signals. The analysis module 200 analyzes and processes the operating parameters of the targeted bearing to determine the real-time status of the bearing. The real-time measurement module 300 measures the loss factor of the targeted insulating medium in the traction equipment in real time. The prediction module 400 predicts the real-time change of the loss factor based on the real-time status of the targeted bearing and the real-time change of the loss factor of the targeted insulating medium. The evaluation module 500 evaluates the real-time operating status of the traction equipment. Based on the evaluation result of the real-time operating status of the traction equipment, the matching and sending module 600 matches the equipment warning information and sends corresponding maintenance suggestions.

[0117] like Figure 7 As shown, as another preferred embodiment of the present invention, the analysis module 200 specifically includes:

[0118] The first calculation unit 201 is used to calculate and analyze the vibration signal based on the time domain analysis method;

[0119] A first acquiring unit 202 is configured to acquire an abnormal parameter value of a vibration signal;

[0120] A conversion unit 203 is configured to convert the vibration signal into a frequency domain based on a frequency domain analysis method if there is an abnormal parameter value of the vibration signal;

[0121] A first generating unit 204 is configured to generate a frequency domain vibration signal;

[0122] An analysis unit 205 is configured to analyze characteristic frequency components based on the frequency domain vibration signal;

[0123] a correlation unit 206 for correlating the targeted bearing temperature signal and the speed signal;

[0124] The determination unit 207 is configured to determine the target bearing fault type and fault location.

[0125] When this embodiment is applied, based on the time domain analysis method, the first calculation unit 201 calculates and analyzes the vibration signal, the first acquisition unit 202 obtains the abnormal parameter value of the vibration signal, if there is an abnormal parameter value of the vibration signal, based on the frequency domain analysis method, the conversion unit 203 converts the vibration signal to the frequency domain, the first generation unit 204 generates a frequency domain vibration signal, based on the frequency domain vibration signal, the analysis unit 205 analyzes the characteristic frequency component, the association unit 206 associates the target bearing temperature signal and the speed signal, and the determination unit 207 determines the target bearing fault type and fault location.

[0126] like Figure 8 As shown, as another preferred embodiment of the present invention, the real-time measurement module 300 specifically includes:

[0127] The measuring unit 301 is configured to measure the target insulation dielectric loss factor at preset time intervals;

[0128] A comparison unit 302 is used to compare two adjacent loss factor measurement values;

[0129] The calculation and generation unit 303 is used to calculate and generate real-time variation;

[0130] The trend analysis unit 304 is used to perform trend analysis on a number of real-time variation quantities.

[0131] When this embodiment is applied, the measuring unit 301 measures the loss factor of the targeted insulating medium at a preset time interval, the comparing unit 302 compares the measured values of the loss factor of two adjacent times, the calculating and generating unit 303 calculates and generates a real-time variation, and the trend analyzing unit 304 performs trend analysis on a number of real-time variation.

[0132] like Figure 9 As shown, as another preferred embodiment of the present invention, the trend analysis unit 304 specifically includes:

[0133] The second calculation unit 3041 is used to calculate the Pearson correlation coefficient of a plurality of real-time change quantities;

[0134] The linear relationship model unit 3042 is used to establish a plurality of linear relationship models between the real-time variation and time if the Pearson correlation coefficient is greater than a preset coefficient threshold;

[0135] The second generating unit 3043 is configured to determine the linear model parameters by the least square method based on the linear relationship model, and generate a linear equation for the real-time variation over time;

[0136] The third generating unit 3044 is used to generate a trend prediction model based on the linear equation;

[0137] The third generating unit 3045 is configured to generate a predicted value of the real-time change of the loss factor according to the trend prediction model.

[0138] When this embodiment is applied, the second calculation unit 3041 calculates the Pearson correlation coefficient of several real-time change quantities. If the Pearson correlation coefficient is greater than the preset coefficient threshold, the linear relationship model unit 3042 establishes several linear relationship models between real-time change quantities and time. Based on the linear relationship model, the linear model parameters are determined by the least squares method. The second generation unit 3043 generates a linear equation for the real-time change quantity changing with time. Based on the linear equation, the third generation unit 3044 generates a trend prediction model. According to the trend prediction model, the third generation unit 3045 generates a predicted value of the real-time change quantity of the loss factor.

[0139] like Figure 10 As shown, as another preferred embodiment of the present invention, the evaluation module 500 specifically includes:

[0140] The second acquisition unit 501 is used to obtain the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor;

[0141] A fusion unit 502 is used to fuse the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor;

[0142] The fourth generating unit 503 is configured to generate a targeted management feature vector;

[0143] An input unit 504 is used to input a targeted management feature vector into a preset fault model;

[0144] The determination unit 505 is configured to determine and report the fault type if the targeted management feature vector matches the fault state pattern in the preset fault model.

[0145] When this embodiment is applied, the second acquisition unit 501 acquires the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor, the fusion unit 502 fuses the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor, the fourth generation unit 503 generates a targeted management feature vector, and the input unit 504 inputs the targeted management feature vector to the preset fault model. If the targeted management feature vector matches the fault state pattern in the preset fault model, the determination unit 505 determines and reports the fault type.

[0146] The above-mentioned embodiment of the present invention provides a management method for traction equipment for power grids, and provides a management system for traction equipment for power grids. First, high-precision sensors are used to collect the vibration signal, temperature signal and speed signal of the targeted bearing in real time. The mean, variance and other parameters of the vibration signal are calculated through time domain analysis, the fault characteristic frequency is determined through frequency domain analysis, and the real-time status of the bearing is accurately judged by combining the temperature and speed signals. A professional dielectric loss measuring instrument is used to measure the loss factor of the targeted insulating medium at fixed time intervals, and time series analysis and other methods are used to predict the real-time change in the loss factor based on historical data and current measurement values. The real-time status of the bearing and the real-time change in the loss factor of the insulating medium are used as key indicators. After normalization, the features are extracted and fused, and input into a fault judgment model based on machine learning or deep learning. The model is matched with the normal and fault state patterns to evaluate the real-time operating status of the traction equipment. Finally, based on the assessment results, if the equipment has a potential fault, corresponding warning information is matched from the equipment maintenance knowledge base based on the fault type and severity. This information is sent via text message, email, and other means, and targeted maintenance measures and repair plan recommendations are provided. This method and system can achieve real-time monitoring and accurate assessment of traction equipment, early detection of potential bearing failures and insulation degradation, and effectively avoid sudden equipment failures. This reduces power outages caused by equipment failures, ensures the stability of power transmission and distribution, reduces economic losses, and improves the reliability and safety of power grid operations.

[0147] In order to enable the above-mentioned method and system to be loaded and run smoothly, in addition to the various modules mentioned above, the system may also include more or fewer components than described above, or a combination of certain components, or different components, for example, it may include input and output devices, network access devices, buses, processors and memories, etc.

[0148] The processor may be a central processing unit, other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor is the control center of the system, connecting various components using various interfaces and lines.

[0149] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0150] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0151] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for managing traction equipment for a power grid, characterized in that: The method comprises: Real-time collection of operating parameters of targeted bearings in traction equipment, including vibration signals, temperature signals, and speed signals; Analyze and process targeted bearing operating parameters to determine the real-time status of the bearing; Real-time measurement of the loss factor of the targeted insulating medium in the traction equipment and prediction of the real-time change of the loss factor; Evaluate the real-time operating status of traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor; Based on the evaluation results of the real-time operating status of the traction equipment, match the equipment warning information and send corresponding maintenance suggestions.

2. The method for managing traction equipment for a power grid according to claim 1, characterized in that: The analysis and processing of the target bearing operating parameters to determine the real-time status of the bearing specifically includes: Based on the time domain analysis method, calculate and analyze the vibration signal to obtain the abnormal parameter value of the vibration signal; If there are abnormal parameter values of the vibration signal, the vibration signal is converted to the frequency domain based on the frequency domain analysis method to generate a frequency domain vibration signal; Analyze characteristic frequency components based on frequency domain vibration signals; Correlate the target bearing temperature signal and speed signal to determine the target bearing fault type and fault location.

3. The method for managing traction equipment for a power grid according to claim 1, characterized in that: The real-time measurement of the loss factor of the targeted insulating medium in the traction equipment and the prediction of the real-time change of the loss factor specifically include: Measuring the targeted insulation dielectric loss factor at preset time intervals; Compare two adjacent loss factor measurement values, calculate and generate real-time changes; Perform trend analysis on several real-time changes.

4. The method for managing traction equipment for a power grid according to claim 3, characterized in that: The trend analysis of a plurality of real-time variation quantities specifically includes: Calculate the Pearson correlation coefficient of several real-time changes; If the Pearson correlation coefficient is greater than a preset coefficient threshold, several linear relationship models between real-time change and time are established; Based on the linear relationship model, the linear model parameters are determined by the least square method to generate a linear equation of the real-time change over time; Generate trend prediction model based on linear equation; Based on the trend prediction model, a predicted value of the real-time change in loss factor is generated.

5. The method for managing traction equipment for a power grid according to claim 2 or claim 4, characterized in that: The evaluation of the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor specifically includes: Obtain the predicted values of abnormal vibration signal parameters and real-time changes in loss factor; Fusion of abnormal vibration signal parameter values and predicted values of real-time loss factor changes to generate a targeted management feature vector; Input the targeted management feature vector into the preset fault model; If the targeted management feature vector matches the fault state pattern in the preset fault model, the fault type is determined and reported.

6. A management system for traction equipment used in a power grid, characterized in that: The method for managing traction equipment for a power grid according to any one of claims 1 to 5 is applied, wherein the system comprises: A real-time acquisition module is used to acquire the operating parameters of the targeted bearing in the traction equipment in real time, wherein the operating parameters include vibration signals, temperature signals, and speed signals; An analysis module is used to analyze and process the operating parameters of the targeted bearing and determine the real-time status of the bearing; A real-time measurement module for measuring the loss factor of a targeted insulating medium in traction equipment in real time; Prediction module, used to predict the real-time change of loss factor; An evaluation module for evaluating the real-time operating status of the traction equipment based on the real-time status of the targeted bearing and the real-time change in the targeted insulation dielectric loss factor; The matching and sending module is used to match equipment warning information and send corresponding maintenance suggestions based on the evaluation results of the real-time operating status of the traction equipment.

7. The management system for traction equipment for a power grid according to claim 6, characterized in that: The analysis module specifically includes: A first calculation unit is used to calculate and analyze the vibration signal based on a time domain analysis method; A first acquiring unit is used to acquire an abnormal parameter value of the vibration signal; a conversion unit, configured to convert the vibration signal into a frequency domain based on a frequency domain analysis method if an abnormal parameter value of the vibration signal exists; A first generating unit, configured to generate a frequency domain vibration signal; An analysis unit, configured to analyze characteristic frequency components based on the frequency domain vibration signal; a correlation unit, configured to correlate a targeted bearing temperature signal and a speed signal; The determination unit is used to determine the target bearing fault type and fault location.

8. The management system for traction equipment for a power grid according to claim 6, characterized in that: The real-time measurement module specifically includes: A measuring unit, configured to measure a targeted insulation dielectric loss factor at preset time intervals; A comparison unit, used to compare two adjacent loss factor measurement values; A calculation and generation unit, used for calculating and generating real-time changes; The trend analysis unit is used to perform trend analysis on a number of real-time change quantities.

9. The management system for traction equipment for a power grid according to claim 8, characterized in that: The trend analysis unit specifically includes: The second calculation unit is used to calculate the Pearson correlation coefficient of several real-time change quantities; A linear relationship model unit is used to establish a plurality of linear relationship models between real-time variation and time if the Pearson correlation coefficient is greater than a preset coefficient threshold; The second generating unit is used to determine the linear model parameters by the least square method based on the linear relationship model, and generate a linear equation in which the real-time variation changes with time; A third generating unit is used to generate a trend prediction model based on the linear equation; The third generating unit is used to generate a predicted value of the real-time change of the loss factor according to the trend prediction model.

10. The management system for traction equipment for a power grid according to claim 7 or claim 9, characterized in that: The evaluation module specifically includes: The second acquisition unit is used to obtain the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor; A fusion unit is used to fuse the abnormal parameter value of the vibration signal and the predicted value of the real-time change of the loss factor; a fourth generating unit, configured to generate a targeted management feature vector; An input unit, used for inputting a targeted management feature vector into a preset fault model; The determination unit is configured to determine and report the fault type if the targeted management feature vector matches the fault state pattern in the preset fault model.

Images