Fault diagnosis method and system for generator excitation system

Abstract

The invention provides a fault diagnosis method and system for a generator excitation system, and the method comprises the steps: collecting the operation parameters of the generator excitation system in real time, and carrying out the preprocessing of the operation parameters; inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and performing optimization solution on the fault diagnosis model by using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system; and displaying a fault diagnosis result corresponding to the operation parameters of the generator excitation system. According to the technical scheme provided by the invention, real-time monitoring, fault diagnosis and performance optimization can be carried out on the excitation system, and the stability and reliability of a power system are improved.

Description

Technical Field

[0001] The present application relates to the technical field of power system monitoring and fault diagnosis, and in particular to a fault diagnosis method and system for a generator excitation system. Background Art

[0002] As a core component of the power system, the excitation system is crucial to maintaining the stable operation of the generator. However, since the excitation system involves many complex electrical and mechanical components, its operating status is easily affected by many factors, such as voltage fluctuations, current overloads, temperature changes, etc. Traditionally, the monitoring and diagnosis of the excitation system mainly rely on manual inspections and regular maintenance. This method is not only time-consuming and labor-intensive, but also inefficient, and it is often difficult to detect and handle faults in the early stages of the fault, which brings potential risks to the stable operation of the power system. Therefore, it is urgent to propose a solution that can efficiently diagnose and monitor the faults of the generator excitation system. Summary of the invention

[0003] The present application provides a fault diagnosis method and system for a generator excitation system, so as to at least solve the technical problems of the prior art that the fault is time-consuming and labor-intensive, inefficient, and difficult to detect and handle immediately at the early stage of the fault.

[0004] The first embodiment of the present application provides a fault diagnosis method for a generator excitation system, the method comprising:

[0005] Collecting operating parameters of the generator excitation system in real time and preprocessing the operating parameters;

[0006] Inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system;

[0007] The fault diagnosis results corresponding to the operating parameters of the generator excitation system are displayed.

[0008] Preferably, the operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

[0009] Furthermore, the fault diagnosis model training process includes:

[0010] Obtaining the preprocessed operating parameters of the generator excitation system at each moment in the historical period and the fault labels corresponding to the operating parameters;

[0011] The operating parameters are used as input, the fault labels corresponding to the operating parameters are used as output, and a particle swarm optimization algorithm is used to optimize and train the initial support vector machine model to obtain a trained fault diagnosis model.

[0012] Furthermore, the method further comprises:

[0013] Constructing a simulation model of the generator excitation system according to digital twin technology;

[0014] Based on the simulation model of the generator excitation system, simulate the system operation status under various preset working conditions to predict the fault type of the generator excitation system;

[0015] Wherein, the simulation model of the generator excitation system includes: a physical model, a behavioral model and an interactive model.

[0016] Furthermore, the method further comprises:

[0017] When the operating data of the generator excitation system is greater than the corresponding threshold value, an alarm is issued.

[0018] The second embodiment of the present application provides a fault diagnosis system for a generator excitation system, comprising:

[0019] The acquisition module is used to acquire the operating parameters of the generator excitation system in real time and pre-process the operating parameters;

[0020] A diagnosis module, used for inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system;

[0021] The display module is used to display the fault diagnosis results corresponding to the operating parameters of the generator excitation system.

[0022] Preferably, the operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

[0023] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in the first aspect is implemented.

[0024] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect of the present application.

[0025] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects:

[0026] The present application proposes a fault diagnosis method and system for a generator excitation system, the method comprising: real-time acquisition of operating parameters of the generator excitation system, and preprocessing of the operating parameters; inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain fault diagnosis results corresponding to the operating parameters of the generator excitation system; and displaying the fault diagnosis results corresponding to the operating parameters of the generator excitation system. The technical solution proposed in the present application can monitor, diagnose faults and optimize the performance of the excitation system in real time, thereby improving the stability and reliability of the power system.

[0027] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0029] Figure 1 A flowchart of a fault diagnosis method for a generator excitation system provided according to an embodiment of the present application;

[0030] Figure 2 A first structural diagram of a fault diagnosis system for a generator excitation system provided according to an embodiment of the present application;

[0031] Figure 3 A second structural diagram of a fault diagnosis system for a generator excitation system provided according to an embodiment of the present application; DETAILED DESCRIPTION

[0032] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0033] The present application proposes a fault diagnosis method and system for a generator excitation system, the method comprising: real-time acquisition of operating parameters of the generator excitation system, and preprocessing of the operating parameters; inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain fault diagnosis results corresponding to the operating parameters of the generator excitation system; and displaying the fault diagnosis results corresponding to the operating parameters of the generator excitation system. The technical solution proposed in the present application can monitor, diagnose faults and optimize the performance of the excitation system in real time, thereby improving the stability and reliability of the power system.

[0034] A fault diagnosis method for a generator excitation system according to an embodiment of the present application is described below with reference to the accompanying drawings.

[0035] Embodiment 1

[0036] Figure 1 A flow chart of a fault diagnosis method for a generator excitation system provided according to an embodiment of the present application is shown in FIG. Figure 1 As shown, the method includes:

[0037] Step 1: collecting operating parameters of the generator excitation system in real time and preprocessing the operating parameters;

[0038] In the embodiment of the present disclosure, the operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

[0039] It should be noted that these operating parameters are collected in real time through sensors and monitoring equipment deployed in key positions of the generator excitation system. The operating parameters include but are not limited to the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, the unit operating condition, real-time abnormal information, the unit operating temperature and other operating parameters, which reflect the real-time operating status of the excitation system.

[0040] It should be noted that the preprocessing of the operating parameters includes:

[0041] The collected operating parameters are cleaned, integrated and formatted to ensure the accuracy and consistency of the data. The processing process includes pre-processing technologies such as data filtering, outlier detection, and data compression.

[0042] Data filtering technology is used to eliminate noise and interference and improve the signal-to-noise ratio of data. Outlier detection technology is used to remove abnormal data points to prevent them from having a negative impact on subsequent analysis. Data compression technology is used to reduce the amount of data and improve the efficiency of data processing. The processed data set will be stored in the database for subsequent intelligent analysis layer use. The database has efficient data storage and retrieval functions and can support the storage and management of large-scale data.

[0043] Step 2: inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system;

[0044] It should be noted that the fault diagnosis model training process includes:

[0045] Obtaining the preprocessed operating parameters of the generator excitation system at each moment in the historical period and the fault labels corresponding to the operating parameters;

[0046] The operating parameters are used as input, the fault labels corresponding to the operating parameters are used as output, and a particle swarm optimization algorithm is used to optimize and train the initial support vector machine model to obtain a trained fault diagnosis model.

[0047] It should be noted that the fault diagnosis function uses machine learning algorithms such as the support vector machine (SVM) algorithm to detect anomalies in the operating data of the excitation system. The SVM algorithm separates normal data from abnormal data by finding the optimal hyperplane in a high-dimensional space. For a given data set, where is a feature vector (such as voltage, current, etc. measurement value) and is the corresponding label (indicating normal or fault), the optimization problem of SVM can be expressed as:

[0048]

[0049] sty i (w T x i +b)≥1-ξ i ,ξ i ≥0,i=1,2,...,n

[0050] Among them, ω and b define the hyperplane, ξ and i are slack variables that allow some data points to be misclassified, and C is a penalty parameter used to control the tolerance of misclassification. By training the SVM model, the platform can identify abnormal data points that do not conform to the normal behavior pattern and trigger an alarm. In addition, the platform also provides a fault model. When training, the input data is the historical operating parameters of the excitation system, including but not limited to the terminal voltage percentage, excitation voltage percentage, current percentage, power factor, rectifier cabinet current sharing coefficient, unit operating temperature, etc. The output data is the label corresponding to these parameters, indicating whether the system is in a normal state or there is some kind of fault.

[0051] When the model is being trained, the input data is the historical operating parameters of the excitation system, including but not limited to the terminal voltage percentage, excitation voltage percentage, current percentage, power factor, rectifier cabinet current sharing coefficient, unit operating temperature, etc. The output data is the labels corresponding to these parameters, indicating whether the system is in a normal state or has some kind of fault.

[0052] An improved support vector machine (SVM) model is used for fault diagnosis. The specific input and output of the model are as follows:

[0053] Input data: eigenvector X = [x1, x2, ..., xn], where xi represents an operating parameter of the excitation system (such as terminal voltage percentage, excitation voltage percentage, etc.), and n is the total number of parameters.

[0054] Output data: label y, indicating the system status. y=1 means the system is normal, y=-1 means the system is faulty.

[0055] SVM model: Given a training data set {(X1,y1),(X2,y2),...,(Xm,ym)}, where Xi is the feature vector and yi is the corresponding label, the training goal of the SVM model is to find an optimal hyperplane so that the two types of samples (normal and faulty) are separated as much as possible. By solving the optimization problem (as shown in the above formula), we can get the parameters ω and b of the SVM model, and thus build a classifier. In practical applications, the real-time collected operating parameters are used as input, and the trained SVM model is used for prediction to obtain the judgment result of whether the system is normal. The preliminary judgment of the type and the possible repair steps guide the maintenance personnel to respond quickly and solve the problem.

[0056] The performance parameters of the excitation system are optimized by using optimization algorithms such as the particle swarm optimization (PSO) algorithm. The PSO algorithm simulates the predation behavior of a flock of birds to find the optimal solution in the search space. Each "particle" represents a possible solution and updates its speed and position based on its own historical best position and the historical best position of the group.

[0057] The particle speed and position update formula is as follows:

[0058] V i (t+1=ω·v i (t)+c1·r1·(pbest i -x i (t))+c2·r2·(gbest-x i (t))

[0059] x i (t+1)+x i (t)+v i (t+1)

[0060] Among them, v i (t) and x i (t) are the speed and position of particle i at time t, pbest,i is the best historical position of particle i, gbest is the best historical position of the group, ω is the inertia weight, c1 and c2 are learning factors, and r1 and r2 are random numbers. The PSO algorithm is used to optimize the performance parameters of the excitation system, such as the adjustment of the excitation current. By setting a clear objective function (such as minimizing power loss or maximizing stability indicators), the platform can automatically explore and recommend the optimal excitation current setting value. This method not only significantly improves the operating efficiency of the system, but also effectively extends the service life of the equipment and reduces maintenance costs.

[0061] Step 3: Displaying the fault diagnosis results corresponding to the operating parameters of the generator excitation system.

[0062] Furthermore, the method further comprises:

[0063] Constructing a simulation model of the generator excitation system according to digital twin technology;

[0064] Based on the simulation model of the generator excitation system, simulate the system operation status under various preset working conditions to predict the fault type of the generator excitation system;

[0065] Wherein, the simulation model of the generator excitation system includes: a physical model, a behavioral model and an interactive model.

[0066] It should be noted that the excitation system simulation model based on digital twin technology realizes real-time mapping and prediction of the excitation system by constructing a digital model that corresponds one-to-one with the physical system.

[0067] The digital twin model consists of three parts: physical model, behavioral model and interactive model. The physical model describes the physical structure and parameters of the excitation system; the behavioral model describes the operating rules and dynamic characteristics of the excitation system; and the interactive model describes the interactive relationship between the excitation system and the external environment. Through the digital twin model, the platform can simulate the system operating status under different working conditions and predict the future behavior of the system. Operation and maintenance personnel can formulate targeted operation and maintenance strategies based on the simulation results to improve the stability and reliability of the system.

[0068] Furthermore, the method further comprises:

[0069] The operating status of the generator excitation system and the performance optimization information corresponding to each operating status are displayed.

[0070] Furthermore, the method further comprises:

[0071] When the operating data of the generator excitation system is greater than the corresponding threshold value, an alarm is issued.

[0072] It should be noted that the method provided in this embodiment provides users with an intuitive operation interface and customized services. Through the graphical interface, users can view information such as the operating status, fault diagnosis results, and performance optimization suggestions of the generator excitation system in real time. The graphical interface adopts an interactive design, and users can view the change trends and historical data of different parameters by clicking, dragging, and other operations. The interface also provides a variety of view modes, such as trend charts, bar charts, pie charts, etc., which is convenient for users to select the appropriate view mode according to their needs.

[0073] In summary, the fault diagnosis method for a generator excitation system proposed in this embodiment can perform real-time monitoring, fault diagnosis and performance optimization of the excitation system, thereby improving the stability and reliability of the power system.

[0074] Embodiment 2

[0075] Figure 2 FIG. 1 is a structural diagram of a fault diagnosis system for a generator excitation system according to an embodiment of the present application, such as Figure 2 As shown, the system comprises:

[0076] The acquisition module 100 is used to acquire the operating parameters of the generator excitation system in real time and pre-process the operating parameters;

[0077] The operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

[0078] The diagnosis module 200 is used to input the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimize and solve the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system;

[0079] It should be noted that the fault diagnosis model training process includes:

[0080] Obtaining the preprocessed operating parameters of the generator excitation system at each moment in the historical period and the fault labels corresponding to the operating parameters;

[0081] The operating parameters are used as input, the fault labels corresponding to the operating parameters are used as output, and a particle swarm optimization algorithm is used to optimize and train the initial support vector machine model to obtain a trained fault diagnosis model.

[0082] The display module 300 is used to display the fault diagnosis results corresponding to the operating parameters of the generator excitation system.

[0083] In the embodiments of the present disclosure, Figure 3 As shown, the system further includes: a simulation module 400;

[0084] The simulation module 400 is used for:

[0085] Constructing a simulation model of the generator excitation system according to digital twin technology;

[0086] Based on the simulation model of the generator excitation system, simulate the system operation status under various preset working conditions to predict the fault type of the generator excitation system;

[0087] Wherein, the simulation model of the generator excitation system includes: a physical model, a behavioral model and an interactive model.

[0088] In the embodiments of the present disclosure, Figure 3 As shown, the system further includes: a display module 500;

[0089] The display module 500 is used for:

[0090] The operating status of the generator excitation system and the performance optimization information corresponding to each operating status are displayed.

[0091] In the embodiments of the present disclosure, Figure 3 As shown, the system further includes: an alarm module 600;

[0092] The alarm module 600 is used for:

[0093] When the operating data of the generator excitation system is greater than the corresponding threshold value, an alarm is issued.

[0094] The alarm module 600 is also used for:

[0095] An alarm is issued when the generator excitation system fails.

[0096] In summary, the fault diagnosis system for a generator excitation system proposed in this embodiment can perform real-time monitoring, fault diagnosis and performance optimization of the excitation system, thereby improving the stability and reliability of the power system.

[0097] Embodiment 3

[0098] In order to implement the above embodiments, the present disclosure further proposes an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in Embodiment 1 is implemented.

[0099] Embodiment 4

[0100] In order to implement the above embodiments, the present disclosure further proposes a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the method described in the first embodiment is implemented.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0102] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0103] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A fault diagnosis method for a generator excitation system, characterized in that: The method comprises: Collecting operating parameters of the generator excitation system in real time and preprocessing the operating parameters; Inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system; The fault diagnosis results corresponding to the operating parameters of the generator excitation system are displayed.

2. The method according to claim 1, characterized in that The operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

3. The method according to claim 2, characterized in that The fault diagnosis model training process includes: Obtaining the preprocessed operating parameters of the generator excitation system at each moment in the historical period and the fault labels corresponding to the operating parameters; The operating parameters are used as input, the fault labels corresponding to the operating parameters are used as output, and a particle swarm optimization algorithm is used to optimize and train the initial support vector machine model to obtain a trained fault diagnosis model.

4. The method according to claim 3, characterized in that The method further comprises: Constructing a simulation model of the generator excitation system according to digital twin technology; Based on the simulation model of the generator excitation system, simulate the system operation status under various preset working conditions to predict the fault type of the generator excitation system; Wherein, the simulation model of the generator excitation system includes: a physical model, a behavioral model and an interaction model.

5. The method according to claim 4, characterized in that The method further comprises: The operating status of the generator excitation system and the performance optimization information corresponding to each operating status are displayed.

6. The method according to claim 5, characterized in that The method further comprises: When the operating data of the generator excitation system is greater than the corresponding threshold value, an alarm is issued.

7. A fault diagnosis system for a generator excitation system, characterized in that: The system comprises: The acquisition module is used to acquire the operating parameters of the generator excitation system in real time and pre-process the operating parameters; A diagnosis module, used for inputting the preprocessed operating parameters of the generator excitation system into a pre-trained fault diagnosis model, and optimizing and solving the fault diagnosis model using a particle swarm optimization algorithm to obtain a fault diagnosis result corresponding to the operating parameters of the generator excitation system; The display module is used to display the fault diagnosis results corresponding to the operating parameters of the generator excitation system.

8. The system according to claim 7, characterized in that The operating parameters include: the percentage of the terminal voltage and current of the generator excitation system, the percentage of the excitation voltage and current, the power factor, the rectifier cabinet current sharing coefficient, and the unit operating temperature.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images