Temperature monitoring and fault prediction method and related system

Abstract

The invention belongs to the technical field of power generation equipment temperature monitoring, and particularly relates to a temperature monitoring and fault prediction method and a related system, through preprocessing (such as de-noising and normalization) of operation parameters of power generation enterprise equipment, the quality and consistency of data are improved, the influence of external interference on a prediction result is reduced, and the prediction efficiency is improved. Therefore, the accuracy of temperature monitoring and fault prediction is improved. According to the method, the temperature monitoring model is trained based on the historical operation data of the equipment, so that the model can adapt to the characteristics of different equipment, and the temperature change trend of the equipment can be accurately reflected. According to the method, the fault feature library is established, the support vector machine (SVM) algorithm is used to construct the fault prediction model, the historical fault data is used to extract features, the identification capability of the model for potential faults is enhanced, and the occurrence of equipment faults is effectively prevented.

Description

Technical Field

[0001] The present invention belongs to the technical field of temperature monitoring of power generation equipment, and in particular relates to a temperature monitoring and fault prediction method and a related system. Background Art

[0002] Power generation companies have a variety of power generation methods, including thermal power generation, hydropower generation, nuclear power, wind power, solar power generation, etc., forming a diversified power production pattern. Actively participate in the construction of power grids to ensure the safe and efficient transmission of power resources to thousands of households. In power generation companies, the stable operation of key equipment is crucial to ensuring power supply. However, due to the long-term operation of equipment in high temperature and high pressure environments, equipment failures caused by abnormal temperature often occur, which not only affects the continuity and safety of power production, but also may lead to high maintenance costs and equipment replacement costs. Therefore, how to effectively monitor equipment temperature and predict potential failures has become an important technical challenge facing power generation companies.

[0003] Traditional temperature monitoring methods mainly rely on simple temperature sensors and data acquisition systems. Although these systems can provide real-time temperature readings, they often lack the ability to deeply analyze temperature trends and predict potential failures. Therefore, there are certain limitations in the accuracy and reliability of temperature monitoring. Summary of the invention

[0004] The purpose of the present invention is to overcome the problem of insufficient in-depth analysis and prediction capabilities of temperature change trends, and to provide a temperature monitoring and fault prediction method and related system.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a temperature monitoring and fault prediction method, comprising the following steps: Obtain the operating parameters of the equipment required by the power generation enterprise; Preprocess the operating parameters, remove noise, and then perform normalization; The normalized operating parameters and the characteristics of the equipment required by the power generation enterprise are combined to establish an initial model for temperature monitoring; The historical data of the equipment required by the power generation enterprise is used to train the initial monitoring model to obtain the temperature monitoring model; Obtain the historical faults of the equipment required by the power generation enterprise, establish a fault feature library, and establish a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The operating parameters of the equipment required in the power generation enterprise are input into the temperature monitoring model and the fault prediction model to obtain the final result.

[0006] A further improvement of the present invention is that the specific method of preprocessing the operating parameters, removing noise, and then normalizing is as follows: The low-pass filtering method is used to remove noise from the operating parameters, and the z-score analysis method is used to detect and process abnormal values ​​in the operating parameters; The denoised operating parameters are normalized to between [0, 1] or [-1, 1].

[0007] A further improvement of the present invention is that the historical data of the equipment required in the power generation enterprise is used to train the initial monitoring model. The specific method of obtaining the temperature monitoring model is as follows: Use time series to analyze the historical data of equipment required by power generation enterprises and form association rules between equipment operating status and temperature; Based on the association rules between the equipment operating status and temperature, the normalized operating parameters are processed using a machine learning algorithm to generate an initial temperature monitoring model.

[0008] A further improvement of the present invention is that the historical data of the equipment required in the power generation enterprise is used to train the initial monitoring model to obtain a temperature monitoring model; Clean the historical temperature data of the equipment required by power generation companies to remove missing values, duplicate values ​​and outliers; Perform feature extraction based on historical data to extract key factors related to device temperature changes; The linear regression method is used to train the initial monitoring model, and the cross-validation method is used to tune the hyperparameters of the initial monitoring model in training; The model is evaluated using data that has not participated in the training. After the evaluation, a temperature monitoring model is obtained.

[0009] A further improvement of the present invention is that the specific method of establishing a fault prediction model based on the fault feature library combined with the support vector machine algorithm model is as follows: Obtain historical faults in the fault feature library and divide the historical faults into a training set and a test set; Establish a support vector machine algorithm model, use the training set to train the support vector machine algorithm model, and use the required kernel function to process linearly inseparable data; The cross-validation method is used to select the optimal penalty parameters and kernel function parameters in the support vector machine algorithm model; The support vector machine algorithm model is tested using the test set to complete the establishment of the fault prediction model.

[0010] A further improvement of the present invention is that the optimal penalty parameter C in the support vector machine algorithm model is:

[0011] The objective function is:

[0012] in, is the Lagrange multiplier, is the number of data features, For the The feature vector of the samples, For the The category labels of the data features, is the kernel function.

[0013] A further improvement of the present invention is that the kernel function parameters are:

[0014] Among them, γ is the parameter of the RBF kernel, For sample and samples The Euclidean distance between .

[0015] In a second aspect, the present invention provides a temperature monitoring and fault prediction system, comprising: Data acquisition module, used to obtain the operating parameters of the equipment required by the power generation enterprise; The preprocessing model is used to preprocess the operating parameters, remove noise, and then perform normalization; The initial model building module combines the normalized operating parameters with the characteristics of the equipment required by the power generation enterprise to build an initial temperature monitoring model; The model training module is used to train the initial monitoring model using the historical data of the equipment required by the power generation enterprise to obtain the temperature monitoring model; The fault prediction model building module is used to obtain the historical faults of the equipment required by the power generation enterprise, build a fault feature library, and build a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The data output module is used to input the operating parameters of the equipment required in the power generation enterprise into the temperature monitoring model and the fault prediction model to obtain the final result.

[0016] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of a temperature monitoring and fault prediction method when executing the computer program.

[0017] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of a temperature monitoring and fault prediction method.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention improves the quality and consistency of data by preprocessing the operating parameters of the equipment of the power generation enterprise (such as denoising and normalization), reduces the impact of external interference on the prediction results, and thus improves the accuracy of temperature monitoring and fault prediction. The present invention trains the temperature monitoring model based on the historical operating data of the equipment, so that the model can adapt to the characteristics of different equipment and help to accurately reflect the temperature change trend of the equipment. The present invention establishes a fault feature library and uses the support vector machine (SVM) algorithm to build a fault prediction model, extracts features using historical fault data, enhances the model's ability to identify potential faults, and effectively prevents the occurrence of equipment failures. The present invention inputs the real-time operating parameters of the equipment into the temperature monitoring and fault prediction model, and can obtain the prediction results in time, which is helpful for real-time tracking of the equipment status and taking preventive measures in advance. Through effective temperature monitoring and fault prediction, the present invention can pre-detect abnormal trends, reduce unplanned downtime and maintenance requirements of the equipment, thereby reducing maintenance costs and extending the service life of the equipment. In summary, the present invention realizes in-depth analysis of equipment temperature changes and accurate prediction of fault risks through systematic data processing, modeling and real-time monitoring processes, thereby improving the safety and reliability of equipment operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the present invention; Figure 2 is a system diagram of the present invention; Figure 3 This is a system diagram of Example 5. DETAILED DESCRIPTION

[0020] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0021] Embodiment 1: See also Figure 1 , the temperature monitoring and fault prediction method comprises the following steps: S1, obtain the operating parameters of the equipment required by the power generation enterprise.

[0022] S2, preprocess the operating parameters, remove noise, and then perform normalization.

[0023] S3, the normalized operating parameters and the characteristics of the equipment required in the power generation enterprise are combined to establish an initial temperature monitoring model.

[0024] S4, using the historical data of the equipment required by the power generation enterprise to train the initial monitoring model to obtain the temperature monitoring model.

[0025] S5, obtain the historical faults of the equipment required by the power generation enterprise, establish a fault feature library, and establish a fault prediction model based on the fault feature library combined with the support vector machine algorithm model.

[0026] S6, inputting the operating parameters of the equipment required in the power generation enterprise into the temperature monitoring model and the fault prediction model to obtain the final result.

[0027] Embodiment 2: See also Figure 2 , temperature monitoring and fault prediction system, including Data acquisition module, used to obtain the operating parameters of the equipment required by the power generation enterprise; The preprocessing model is used to preprocess the operating parameters, remove noise, and then perform normalization; The initial model building module combines the normalized operating parameters with the characteristics of the equipment required by the power generation enterprise to build an initial temperature monitoring model; The model training module is used to train the initial monitoring model using the historical data of the equipment required by the power generation enterprise to obtain the temperature monitoring model; The fault prediction model building module is used to obtain the historical faults of the equipment required by the power generation enterprise, build a fault feature library, and build a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The data output module is used to input the operating parameters of the equipment required in the power generation enterprise into the temperature monitoring model and the fault prediction model to obtain the final result.

[0028] Embodiment 3: This embodiment provides a temperature monitoring and fault prediction method for power generation enterprise equipment, including the following steps: Step 1: Obtain operating parameters from the power generation company's equipment for modeling of temperature monitoring and fault prediction.

[0029] Step 2: parameter preprocessing: Low-pass filtering is used to remove noise from operating parameters.

[0030] Combined with z-score analysis method to detect and deal with outliers.

[0031] Normalize the denoised running parameters so that their values ​​range between 0,1 or −1,1.

[0032] Step 3: Construction of temperature monitoring model: The preprocessed operating parameters are combined with the equipment characteristics to form an initial model for temperature monitoring.

[0033] The historical data of the equipment is used for time series analysis to form the association rules between the equipment operating status and temperature. Combined with the machine learning algorithm, the normalized operating parameters are analyzed to generate the initial temperature monitoring model.

[0034] The historical temperature data is cleaned to remove missing values, duplicate values ​​and outliers, and feature extraction is performed to extract key factors related to temperature changes.

[0035] The linear regression method was used to train the initial temperature monitoring model, and the cross-validation method was used to tune the hyperparameters during the training process.

[0036] The model is evaluated using data that has not participated in the training. After the evaluation passes, the final temperature monitoring model is obtained.

[0037] Step 4: Construction of fault prediction model: Establish a fault feature library: Based on the historical fault records of the equipment, establish a data set containing the equipment fault features.

[0038] The historical fault data is divided into a training set and a test set. The SVM model is used to train the training set and an appropriate kernel function is selected to process linearly inseparable data. The cross-validation method is used to select the optimal penalty parameter (C) and kernel function parameter (such as the parameter γ of the RBF kernel) in the SVM model. The test set is used to test the model and evaluate the performance of the fault prediction model.

[0039] Input the real-time operating parameters of the equipment into the temperature monitoring model and the fault prediction model. Output the current temperature monitoring results and fault prediction results of the equipment.

[0040] Among them, the objective function of the optimal penalty parameter C of the support vector machine algorithm model is:

[0041] in, is the Lagrange multiplier, is the number of data features, For the The feature vector of the samples, For the The category labels of the data features, is the kernel function. In addition, the specific value of γ is determined according to the calculation of the RBF kernel function, where:

[0042] Embodiment 4: Assume that the real-time operating parameters of a generator set include temperature, vibration velocity and current. The original data obtained are: temperature 85°C, vibration velocity 4.5 mm / s, current 400 A.

[0043] The temperature, vibration velocity and current were subjected to low-pass filtering and denoising respectively. The denoised temperature data was 83.5°C, the vibration velocity was 4.3 mm / s, and the current was 395 A.

[0044] Performing z-score analysis on the denoised data, the mean temperature of the device is 80°C, the standard deviation is 5°C, the mean vibration speed is 4 mm / s, and the standard deviation is 0.5 mm / s. The z-score is calculated as: The temperature anomaly value is (83.5−80) / 5=0.7, which is within a reasonable range; The vibration speed is (4.3−4) / 0.5=0.6, which is within a reasonable range; Therefore no further processing is required.

[0045] Normalize the denoised data to the interval [0,1] using the normalization formula: .

[0046] Assume a temperature range of 60-100°C, a vibration velocity range of 0-10 mm / s, and a current range of 300-500 A.

[0047] The normalized temperature is: (83.5−60) / (100−60)=0.5875; The vibration speed is: (4.3-0) / (10-0)=0.43; The current is: (395−300) / (500−300)=0.475.

[0048] The initial temperature monitoring model is formed using the historical temperature data of the equipment. The temperature range of the historical data is 60°C-100°C, and there is a linear correlation between the temperature and the operating state. The temperature prediction model is established using the linear regression method. After training, the pseudo linear regression formula is: temperature prediction value T=0.5×current+10×vibration speed+50. On the evaluation data set, the mean square error (MSE) of the model is 2.5, the evaluation passes, and the final temperature monitoring model is obtained.

[0049] The fault prediction model is established using the support vector machine algorithm (SVM), and the model is trained in combination with the fault feature library, which contains the following historical fault data: Fault 1: Temperature 90°C, vibration speed 5 mm / s, current 410 A.

[0050] Fault 2: Temperature 95°C, vibration speed 5.5 mm / s, current 420 A.

[0051] Fault 3: Temperature 100°C, vibration speed 6 mm / s, current 430 A.

[0052] The data was normalized and used for model training. The RBF kernel function was selected with penalty parameter C=1.0 and kernel function parameter γ=0.1.

[0053] The penalty parameters and kernel parameters were optimized through cross-validation, and the model was evaluated on the test set. The accuracy rate reached 95%, which met the prediction accuracy requirements. Finally, a fault prediction model was established.

[0054] The real-time operating parameters (temperature 83.5°C, vibration velocity 4.3 mm / s, current 395 A) were input into the temperature monitoring model and the fault prediction model.

[0055] Temperature monitoring results: Use the linear regression formula to calculate the predicted temperature value T=0.5×395+10×4.3+50=256.5.

[0056] Fault prediction results: The SVM model determines that there is no abnormal fault risk.

[0057] Finally, this specific embodiment realizes real-time monitoring and fault prediction of the temperature of power generation equipment through the above process, effectively improving the safety and stability of equipment operation.

[0058] Embodiment 5: See also Figure 3 As shown, the present invention also provides an electronic device 100 for temperature monitoring and fault prediction method; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0059] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the temperature monitoring and fault prediction method described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0060] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0061] The memory 101 in the electronic device 100 stores a plurality of instructions to implement the temperature monitoring and fault prediction method, and the processor 102 can execute the plurality of instructions to implement: Obtain the operating parameters of the equipment required by the power generation enterprise; Preprocess the operating parameters, remove noise, and then perform normalization; The normalized operating parameters and the characteristics of the equipment required by the power generation enterprise are combined to establish an initial model for temperature monitoring; The historical data of the equipment required by the power generation enterprise is used to train the initial monitoring model to obtain the temperature monitoring model; Obtain the historical faults of the equipment required by the power generation enterprise, establish a fault feature library, and establish a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The operating parameters of the equipment required in the power generation enterprise are input into the temperature monitoring model and the fault prediction model to obtain the final result.

[0062] Embodiment 6: If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0063] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0065] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A temperature monitoring and fault prediction method, characterized in that: The following steps are involved: Obtain the operating parameters of the equipment required by the power generation enterprise; Preprocess the operating parameters, remove noise, and then perform normalization; The normalized operating parameters and the characteristics of the equipment required by the power generation enterprise are combined to establish an initial model for temperature monitoring; The historical data of the equipment required by the power generation enterprise is used to train the initial monitoring model to obtain the temperature monitoring model; Obtain the historical faults of the equipment required by the power generation enterprise, establish a fault feature library, and establish a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The operating parameters of the equipment required in the power generation enterprise are input into the temperature monitoring model and the fault prediction model to obtain the final result.

2. The temperature monitoring and fault prediction method according to claim 1, characterized in that: The specific method of preprocessing the operating parameters, removing noise, and then normalizing is as follows: The low-pass filtering method is used to remove noise from the operating parameters, and the z-score analysis method is used to detect and process abnormal values ​​in the operating parameters; The denoised operating parameters are normalized to between [0, 1] or [-1, 1].

3. The temperature monitoring and fault prediction method according to claim 1, characterized in that: The specific method of training the initial monitoring model using the historical data of the equipment required by the power generation enterprise to obtain the temperature monitoring model is as follows: Use time series to analyze the historical data of equipment required by power generation enterprises and form association rules between equipment operating status and temperature; Based on the association rules between the equipment operating status and temperature, the normalized operating parameters are processed using a machine learning algorithm to generate an initial temperature monitoring model.

4. The temperature monitoring and fault prediction method according to claim 1, characterized in that: The historical data of the equipment required by the power generation enterprise is used to train the initial monitoring model to obtain the temperature monitoring model; Clean the historical temperature data of the equipment required by power generation companies to remove missing values, duplicate values ​​and outliers; Perform feature extraction based on historical data to extract key factors related to device temperature changes; The linear regression method is used to train the initial monitoring model, and the cross-validation method is used to tune the hyperparameters of the initial monitoring model in training; The model is evaluated using data that has not participated in the training. After the evaluation, a temperature monitoring model is obtained.

5. The temperature monitoring and fault prediction method according to claim 1, characterized in that: The specific method of establishing a fault prediction model based on the fault feature library combined with the support vector machine algorithm model is as follows: Obtain historical faults in the fault feature library and divide the historical faults into a training set and a test set; Establish a support vector machine algorithm model, use the training set to train the support vector machine algorithm model, and use the required kernel function to process linearly inseparable data; The cross-validation method is used to select the optimal penalty parameters and kernel function parameters in the support vector machine algorithm model; The support vector machine algorithm model is tested using the test set to complete the establishment of the fault prediction model.

6. The temperature monitoring and fault prediction method according to claim 5, characterized in that: The optimal penalty parameter C in the support vector machine algorithm model is: The objective function is: in, is the Lagrange multiplier, is the number of data features, For the The feature vector of the samples, For the The category labels of the data features, is the kernel function.

7. The temperature monitoring and fault prediction method according to claim 5, characterized in that: The kernel function parameters are: Among them, γ is the parameter of the RBF kernel, For sample and samples The Euclidean distance between .

8. Temperature monitoring and fault prediction system, characterized in that: include Data acquisition module, used to obtain the operating parameters of the equipment required by the power generation enterprise; The preprocessing model is used to preprocess the operating parameters, remove noise, and then perform normalization; The initial model building module combines the normalized operating parameters with the characteristics of the equipment required by the power generation enterprise to build an initial temperature monitoring model; The model training module is used to train the initial monitoring model using the historical data of the equipment required by the power generation enterprise to obtain the temperature monitoring model; The fault prediction model building module is used to obtain the historical faults of the equipment required by the power generation enterprise, build a fault feature library, and build a fault prediction model based on the fault feature library combined with the support vector machine algorithm model; The data output module is used to input the operating parameters of the equipment required in the power generation enterprise into the temperature monitoring model and the fault prediction model to obtain the final result.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the temperature monitoring and fault prediction method according to any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the temperature monitoring and fault prediction method according to any one of claims 1 to 7 are implemented.

Images