Engine intake and exhaust system state evaluation method and system based on heterogeneous data
By adopting a state evaluation method based on heterogeneous data in the inlet and exhaust system of high-power diesel engines, and optimizing the SVM model using wavelet transformation and particle swarm algorithm, the problems of large signal interference and low accuracy are solved, and high accuracy and rapid failures are achieved diagnosis.
Patent Information
- Application Number
- CN202411606272.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-12
- Publication Date
- 2025-02-18
AI Technical Summary
The intake and exhaust system of high-power diesel engines frequently occurs in harsh environments, and it is difficult to effectively diagnose the existing technology, especially the problems of large signal interference, insufficient single information source, and low accuracy of traditional SVM algorithms.
The engine intake and exhaust system state evaluation method based on heterogeneous data is adopted, and the vibration signal and thermal engineering signal are obtained, wavelet transformation and time domain feature extraction are performed, and the features are combined to obtain the diesel engine motion state feature vector. Then, the SVM model is optimized using the particle swarm algorithm to conduct an online state evaluation of the engine inlet and exhaust system.
It improves the accuracy of engine operating status evaluation, reduces signal interference, takes into account both rapidity and high accuracy, and realizes end-to-end real-time automatic fault diagnosis, suitable for deployment to edge devices.
Smart Images
Figure CN119475057A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of engine fault diagnosis, and in particular, relates to a method and system for evaluating the state of an engine intake and exhaust system based on heterogeneous data. Background Art
[0002] As one of the five major systems of a diesel engine, the intake and exhaust system needs to provide clean and sufficient air to each working cylinder for combustion and work in the cylinder, and discharge the exhaust gas after combustion into the atmosphere. This is the premise for the normal operation of the diesel engine. However, since diesel engines often operate in harsh conditions and poor air quality external environments, especially for high-power diesel engines with more than 500kw and 10 cylinders, the various components of its intake and exhaust system are in a high-temperature and high-pressure internal environment for a long time, resulting in frequent failures of the intake and exhaust system. Therefore, conducting fault diagnosis research on the intake and exhaust system of high-power multi-cylinder diesel engines is of great significance to ensure the stable operation of production operations.
[0003] Common faults in the intake and exhaust systems include abnormal valve clearance, clogged intake filters, and abnormal exhaust temperatures. For such faults, a fault identification method based on in-cylinder pressure monitoring and analysis was proposed earlier. In addition, methods based on exhaust temperature monitoring, vibration analysis, and instantaneous speed analysis have been proposed and have achieved certain results. However, the above methods are all aimed at diesel engines with lower power, without real problems such as signal interference and coverage, and based on a single type of signal, it is impossible to obtain global physical information associated with diesel engine intake and exhaust faults. The above methods all have ideal results in host computer tests, but when deployed on edge devices, they often have problems such as slow inference speed and decreased diagnostic accuracy after quantization, and the fault false alarm rate is high. Summary of the invention
[0004] In view of this, the present application aims to propose an engine intake and exhaust system status assessment method and system based on heterogeneous data to solve the problems of large signal interference in high-power diesel engines, a single information source as a basis for diagnosis, and low accuracy of existing intake and exhaust system status assessment methods based on traditional SVM algorithms.
[0005] To achieve the above purpose, the technical solution of this application is implemented as follows:
[0006] In a first aspect, the present application provides a method for evaluating the state of an engine intake and exhaust system based on heterogeneous data, comprising:
[0007] Obtain vibration signals and thermal signals under diesel engine intake and exhaust system fault simulation test;
[0008] Performing wavelet transform on the vibration signal to obtain a combined wavelet feature, extracting the time domain feature of the vibration signal, and combining the wavelet feature, the time domain feature and the thermal signal to obtain a diesel engine motion state feature vector;
[0009] An optimized SVM model is obtained based on a particle swarm algorithm, and an online state evaluation of an engine intake and exhaust system is performed based on the SVM model, wherein the SVM model is trained by a data set constructed by a feature vector.
[0010] In the second aspect, based on the same inventive concept, the present application also provides an engine intake and exhaust system state assessment system based on heterogeneous data, comprising:
[0011] A signal acquisition module is configured to acquire vibration signals and thermal signals under a fault simulation test of an intake and exhaust system of a diesel engine;
[0012] A feature processing module is configured to perform wavelet transform on the vibration signal to obtain a combined wavelet feature, extract a time domain feature of the vibration signal, and combine the wavelet feature, the time domain feature and the thermal signal to obtain a diesel engine motion state feature vector;
[0013] The state assessment module is configured to perform online state assessment on the engine intake and exhaust system based on an SVM model optimized based on a particle swarm algorithm, wherein the SVM model is trained by a data set constructed by a feature vector.
[0014] In a third aspect, based on the same inventive concept, the present application also 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.
[0015] In a fourth aspect, based on the same inventive concept, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in the first aspect.
[0016] Compared with the prior art, the engine intake and exhaust system status assessment method and system based on heterogeneous data described in this application have the following beneficial effects:
[0017] (1) The method and system for evaluating the state of the engine intake and exhaust system based on heterogeneous data described in the present application obtain the wavelet coefficients of the vibration signal in each frequency band as features through wavelet decomposition, which reduces the impact noise of the vibration signal of a high-power multi-cylinder diesel engine to a certain extent, while taking into account the time domain characteristics of the vibration signal and the thermal information of the diesel engine, thereby evaluating the operating state of the engine from a more comprehensive dimension, so its evaluation accuracy is relatively high.
[0018] (2) The method and system for evaluating the status of an engine intake and exhaust system based on heterogeneous data described in the present application take into account both the rapidity of traditional feature evaluation and the high precision of machine learning diagnosis, and use a particle swarm algorithm to automatically capture the optimal hyperparameters of the SVM, thereby reducing the problem of low algorithm accuracy caused by human interference. In addition, the algorithm has low computational complexity and fast inference speed, and can achieve end-to-end real-time automatic fault diagnosis. It is suitable for deployment on edge devices and can achieve fast and accurate online status evaluation of localized diesel engine intake and exhaust systems. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0020] Figure 1 This is a flow chart of the engine intake and exhaust system state assessment method based on heterogeneous data according to an embodiment of the present application;
[0021] Figure 2 This is a flow chart of wavelet feature extraction described in an embodiment of the present application;
[0022] Figure 3 A flowchart of constructing a SVM model optimized by a particle swarm algorithm according to an embodiment of the present application;
[0023] Figure 4 A comparison chart of the fault diagnosis accuracy of the method described in the embodiment of the present application compared with the traditional machine learning method;
[0024] Figure 5 A comparison chart of the fault diagnosis accuracy of the method described in the embodiment of the present application compared with a single structure data source;
[0025] Figure 6 This is a schematic diagram of the structure of the engine intake and exhaust system state assessment system based on heterogeneous data according to an embodiment of the present application;
[0026] Figure 7 This is a schematic diagram of the hardware structure of the electronic device described in the embodiment of the present application. DETAILED DESCRIPTION
[0027] In order to make the objectives, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.
[0028] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present application should be the usual meanings understood by people with ordinary skills in the field to which the present application belongs. The "first", "second" and similar words used in the embodiments of the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.
[0029] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0030] See also Figure 1 As shown, this embodiment provides a method for evaluating the state of an engine intake and exhaust system based on heterogeneous data, including:
[0031] Step S101: Obtain vibration signals and thermal signals under a diesel engine intake and exhaust system fault simulation test.
[0032] Specifically, in this embodiment, a fault simulation test is set up for the main fault modes of the diesel engine intake and exhaust system, and data is collected through the laboratory data acquisition system and the vibration signal acquisition equipment to create a data set and add corresponding status labels, wherein the acquisition frequency of the vibration signal must be greater than twice the maximum frequency of the diesel engine, and the vibration sensor should be arranged in the center of the cylinder head; the thermal signal parameters should include all monitoring quantities of the intake and exhaust system involved in the main faults of concern, such as diesel engine speed, torque, power, fuel consumption, cylinder intake and exhaust pressure, intake and exhaust temperature, etc. The data set should include common fault modes such as abnormal intake and exhaust valve clearance, intake filter blockage, and abnormal intake and exhaust temperature, and the data volume of each fault mode should be sufficient and balanced.
[0033] Step S102, performing wavelet transform on the vibration signal to obtain the combined wavelet features, extracting the time domain features of the vibration signal, combining the wavelet features, the time domain features and the thermal signal to obtain the diesel engine motion state feature vector.
[0034] Specifically, in this embodiment, Figure 2As shown, the vibration signal in step S101 is subjected to wavelet transform, the wavelet basis function and the decomposition level are selected according to the size of the data set, the statistical information (statistical features) of the decomposition results are extracted and merged into wavelet features, and in addition, the time domain features of the original vibration signal are extracted, and the wavelet features, time domain features and thermal parameters in the original data set are combined to obtain the diesel engine motion state feature vector, that is, to create a new feature data set.
[0035] Among them, feature extraction based on wavelet transform includes the following steps:
[0036] S201, select appropriate wavelet basis function and decomposition level. Different wavelet basis functions and decomposition levels will have different effects on feature extraction results. Here, the data set size, noise reduction effect and reasoning speed are balanced. In this embodiment, the wavelet basis function is Morlet, and the decomposition level is 6.
[0037] Wavelet transform is a localized analysis of time (space) and frequency. It gradually refines the signal (function) at multiple scales through telescoping and translation operations, and finally achieves time subdivision at high frequencies and frequency subdivision at low frequencies. It can automatically adapt to the requirements of time-frequency signal analysis, so as to focus on any details of the signal and solve the difficult problem of Fourier transform. The calculation formula of continuous wavelet transform is:
[0038]
[0039] In the formula, f(t) represents the vibration signal, a represents the positioning frequency, and b represents the positioning time. is the general form of the wavelet function.
[0040] S202: Perform wavelet transformation on the original signal (collected vibration signal), and obtain wavelet coefficients at different scales by calculating the inner product of the signal and the wavelet function.
[0041] S203, extracting wavelet coefficients as statistical features (including statistical information such as energy, mean value and standard deviation), and selecting some or all of the wavelet coefficients as statistical features, which can be used for subsequent machine learning model training.
[0042] S204, integrating the features. In order to improve the performance of the model, the extracted wavelet coefficients are further processed, such as dimension reduction, normalization, etc. Here, a simple merging is sufficient.
[0043] In addition, the time domain features to be extracted from the vibration signal in step S102 include the following parts:
[0044] Maximum value, minimum value, mean value, peak-to-peak value, absolute mean value, RMS value, RMS amplitude, standard deviation, skewness, kurtosis, margin index, waveform index, pulse index, peak index.
[0045] Thermal signals include diesel engine speed, torque, power, fuel consumption, cylinder intake and exhaust pressure, and intake and exhaust temperature parameters.
[0046] Step S103: obtaining an optimized SVM model based on the particle swarm algorithm, and performing online state evaluation on the engine intake and exhaust system based on the SVM model, wherein the SVM model is trained by a data set constructed by the feature vector.
[0047] Specifically, in this embodiment, the feature vector in step S103 is used to create a feature data set, and a diesel engine intake and exhaust system state assessment algorithm based on a particle swarm algorithm-optimized SVM (Support Vector Machines, hereinafter referred to as SVM) model is trained and verified, and the particle swarm algorithm is used to automatically search for the optimal hyperparameters of the SVM;
[0048] Wavelet transform, time domain feature extraction, feature merging, and the trained SVM model structure and weights are deployed in series to the edge device board for data processing and online diesel engine intake and exhaust system status assessment.
[0049] like Figure 3 As shown, the state assessment algorithm training process of the SVM model based on particle swarm algorithm optimization involved in step S103 is:
[0050] Initialize the particle swarm algorithm parameters (including the particle swarm's inertia factor, learning factor, iteration coefficient, population size, etc.) and support vector machine parameters, define the SVM classifier, set its kernel function to the Gaussian kernel function and set the penalty parameter C;
[0051] Among them, the Gaussian kernel function is a kind of radially symmetric scalar function, which is used to map finite-dimensional data to high-dimensional space. It is usually defined as a monotonic function of the Euclidean distance between any point x in space and a central point x′, which can be recorded as k(||xx′||). When x is far away from x′, the function value is very small. The function is defined as:
[0052]
[0053] x′ is the center of the kernel function, ‖xx′‖ 2 is the Euclidean distance between vector x and vector x′. As the distance increases, the Gaussian kernel function decreases monotonically. σ is the bandwidth. As σ increases, the local influence range of the Gaussian kernel function increases.
[0054] The penalty parameters and SVM hyperparameters are encoded as the initial population of the particle swarm algorithm, and the new parameters are decoded. The SVM model is trained based on the new parameters, and the training is verified through CV cross-validation. The obtained n-fold best accuracy is used as the fitness value;
[0055] Determine whether the fitness value meets the termination condition. In response to meeting the termination condition, decode it and output it as the optimal parameter of SVM. In response to not meeting the termination condition, perform particle swarm algorithm iteration, update the global optimal individual, particle position and speed to form a new population, and re-train and cross-validate.
[0056] In addition, in this embodiment, it also includes:
[0057] Preprocess the new feature data set and randomly divide the preprocessed data set into training set, validation set and test set;
[0058] The constructed SVM model is trained based on the training set, the trained SVM model is verified based on the verification set, and the verified SVM model is tested based on the test set to finalize the SVM model training verification.
[0059] Based on the above method, Figure 4 The fault diagnosis accuracy of the method proposed in the present invention is compared with that of the traditional machine learning algorithm; Figure 5 The fault diagnosis accuracy using multi-source heterogeneous information was compared with that not using this information. Both comparisons used the same data set, and the five intake and exhaust system faults diagnosed included excessive intake and exhaust valve clearance, insufficient intake and exhaust valve clearance, and intake filter blockage.
[0060] The engine intake and exhaust system state assessment method based on heterogeneous data described in this embodiment solves to a certain extent the problems of large signal interference of high-power multi-cylinder diesel engines with 500kw and more than 10 cylinders and low accuracy of existing intake and exhaust system state assessment methods using a single information source as a basis for diagnosis. At the same time, the method uses a particle swarm algorithm to automatically search for the optimal hyperparameters of SVM, has low computational complexity, fast inference speed, can realize end-to-end intelligent online assessment, consumes less hardware resources, and has good engineering application prospects.
[0061] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0062] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, an embodiment of the present application also provides an engine intake and exhaust system state assessment system based on heterogeneous data.
[0063] like Figure 6 As shown, the engine intake and exhaust system state evaluation system based on heterogeneous data includes:
[0064] The signal acquisition module 11 is configured to acquire vibration signals and thermal signals under a fault simulation test of a diesel engine intake and exhaust system;
[0065] The feature processing module 12 is configured to perform wavelet transform on the vibration signal to obtain a combined wavelet feature, extract the time domain feature of the vibration signal, and combine the wavelet feature, the time domain feature and the thermal signal to obtain a diesel engine motion state feature vector;
[0066] The state evaluation module 13 is configured to perform online state evaluation on the engine intake and exhaust system based on the SVM model optimized by the particle swarm algorithm, wherein the SVM model is trained by a data set constructed by feature vectors.
[0067] For the convenience of description, the above system is described by dividing the functions into various modules. Of course, when implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.
[0068] The system of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.
[0069] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, an embodiment of the present application also provides 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 any of the above embodiments is implemented.
[0070] Figure 7 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.
[0071] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.
[0072] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.
[0073] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.
[0074] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).
[0075] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).
[0076] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.
[0077] The electronic device of the above embodiment is used to implement the corresponding method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.
[0078] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the method described in any of the above embodiments.
[0079] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.
[0080] The computer instructions stored in the storage medium of the above embodiments are used to enable the computer to execute the method described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.
[0081] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples. In line with the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.
[0082] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are changed. Therefore, these descriptions should be considered to be illustrative rather than restrictive.
[0083] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.
[0084] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.
Claims
1. A method for evaluating the state of an engine intake and exhaust system based on heterogeneous data, characterized in that: include: Obtain vibration signals and thermal signals under diesel engine intake and exhaust system fault simulation test; Performing wavelet transform on the vibration signal to obtain a combined wavelet feature, extracting the time domain feature of the vibration signal, and combining the wavelet feature, the time domain feature and the thermal signal to obtain a diesel engine motion state feature vector; An optimized SVM model is obtained based on a particle swarm algorithm, and an online state evaluation of an engine intake and exhaust system is performed based on the SVM model, wherein the SVM model is trained by a data set constructed by a feature vector.
2. The method according to claim 1, characterized in that The wavelet transform is performed on the vibration signal to obtain the combined wavelet feature, the time domain feature of the vibration signal is extracted, and the wavelet feature, the time domain feature and the thermal signal are combined to obtain the diesel engine motion state feature vector, including: Acquire the vibration signal of the diesel engine, select the wavelet basis function and the decomposition level to perform wavelet transform, decompose to obtain the statistical characteristics of the wavelet coefficients of each level, and combine the statistical characteristics to form wavelet characteristics; The wavelet features, time domain features and thermal signals are combined to obtain a diesel engine motion state feature vector.
3. The method according to claim 2, characterized in that The wavelet transform formula is expressed as: In the formula, f(t) represents the vibration signal, a represents the positioning frequency, and b represents the positioning time.
4. The method according to claim 2, characterized in that: The time domain characteristics include maximum value, minimum value, mean value, peak-to-peak value, absolute mean value, root mean square value, root square amplitude, standard deviation, skewness, kurtosis, margin index, waveform index, pulse index and peak index; The thermal signals include diesel engine speed, torque, power, fuel consumption, cylinder intake and exhaust pressure, and intake and exhaust temperature parameters.
5. The method according to claim 1, characterized in that The SVM model optimized based on the particle swarm algorithm includes: Initialize the particle swarm algorithm parameters and support vector machine parameters, define the SVM classifier, set its kernel function to the Gaussian kernel function and set the penalty parameters; The penalty parameters and SVM hyperparameters are encoded as the initial population of the particle swarm algorithm, and new parameters are obtained by decoding. The SVM model is trained based on the new parameters, and the training is verified by CV cross validation, and the best accuracy is set as the fitness value; Determine whether the fitness value meets the termination condition. In response to satisfying the termination condition, decode it and output it as the optimal parameter of SVM. In response to not satisfying the termination condition, perform particle swarm algorithm iteration, update the global optimal individual, particle position and speed to form a new population, and re-train and cross-validate.
6. The method according to claim 5, characterized in that Also includes: Randomly divide the data set into a training set, a validation set, and a test set; The constructed SVM model is trained based on the training set, the trained SVM model is verified based on the verification set, and the verified SVM model is tested based on the test set, so as to finalize the SVM model training and verification.
7. An engine intake and exhaust system status assessment system based on heterogeneous data, characterized in that: include: A signal acquisition module is configured to acquire vibration signals and thermal signals under a fault simulation test of an intake and exhaust system of a diesel engine; A feature processing module is configured to perform wavelet transform on the vibration signal to obtain a combined wavelet feature, extract a time domain feature of the vibration signal, and combine the wavelet feature, the time domain feature and the thermal signal to obtain a diesel engine motion state feature vector; The state assessment module is configured to perform online state assessment on the engine intake and exhaust system based on an SVM model optimized based on a particle swarm algorithm, wherein the SVM model is trained by a data set constructed by a feature vector.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.
9. A non-transitory computer-readable storage medium, characterized in that: in, The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 6.