Vehicle-mounted refrigerator NVH (Noise Vibration and Harshness) diagnosis method, system and equipment and storage medium

Abstract

The invention relates to a vehicle-mounted refrigerator NVH diagnosis method, system and device and a storage medium, data obtained through simulation of different structural parameters of a vehicle body TB network model and the vehicle-mounted refrigerator is used as training data, and an initial network model is trained in combination with an SVM algorithm to form an NVH data training diagnosis model special for the vehicle-mounted refrigerator; therefore, when the design of the vehicle-mounted refrigerator is changed next time, modeling simulation analysis does not need to be conducted again, the structural parameters of the vehicle-mounted refrigerator with the changed design are directly input into the NVH data training diagnosis model, whether the vehicle-mounted refrigerator with the changed design meets the NVH performance requirement or not can be known, the analysis calculation power is greatly reduced, and the analysis efficiency is improved. Simulation working conditions related to the NVH performance of the vehicle-mounted refrigerator are matched, the diagnosis result is output, and the simulation result can be predicted without simulation operation.

Description

Technical Field

[0001] The present application relates to the field of vehicle NVH technology, and in particular to a vehicle refrigerator NVH diagnosis method, system, device and storage medium. Background Art

[0002] Traditional mechanism design requires a lot of time and computing resources. If there are problems in the later stage of product design, it is necessary to repeatedly optimize and adjust the model and resubmit the simulation calculation. At the same time, the experience reserves of ordinary engineers will be stretched for new demands such as car refrigerators and TV stands. Later, the introduction of parametric models greatly improved the efficiency of optimization; the parametric model establishes a structural feature database by targeting the performance of floor sheet metal refrigerator installation point stiffness, vibration / noise transfer function and installation mode for a single model; when faced with the simulation evaluation of the modified auxiliary instrument panel and car refrigerator or surrounding sheet metal with small design changes, engineers can set parameters through empirical design change structure, and then simulate and predict the performance of installation point stiffness, vibration / noise transfer function, installation mode and so on by changing the parameters, so as to evaluate the NVH (Noise, Vibration, Harshness) performance related to the car refrigerator.

[0003] However, this method still relies on the experience of engineers to change parameters. Faced with the high-speed iteration of today's products, which leads to small design changes of the car refrigerator or surrounding sheet metal, human experience accumulation is not enough to support the performance prediction after the structural change. Therefore, how to reduce the computing power consumption during NVH analysis has become an urgent problem to be solved.

[0004] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The embodiments of the present application provide a vehicle refrigerator NVH diagnostic method, system, device and storage medium to solve the problem in the related art that high-speed product iteration leads to small design changes of the vehicle refrigerator or surrounding sheet metal, and the use of parametric models for simulation design leads to high computing power consumption during NVH analysis.

[0006] In a first aspect, a vehicle refrigerator NVH diagnostic method is provided, which includes:

[0007] Based on the TB network model of the upper body and different structural parameters of the onboard refrigerator, training data is obtained through simulation;

[0008] Training the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model;

[0009] The structural parameters of the vehicle refrigerator to be diagnosed are input into the NVH data training diagnosis model to obtain the NVH performance diagnosis report.

[0010] In some embodiments, based on the upper vehicle body TB network model and different structural parameters of the vehicle refrigerator, simulation to obtain training data includes the following steps:

[0011] The different structural parameters of the vehicle refrigerator are input into the TB network model of the upper body respectively, and the simulation outputs the installation mode, installation point dynamic stiffness, vibration / noise transfer function and strain energy distribution cloud map corresponding to the different structural parameters;

[0012] The structural parameters of the vehicle refrigerator are used as input parameters;

[0013] The installation mode, installation point stiffness, vibration / noise transfer function and strain energy distribution cloud diagram are used as output parameters;

[0014] The input parameters and output parameters are collected and associated with each other to serve as training data.

[0015] In some embodiments, the vehicle refrigerator includes a refrigerator body and a mounting bracket;

[0016] The structural parameters include CAD data of the refrigerator body and the mounting bracket, the mounting point position of the mounting bracket, the welding point information of the mounting bracket, the material and material thickness, and the mass center parameters of the refrigerator body and the mounting bracket;

[0017] The output parameters include the installation mode of the refrigerator body, the installation point stiffness of the mounting bracket, the vibration / noise transfer function of the refrigerator body and the mounting bracket, and the strain energy distribution cloud diagram of the mounting bracket.

[0018] In some embodiments, training the initial network model and the training data based on the SVM algorithm to establish the NVH data training diagnosis model includes the following steps:

[0019] Placing the input parameter and the output parameter in a target file;

[0020] Read the target file according to the target path, and divide the input parameters and output parameters in the target file into a first list and a second list respectively, wherein the input parameters are associated with the output parameters;

[0021] Determine a training set and a test set according to the input parameters in the first list and the output parameters in the second list according to a preset division rule;

[0022] According to the training set, an initial network model is trained by using an SVM algorithm to obtain a prediction set;

[0023] A NVH data training diagnostic model is determined based on the prediction set and the test set.

[0024] In some embodiments, determining the NVH data training diagnostic model according to the prediction set and the test set comprises the following steps:

[0025] Determine the total sample size and the number of parameter points corresponding to the test set;

[0026] Calculate the error rate based on the prediction set, the test set, the total sample size and the number of digits of the parameter points;

[0027] Determining the degree of test fit based on the total sample size, the number of parameter points, the test set average, the prediction set, and the test set;

[0028] Determining whether the error rate satisfies a preset error condition, and whether the test fit degree satisfies a preset fit condition;

[0029] When the error rate satisfies the preset error condition and the test fit degree satisfies the preset fit condition, the trained initial network model is used as the NVH data training diagnostic model.

[0030] In some embodiments, the following steps are also included:

[0031] When the error rate meets the preset error condition and the test fit degree does not meet the preset fit condition, the initial network model is retrained and learned based on the input parameters and the output parameters in combination with the SVM algorithm.

[0032] In some embodiments, inputting the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report includes the following steps:

[0033] The output result after obtaining the structural parameters of the vehicle refrigerator to be diagnosed and inputting the NVH data to train the diagnostic model; the output structure includes the refrigerator body installation mode, the mounting bracket installation point dynamic stiffness, the vibration / noise transfer function of the refrigerator body and the mounting bracket, and the strain energy distribution cloud map of the mounting bracket;

[0034] Compare the refrigerator body installation mode and the mounting bracket installation point dynamic stiffness with the corresponding pre-standard threshold value, and compare the vibration / noise transfer function of the refrigerator body and the mounting bracket with the standard function;

[0035] The comparison results and the strain energy distribution cloud diagram of the mounting bracket are used as the NVH performance diagnosis report.

[0036] In a second aspect, a vehicle refrigerator NVH diagnostic system is provided, the vehicle refrigerator NVH diagnostic system comprising:

[0037] The first module is used to simulate and obtain training data based on different structural parameters of the vehicle refrigerator and the TB network model of the upper vehicle body;

[0038] The second module is used to train the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model;

[0039] The third module is used to input the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report.

[0040] In a third aspect, a vehicle refrigerator NVH diagnostic device is provided, the vehicle refrigerator NVH diagnostic device comprising a processor, a memory, and a vehicle refrigerator NVH diagnostic program stored in the memory and executable by the processor, wherein when the vehicle refrigerator NVH diagnostic program is executed by the processor, the steps of the vehicle refrigerator NVH diagnostic method are implemented.

[0041] In a fourth aspect, a computer-readable storage medium is provided, on which a vehicle refrigerator NVH diagnostic program is stored, wherein when the vehicle refrigerator NVH diagnostic program is executed by a processor, the steps of the vehicle refrigerator NVH diagnostic method are implemented.

[0042] The beneficial effects of the technical solution provided by this application include: (only write the benefits of exclusive rights)

[0043] The embodiments of the present application provide a vehicle refrigerator NVH diagnosis method, system, device and storage medium, which use the data obtained by simulating the TB network model of the vehicle body and different structural parameters of the vehicle refrigerator as training data, and combine the SVM algorithm to train the initial network model to form an NVH data training diagnosis model dedicated to the vehicle refrigerator; when the vehicle refrigerator is changed in design next time, there is no need to re-model the simulation analysis, and the structural parameters of the vehicle refrigerator with the changed design can be directly input into the NVH data training diagnosis model, so that it can be known whether the vehicle refrigerator with the changed design meets the NVH performance requirements, thereby greatly reducing the analysis computing power, achieving the matching of simulation conditions related to the NVH performance of the vehicle refrigerator, and outputting the diagnosis results, and the simulation results can be predicted without the need for simulation operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A schematic diagram of the general flow of the vehicle refrigerator NVH diagnostic method provided in the embodiment of the present application;

[0046] Figure 2 A schematic diagram of a specific process of the vehicle refrigerator NVH diagnostic method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0048] What should be understood in this application is that, in the face of today's high-speed product iterations, which lead to small design changes in the car refrigerator or surrounding sheet metal, human experience accumulation is not enough to support the performance prediction after the structural change, resulting in each small design change of the car refrigerator or surrounding sheet metal requiring re-modeling and simulation analysis to know whether it meets the requirements; when it does not meet the requirements, the parameters are adjusted according to the simulation results, and the optimization is finally completed through multiple analysis and adjustments. This leads to the consumption of computing power during NVH analysis.

[0049] In addition, the NVH (vehicle body vibration and noise problem) simulation efficiency related to car refrigerators is low, and it is difficult to diagnose and optimize; most existing machine learning algorithms and simulation output data are single, and do not have the ability to predict simulation results and output diagnostic results at the same time; there are also differences in calculation accuracy among machine learning algorithms.

[0050] Therefore, in order to solve the problem that the high-speed iteration of products in related technologies leads to small design changes of vehicle refrigerators or surrounding sheet metals, which results in high computing power consumption during NVH analysis using parametric models for simulation design, a vehicle refrigerator NVH diagnosis method is proposed.

[0051] refer to Figure 1 In a first aspect, a vehicle refrigerator NVH diagnostic method comprises:

[0052] Step 100: Based on the TB network model of the upper vehicle body and different structural parameters of the vehicle refrigerator, simulation is performed to obtain training data;

[0053] Step 101: Train the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model;

[0054] Step 102: Input the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain an NVH performance diagnosis report.

[0055] The above-mentioned car refrigerators should refer to the same type of car refrigerators, and their design changes are minor design changes of the car refrigerator or surrounding sheet metal.

[0056] In the above, the data obtained by simulating different structural parameters of the vehicle body TB network model and the vehicle refrigerator are used as training data, and then the initial network model is trained using the SVM algorithm using the training data to form an NVH data training diagnosis model dedicated to the vehicle refrigerator; in this way, the next time the design of the vehicle refrigerator is changed, there is no need to re-model the simulation analysis, and the structural parameters of the vehicle refrigerator with the changed design can be directly input into the NVH data training diagnosis model, so that it can be known whether the vehicle refrigerator with the changed design meets the NVH performance requirements, thereby greatly reducing the analysis computing power, achieving the matching of simulation conditions related to the NVH performance of the vehicle refrigerator, and outputting the diagnosis results, and the simulation results can be predicted without the need for simulation operations.

[0057] The above can be understood as: Support Vector Machine (SVM) is a generalized linear classification algorithm that performs binary classification of data in a supervised learning manner, and has been applied in pattern recognition problems such as portrait recognition and text classification. This application is based on Python language, calling the Scikit-learn machine learning library, combining the support vector machine algorithm with simulation to perform simulation prediction, and screening the results that meet the requirements before output, combined with modal calculation, dynamic stiffness, vibration / noise transfer function analysis (N / VTF) and strain energy distribution cloud map and other diagnostic methods, that is, it can realize the input of the vehicle refrigerator and its bracket structure model data (CAD) and then output the NVH performance diagnosis of the vehicle refrigerator and the optimization plan for its bracket structure, so that it avoids the time and computing resources required for a large number of traditional NVH working condition simulations in the later stage.

[0058] refer to Figure 2 In some preferred embodiments, step 100, based on the upper vehicle body TB network model and different structural parameters of the vehicle refrigerator, simulation to obtain training data includes the following steps:

[0059] Step 10001, input different structural parameters of the vehicle refrigerator into the upper body TB network model respectively, and simulate and output installation modes, installation point dynamic stiffness, vibration / noise transfer function and strain energy distribution cloud map corresponding to different structural parameters;

[0060] Step 10002: taking the structural parameters of the vehicle refrigerator as input parameters;

[0061] Step 10003: Use the installation mode, installation point stiffness, vibration / noise transfer function and strain energy distribution cloud map as output parameters;

[0062] Step 10004: Collect the input parameters and output parameters, and associate the input parameters and output parameters to serve as training data.

[0063] Wherein, the vehicle-mounted refrigerator comprises a refrigerator body and a mounting bracket;

[0064] The structural parameters include CAD data of the refrigerator body and the mounting bracket, the mounting point position of the mounting bracket, the welding point information of the mounting bracket, the material and material thickness, and the mass center parameters of the refrigerator body and the mounting bracket;

[0065] The output parameters include the refrigerator body installation mode, the mounting bracket installation point dynamic stiffness, the refrigerator body and the mounting bracket vibration / noise transfer function, and the mounting bracket strain energy distribution cloud map. The vibration / noise transfer function is the NTF / VTF function.

[0066] In some preferred embodiments, step 101, training the initial network model and the training data based on the SVM algorithm to establish the NVH data training diagnosis model, includes the following steps:

[0067] Step 10101, placing the input parameters and the output parameters in a target file;

[0068] Step 10102: read the target file according to the target path, and divide the input parameters and output parameters in the target file into a first list and a second list respectively, wherein the input parameters are associated with the output parameters;

[0069] Step 10103: Determine a training set and a test set according to the input parameters in the first list and the output parameters in the second list according to a preset division rule;

[0070] Step 10104: train the initial network model using the SVM algorithm according to the training set to obtain a prediction set;

[0071] Step 10105: Determine the NVH data training diagnostic model based on the prediction set and the test set.

[0072] The above steps 10101 to 10103 can be understood as:

[0073] In Python for machine learning, select the path and read the Excel file, i.e. the target file. The first step is to divide the data into two lists (the first list for input and the second list for output); the second step is to adjust the rows and columns of the two lists so that the number of parameter points corresponds; the third step is to randomly classify the parameters into training sets and test sets (input parameters and output parameters are performed at the same time). The number can be modified by yourself, and 7:3 is recommended. Then change the parameter format to str (string) so that the sklearn library can calculate decimals. After the modification, call the SVM algorithm in the sklearn library, input the training set as the input parameter into the initial network model for training, obtain the prediction result through training, and use the prediction result as the output parameter.

[0074] It should also be noted that the selected path as the target path may be a pre-set path. Support vector machine (SVM) is a generalized linear classification algorithm that performs binary classification on data in a supervised learning manner.

[0075] It should also be understood that the preset division rule can be a user-defined setting, which can be 7:3, or 8:2, etc., and this embodiment does not limit this.

[0076] Further, step 10105 specifically includes the following steps:

[0077] Step 101051, determine the total sample size and the number of parameter points corresponding to the test set;

[0078] Step 101052: Calculate the error rate based on the prediction set, the test set, the total sample size, and the number of digits of the parameter points;

[0079] Step 101053, determining the test fit degree according to the total sample size, the number of digits of the parameter points, the average of the test set, the prediction set and the test set;

[0080] Step 101054: determine whether the error rate meets a preset error condition, and whether the test fit degree meets a preset fit condition;

[0081] Step 101055: when the error rate satisfies the preset error condition and the test fit degree satisfies the preset fit condition, the trained initial network model is used as the NVH data training diagnosis model;

[0082] Step 101056: When the error rate meets the preset error condition and the test fit degree does not meet the preset fit condition, retrain the initial network model based on the input parameters and the output parameters in combination with the SVM algorithm.

[0083] The above two measurement standards are used to jointly evaluate the completion of machine learning training, one to check the error and the other to check the fit. If the result does not meet the requirements, the machine learning will be re-performed, which solves the problem of insufficient accuracy of many machine learning algorithms. The specific formula is as follows:

[0084] The first one: test error rate

[0085]

[0086] Among them, T is the test set, P is the prediction set, n is the total sample size, and i is the number of parameter points. For example, T[5] represents the 5th number in the test set.

[0087] Second: Test the degree of fit

[0088]

[0089] Among them, a is the average of all test sets of the parameter, P is the prediction set, T is the test set, n is the total sample size, and i is the number of digits in the parameter point, such as T[5] represents the 5th digit in the test set;

[0090] If the calculation result of R square does not meet the set conditions (can be changed according to your own needs), re-enter step 2, and the machine learning data verification result will be output in the form of images and text:

[0091] The image is a comparison of all parameter points between the true value and the predicted value of each output parameter. The text is the specific value of the error rate and R-square of each output parameter. When the error rate and R-square reach the training set target, the NVH data training diagnosis model is completed and can be put into practical use.

[0092] The above comparison of the prediction set (training results) and the test set (real results) is used for data verification. This application uses the above two measurement standards to jointly evaluate the completion of machine learning training.

[0093] refer to Figure 2 In some preferred embodiments, step 102, inputting the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report, includes the following steps:

[0094] Step 10201, obtaining the output result after inputting the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model; the output structure includes the refrigerator body installation mode, the mounting bracket installation point dynamic stiffness, the vibration / noise transfer function of the refrigerator body and the mounting bracket, and the strain energy distribution cloud map of the mounting bracket;

[0095] Step 10202: compare the refrigerator body installation mode and the installation point dynamic stiffness of the mounting bracket with the corresponding pre-standard threshold values, and compare the vibration / noise transfer function of the refrigerator body and the mounting bracket with the standard function;

[0096] Step 10203: Use the comparison result and the strain energy distribution cloud diagram of the mounting bracket as an NVH performance diagnosis report.

[0097] Step 10204: Locate the part that does not meet the standard in the NVH performance diagnosis report and optimize the position.

[0098] The above implementation achieves the following: when a certain vehicle model project is changed in design, the structural parameters of the vehicle refrigerator and bracket after the design change are input, and the NVH data training diagnosis model completed through machine learning training is used to train the diagnosis model. The NVH performance diagnosis report (items not meeting the standards) of the project design change when the vehicle refrigerator is installed under the NVH data training diagnosis model is output. At the same time, the optimization plan of the vehicle refrigerator bracket (sheet metal part) is output to complete the analysis and optimization closed loop, thereby improving the simulation efficiency.

[0099] In summary, the above-mentioned redefines the simulation analysis of the actual problems of the NVH performance of vehicle refrigerators. The analysis items that highly rely on the experience of engineers and require multiple verifications, such as modal, dynamic stiffness, N / VTF and other working condition analysis processes, can be used to achieve single input (CAD structural parameters after design changes) and multiple working condition outputs (modal, dynamic stiffness, N / VTF, bracket strain energy distribution cloud map and optimization suggestions) through machine learning training. The setting of multiple output parameters solves the problem that many previous machine learning algorithms could only output a single parameter but could not consider multiple parameters at the same time.

[0100] In a second aspect, a vehicle refrigerator NVH diagnostic system is provided, the vehicle refrigerator NVH diagnostic system comprising:

[0101] The first module is used to simulate and obtain training data based on different structural parameters of the vehicle refrigerator and the TB network model of the upper vehicle body;

[0102] The second module is used to train the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model;

[0103] The third module is used to input the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report.

[0104] Among them, the functional implementation of each module in the above-mentioned vehicle refrigerator NVH diagnostic system corresponds to each step in the above-mentioned vehicle refrigerator NVH diagnostic method embodiment, and its functions and implementation processes are not repeated here one by one. It is easy to understand that the execution subject of this embodiment can be a vehicle refrigerator NVH diagnostic system with functions such as data processing, network communication and program running, or other computer equipment with similar functions, etc., and this embodiment is not limited.

[0105] In a third aspect, a vehicle refrigerator NVH diagnostic device is provided, the vehicle refrigerator NVH diagnostic device comprising a processor, a memory, and a vehicle refrigerator NVH diagnostic program stored in the memory and executable by the processor, wherein when the vehicle refrigerator NVH diagnostic program is executed by the processor, the steps of the vehicle refrigerator NVH diagnostic method are implemented.

[0106] The vehicle refrigerator NVH diagnostic device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and a memory.

[0107] Among them, the communication bus is used to realize the connection and communication between these components. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface may also include a standard wired interface and a wireless interface. The network interface may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, Wi-Fi) interface). The memory may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory may also be an optional storage system independent of the aforementioned processor.

[0108] In a fourth aspect, a computer-readable storage medium is provided, on which a vehicle refrigerator NVH diagnostic program is stored, wherein when the vehicle refrigerator NVH diagnostic program is executed by a processor, the steps of the vehicle refrigerator NVH diagnostic method are implemented.

[0109] Those skilled in the art will appreciate that the above structure does not constitute a limitation on the NVH diagnostic device based on a vehicle refrigerator, and may include more or fewer components, or a combination of certain components, or different component arrangements. The memory as a storage medium may include an operating system, a network communication module, a user interface module, and a vehicle refrigerator NVH diagnostic program. In the vehicle refrigerator NVH diagnostic device, the network interface is mainly used for data communication with a network server; the user interface is mainly used for data interaction with a user; the processor and memory in the vehicle refrigerator NVH diagnostic device of the present invention may be arranged in the vehicle refrigerator NVH diagnostic device, and the vehicle refrigerator NVH diagnostic device calls the vehicle refrigerator NVH diagnostic program stored in the memory through the processor, and executes the vehicle refrigerator NVH diagnostic method provided in an embodiment of the present invention.

[0110] In the description of the present application, it should be noted that the terms "upper", "lower", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. Unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances.

[0111] It should be noted that, in this application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0112] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.

Claims

1. A vehicle refrigerator NVH diagnostic method, characterized in that: It includes: Based on the TB network model of the upper body and different structural parameters of the onboard refrigerator, training data is obtained through simulation; Training the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model; The structural parameters of the vehicle refrigerator to be diagnosed are input into the NVH data training diagnosis model to obtain the NVH performance diagnosis report.

2. The vehicle refrigerator NVH diagnostic method according to claim 1, characterized in that: Based on the TB network model of the upper body and different structural parameters of the vehicle refrigerator, the training data is obtained by simulation, including the following steps: The different structural parameters of the vehicle refrigerator are input into the TB network model of the upper body respectively, and the simulation outputs the installation mode, installation point dynamic stiffness, vibration / noise transfer function and strain energy distribution cloud map corresponding to the different structural parameters; The structural parameters of the vehicle refrigerator are used as input parameters; The installation mode, installation point stiffness, vibration / noise transfer function and strain energy distribution cloud diagram are used as output parameters; The input parameters and output parameters are collected and associated with each other to serve as training data.

3. The vehicle refrigerator NVH diagnostic method according to claim 2, characterized in that: The vehicle-mounted refrigerator comprises a refrigerator body and a mounting bracket; The structural parameters include CAD data of the refrigerator body and the mounting bracket, the mounting point position of the mounting bracket, the welding point information of the mounting bracket, the material and material thickness, and the mass center parameters of the refrigerator body and the mounting bracket; The output parameters include the installation mode of the refrigerator body, the installation point stiffness of the mounting bracket, the vibration / noise transfer function of the refrigerator body and the mounting bracket, and the strain energy distribution cloud diagram of the mounting bracket.

4. The vehicle refrigerator NVH diagnostic method according to claim 2, characterized in that: Training the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model includes the following steps: Placing the input parameter and the output parameter in a target file; Read the target file according to the target path, and divide the input parameters and output parameters in the target file into a first list and a second list respectively, wherein the input parameters are associated with the output parameters; Determine a training set and a test set according to the input parameters in the first list and the output parameters in the second list according to a preset division rule; According to the training set, an initial network model is trained by using an SVM algorithm to obtain a prediction set; A NVH data training diagnostic model is determined based on the prediction set and the test set.

5. The vehicle refrigerator NVH diagnostic method according to claim 4, characterized in that: Determining the NVH data training diagnostic model according to the prediction set and the test set comprises the following steps: Determine the total sample size and the number of parameter points corresponding to the test set; Calculate the error rate based on the prediction set, the test set, the total sample size and the number of digits of the parameter points; Determining the degree of test fit based on the total sample size, the number of parameter points, the test set average, the prediction set, and the test set; Determining whether the error rate satisfies a preset error condition, and whether the test fit degree satisfies a preset fit condition; When the error rate satisfies the preset error condition and the test fit degree satisfies the preset fit condition, the trained initial network model is used as the NVH data training diagnostic model.

6. The vehicle refrigerator NVH diagnostic method according to claim 5, characterized in that: The following steps are also included: When the error rate meets the preset error condition and the test fit degree does not meet the preset fit condition, the initial network model is retrained and learned based on the input parameters and the output parameters in combination with the SVM algorithm.

7. The vehicle refrigerator NVH diagnostic method according to claim 3, characterized in that: Inputting the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report includes the following steps: The output result after obtaining the structural parameters of the vehicle refrigerator to be diagnosed and inputting the NVH data to train the diagnostic model; the output structure includes the refrigerator body installation mode, the mounting bracket installation point dynamic stiffness, the vibration / noise transfer function of the refrigerator body and the mounting bracket, and the strain energy distribution cloud map of the mounting bracket; Compare the refrigerator body installation mode and the mounting bracket installation point dynamic stiffness with the corresponding pre-standard threshold value, and compare the vibration / noise transfer function of the refrigerator body and the mounting bracket with the standard function; The comparison results and the strain energy distribution cloud diagram of the mounting bracket are used as the NVH performance diagnosis report.

8. A vehicle refrigerator NVH diagnostic system, characterized in that: The vehicle refrigerator NVH diagnostic system comprises: The first module is used to simulate and obtain training data based on different structural parameters of the vehicle refrigerator and the TB network model of the upper vehicle body; The second module is used to train the initial network model and the training data based on the SVM algorithm to establish an NVH data training diagnosis model; The third module is used to input the structural parameters of the vehicle refrigerator to be diagnosed into the NVH data training diagnosis model to obtain the NVH performance diagnosis report.

9. A vehicle refrigerator NVH diagnostic equipment, characterized in that: The vehicle refrigerator NVH diagnostic device includes a processor, a memory, and a vehicle refrigerator NVH diagnostic program stored in the memory and executable by the processor, wherein when the vehicle refrigerator NVH diagnostic program is executed by the processor, the steps of the vehicle refrigerator NVH diagnostic method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a vehicle refrigerator NVH diagnostic program, wherein when the vehicle refrigerator NVH diagnostic program is executed by a processor, the steps of the vehicle refrigerator NVH diagnostic method according to any one of claims 1 to 7 are implemented.

Images