Multi-objective optimization method for car body acoustic package based on hierarchical decomposition sensitivity analysis

Abstract

This application relates to the field of automotive noise reduction technology, and specifically to a multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis. The method mainly includes: dividing the entire vehicle into eight systems to construct a four-level knowledge graph; training the four-level knowledge graph to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels; performing step-by-step sensitivity analysis on the four-level knowledge graph based on the prediction model between the first and second levels and the sensitivity analysis model between adjacent levels until the basic set parameters at the flat level are determined, thus obtaining the sensitivity analysis results; and performing multi-objective optimization of the vehicle body acoustic package based on the sensitivity analysis results. This solves the problems of related technologies that mainly rely on simulation and experimental analysis, which are time-consuming, inefficient, and lack direct and effective analysis methods.

Description

Technical Field

[0001] This application relates to the field of automotive noise reduction technology, and in particular to a multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis. Background Technology

[0002] In the development of automotive acoustic packages, it is challenging to quickly improve the sound absorption and insulation performance of a particular path, while also optimizing cost and weight to ensure minimal impact on performance.

[0003] Related technologies have proposed a method for determining the sound insulation contribution of a vehicle, which can quickly and accurately obtain the degree of contribution of each component of the vehicle to the sound insulation when passing through different transmission paths. This is beneficial for quickly identifying weak sound insulation locations for optimization and improvement. However, after identifying the weak sound insulation areas, how to formulate an effective solution to improve the sound insulation at these weak locations remains a technical challenge. Currently, there is limited research on this topic, with most studies relying on simulations and experiments, which are time-consuming, inefficient, and lack direct and effective analytical methods. Summary of the Invention

[0004] This application provides a multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis, in order to solve the problems of related technologies that mainly rely on simulation and experimental analysis, which are time-consuming, inefficient, and lack direct and effective analysis methods.

[0005] The first aspect of this application provides a multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis, including the following steps: The entire vehicle is divided into eight systems to construct a four-level knowledge graph; The four-level knowledge graph is trained to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels. Based on the first and second level inter-level prediction model and the sensitivity analysis model between adjacent levels, the four-level knowledge graph is subjected to level-by-level sensitivity analysis until the basic set parameters of the flat plate level are determined, and the sensitivity analysis results are obtained. Based on the sensitivity analysis results, the vehicle's body acoustic package was optimized using a multi-objective approach.

[0006] Optionally, the eight systems include a front enclosure system, a front door system, a rear door system, a side enclosure system, a front floor system, a rear floor system, a roof system, and a rear enclosure system.

[0007] Optionally, the process of dividing the entire vehicle into eight systems to construct a four-level knowledge graph includes: Obtain the engine compartment acoustic transmission function of the entire vehicle and divide the entire vehicle into eight systems; The components of each acoustic package attached to the eight systems are set as component level, and the material composition, area, coverage and thickness distribution of each acoustic package component are set as plate level. Based on the cabin acoustic communication function, the eight systems, the component level, and the tablet level, a four-level knowledge graph is constructed, comprising cabin acoustic communication function, eight systems, component level, and tablet level.

[0008] Optionally, the step of performing a step-by-step sensitivity analysis on the four-level knowledge graph based on the first and second-level inter-level prediction model and the sensitivity analysis model between adjacent levels until the basic set parameters of the flat-level are clearly defined, and obtaining the sensitivity analysis results, includes: The first maximum and minimum sensitivity units of the eight systems to the cabin acoustic transfer function are predicted according to the first and second level inter-level prediction model. Predict the maximum and minimum second sensitivity units of the component level to the eight systems based on the sensitivity analysis model between the adjacent levels; The maximum and minimum third sensitivity units of the plate level to the component level are predicted based on the sensitivity analysis model between the adjacent levels. The first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit are used to construct the sensitivity analysis result.

[0009] A second aspect of this application provides a multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis, comprising: The building module is used to divide the entire vehicle into eight systems to construct a four-level knowledge graph; A module is built to train the four-level knowledge graph in order to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels. The sensitivity analysis module is used to perform a step-by-step sensitivity analysis on the four-level knowledge graph based on the first and second level inter-level prediction model and the sensitivity analysis model between adjacent levels, until the basic set parameters of the flat plate level are determined, and the sensitivity analysis results are obtained. The optimization module is used to perform multi-objective optimization of the vehicle's body acoustic package based on the sensitivity analysis results.

[0010] Optionally, the eight systems include a front enclosure system, a front door system, a rear door system, a side enclosure system, a front floor system, a rear floor system, a roof system, and a rear enclosure system.

[0011] Optionally, the building module includes: A partitioning unit is used to acquire the engine compartment acoustic transmission function of the entire vehicle and divide the entire vehicle into eight systems; The setting unit is used to set the various acoustic package components attached to the eight systems as component level, and to set the material composition, area, coverage and thickness distribution of each acoustic package component as plate level; The construction unit is used to construct a four-level knowledge graph containing the cabin acoustic transmission function, the eight systems, the component level, and the tablet level, based on the cabin acoustic transmission function, the eight systems, the component level, and the tablet level.

[0012] Optionally, the sensitivity analysis module includes: The first sensitivity analysis unit is used to predict the first maximum and minimum sensitivity units of the eight systems to the cabin acoustic transmission function based on the first two-level inter-level prediction model. The second sensitivity analysis unit is used to predict the maximum and minimum second sensitivity units of the component level to the eight systems based on the sensitivity analysis model between the adjacent levels. The third sensitivity analysis unit is used to predict the maximum and minimum third sensitivity units of the plate level to the component level based on the sensitivity analysis model between the adjacent levels. The sensitivity analysis result unit is used to construct the sensitivity analysis result from the first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit.

[0013] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis as described in the above embodiments.

[0014] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis.

[0015] The multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis proposed in this application constructs a hierarchical decomposition architecture for the sound absorption and insulation performance of vehicle acoustic packages, based on the vehicle structure and noise transmission path, from "vehicle level to system level to component level to flat panel level". By constructing a predictive model to conduct sensitivity analysis between adjacent levels, it identifies key factors affecting the performance of a certain level in the previous level, providing a reliable design basis for optimizing the performance, cost, and weight of each path at the vehicle level. This enables accurate prediction and optimization design of the performance of the vehicle acoustic package, and is applicable to the forward development of the vehicle acoustic package and the intelligent design scenarios for later optimization of a specific path.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis provided in an embodiment of this application; Figure 2 This is a schematic diagram of a four-level knowledge graph structure provided according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a front panel system (SEA) model according to an embodiment of this application; Figure 4 This is a block diagram of a multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application.

[0018] Explanation of reference numerals in the attached figures: 40-Multi-objective optimization device for vehicle body acoustic package based on hierarchical decomposition sensitivity analysis; 401-Construction module; 402-Building module; 403-Sensitivity analysis module; 404-Optimization module; 501-Memory; 502-Processor; 503-Communication interface. Detailed Implementation

[0019] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0020] The following description, with reference to the accompanying drawings, describes a multi-objective optimization of the vehicle acoustic package based on hierarchical decomposition sensitivity analysis, according to an embodiment of this application.

[0021] Figure 1 This is a schematic diagram illustrating a multi-objective optimization process for a vehicle body acoustic package based on hierarchical decomposition sensitivity analysis, provided as an embodiment of this application.

[0022] like Figure 1 As shown, the multi-objective optimization of the vehicle acoustic package based on hierarchical decomposition sensitivity analysis includes the following steps: In step S101, the vehicle is divided into eight systems to construct a four-level knowledge graph.

[0023] In some embodiments, the eight systems include a front enclosure system, a front door system, a rear door system, a side enclosure system, a front floor system, a rear floor system, a roof system, and a rear enclosure system.

[0024] In some embodiments, the vehicle is divided into eight systems to construct a four-level knowledge graph, including: Obtain the engine compartment acoustic transmission function of the entire vehicle and divide the entire vehicle into eight systems; The components of each acoustic package attached to the eight systems are set as component level, and the material composition, area, coverage and thickness distribution of each acoustic package component are set as plate level. A four-level knowledge graph is constructed based on the cabin acoustic communication function, eight systems, component level, and tablet level, encompassing the cabin acoustic communication function, eight systems, component level, and tablet level.

[0025] In actual implementation, such as Figure 2 As shown, based on the vehicle passenger compartment, the entire vehicle is divided into eight systems. The acoustic package components attached to the eight systems are classified as component level, and the material composition, area, coverage, and thickness distribution of each acoustic package component are classified as flat plate level. Based on the cabin acoustic transmission function, the eight systems, component level, and flat plate level, a four-level knowledge graph is constructed, including cabin acoustic transmission function, eight systems, component level, and flat plate level.

[0026] In step S102, the four-level knowledge graph is trained to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels.

[0027] In step S103, the four-level knowledge graph is subjected to progressive sensitivity analysis based on the prediction model between the first and second levels and the sensitivity analysis model between adjacent levels until the basic set parameters of the flat-level are determined, and the sensitivity analysis results are obtained.

[0028] In some embodiments, a step-by-step sensitivity analysis is performed on the four-level knowledge graph based on the first and second level prediction model and the sensitivity analysis model between adjacent levels until the basic set parameters of the flat-level are clearly defined, and the sensitivity analysis results are obtained, including: The first maximum and minimum sensitivity units of the eight systems to the cabin acoustic transfer function are predicted based on the first and second level inter-level prediction model. Predict the maximum and minimum second sensitivity units of the component level for eight systems based on the sensitivity analysis model between adjacent levels; Predict the maximum and minimum third sensitivity units of the plate level to the component level based on the sensitivity analysis model between adjacent levels; The first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit are used to construct the sensitivity analysis results.

[0029] In step S104, the vehicle body acoustic package is optimized for multiple objectives based on the sensitivity analysis results.

[0030] In actual implementation, machine learning is used to train the four-level samples in the four-level knowledge graph to obtain a sensitivity analysis model between adjacent levels and a prediction model between the first and second levels.

[0031] Furthermore, based on the prediction model between the first and second levels and the sensitivity analysis model between adjacent levels, a step-by-step sensitivity analysis is performed on the four-level knowledge graph to obtain the maximum and minimum sensitivity units of the next level relative to the previous level, until the basic geometric parameter coverage and thickness distribution of the lowest level flat plate are determined. This yields the first, second, and third maximum and minimum sensitivity units, which form the sensitivity analysis results. Finally, based on the sensitivity analysis results, multi-objective optimization is performed on the vehicle's body acoustic package to improve performance or optimize the design for cost and quality control.

[0032] Taking the cabin acoustic transmission function as an example, the analysis frequency is 400 Hz - 8000 Hz 1 / 3 octave band. In order to improve the sound absorption and insulation performance of the transmission path from the front cabin to the passenger compartment, the cabin acoustic transmission function is taken as the first level, the sound insulation performance of the eight systems is taken as the second level, the components are taken as the third level, and the basic geometric parameters coverage and thickness distribution of the components are taken as the fourth level. After obtaining the prediction model between the first and second levels through machine learning, the sensitivity analysis of the cabin acoustic transmission function is carried out. The original state of the basic geometric parameters coverage and thickness distribution of the components that currently reflect the body acoustic package technology solution is taken as the benchmark solution. Taking the front baffle pad and the front sound insulation pad as examples, the coverage and thickness distribution are shown in Tables 1 and 2.

[0033] Table 1 Coverage Statistics

[0034] Table 2 Thickness Distribution Statistics

[0035] Based on the baseline scheme, with the cabin acoustic transfer function as the response variable and the sound insulation of eight systems as the design variable, a normal distribution characteristic is constructed by introducing a 10% standard deviation. Disturbance modeling is performed on each of the eight design variables. Based on this distribution, random sampling is conducted using the Monte Carlo method, performing at least 10,000 predictions, and calculating the mean and variance to obtain the sensitivity results of each system to the cabin acoustic transfer function. Similarly, taking the sound insulation of the front enclosure system as an example, the sound insulation of the front enclosure system is taken as the response variable, and the sound insulation of the acoustic package components, including the front baffle pad and the front enclosure sound insulation pad, are taken as design variables. Again, a normal distribution characteristic is constructed by introducing a 10% standard deviation. Disturbance modeling is performed on each of the two design variables. Based on this distribution, random sampling is conducted using the Monte Carlo method, performing at least 10,000 predictions, and calculating the mean and variance to obtain the sensitivity results of each system to the cabin acoustic transfer function. Sensitivity results for the sound insulation of the front fender pad and the front fender sound insulation pad were obtained. Similarly, the sound insulation of the front fender pad was used as the response variable, and the coverage of the front fender pad and eight thickness distributions were used as design variables. The standard deviation of 10% of the amplitude was also introduced to construct the normal distribution characteristics. It should be noted that in order to ensure that the sum of the proportions of each thickness is kept at 100%, the other thicknesses are scaled proportionally by normalization. This can avoid the problem of total non-conservation, while keeping the relative relationship between other thicknesses unchanged. The nine design variables were perturbed and modeled. Based on the distribution, the Monte Carlo method was used for random sampling, and at least 10,000 predictions were performed. The mean and variance were calculated to obtain the sensitivity results for the coverage and thickness distribution of the sound insulation of the front fender pad.

[0036] After obtaining the sensitivity analysis results between each level, the sensitivity analysis results of the design variables of each level can be divided into high sensitivity, low sensitivity and negative sensitivity. Among them, appropriately increasing the high sensitivity helps to enhance the performance of the previous level, while appropriately reducing the low sensitivity and negative sensitivity results has little or no impact on the performance of the previous level.

[0037] After changes in the design variables of the flat-panel prototype, simulation calculations can be used to calculate the component-level sound insulation for both the upward and downward adjustments, as well as system-level sound insulation calculations. Figure 3The diagram shows two complete sets of sound insulation curves. By comparing these two sets of curves with the baseline scheme, the corresponding impact value (IV) can be calculated. Specifically, subtracting the sound insulation after increasing the thickness from the sound insulation after decreasing it yields the impact value of that thickness at different frequency points. Furthermore, by averaging the impact value across the entire frequency range, the mean impact value (MIV) of that thickness can be obtained, thus quantifying its contribution to the overall sound insulation performance. Similarly, the sensitivity analysis of coverage can be performed by comparing the differences in sound insulation when coverage increases and decreases, thus obtaining the sensitivity index of coverage to system performance.

[0038] It's important to note that MIV theory is a method used in complex systems to identify and assess the importance of influencing factors. It primarily uses sensitivity analysis to help analyze the degree of influence of different design variables (factors) on the response output. MIV theory is widely used in noise and vibration control, engineering optimization design, and is particularly important in vehicle design. The core of MIV theory lies in sensitivity analysis. By varying various variables of the system, it assesses the degree of impact of these changes on system outcomes (such as noise and vibration). Typically, the sensitivity of each variable to the output is obtained through numerical simulation or experimental data analysis. These sensitivity values ​​reflect the degree of influence of variable changes on the system output. Through sensitivity analysis, MIV theory helps engineers identify which variables have a significant impact on the target output (e.g., in-vehicle noise and vibration). By comparing all variables, the most important variables can be identified. These important variables are usually the factors that need to be prioritized in the system design, optimization, and control process. MIV theory not only focuses on the impact of individual variables but also analyzes the interactions between different variables and how these interactions affect the final result. In the control of vehicle noise and vibration, the interaction between variables can affect the noise intensity inside the vehicle through vibration propagation, resonance, and other means. Therefore, MIV theory helps to reveal the key pathways of these interactions.

[0039] After obtaining the sensitivity analysis results at each level in the embodiments of this application, corresponding requirements can be proposed in combination with the actual working scenario. For example, if it is necessary to enhance the sound absorption and insulation performance of a certain transmission path, the response of the system with the highest sensitivity—the sound insulation performance of the component—and the geometric parameters of the component can be enhanced according to the results of the sensitivity analysis. If it is necessary to control the cost and weight, the response of the system with the lowest sensitivity—the sound insulation performance of the component—and the geometric parameters of the component can be weakened to ensure that the cost and weight are controlled while minimizing the impact on performance.

[0040] In summary, the multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis proposed in this application realizes sensitivity analysis of parameters such as thickness, area coverage, etc., of one or more noise transmission paths to various components. It directly and effectively determines the most sensitive and least sensitive sensitivity analysis results for the sound transmission function of a certain path. Based on the sensitivity analysis results, the optimal technical solution for improving sound insulation can be determined, which can also directly and effectively improve the performance of the acoustic package along that path while achieving multi-objective optimization of performance, cost, and weight. It can be applied in the design stage of automobile R&D, allowing for component modifications before the placement and space are locked, reducing manpower and development costs.

[0041] Next, referring to the accompanying drawings, a multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis is described according to an embodiment of this application.

[0042] Figure 4 This is a block diagram of a multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis provided in an embodiment of this application.

[0043] like Figure 4 As shown, the multi-objective optimization device 40 for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis includes: a construction module 401, a building module 402, a sensitivity analysis module 403, and an optimization module 404.

[0044] The system comprises the following modules: Construction module 401 divides the vehicle into eight systems to build a four-level knowledge graph; Setup module 402 trains the four-level knowledge graph to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels; Sensitivity analysis module 403 performs a step-by-step sensitivity analysis on the four-level knowledge graph based on the prediction model between the first and second levels and the sensitivity analysis model between adjacent levels, until the basic set parameters of the flat-level module are determined, thus obtaining the sensitivity analysis results; and Optimization module 404 performs multi-objective optimization of the vehicle's body acoustic package based on the sensitivity analysis results.

[0045] In some embodiments, the eight systems include a front enclosure system, a front door system, a rear door system, a side enclosure system, a front floor system, a rear floor system, a roof system, and a rear enclosure system.

[0046] In some embodiments, the construction module 401 includes: The segmentation unit is used to obtain the engine compartment acoustic transmission function of the whole vehicle and divide the whole vehicle into eight systems; The setting unit is used to set the various acoustic package components attached to the eight systems as component level, and to set the material composition, area, coverage and thickness distribution of each acoustic package component as plate level; The building unit is used to construct a four-level knowledge graph based on the cabin acoustic transmission function, eight systems, component level, and tablet level, including the cabin acoustic transmission function, eight systems, component level, and tablet level.

[0047] In some embodiments, the sensitivity analysis module 403 includes: The first sensitivity analysis unit is used to predict the maximum and minimum first sensitivity units of the eight systems to the cabin acoustic transfer function based on the first and second level inter-level prediction model. The second sensitivity analysis unit is used to predict the maximum and minimum second sensitivity units of the component level for eight systems based on the sensitivity analysis model between adjacent levels. The third sensitivity analysis unit is used to predict the maximum and minimum third sensitivity units of the plate level to the component level based on the sensitivity analysis model between adjacent levels. The sensitivity analysis result unit is used to construct the sensitivity analysis result from the first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit.

[0048] It should be noted that the foregoing explanation of the embodiment of the multi-objective optimization method for vehicle acoustic package based on hierarchical decomposition sensitivity analysis also applies to the multi-objective optimization device for vehicle acoustic package based on hierarchical decomposition sensitivity analysis in this embodiment, and will not be repeated here.

[0049] The multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis proposed in this application realizes sensitivity analysis of parameters such as thickness, area coverage, etc., of one or more noise transmission paths to various components. It directly and effectively determines the most sensitive and least sensitive sensitivity analysis results for the sound transmission function of a certain path. Based on the sensitivity analysis results, it determines the optimal technical solution to improve sound insulation, and can also directly and effectively improve the performance of the acoustic package along that path while achieving multi-objective optimization of performance, cost, and weight. It can be applied in the design stage of automobile R&D, allowing for component modifications before the placement and space are locked, reducing manpower and development costs.

[0050] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0051] The electronic device may include: a memory 501, a processor 502, and a computer program stored on the memory 501 and capable of running on the processor 502.

[0052] When the processor 502 executes the program, it implements the multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis provided in the above embodiments.

[0053] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0054] The memory 501 is used to store computer programs that can run on the processor 502.

[0055] Memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0056] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0057] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0058] Processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0059] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis.

[0060] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0061] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0062] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0063] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0064] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0065] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0066] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0067] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis, characterized in that, Includes the following steps: The entire vehicle is divided into eight systems to construct a four-level knowledge graph; The four-level knowledge graph is trained to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels. Based on the first and second level inter-level prediction model and the sensitivity analysis model between adjacent levels, the four-level knowledge graph is subjected to level-by-level sensitivity analysis until the basic set parameters of the flat plate level are determined, and the sensitivity analysis results are obtained. Based on the sensitivity analysis results, the vehicle's body acoustic package was optimized using a multi-objective approach.

2. The multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis according to claim 1, characterized in that, The eight systems include the front enclosure system, front door system, rear door system, side enclosure system, front floor system, rear floor system, roof system, and rear enclosure system.

3. The multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis according to claim 2, characterized in that, The process of dividing the entire vehicle into eight systems to construct a four-level knowledge graph includes: Obtain the engine compartment acoustic transmission function of the entire vehicle and divide the entire vehicle into eight systems; The components of each acoustic package attached to the eight systems are set as component level, and the material composition, area, coverage and thickness distribution of each acoustic package component are set as plate level. Based on the cabin acoustic communication function, the eight systems, the component level, and the tablet level, a four-level knowledge graph is constructed, comprising cabin acoustic communication function, eight systems, component level, and tablet level.

4. The multi-objective optimization method for vehicle body acoustic package based on hierarchical decomposition sensitivity analysis according to claim 3, characterized in that, The sensitivity analysis of the four-level knowledge graph is performed step-by-step based on the first and second level inter-level prediction models and the sensitivity analysis models between adjacent levels until the basic set parameters of the flat-level knowledge graph are determined, and the sensitivity analysis results are obtained, including: The first maximum and minimum sensitivity units of the eight systems to the cabin acoustic transfer function are predicted according to the first and second level inter-level prediction models. Predict the maximum and minimum second sensitivity units of the component level to the eight systems based on the sensitivity analysis model between the adjacent levels; The maximum and minimum third sensitivity units of the plate level to the component level are predicted based on the sensitivity analysis model between the adjacent levels. The first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit are used to construct the sensitivity analysis result.

5. A multi-objective optimization device for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis, characterized in that, include: The building module is used to divide the entire vehicle into eight systems to construct a four-level knowledge graph; A module is built to train the four-level knowledge graph in order to build a prediction model between the first and second levels and a sensitivity analysis model between adjacent levels. The sensitivity analysis module is used to perform a step-by-step sensitivity analysis on the four-level knowledge graph based on the first and second level inter-level prediction model and the sensitivity analysis model between adjacent levels, until the basic set parameters of the flat plate level are determined, and the sensitivity analysis results are obtained. The optimization module is used to perform multi-objective optimization of the vehicle's body acoustic package based on the sensitivity analysis results.

6. The multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis according to claim 5, characterized in that, The eight systems include the front enclosure system, front door system, rear door system, side enclosure system, front floor system, rear floor system, roof system, and rear enclosure system.

7. The multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis according to claim 6, characterized in that, The building module includes: A partitioning unit is used to acquire the engine compartment acoustic transmission function of the entire vehicle and divide the entire vehicle into eight systems; The setting unit is used to set the various acoustic package components attached to the eight systems as component level, and to set the material composition, area, coverage and thickness distribution of each acoustic package component as plate level; The construction unit is used to construct a four-level knowledge graph containing the cabin acoustic transmission function, the eight systems, the component level, and the tablet level, based on the cabin acoustic transmission function, the eight systems, the component level, and the tablet level.

8. The multi-objective optimization device for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis according to claim 7, characterized in that, The sensitivity analysis module includes: The first sensitivity analysis unit is used to predict the first maximum and minimum sensitivity units of the eight systems to the cabin acoustic transmission function based on the first two-level inter-level prediction model. The second sensitivity analysis unit is used to predict the maximum and minimum second sensitivity units of the component level to the eight systems based on the sensitivity analysis model between the adjacent levels. The third sensitivity analysis unit is used to predict the maximum and minimum third sensitivity units of the plate level to the component level based on the sensitivity analysis model between the adjacent levels. The sensitivity analysis result unit is used to construct the sensitivity analysis result from the first maximum and minimum sensitivity unit, the second maximum and minimum sensitivity unit, and the third maximum and minimum sensitivity unit.

9. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the multi-objective optimization method for vehicle acoustic packages based on hierarchical decomposition sensitivity analysis as described in any one of claims 1-4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-objective optimization method for vehicle body acoustic packages based on hierarchical decomposition sensitivity analysis as described in any one of claims 1-4.

Images