Suspension system weight target analysis method and system, electronic equipment and storage medium
By establishing linear and multi-eigen models to predict the weight target of the suspension system, combined with machine learning algorithms, the problem of difficult to determine the weight target of the suspension system in automobile development projects is solved, and scientific and reasonable weight targets and lightweight solutions are achieved. Avoid project delays and cost increase.
Patent Information
- Application Number
- CN202411041068.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-12-06
AI Technical Summary
In the early stages of automobile development projects, it was difficult for the existing technology to scientifically and reasonably determine the weight target of the suspension system, resulting in problems such as prolonging project development cycle, increasing costs, and unidentified energy consumption and endurance risks.
By collecting the data on the front and rear axle loads at full loads of multiple models, a linear relationship model of the front and rear axle loads and suspension weight is established, the suspension weight target is predicted, and a multi-feature suspension weight prediction model is established based on machine learning algorithms. Develop a lightweight plan to ensure the scientific and rationality of weight goals.
It effectively avoids project delays and cost increases caused by unreasonable weight targets, ensures the rationality of vehicle weight targets and controls lightweight costs, and avoids the problem of insufficient suspension load design.
Smart Images

Figure CN119089647A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of suspension systems, and in particular to an analysis method, system, electronic equipment and storage medium for a suspension system weight target, which are applicable to various types of transportation vehicles such as road vehicles and rail transit vehicles. Background Art
[0002] At present, Energy Conservation and Automotive Technology 2.0 proposes that the average fuel consumption target of passenger car companies is expected to reach 3.2L / 2.0L / 100km in 2030 / 2035, and the annual sales of new energy vehicles must reach 50%. Vehicle weight reduction is the key to effectively reducing vehicle energy consumption and increasing driving range. With the rapid development of new energy vehicles, vehicle weight reduction is of great significance to reducing energy consumption and increasing driving range. In the early stages of automotive development projects, how to determine a reasonable weight target for the suspension system and ensure the achievability of the target is a difficult problem in weight work.
[0003] However, determining the reasonable weight target of the suspension system in the early stage of the project is a big problem. The existing technology usually determines the weight of the suspension system based on the summary of the weight of the parts, but it is unable to evaluate the rationality of the weight of the early suspension system, which easily leads to problems such as extended project development cycle and increased costs. This method in the existing technology has the following disadvantages:
[0004] 1. Weight professionals are unable to determine the rationality of the weight of the suspension system in the early stages, and are unable to assess the weight trend of the suspension system in the later stages of vehicle development. The target risk of chassis platform weight is difficult to assess, which results in the inability to identify energy consumption and endurance risks.
[0005] 2. If the early weight target is unreasonable, the suspension system may need to be redeveloped due to insufficient design load-bearing capacity, which will extend the project development cycle and cause great losses to the project.
[0006] 3. Failure to reasonably evaluate the application of lightweight technology in the early stages may result in the use of lightweight technology when the vehicle is overweight in the later stages, causing project delays or increased costs; or excessive lightweighting in the early stages, resulting in a significant increase in costs.
[0007] Therefore, a method is needed to scientifically and reasonably determine the weight target of the suspension system in the early stage of the project to solve the above problems. Summary of the invention
[0008] In order to solve the above problems, the purpose of the present invention is to propose a suspension system weight target analysis method, system, electronic equipment and storage medium, which are used to determine a reasonable suspension system weight target in the early stage of project development, thereby avoiding development delays and cost increases caused by unreasonable weight targets.
[0009] To achieve the above object, in a first aspect, the present invention provides a method for analyzing a weight target of a suspension system, comprising the following steps:
[0010] S1, collect the front and rear axle load data and the corresponding front and rear suspension weight data of multiple models when fully loaded;
[0011] S2, establishing a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight;
[0012] S3, predicting the front suspension weight target and the rear suspension weight target respectively using the linear relationship model according to the fully loaded front and rear axle load data of the vehicle type to be analyzed.
[0013] Preferably, step S2 specifically includes:
[0014] S21. Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis;
[0015] S22, performing linear regression analysis on the scatter plot to obtain a linear relationship equation between the front axle load and the front suspension weight;
[0016] S23, draw a scatter plot with the rear axle load as the horizontal coordinate and the rear suspension weight as the vertical coordinate;
[0017] S24. Perform linear regression analysis on the scatter plot to obtain a linear relationship equation between the rear axle load and the rear suspension weight.
[0018] Further preferably, the linear relationship equation is in the form of: y=ax+b; wherein y represents the suspension weight, x represents the axle load, and a and b are regression coefficients.
[0019] Preferably, the method further comprises step S4: formulating a corresponding lightweight solution according to the predicted front suspension weight target and rear suspension weight target.
[0020] Further preferably, the method further comprises the following steps:
[0021] S5, collects characteristic data such as vehicle type, vehicle size, suspension type, drive mode, and power type;
[0022] S6, building a multi-feature suspension weight prediction model using machine learning algorithms;
[0023] S7, optimizing the prediction result by using the multi-feature suspension weight prediction model.
[0024] Still further preferably, the method further includes step S8: comparing the prediction results of the linear regression model and the machine learning model, and analyzing the reasons for the differences.
[0025] In a second aspect, the present invention provides a suspension system weight target analysis system, comprising:
[0026] A data collection module is used to collect the front and rear axle load data and the corresponding front and rear suspension weight data of multiple models when fully loaded;
[0027] A model building module, used to build a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight;
[0028] The target prediction module is used to predict the front suspension weight target and the rear suspension weight target respectively according to the fully loaded front and rear axle load data of the vehicle model to be analyzed using the linear relationship model.
[0029] Preferably, the model building module is specifically used for:
[0030] Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis;
[0031] Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the front axle load and the front suspension weight;
[0032] Draw a scatter plot with the rear axle load as the horizontal axis and the rear suspension weight as the vertical axis;
[0033] Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the rear axle load and the rear suspension weight.
[0034] Preferably, the system further comprises a lightweight solution formulation module for formulating a corresponding lightweight solution according to the predicted front suspension weight target and rear suspension weight target.
[0035] Further preferably, the system further comprises:
[0036] A characteristic data collection module is used to collect characteristic data such as vehicle type, vehicle size, suspension type, driving mode and power type;
[0037] A machine learning model building module, used to build a multi-feature suspension weight prediction model using a machine learning algorithm;
[0038] The prediction result optimization module is used to optimize the prediction result by using the multi-feature suspension weight prediction model.
[0039] Still further preferably, the system also includes a result comparison and analysis module for comparing the prediction results of the linear regression model and the machine learning model and analyzing the reasons for the differences.
[0040] In a third aspect, the present invention provides an electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; the memory is used to store computer programs; and the processor is used to implement any of the methods described in the first aspect when executing the programs stored in the memory.
[0041] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any method described in the first aspect is implemented.
[0042] The beneficial effects of the present invention are as follows: the present invention can avoid the problem that when the vehicle is overweight in the later stage and other performance cannot be achieved, the use of lightweight technology will be considered, resulting in project development delays or increased budget costs in the middle of the process. At the same time, it can also avoid the problem that the early system target requirements are too high, excessive lightweight solutions are conceived, resulting in a significant increase in costs, and the early chassis weight target is defined too low, resulting in insufficient suspension load design.
[0043] The present invention has obvious advantages such as reasonable target definition and reasonable lightweight cost investment, which are specifically described as follows:
[0044] 1. Improved work: After using this method, data can be used as support when determining the weight target of the suspension system, so that the decomposition of the vehicle weight target is based on evidence and is scientific and reasonable.
[0045] 2. Scientific method: This method is suitable for early definition of suspension system weight targets and the conception of lightweight solutions for major applications in the corresponding industry, and maintaining them at a reasonable value. This method can avoid problems such as delays in project development or increased budget costs when lightweight technology is considered later due to vehicle overweight and other performance cannot be achieved. It can also avoid problems such as excessively high system target requirements in the early stage, excessive lightweight solutions, and significant cost increases, as well as problems such as insufficient suspension load design due to too low chassis weight targets in the early stage.
[0046] 3. Work cycle: This work method will not affect the original project development cycle.
[0047] 4. Technical cost: This method does not increase material cost and has low technical cost. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 is a flow chart of a method for analyzing a weight target of a suspension system provided by an embodiment of the present invention;
[0049] Figure 2 is a schematic diagram of setting the weight target of the front suspension of the present invention;
[0050] Figure 3 is a schematic diagram of setting the rear suspension weight target of the present invention;
[0051] Figure 4 is a logic block diagram of an analysis system for a suspension system weight target provided by an embodiment of the present invention;
[0052] Figure 5 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0053] The technical solution of the present invention (including the preferred technical solution) is further described in detail below by means of the accompanying drawings and by listing some optional embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0054] Example 1
[0055] This embodiment provides a method for analyzing a suspension system weight target, comprising the following steps:
[0056] S1. Collect the fully loaded front and rear axle load data and the corresponding front and rear suspension weight data of multiple vehicle models.
[0057] First, collect the front axle load and rear axle load data of a batch of vehicles under full load, as well as the corresponding front suspension weight and rear suspension weight data, and record and organize them as shown in Table 1 below:
[0058] Table 1 Fully loaded front and rear axle loads and front and rear suspension system weight measurement data record
[0059]
[0060]
[0061] S2. Establish a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight.
[0062] S21. Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis, such as Figure 2 As shown;
[0063] S22, performing linear regression analysis on the scatter plot to obtain a linear relationship equation between the front axle load and the front suspension weight;
[0064] S23. Draw a scatter plot with the rear axle load as the horizontal axis and the rear suspension weight as the vertical axis, such as Figure 3 As shown;
[0065] S24. Perform linear regression analysis on the scatter plot to obtain a linear relationship equation between the rear axle load and the rear suspension weight.
[0066] The general form of the linear relationship equation is: y=ax+b; where y represents the suspension weight, x represents the axle load, and a and b are regression coefficients.
[0067] Through the above steps, we can get Figure 2 The front suspension weight target setting diagram shown in the figure and Figure 3 Rear suspension weight target setting diagram shown.
[0068] S3. According to the fully loaded front and rear axle load data of the vehicle model to be analyzed, the linear relationship model is used to respectively predict the front suspension weight target and the rear suspension weight target.
[0069] For example, for a new model to be developed, its fully loaded front axle load is 1200kg and its fully loaded rear axle load is 1500kg. Figure 2 The front suspension weight target setting diagram shown in the figure shows that the front suspension weight target of this model is about 59kg; Figure 2 From the rear suspension weight target setting diagram shown, it can be obtained that the rear suspension weight target of this model is approximately 59.5kg.
[0070] S4. Develop a corresponding lightweight plan based on the predicted front suspension weight target and rear suspension weight target
[0071] According to the predicted front suspension weight target of 59kg and rear suspension weight target of 59.5kg, a corresponding lightweight solution can be formulated. For example:
[0072] 1. Lightweight materials: Use high-strength steel, aluminum alloy, magnesium alloy and other lightweight materials to replace traditional steel;
[0073] 2. Structural optimization: Optimize the structural design of suspension parts through topological optimization, size optimization and other methods;
[0074] 3. Process innovation: Use advanced molding processes, such as thermoforming and extrusion molding, to reduce the number and weight of parts;
[0075] 4. Functional integration: Integrate the functions of multiple parts into one part to reduce connectors and total weight.
[0076] Example 2
[0077] This embodiment provides an improvement on the suspension system weight target analysis method based on machine learning.
[0078] Based on Example 1, this example introduces a machine learning algorithm to improve prediction accuracy and adaptability. The specific steps are as follows:
[0079] S5. Data collection and preprocessing
[0080] In addition to collecting fully loaded front and rear axle load data and corresponding front and rear suspension weight data, the following characteristic data were also collected:
[0081] a. Vehicle type (sedan, SUV, MPV, etc.);
[0082] b. Vehicle dimensions (length, width, height);
[0083] c. Suspension type (McPherson, multi-link, torsion beam, etc.);
[0084] d. Drive mode (front-wheel drive, rear-wheel drive, four-wheel drive);
[0085] e. Power type (fuel, hybrid, pure electric);
[0086] The collected data are cleaned and normalized.
[0087] S6. Feature selection
[0088] Feature selection was performed using principal component analysis to identify the features that have the greatest impact on suspension weight.
[0089] S7. Model training
[0090] The model is trained using a machine learning algorithm. In this embodiment, a random forest algorithm is used to train the model, and the data set is divided into a training set (80%) and a test set (20%).
[0091] S8. Model evaluation and optimization
[0092] The model performance was evaluated using root mean square error and coefficient of determination. The model was optimized by adjusting hyperparameters such as the number of trees, maximum depth of the tree, etc.
[0093] S9, predicted suspension weight target
[0094] Input the feature data of the new vehicle model and use the trained model to predict the front suspension weight target and the rear suspension weight target.
[0095] S10. Result analysis and lightweight solution formulation
[0096] Compare the prediction results of the machine learning model with those of the linear regression model and analyze the reasons for the differences. Combine the results of the two methods to develop a more accurate and personalized lightweight solution.
[0097] The present invention introduces a machine learning algorithm, which can take into account more influencing factors, improve prediction accuracy, and can adapt to different types of vehicles, providing a more reliable basis for determining the weight target of the suspension system.
[0098] Example 3
[0099] This embodiment provides a suspension system weight target analysis system, including:
[0100] A data collection module is used to collect fully loaded front and rear axle load data and corresponding front and rear suspension weight data of multiple vehicle models;
[0101] A model building module, used to build a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight;
[0102] The target prediction module is used to predict the front suspension weight target and the rear suspension weight target respectively according to the fully loaded front and rear axle load data of the vehicle model to be analyzed using the linear relationship model.
[0103] Among them, the model building module is specifically used for:
[0104] Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis;
[0105] Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the front axle load and the front suspension weight;
[0106] Draw a scatter plot with the rear axle load as the horizontal axis and the rear suspension weight as the vertical axis;
[0107] Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the rear axle load and the rear suspension weight.
[0108] The system also includes a lightweight solution formulation module for formulating a corresponding lightweight solution based on the predicted front suspension weight target and rear suspension weight target.
[0109] Example 4
[0110] Based on Example 1, the system described in this embodiment further includes:
[0111] A characteristic data collection module is used to collect characteristic data such as vehicle type, vehicle size, suspension type, driving mode and power type;
[0112] A machine learning model building module, used to build a multi-feature suspension weight prediction model using a machine learning algorithm;
[0113] The prediction result optimization module is used to optimize the prediction result by using the multi-feature suspension weight prediction model.
[0114] The result comparison and analysis module is used to compare the prediction results of the linear regression model and the machine learning model and analyze the reasons for the differences.
[0115] Example 5
[0116] The present invention provides an electronic device, comprising a processor 1, a communication interface 2, a memory 3 and a communication bus 4, wherein the processor 1, the communication interface 2 and the memory 3 communicate with each other via the communication bus 4; the memory 4 is used to store computer programs; the processor 1 is used to implement the analysis method of the suspension system weight target described in Example 1 when executing the program stored in the memory 8.
[0117] The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0118] The memory may include a random access memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory.
[0119] The memory may be a volatile memory, such as a random-access memory (RAM); the memory may also be a non-volatile memory, such as a read-only memory, a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD), or the memory is any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may be a combination of the above memories.
[0120] Example 6
[0121] The present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for analyzing the weight target of the suspension system as described in Example 1.
[0122] The present invention can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidState Disk (SSD)), etc.
[0123] Those skilled in the art will readily appreciate that the above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, combinations, replacements, improvements, etc. made within the spirit and principles of the present invention are included within the protection scope of the present invention.
Claims
1. A method for analyzing a suspension system weight target, characterized in that: The following steps are involved: S1, collect the front and rear axle load data and the corresponding front and rear suspension weight data of multiple models when fully loaded; S2, establishing a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight; S3, predicting the front suspension weight target and the rear suspension weight target respectively using the linear relationship model according to the fully loaded front and rear axle load data of the vehicle type to be analyzed.
2. The method for analyzing the weight target of the suspension system according to claim 1, characterized in that: Step S2 specifically includes: S21. Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis; S22, performing linear regression analysis on the scatter plot to obtain a linear relationship equation between the front axle load and the front suspension weight; S23, draw a scatter plot with the rear axle load as the horizontal coordinate and the rear suspension weight as the vertical coordinate; S24. Perform linear regression analysis on the scatter plot to obtain a linear relationship equation between the rear axle load and the rear suspension weight.
3. The method for analyzing the weight target of a suspension system according to any one of claims 1 or 2, characterized in that: The method further comprises step S4: formulating a corresponding lightweight solution according to the predicted front suspension weight target and rear suspension weight target.
4. The method for analyzing the weight target of the suspension system according to claim 3, characterized in that: The method also The following steps are involved: S5, collects characteristic data such as vehicle type, vehicle size, suspension type, drive mode, and power type; S6, building a multi-feature suspension weight prediction model using machine learning algorithms; S7, optimizing the prediction result by using the multi-feature suspension weight prediction model; S8: Compare the prediction results of the linear regression model and the machine learning model and analyze the reasons for the differences.
5. A suspension system weight target analysis system, characterized in that: include: A data collection module is used to collect the front and rear axle load data and the corresponding front and rear suspension weight data of multiple models when fully loaded; A model building module, used to build a linear relationship model between the front axle load and the front suspension weight, and a linear relationship model between the rear axle load and the rear suspension weight; The target prediction module is used to predict the front suspension weight target and the rear suspension weight target respectively according to the fully loaded front and rear axle load data of the vehicle model to be analyzed using the linear relationship model.
6. The analysis system of the suspension system weight target according to claim 5, characterized in that: The model building module is specifically used for: Draw a scatter plot with the front axle load as the horizontal axis and the front suspension weight as the vertical axis; Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the front axle load and the front suspension weight; Draw a scatter plot with the rear axle load as the horizontal axis and the rear suspension weight as the vertical axis; Linear regression analysis was performed on the scatter plot to obtain the linear relationship equation between the rear axle load and the rear suspension weight.
7. The analysis system of the suspension system weight target according to claim 5 or 6, characterized in that: The system also includes a lightweight solution formulation module, which is used to formulate a corresponding lightweight solution according to the predicted front suspension weight target and rear suspension weight target.
8. The analysis system of the suspension system weight target according to claim 7, characterized in that: The system further comprises: A characteristic data collection module is used to collect characteristic data such as vehicle type, vehicle size, suspension type, driving mode and power type; A machine learning model building module, used to build a multi-feature suspension weight prediction model using a machine learning algorithm; A prediction result optimization module, used to optimize the prediction result using the multi-feature suspension weight prediction model; The result comparison and analysis module is used to compare the prediction results of the linear regression model and the machine learning model and analyze the reasons for the differences.
9. An electronic device comprising a processor, a communication interface, a memory and a communication bus, wherein: The processor, the communication interface, and the memory communicate with each other via a communication bus; the memory is used to store computer programs; the processor is used to implement the method for analyzing the weight target of the suspension system as described in any one of claims 1 to 5 when executing the program stored in the memory.
10. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the method for analyzing a weight target of a suspension system according to any one of claims 1 to 5 is implemented.
