Method and system for calculating volume of passenger compartment
By applying the 3D model of the vehicle and the cross-section recognition network, the rapid calculation of the passenger compartment volume is achieved, the problems of low computing efficiency and high time cost in the prior art are solved, and the efficiency of vehicle development is improved.
Patent Information
- Application Number
- CN202411812069.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-10
- Publication Date
- 2025-04-11
AI Technical Summary
In the process of vehicle research and development, the method of calculating the passenger compartment volume consumes a lot of manpower and computing resources, and the time cost is high, making it difficult to keep up with the project development progress, affecting the efficiency of vehicle development.
By obtaining the three-dimensional model of the vehicle, building a square box and cutting it in the same direction, a two-dimensional coordinate data set of each section is constructed, and a closed curve is identified using the cross-section identification network and the enclosing area is calculated. Based on these data, the crew cabin volume is obtained.
It realizes rapid calculation of the passenger compartment volume, improves calculation efficiency, saves computing resources, and facilitates the rapid development of vehicle cooling and heating analysis work.
Smart Images
Figure CN119808365A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of automobile thermal management, and in particular to a method and system for calculating the volume of a passenger compartment. Background Art
[0002] During the vehicle development process, it is necessary to evaluate the cooling speed and cooling effect of the air conditioning system as well as the heating speed and heating effect. If the passenger compartment volume is significantly different from the actual vehicle during the evaluation, the actual vehicle's cooling and heating performance will be reduced or excessive, which will in turn increase the development and production costs. Therefore, it is necessary to calculate the passenger compartment volume of the vehicle during the development process. As the project development progresses, the passenger compartment data changes from being brief to being concrete step by step, and its volume is also constantly changing.
[0003] In the prior art, during the vehicle development stage, a passenger compartment model is usually built through CFD software (such as FLUENT), and the spatial volume of the passenger compartment is obtained through built-in functions; or a 3D scanning module and system is used to obtain point cloud data through 3D scanning, fill holes, calculate the volume of the maximum bounding box, and finally calculate the volume of the passenger compartment. However, these two methods not only consume a lot of manpower and computing resources, but also have a high time cost. Especially during the research and development process, the passenger compartment volume is constantly changing, which makes it difficult for the calculation speed of the passenger compartment volume to keep up with the development progress of the project, affecting the efficiency of vehicle development. Summary of the invention
[0004] The embodiment of the present disclosure provides a method and system for calculating the volume of a passenger compartment to achieve rapid calculation of the volume of the passenger compartment. The technical solution is as follows:
[0005] In a first aspect, a method for calculating the volume of a passenger compartment is provided, comprising:
[0006] Obtain a three-dimensional model of the vehicle and construct a box outside the vehicle model; cut the passenger compartment along the same direction with a set gap length, and output the cut sections in spatial order;
[0007] Construct a 2D coordinate data set for each cross section;
[0008] The obtained two-dimensional coordinate data set is input into the cross-section recognition network to recognize the closed curve in the cross-section and obtain the enclosed area of the closed curve;
[0009] The volume of the passenger compartment is obtained by integrating the enclosed area of the closed curve corresponding to each cross section and the set gap length when the corresponding cross section is cut.
[0010] In a second aspect, a passenger compartment volume calculation system is provided, comprising:
[0011] The cutting module is configured to obtain a three-dimensional model of the vehicle, construct a box outside the vehicle model, cut the passenger compartment along the same direction with a set gap length, and output the cut sections in a spatial order;
[0012] A two-dimensional coordinate data set construction module is configured to construct a two-dimensional coordinate data set for each cross section;
[0013] A recognition module is configured to input the obtained two-dimensional coordinate data set into a section recognition network, identify a closed curve in the section, and obtain an enclosed area of the closed curve;
[0014] The calculation module is configured to integrate the volume of the passenger compartment based on the enclosed area of the closed curve corresponding to each cross section obtained and the set gap length when the corresponding cross section is cut.
[0015] In a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to complete the steps of the above-mentioned method for calculating the volume of a passenger compartment.
[0016] In a fourth aspect, a computer-readable storage medium is provided for storing computer instructions, which, when executed by a processor, complete the steps of the above-mentioned method for calculating the volume of a passenger compartment.
[0017] In a fifth aspect, a computer program product is provided, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned method for calculating the volume of a passenger compartment.
[0018] The technical solution provided by the disclosed embodiment has the following beneficial effects: In the disclosed embodiment, a unified calculation method for the passenger compartment volume suitable for different models and different interior configurations is given based on the integral concept. By sectioning the three-dimensional model, the area of the internal area of the passenger compartment corresponding to each section after sectioning is calculated respectively, and then multiplied by the gap length during sectioning, the approximate passenger compartment volume can be obtained. Compared with the traditional method of software simulation calculation, the calculation efficiency is greatly improved, which can facilitate the rapid development of vehicle cooling and heating analysis. The cross-sectional area is calculated based on the trained convolutional neural network, which has higher calculation efficiency and saves computing resources.
[0019] Advantages of additional aspects of the present disclosure will be given in part in the following description and in part will become apparent from the following description or will be learned through practice of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, 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 disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0021] Figure 1 is a flow chart of a method for calculating the volume of a passenger compartment provided by an embodiment of the present disclosure;
[0022] Figure 2 is a structural block diagram of a passenger compartment volume calculation system provided by an embodiment of the present disclosure;
[0023] Figure 3 It is a structural block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0024] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the embodiments of the present disclosure will be further described in detail below with reference to the accompanying drawings.
[0025] Figure 1 is a flow chart of a method for calculating the volume of a passenger compartment provided by an embodiment of the present disclosure, see Figure 1 , the method comprising:
[0026] Step 101, obtaining a three-dimensional model of the vehicle, constructing a box outside the vehicle model; cutting the passenger compartment along the same direction with a set gap length, and outputting the cut sections in spatial order;
[0027] Step 102, constructing a two-dimensional coordinate data set for each cross section;
[0028] Step 103, input the obtained two-dimensional coordinate data set into the section recognition network, identify the closed curve in the section, and obtain the enclosed area of the closed curve;
[0029] Step 104 : Based on the enclosed area of the closed curve corresponding to each cross section obtained, and the set gap length when the corresponding cross section is cut, the passenger compartment volume is obtained by integration.
[0030] As the vehicle development cycle is gradually shortened, the traditional solution of calculating the passenger compartment volume based on software simulation is limited by factors such as labor cost, calculation cost, time cost, etc., which makes it difficult to meet the vehicle development progress requirements and affects the vehicle development efficiency. In fact, the calculation of the passenger compartment volume does not require too high precision. Although the software simulation method has high precision, it cannot achieve a balance between precision and efficiency. Based on this, this embodiment provides a new way of calculating the passenger compartment volume based on the idea of integration and combined with the powerful prediction ability of convolutional neural networks to achieve rapid acquisition of the passenger compartment volume. First, the three-dimensional model of the vehicle passenger compartment is cut into sections, and then the convolutional neural network is used to calculate the area inside the closed curve of each obtained section, that is, the cross-sectional area inside the passenger compartment, and finally the volume of the entire passenger compartment is obtained by integration.
[0031] In step 101, the three-dimensional model of the vehicle can be a CAD data model. According to the three-dimensional data of the length, width and height of the vehicle, a square box is built outside the passenger compartment, which is slightly larger than the boundary of the passenger compartment and completely wraps the passenger compartment. Then the passenger compartment data model is divided into sections in the same direction, that is, multiple sections are cut along one direction at different depths to obtain multiple sections, and the section data is output in a spatial order and a certain proportion. At this time, the section boundary is the boundary of the square box. Taking the section of the vehicle in the yz direction as an example, the section boundary is the length and height of the whole vehicle.
[0032] Use the section commands of the CAD software (such as SECTION or MVIEW in AutoCAD) to create section views, and ensure that each section view correctly reflects the required section. To achieve quick sectioning and output sections, use the script or macro function provided by the CAD software (such as Auto LISP, VBA or Python script) to write an automated script to generate multiple section views. Set the section position, scale and output parameters according to the actual sectioning needs, use the MVIEW command to create multiple section views, and arrange them in the model space. Finally, set the specified output type (such as PDF or DWG) and the path of the output file to complete the output of each section in sequence.
[0033] In order to achieve fast output and reduce calculations, in some embodiments, a uniform reduction ratio setting is applied to each section view, and the scale factor a is set. This can be achieved by setting the view scale or using the layout viewport, thereby greatly reducing the amount of calculation in the sectioning process. After the length and width are reduced by the scale factor a, the cross-sectional area is reduced by a. 2 Therefore, when calculating the integral in step 104, the enclosed area needs to be enlarged proportionally.
[0034] In order to further achieve fast output and reduce calculations, in some embodiments, variable speed cutting can also be performed during sectioning. Normally, the sectioning process is uniform cutting at a constant speed, that is, the passenger compartment is cut inward at equal intervals in the same direction, and the distances between adjacent sections are equal. However, considering that the passenger compartment structure changes differently at different locations, uniform cutting is used. In some locations with more complex structures, the changes between adjacent sections are more drastic, resulting in larger errors in subsequent integral calculations. In some locations with smaller structural changes, the shapes between adjacent sections do not change much, so too much cutting will cause meaningless calculations. Based on this, this embodiment replaces uniform cutting at a constant speed with variable speed cutting, that is, in areas where the cutting surface of the passenger compartment changes less, the gap between the surfaces increases, and in locations where the changes are more drastic, the gap between the surfaces decreases, so as to achieve a balance between accuracy and calculation speed. Considering that the passenger compartment layout of most models on the market is similar, the cabin volume is mainly affected by the wheelbase, vehicle height, internal seats, armrest box layout, etc. Therefore, in this embodiment, the relationship between the internal layout of models on the market and the wheelbase in the length direction of the vehicle is summarized, and the relationship curve between different wheelbases and cutting speeds is obtained, so as to achieve variable speed cutting by matching different cutting speed relationship curves according to the wheelbase information of different vehicles.
[0035] In step 102, for each obtained cross section, an xy coordinate axis is uniformly established at the cross section boundary to obtain a two-dimensional coordinate data set of each cross section, and at the same time, the coordinate data sets of all cross sections are output in the order of the cross sections.
[0036] In step 103, the section recognition network is trained based on the convolutional neural network CNN. The obtained two-dimensional coordinate data set of each section is input into the trained section recognition network to identify the position of the closed curve and predict whether each pixel in the section is inside the closed curve. The area of all pixels inside the closed curve is the enclosing area of the closed curve of the section, that is, the area of the interior of the passenger compartment corresponding to the section. The enclosing area can be calculated by the proportion of pixels located in the closed curve. Considering that the boundary of the section is known, that is, the area of the section is known, the enclosing area can be obtained by calculating the ratio of the number of pixels inside the closed curve to the total number of pixels, and multiplying it by the area of the section.
[0037] The cross-section recognition network is trained with a large number of existing two-dimensional coordinate data sets of passenger compartment cross sections to identify closed curves (i.e., the boundaries of the passenger compartment) and predict whether each pixel in a single cross section is inside the closed curve. The existing finite element meshing model and its original CAD data can be subjected to the same sectioning steps at the same time, thereby obtaining the cross-section area, cross-section CAD file, and the corresponding two-dimensional coordinate data set at the same time. The cross-section recognition network is trained with the two-dimensional coordinate data set and verified with the cross-section area. The correctness of the network is further verified based on the known cross-section area and passenger compartment volume.
[0038] In step 104, the passenger compartment volume is calculated in the form of integration. The enclosed area of the closed curve corresponding to each section obtained in step 103 is multiplied by the gap length between the section and the next section when the section is cut, and the volume of the passenger compartment part corresponding to the section can be approximately obtained. If the section is also reduced according to the proportional coefficient a in step 101, the area is reduced by a correspondingly. 2 , when calculating the enclosed area, the output result needs to be multiplied by 1 / a 2 The actual area can be obtained. The above calculation steps are performed for each cross section, and then the calculation results are summed up, which is equivalent to using the integration method. Finally, the volume of the passenger compartment is calculated for subsequent vehicle cooling and heating analysis.
[0039] Figure 2 is a structural block diagram of a passenger compartment volume calculation system 200 provided in an embodiment of the present disclosure, such as Figure 2 As shown, the system includes: a cutting module 201 , a two-dimensional coordinate data set construction module 202 , a recognition module 203 , and a calculation module 204 .
[0040] The cutting module 201 is configured to obtain a three-dimensional model of the vehicle, construct a box outside the vehicle model, cut the passenger compartment along the same direction with a set gap length, and output the cut sections in a spatial order;
[0041] A two-dimensional coordinate data set construction module 202 is configured to construct a two-dimensional coordinate data set for each cross section;
[0042] The recognition module 203 is configured to input the obtained two-dimensional coordinate data set into a cross-section recognition network, recognize a closed curve in the cross-section, and obtain the enclosed area of the closed curve;
[0043] The calculation module 204 is configured to integrate the enclosed area of the closed curve corresponding to each cross section obtained and the set gap length when the corresponding cross section is cut to obtain the passenger compartment volume.
[0044] It should be noted that: the passenger compartment volume calculation system 200 provided in the above embodiment only uses the division of the above functional modules as an example to illustrate when calculating the passenger compartment volume. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the passenger compartment volume calculation system 200 provided in the above embodiment and the passenger compartment volume calculation method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
[0045] Figure 3is a structural block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 3 As shown, the electronic device 300 may be a computer. The electronic device 300 includes: a processor 301 and a memory 302 .
[0046] The processor 301 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 301 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and LA (Programmable Logic Array). The processor 301 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 301 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 301 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.
[0047] The memory 302 may include one or more computer-readable media, which may be non-transitory. The memory 302 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable medium in the memory 302 is used to store at least one computer program, which is used to be executed by the processor 301 to implement a front-end module aperture ratio calibration method provided in an embodiment of the present disclosure.
[0048] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the electronic device 300, and may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.
[0049] The embodiment of the present disclosure also provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of a passenger compartment volume calculation method provided in the embodiment of the present disclosure can be completed.
[0050] The embodiment of the present disclosure also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of a passenger compartment volume calculation method provided in the embodiment of the present disclosure.
[0051] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.
Claims
1. A method for calculating the volume of a passenger compartment, characterized in that: include: Obtain a three-dimensional model of the vehicle and construct a box outside the vehicle model; The passenger compartment is cut along the same direction with a set gap length, and the cut sections are output in spatial order; Construct a 2D coordinate data set for each cross section; The obtained two-dimensional coordinate data set is input into the cross-section recognition network to recognize the closed curve in the cross-section and obtain the enclosed area of the closed curve; The volume of the passenger compartment is obtained by integrating the enclosed area of the closed curve corresponding to each cross section and the set gap length when the corresponding cross section is cut.
2. A passenger compartment volume calculation method as claimed in claim 1, characterized in that: During the sectioning process, the view is scaled proportionally.
3. A passenger compartment volume calculation method as claimed in claim 1, characterized in that: The passenger compartment is cut along the same direction with the same set gap length, or the passenger compartment is cut along the same direction with different set gap lengths.
4. A passenger compartment volume calculation method as claimed in claim 3, characterized in that: When the passenger compartment is sectioned along the same direction with different set gap lengths, the gap length is determined according to the severity of the change of the cutting surface of the passenger compartment in the sectioning direction.
5. A passenger compartment volume calculation method as claimed in claim 1, characterized in that: The cross-section recognition network is a convolutional neural network, and the cross-section recognition network obtains the enclosing area of the closed curve according to the ratio of the number of pixels inside the closed curve to the number of total pixels.
6. A passenger compartment volume calculation method as claimed in claim 1, characterized in that: The enclosed area of the closed curve corresponding to each section is multiplied by the set gap length when the corresponding section is cut, and the calculation results of each section are summed to obtain the volume of the passenger compartment.
7. A passenger compartment volume calculation system, characterized in that: include: A sectioning module is configured to obtain a three-dimensional model of a vehicle and construct a box outside the vehicle model; The passenger compartment is cut along the same direction with a set gap length, and the cut sections are output in spatial order; A two-dimensional coordinate data set construction module is configured to construct a two-dimensional coordinate data set for each cross section; A recognition module is configured to input the obtained two-dimensional coordinate data set into a section recognition network, identify a closed curve in the section, and obtain an enclosed area of the closed curve; The calculation module is configured to integrate the volume of the passenger compartment based on the enclosed area of the closed curve corresponding to each cross section obtained and the set gap length when the corresponding cross section is cut.
8. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to complete the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.