Weight prediction method and device of vehicle system, electronic equipment and storage medium

Abstract

The invention relates to the field of vehicles, in particular to a weight prediction method and device for a vehicle system, electronic equipment and a storage medium, and the method comprises the steps: obtaining target boundary data of a target system, the target system being the whole vehicle of the target vehicle or a part of the target vehicle, and the target system being a system of which the weight is to be predicted; the target boundary data comprises the boundary size of the target system; according to the target boundary data and a vehicle system database, the target weight of the target system is predicted, and the vehicle system database comprises the first boundary data of the first systems of the other vehicles and the actual weight of the first systems of the other vehicles. According to the method and the device, the estimated weight of the system of the target vehicle is predicted through the boundary data and the actual weight of the systems of other vehicles, so that the problem of inaccurate weight estimation of the system of the vehicle is solved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a method, device, electronic device, and storage medium for predicting the weight of a vehicle system. Background Art

[0002] To implement the national new energy vehicle strategy, all automakers are developing hardware platforms for new energy vehicles. Predicting the weight of hardware platforms is crucial. Predicting the weight of hardware platforms can provide important data foundation for subsequent platform development and vehicle appearance adjustments.

[0003] The prior art does not propose a complete method for predicting the weight of a vehicle hardware platform, and therefore the predicted weight of the vehicle hardware platform is not accurate. Summary of the Invention

[0004] The present application provides a weight prediction method for a vehicle system to solve the problem of inaccurate weight prediction of a vehicle's hardware platform.

[0005] In a first aspect, the present application provides a method for predicting the weight of a vehicle system, comprising: obtaining target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system whose weight is to be predicted, and the target boundary data includes the boundary size of the target system; predicting the target weight of the target system based on the target boundary data and a vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of the other vehicles.

[0006] In the second aspect, the present application provides a weight prediction device for a vehicle system, including: an acquisition module for acquiring target boundary data of a target system, wherein the above-mentioned target system is the entire vehicle of the target vehicle or a partial system of the above-mentioned target vehicle, and the above-mentioned target system is the system whose weight is to be predicted, and the above-mentioned target boundary data includes the boundary size of the above-mentioned target system; a prediction module for predicting the target weight of the above-mentioned target system based on the above-mentioned target boundary data and a vehicle system database, wherein the above-mentioned vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of the above-mentioned other vehicles.

[0007] In a third aspect, the present application provides a weight prediction device for a vehicle system, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: obtain target boundary data of a target system, wherein the target system is the entire vehicle of a target vehicle or a partial system of the target vehicle, and the target system is a system whose weight is to be predicted, and the target boundary data includes the boundary size of the target system; predict the target weight of the target system based on the target boundary data and a vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of the other vehicles.

[0008] In a fourth aspect, the present application further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute any of the above-mentioned vehicle system weight prediction methods of the present application.

[0009] Beneficial effects of this application:

[0010] The present application obtains target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system whose weight is to be predicted, and the target boundary data includes the boundary size of the target system; based on the target boundary data and a vehicle system database, the target weight of the target system is predicted, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of the other vehicles, so that the estimated weight of the target system of the target vehicle can be predicted based on the relationship between the acquired target boundary data of the target system and the first boundary data of other vehicles stored in the vehicle system database and the actual weight of the first system of other vehicles, thereby improving the accuracy of the estimated weight of the target system. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of a method for predicting the weight of a vehicle system according to the present application;

[0012] Figure 2 A schematic diagram of vehicle boundary data for the weight prediction method of the vehicle system of the present application;

[0013] Figure 3 A flowchart of another method for predicting the weight of a vehicle system according to the present application;

[0014] Figure 4 A flowchart of another method for predicting the weight of a vehicle system according to the present application;

[0015] Figure 5 A schematic diagram of a correlation curve for the weight prediction method of the vehicle system of the present application;

[0016] Figure 6 This is a schematic diagram of a weight prediction device for a vehicle system of the present application. DETAILED DESCRIPTION

[0017] The following will describe the embodiments of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand the other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for the purpose of illustrating the present application and are not intended to limit the scope of protection of the present application.

[0018] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0019] For ease of description, spatially relative terms may be used herein to describe the relative position or movement of one element or feature relative to another element or feature as shown in the figures, such as "inside," "outside," "inside," "outside," "below," "beneath," "above," "above," "front," "back," and the like. Such spatially relative terms are intended to include different orientations of the device in use or operation in addition to the orientation depicted in the figures. For example, if the device in the figures undergoes a positional flip or a change in posture or motion state, then these directional indications will also change accordingly. For example, an element described as "below" or "below" another element or feature will then be oriented as "above" or "above" another element or feature. Thus, the example term "below" can include both above and below orientations. The device can be oriented otherwise (rotated 90 degrees or in other orientations) and the spatially relative descriptors used herein will be interpreted accordingly.

[0020] In order to solve the technical problem of low accuracy in estimating the weight of a hardware platform in the prior art, the present application provides a weight prediction method for a vehicle system, which can improve the accuracy of estimating the weight of a vehicle system.

[0021] Figure 1A method for predicting the weight of a vehicle system provided in an embodiment of the present application includes:

[0022] S101, obtaining target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system for which weight is to be predicted, and the target boundary data includes boundary dimensions of the target system;

[0023] S102 , predicting a target weight of the target system based on the target boundary data and a vehicle system database, wherein the vehicle system database includes first boundary data of first systems of other vehicles and actual weights of the first systems of the other vehicles.

[0024] The above vehicles can be fuel-powered vehicles, pure electric vehicles (Blade Electric Vehicles, BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), extended-range electric vehicles (EREV) or fuel cell electric vehicles (FCEV)

[0025] In the vehicle system weight prediction method of this embodiment, the vehicle system mentioned herein can be the entire target vehicle or a partial system of the target vehicle. If the target vehicle is the entire target vehicle, the vehicle weight is predicted for the entire vehicle. If the target vehicle is a partial system, the weight of the partial system is predicted for the vehicle. The partial system can be the vehicle's chassis system, or the transmission system, steering system, braking system, or driving system within the chassis system. Alternatively, the partial system can be a component of the target vehicle, such as the vehicle shell or tires.

[0026] The first system of the other vehicles is the same as the target system of the target vehicle. For example, if the target system of the target vehicle is the entire vehicle, then the first system of the other vehicles is also the entire vehicle. If the target system of the target vehicle is the chassis system, then the first system of the other vehicles is also the chassis system.

[0027] In the target boundary data of the target system or the first boundary data of the first system, the boundary data can be the boundary size of the system. That is, the boundary of the system is obtained, and the boundary is the outermost minimum bounding box of the system. The size data of the outermost minimum bounding box can be used as the boundary data. For example, Figure 2 For simplicity of explanation, Figure 2The example is an example of the minimum bounding box of a vehicle's top view, with the vehicle's minimum circumscribed bounding box as the boundary. It should be noted that because the vehicle is three-dimensional, when constructing the minimum circumscribed bounding box, the minimum circumscribed bounding box of the three-dimensional vehicle is constructed. Therefore, the boundary lines are more complex and numerous.

[0028] The vehicle system database in this embodiment may include first boundary data for the first systems of different vehicles and the actual weights of the vehicles. The first boundary data and actual weights of the first systems of different vehicles are stored in the vehicle system database. The vehicle system database analyzes this data to determine the relationship between the boundary data and the actual weights of the vehicles. Once the relationship between the boundary data and the actual weights is determined, the acquired target boundary data can be used to predict the target weight of the target system.

[0029] For example, to predict the target weight of a vehicle's chassis system, the first boundary data and weights of the chassis systems of other vehicles are obtained to form a vehicle system database. The relationship between the chassis systems of other vehicles and their actual weights is then learned from the vehicle system database. Once the relationship is learned, the target boundary data of the vehicle chassis system can be input into the vehicle system database to obtain the corresponding target weight.

[0030] The present application obtains target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system for which weight is to be predicted, and the target boundary data includes the boundary dimensions of the target system; based on the target boundary data and a vehicle system database, the target weight of the target system is predicted, wherein the vehicle system database includes the first boundary data of target systems of other vehicles and the actual weights of the target systems of the other vehicles, so that the estimated weight of the target system of the target vehicle can be predicted based on the relationship between the acquired target boundary data of the target system and the first boundary data of other vehicles stored in the vehicle system database and the actual weights of the target systems of other vehicles, thereby improving the accuracy of the estimated weight of the target system.

[0031] As an optional example, before predicting the target weight of the target system based on the target boundary data and the vehicle system database, the method further includes: determining a correlation curve between each boundary parameter in the first boundary data and the actual weight based on the first boundary data in the vehicle system database and the actual weight.

[0032] In this embodiment, a correlation relationship can be established between the first boundary data of other vehicles in the vehicle system database and the actual weight of other vehicles to generate a correlation curve. When generating the correlation curve, the correlation curve between each boundary parameter in the first boundary data of other vehicles and the actual weight can be determined. For example Figure 2 There are multiple boundary parameters in the first boundary data, and each boundary parameter has a certain correlation with the actual weight. By comparing the correlation between each boundary parameter and the actual weight, the influence of each boundary parameter on the weight is determined.

[0033] In this example, each boundary parameter and actual weight in the first boundary data can be input into the analysis model, which then analyzes the relationship between each boundary parameter and the actual weight. For example, for different vehicles, the model can analyze the boundary parameters and actual weight horizontally, analyzing the change in actual weight when multiple boundary parameters are the same but some boundary parameters are different, or vertically analyzing the corresponding relationship between different boundary parameters and actual weight for a vehicle.

[0034] In addition, in this embodiment, the least squares method can be used to fit the model, wherein the boundary parameters are independent variables and the actual weight is the dependent variable, to perform multivariate fitting regression to determine the relationship between each boundary parameter and the actual weight.

[0035] In addition to recording the correlation between each boundary parameter and the actual weight, this embodiment also analyzes the impact of the combination of multiple boundary parameters on the actual weight. For example, the boundary data contains 10 boundary parameters, each of which has a correlation with the actual weight. Furthermore, the 10 boundary parameters may include combinations of multiple boundary parameters, and the relationship between these combinations and the actual weight may not be consistent with the relationship between a single boundary parameter and the actual weight. For example, suppose the first boundary parameter of the 10 boundary parameters has a positive correlation with the actual weight, and the second boundary parameter also has a positive correlation with the actual weight. However, when the first and second boundary parameters are adjusted in combination, they have a negative correlation with the actual weight. In this case, the combination of the first and second boundary parameters should also be correlated with the actual weight. Alternatively, if the first boundary parameter has a positive correlation with the actual weight at a ratio of K1, the second boundary parameter has a positive correlation with the actual weight at a ratio of K2, and the combination of the first and second boundary parameters has a positive correlation with the actual weight at a ratio of K3, where K3 is significantly greater than either K1 or K2, then the correlation between the combination of the first and second boundary parameters and the actual weight should also be recorded. It should be noted that the above are only two examples. In this embodiment, the relationship between the combination of multiple boundary parameters and the actual weight is actually recorded when the relationship between the combination of multiple boundary parameters and the actual weight does not match the relationship between a single boundary parameter and the actual weight.

[0036] As an optional example, after determining the association curve between each boundary parameter in the first boundary data and the actual weight based on the first boundary data in the vehicle system database and the actual weight, the method further includes: determining the top N boundary parameters in the ranking results of their influence on the actual weight among all the boundary parameters of the first boundary data based on the association curve, where N is a positive integer; and retaining the association curves corresponding to the top N boundary parameters.

[0037] In this embodiment, with respect to the first boundary data and the actual weight in the vehicle system database, the various boundary parameters in the first boundary data have different effects on the actual weight. Some boundary parameters may have very little effect on the actual weight. In this case, the boundary parameters with very little effect on the actual weight may be ignored.

[0038] For example, the first boundary data in the vehicle system database includes 10 boundary parameters. After determining that each of the 10 boundary parameters has a correlation with the actual weight, one or two of the boundary parameters have a significant impact on the actual weight, while the other boundary parameters have little impact on the actual weight. In this case, the boundary parameters with a significant impact on the actual weight can be retained in the correlation curve, while the boundary parameters with a smaller impact can be omitted.

[0039] In this example, we also consider the case where a single boundary parameter has little effect on the actual weight, while the combination of multiple boundary parameters has a greater impact on the actual weight. In this case, the association curve for the single boundary parameter is still retained, and the association curve for the combination of multiple boundary parameters and the actual weight is also retained.

[0040] In this embodiment, the aforementioned N is a positive integer. That is, the first N boundary parameters that have the greatest impact on the actual weight are retained. The value of N can be flexibly determined. The specific approach is to sort all first boundary parameters from greatest to least according to their impact on the actual weight, and then determine if two adjacent boundary parameters have a significant difference in impact on the actual weight, where the difference exceeds a preset value. In this case, the boundary parameter with the smaller impact of the two adjacent boundary parameters and the boundary parameter after the boundary parameter can be determined as boundary parameters not to be saved, while the boundary parameter with the larger impact of the two adjacent boundary parameters and the boundary parameter before the boundary parameter can be determined as boundary parameters to be retained.

[0041] As an optional example, the above-mentioned prediction of the target weight of the target system based on the above-mentioned target boundary data and the vehicle system database includes: when obtaining the above-mentioned target boundary data, determining the first N boundary parameters in the ranking result of their influence on the weight of the target system of the above-mentioned target vehicle as the above-mentioned target boundary data, wherein the above-mentioned N is a positive integer; and inputting the obtained above-mentioned target boundary data into the association curve in the above-mentioned vehicle system database to determine the predicted weight of the target system of the above-mentioned target vehicle.

[0042] After the vehicle system database is determined in the above embodiment, the vehicle system database includes the correlation curve between the first boundary data and the actual weight of various vehicles. Therefore, after obtaining the target boundary data of the target system of the target vehicle, the target boundary data can be input into the above-mentioned correlation curve to predict the predicted weight of the corresponding target system.

[0043] In this embodiment, when acquiring target boundary data, the top N boundary data from among all boundary data of the target system ranked by their impact on weight prediction can be determined as target boundary data. This means that rather than using all boundary data of the target system as target boundary data for weight prediction, only the boundary parameters with the greatest impact on weight prediction are retained for further weight prediction of the target system. These top N boundary parameters can be determined in the same manner as the first boundary parameter in the first boundary data. This will not be further elaborated here.

[0044] As an optional example, the above-mentioned obtaining target boundary data of the target system includes: constructing a three-dimensional model of the above-mentioned target vehicle in a virtual three-dimensional space; and obtaining the above-mentioned target boundary data through the above-mentioned three-dimensional model.

[0045] In this embodiment, a 3D model can be constructed in a virtual 3D space. This 3D model is a model of the target system of the target vehicle. The 3D model of the target vehicle can be constructed first, and then the non-target system portions can be temporarily hidden. The remaining 3D model of the target system can then be used to obtain boundary data. Alternatively, the 3D model of the target system can be directly constructed to obtain boundary data.

[0046] When constructing a 3D model in a virtual 3D space, it is necessary to construct a virtual model of each component of the target vehicle, thereby assembling the resulting 3D model. Alternatively, if multiple components are combined into a large component, a virtual model of the large component can be constructed in the virtual 3D space, thereby assembling the virtual models of the large virtual components to form the 3D model. When constructing a 3D model, the positional connection relationship between each component must be considered to avoid overlapping components.

[0047] After the 3D model is constructed, the boundary data of the 3D model can be obtained from the virtual 3D space, thereby obtaining the target boundary data of the target system. When obtaining the target boundary data, the mapping ratio between the virtual 3D space and the real space can be determined, and the 3D data in the virtual space can be mapped to the target boundary data in the real space.

[0048] As an optional example, after predicting the target weight of the target system based on the target boundary data and the vehicle system database, the method further includes: obtaining a first weight input by a user; adjusting the shape of the three-dimensional model in the virtual three-dimensional space according to preset conditions until the estimated target weight is less than the first weight; and outputting the shape of the three-dimensional model when the target weight is less than the first weight.

[0049] In this embodiment, after the target boundary data is obtained through the virtual three-dimensional space, and the corresponding target weight is predicted based on the target boundary data according to the vehicle system database, it is possible to check whether the target weight is appropriate. For example, for the target vehicle being developed, if the target weight is too heavy, it needs to be adjusted. At this time, a first weight can be set, and the first weight is used to constrain the target vehicle currently being developed. The boundary data of the three-dimensional model can be adjusted, such as lengthening or shortening the boundary data therein, and the adjusted boundary data is used to determine the target weight again through the vehicle system database. When the determined target weight is less than the first weight, it means that the current three-dimensional model size, components, etc. are relatively appropriate, and the shape of the current three-dimensional model can be retained.

[0050] That is to say, in this embodiment, by constraining a first weight, the size and shape of the three-dimensional model in the virtual three-dimensional space can be adjusted to make the weight of the target vehicle corresponding to the three-dimensional model meet the first weight requirement. In this way, a three-dimensional model that meets the first weight requirement can be obtained. When a vehicle is produced according to the three-dimensional model, the produced vehicle meets the first weight requirement.

[0051] As an optional example, the above-mentioned adjusting the shape of the three-dimensional model in the above-mentioned virtual three-dimensional space according to preset conditions until the estimated target weight is less than the above-mentioned first weight includes: obtaining the above-mentioned preset conditions, wherein the above-mentioned preset conditions include restrictions on the size and / or structure and / or position of the target component in the above-mentioned three-dimensional model; and adjusting the shape of the above-mentioned three-dimensional model according to the above-mentioned preset conditions.

[0052] In this embodiment, when adjusting the size and shape of a 3D model in a virtual 3D space, in order to avoid adjusting the size and shape of the 3D model according to a single condition, such as proportional expansion or reduction, preset conditions can be input in this embodiment. The preset conditions are used to indicate the constraints of the 3D model in the virtual 3D space when adjusting its boundaries and dimensions. For example, the constraints may include maintaining one or more of the boundary dimensions unchanged, maintaining proportional adjustment of certain related boundary parameters within the boundary dimensions, allowing only certain boundary parameters of the boundary dimensions to be adjusted, or constraining the spatial position, combination relationship, connection relationship, etc. of certain components of the 3D model. The constraints of these constraints can ensure that the 3D model is adjusted according to the constraints when adjusting its boundaries, dimensions, position, and space, thereby avoiding situations where the adjusted 3D model does not meet development requirements.

[0053] The system weight assessment model provided by this patent inputs the vehicle boundary factors that affect the system weight into the parameter input interface of the system weight assessment device. The device will calculate the predicted value and confidence interval of the system weight. At this stage, the rationality of the system weight can be judged.

[0054] Secondly, based on the weight level positioning requirements, a system weight target is set to determine the weight range that meets the positioning requirements and guide the setting of the system weight target. Based on the requirements, the weight level of the existing system can also be determined by using a weight assessment method to calculate the difference between the predicted system weight and the actual system weight, and consulting the industry's new energy vehicle weight level evaluation table.

[0055] The model can also be used during the vehicle boundary parameter presetting phase to analyze the impact of changes in boundary factors on weight using a weight assessment method, with a weight reduction focus. This can then be used to infer the optimization direction for the vehicle boundary. Specifically, the model adjusts the parameters in the boundary data with weight reduction as the guide, inputs the target weight, and determines which parameters to adjust and how to adjust them based on their impact on weight.

[0056] In this embodiment, two programs and an EXCLE file can be generated. One program is a weight prediction program with big data analysis and data storage functions. The other program is a weight assessment evaluation form used to evaluate the weight excellence of a vehicle. The EXCLE file is a front-end program file for executing and displaying the weight assessment model.

[0057] In this example, the database sample size selection process is first carefully planned. A weight prediction program is stored in the database. Using the least squares method of the fitted model within the program, with system weight as the dependent variable and boundary parameters as independent variables, a multivariate regression is performed to achieve weight prediction and confidence intervals. Both quantitative and field parameters can participate in the fitted regression, allowing for real-time application through the storage of the constructed fitting model (including the database).

[0058] The model evaluates the difference between the actual and predicted system weights of vehicle models, ranking them by percentile and creating a visual evaluation table to assess their competitiveness. A larger negative difference indicates a better weight level, while a larger positive difference indicates a worse weight level.

[0059] The weight assessment model is used to execute and display a program, which is coupled with the weight prediction program and evaluation table to realize the relevant parameter input, command execution, and result output interface.

[0060] Through the above scheme, the system weight level positioning based on the front-end input can be realized, the weight range that meets the positioning conditions can be analyzed, the actual weight level can be evaluated, and the professional optimization weight reduction with poor competitiveness can be guided. It can also guide the optimization of the boundary parameters of the whole vehicle to achieve weight reduction. This invention not only supports the setting of platform weight targets, but also can combine the whole vehicle weight target requirements and the highlight scene creation requirements to carry out targeted decomposition of system weight targets.

[0061] Figure 3 This is a flow chart of this embodiment. Information is collected about the target system, and the impact factor boundary parameters are obtained. These parameters are then input into the evaluation device for evaluation. The estimated weight output by the evaluation device is compared with the reasonable range to determine whether the estimated weight is reasonable. Furthermore, a weight reduction optimization goal is input, and the boundary parameters are adjusted inversely.

[0062] Figure 4 This is the evaluation flow chart for the evaluation device. The target system weight database is used to collect vehicle boundary parameter and weight data for each vehicle model. Based on this data, a correlation curve is constructed between the boundary parameters and weight. Once the correlation curve is constructed, vehicles are ranked according to the difference between the estimated weight and the actual weight. This difference can be negative; the smaller the difference, the higher the ranking. When predicting the weight of a specific vehicle, the vehicle's boundary parameters and the target system weight database are used to estimate the vehicle's weight.

[0063] By establishing a professional system weight evaluation system that can evaluate the development of new energy vehicle platforms and setting it in a competitive weight range according to the positioning, on the one hand, it can evaluate the rationality of the system weight during the development phase, and on the other hand, it can guide the optimization of vehicle boundary parameters in the early stages of vehicle / platform planning with weight reduction as the guide.

[0064] Weight prediction includes the following processes:

[0065] The first step is to clarify the requirements of vehicle / platform development for target system weight analysis and collect the vehicle boundary parameters that affect the system weight during vehicle / platform development.

[0066] The second step is to enter the vehicle boundary parameters of the system weight in the weight assessment device operation interface and click the execute command according to the assessment requirements;

[0067] The third step is to output the system weight assessment list.

[0068] The construction of the weight prediction device includes the following processes:

[0069] The first step is to establish a target system weight database. The database contains 80% of the industry's mainstream new energy vehicles, covering a complete range of vehicle levels, body types, new energy categories, and automobile companies (joint ventures, new energy vehicles, and traditional automobile companies). The database information includes the weight of the system for all models and the vehicle boundary parameters that affect the system weight.

[0070] The second step is to import the database into the weight prediction program, select the least squares method of the linear regression model, select the system weight as the dependent variable y, and select the vehicle boundary parameter as the independent variable x. Run to obtain the correlation degree between each factor and weight. According to the order of correlation degree, filter and delete the factors with less influence, and lock the final list of factors included in the analysis. Figure 5 Schematic diagram of an exemplary correlation curve.

[0071] The third step is to select linear regression again according to the locked factor list, perform fitting regression on multiple factors, click the profiler to realize the system weight prediction and confidence interval judgment function, save the program to the computer, and form the system weight prediction program.

[0072] The fourth step is to predict the predicted values ​​of all vehicle models in the system weight prediction program, and export the system weight, predicted value and other information corresponding to each vehicle model to EXCLE, sort them in descending order according to the difference between the system weight and the predicted value, and form a weight level evaluation table according to the weight level standard defined by the weight level.

[0073] The fifth step is to establish an operation execution program. This program uses parameter input and realizes one-click analysis and result output according to analysis requirements. This program is coupled and associated with the system weight prediction program and weight level evaluation table established above to realize its functions.

[0074] For example, analyze the weight of the chassis system of the object, whether the current chassis system weight is reasonable, and what weight target range should be set to support the weight level to reach the industry level.

[0075] Establish a chassis weight database that includes different pure electric, hybrid and other new energy vehicle models, the corresponding chassis weight of each model, vehicle weight, front and rear wheelbase, front and rear suspension structure, drive mode, fuel type, key configuration and other information.

[0076] Import the database into the weight prediction program and click Fit Model. Perform a correlation analysis using chassis weight as the dependent variable and vehicle boundary parameters such as vehicle weight, fuel type, front and rear wheelbase, and front and rear suspension as independent variables. Fuel type has little correlation with chassis weight, so it was eliminated, ultimately locking in eight factors.

[0077] In the weight prediction program, the locked 8 factors were selected as independent variables and the chassis weight was the dependent variable, and multiple linear regression fitting was performed. When the analysis result predicted value RMSE = 14.946, RSq = 0.92 p value = <.0001, it was determined that the model was feasible.

[0078] In the above program, click the profiler to realize the prediction of chassis system weight and confidence interval judgment function, store the program and define it as chassis new energy vehicle weight prediction to realize database storage and weight prediction.

[0079] After the chassis weight level assessment, the difference between the actual and predicted values ​​for each vehicle model is ranked in descending order, and a weight level evaluation table is generated based on the weight level evaluation criteria. The difference Δ between the actual and predicted weight of the chassis system to be analyzed is calculated. By querying the weight level ranking of the evaluation table where Δ falls, the excellence of the vehicle's estimated weight is determined. Generally, the lighter the estimated weight is compared to the actual weight, the better. If the chassis system weight falls within the excellent weight range, the system weight x of the chassis is first predicted. The excellent level difference range Δmin and Δmax are set in the evaluation table, and the excellent weight range = [x + Δmin, x + Δmax].

[0080] A chassis system weight assessment interface was established, including input fields for chassis weight assessment parameters, an analysis module, operational commands, and a corresponding display interface. This information was coupled with the chassis weight prediction program and the chassis weight level evaluation table for new energy vehicles.

[0081] Input the weight-related parameters of the chassis system to be analyzed in the operation interface, analyze the rationality of the chassis system weight, whether it reaches the excellent weight range, etc.

[0082] If the weight is reasonable but there is still a gap between the weight range goals and the weight range goals, it is necessary to continue to optimize the weight loss path to achieve a competitive weight range.

[0083] This embodiment further provides a vehicle system weight prediction device, comprising:

[0084] an acquisition module, configured to acquire target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system whose weight is to be predicted, and the target boundary data includes boundary dimensions of the target system;

[0085] The prediction module is used to predict the target weight of the target system based on the target boundary data and the vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of other vehicles.

[0086] The above vehicles can be fuel-powered vehicles, pure electric vehicles (Blade Electric Vehicles, BEV), hybrid electric vehicles (HEV), plug-in hybrid electric vehicles (PHEV), extended-range electric vehicles (EREV) or fuel cell electric vehicles (FCEV)

[0087] In the vehicle system weight prediction device of this embodiment, the vehicle system mentioned herein can be the entire target vehicle or a partial system of the target vehicle. If the target vehicle is the entire target vehicle, the vehicle weight of the entire vehicle is predicted. If the target vehicle is a partial system, the weight of the partial system of the vehicle is predicted. The partial system can be the chassis system of the vehicle, or the transmission system, steering system, braking system, driving system, etc. within the chassis system. Alternatively, the partial system can be a partial component of the target vehicle, such as the vehicle shell, vehicle tires, etc.

[0088] The first system of the other vehicles is the same as the target system of the target vehicle. For example, if the target system of the target vehicle is the entire vehicle, then the first system of the other vehicles is also the entire vehicle. If the target system of the target vehicle is the chassis system, then the first system of the other vehicles is also the chassis system.

[0089] In the target boundary data of the target system or the first boundary data of the first system, the boundary data can be the boundary size of the system. That is, the boundary of the system is obtained, and the boundary is the outermost minimum bounding box of the system. The size data of the outermost minimum bounding box can be used as the boundary data. For example, Figure 2 For simplicity of explanation, Figure 2 The example is an example of the minimum bounding box of a vehicle's top view, with the vehicle's minimum circumscribed bounding box as the boundary. It should be noted that because the vehicle is three-dimensional, when constructing the minimum circumscribed bounding box, the minimum circumscribed bounding box of the three-dimensional vehicle is constructed. Therefore, the boundary lines are more complex and numerous.

[0090] The vehicle system database in this embodiment may include first boundary data for the first systems of different vehicles and the actual weights of the vehicles. The first boundary data and actual weights of the first systems of different vehicles are stored in the vehicle system database. The vehicle system database analyzes this data to determine the relationship between the boundary data and the actual weights of the vehicles. Once the relationship between the boundary data and the actual weights is determined, the acquired target boundary data can be used to predict the target weight of the target system.

[0091] For example, to predict the target weight of a vehicle's chassis system, the first boundary data and weights of the chassis systems of other vehicles are obtained to form a vehicle system database. The relationship between the chassis systems of other vehicles and their actual weights is then learned from the vehicle system database. Once the relationship is learned, the target boundary data of the vehicle chassis system can be input into the vehicle system database to obtain the corresponding target weight.

[0092] The present application obtains target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system for which weight is to be predicted, and the target boundary data includes the boundary dimensions of the target system; based on the target boundary data and a vehicle system database, the target weight of the target system is predicted, wherein the vehicle system database includes the first boundary data of target systems of other vehicles and the actual weights of the target systems of the other vehicles, so that the estimated weight of the target system of the target vehicle can be predicted based on the relationship between the acquired target boundary data of the target system and the first boundary data of other vehicles stored in the vehicle system database and the actual weights of the target systems of other vehicles, thereby improving the accuracy of the estimated weight of the target system.

[0093] like Figure 6 As shown, an embodiment of the present application provides a weight prediction device for a vehicle system, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other via the communication bus 114.

[0094] Memory 113, for storing computer programs;

[0095] In one embodiment of the present application, the processor 111 is used to implement the vehicle system weight prediction method provided in any of the aforementioned method embodiments when executing the program stored in the memory 113, including: obtaining target boundary data of the target system, wherein the target system is the entire vehicle of the target vehicle or a partial system of the target vehicle, and the target system is the system whose weight is to be predicted, and the target boundary data includes the boundary size of the target system; predicting the target weight of the target system based on the target boundary data and the vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of other vehicles.

[0096] A computer-readable storage medium is also provided in an embodiment of the present application, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle system weight prediction method provided in any of the aforementioned method embodiments are implemented.

[0097] The device embodiments described above are illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the solutions of this embodiment.

[0098] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, or of course by hardware. Based on this understanding, the above technical solution, in essence, or the part that contributes to the relevant technology, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment, or certain parts of the embodiments.

[0099] It should be understood that the terms used herein are for the purpose of describing specific example embodiments only and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "comprise", "include", "contain" and "have" are inclusive and therefore specify the presence of stated features, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not to be construed as necessarily requiring them to be performed in the specific order described or illustrated, unless the order of execution is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0100] The foregoing is merely a list of specific embodiments of the present application, intended to enable those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the broadest scope consistent with the principles and novel features of the present application.

Claims

1. A method for predicting the weight of a vehicle system, characterized in that: include: Acquiring target boundary data of a target system, wherein the target system is an entire target vehicle or a partial system of the target vehicle, and the target system is a system for which weight is to be predicted, and the target boundary data includes boundary dimensions of the target system; The target weight of the target system is predicted based on the target boundary data and a vehicle system database, wherein the vehicle system database includes first boundary data of first systems of other vehicles and actual weights of the first systems of the other vehicles.

2. The method according to claim 1, characterized in that Before predicting the target weight of the target system based on the target boundary data and the vehicle system database, the method further includes: According to the first boundary data and the actual weight in the vehicle system database, a correlation curve between each boundary parameter in the first boundary data and the actual weight is determined.

3. The method according to claim 2, characterized in that After determining a correlation curve between each boundary parameter in the first boundary data and the actual weight based on the first boundary data in the vehicle system database and the actual weight, the method further includes: Determine, according to the association curve, top N boundary parameters in a ranking result of their influence on the actual weight among all boundary parameters of the first boundary data, where N is a positive integer; The association curves corresponding to the first N boundary parameters are retained.

4. The method according to claim 1, wherein The predicting the target weight of the target system according to the target boundary data and the vehicle system database includes: When acquiring the target boundary data, first N boundary parameters in the ranking result of the influence on the weight of the target system of the target vehicle are determined as the target boundary data, wherein N is a positive integer; The acquired target boundary data is input into a correlation curve in the vehicle system database to determine a predicted weight of the target system of the target vehicle.

5. The method according to claim 1, wherein The acquiring target boundary data of the target system includes: Constructing a three-dimensional model of the target vehicle in a virtual three-dimensional space; The target boundary data is acquired through the three-dimensional model.

6. The method according to claim 5, characterized in that After predicting the target weight of the target system based on the target boundary data and the vehicle system database, the method further includes: Get the first weight input by the user; adjusting the shape of the three-dimensional model in the virtual three-dimensional space according to preset conditions until the estimated target weight is less than the first weight; Outputting a shape of the three-dimensional model when the target weight is less than the first weight.

7. The method according to claim 6, characterized in that The adjusting the shape of the three-dimensional model in the virtual three-dimensional space according to a preset condition until the estimated target weight is less than the first weight includes: Acquiring the preset conditions, wherein the preset conditions include constraints on the size, structure, and / or position of the target component in the three-dimensional model; The shape of the three-dimensional model is adjusted according to the preset condition.

8. A weight prediction device for a vehicle system, characterized in that: include: an acquisition module, configured to acquire target boundary data of a target system, wherein the target system is the entire target vehicle or a partial system of the target vehicle, and the target system is a system for which weight is to be predicted, and the target boundary data includes boundary dimensions of the target system; A prediction module is used to predict the target weight of the target system based on the target boundary data and a vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of the other vehicles.

9. A weight prediction device for a vehicle system, characterized in that: It includes at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; and at least one memory connected to the at least one bus, wherein the processor is configured to: obtain target boundary data of a target system, wherein the target system is the entire vehicle of a target vehicle or a partial system of the target vehicle, and the target system is a system whose weight is to be predicted, and the target boundary data includes the boundary size of the target system; predict the target weight of the target system based on the target boundary data and a vehicle system database, wherein the vehicle system database includes the first boundary data of the first system of other vehicles and the actual weight of the first system of other vehicles.

10. A computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the vehicle system weight prediction method described in any one of the above items of the present application.

Images