Method, device and equipment for predicting fuel consumption based on vehicle parameters and readable storage medium

Abstract

Based on a vehicle parameter oil consumption prediction method, device and equipment and a readable storage medium, a correlation basis is constructed based on homologous data of heavy commercial vehicles of the same vehicle type and different types, and correlation characteristics are clarified by combining correlation analysis; the correlation relation expression obtained through regression analysis optimization can accurately represent the internal correlation between the parameters and the fuel consumption of the different types of vehicles under the vehicle type, and a large number of real vehicle tests do not need to be carried out for the different types of vehicles under the vehicle type to accumulate data. The fuel consumption prediction of different types of vehicles under the vehicle type can be realized through the incidence relation expression, the rapid pre-judgment requirement of the fuel consumption of different types of vehicles under the vehicle type in the vehicle development stage is met, and timely guidance is provided for the design optimization of different types of vehicles under the vehicle type to improve the research and development efficiency. And meanwhile, the problems of high cost and time investment caused by respectively carrying out a large number of real vehicle tests for different types of vehicles are avoided.

Description

Technical Field

[0001] This application relates to the field of vehicle energy consumption prediction, specifically to a method, apparatus, device, and readable storage medium for predicting fuel consumption based on vehicle parameters. Background Technology

[0002] With the continuous upgrading of global requirements for energy conservation and emission reduction in automobiles, fuel consumption has become a key indicator for heavy-duty commercial trucks, which are core equipment for logistics transportation. It is also a crucial consideration for vehicles to meet national environmental regulations and reduce operating costs. Currently, the heavy-duty commercial truck industry is facing increasingly stringent fuel consumption limits. Manufacturers need to predict fuel consumption performance in advance during vehicle development to avoid problems such as R&D rework and increased costs due to failure to meet standards in later testing. Therefore, the demand for accurate and efficient fuel consumption prediction technology is becoming increasingly urgent.

[0003] In related technologies, some fuel consumption prediction solutions rely on big data collection, requiring extensive real-vehicle testing of the target vehicle to accumulate data, and then using data-driven models to predict fuel consumption.

[0004] However, solutions that rely on a large amount of real-vehicle test data require significant investment in testing costs and time, which contradicts the need for rapid prediction and early optimization during the vehicle development phase. This approach fails to provide timely and accurate guidance for vehicle design optimization, thus limiting R&D efficiency. Summary of the Invention

[0005] This application provides a method, apparatus, device, and readable storage medium for predicting fuel consumption based on vehicle parameters, which can solve the technical problems in related technologies where fuel consumption prediction relies on a large amount of test data, has a narrow scope of application, and cannot provide timely optimization guidance for vehicle development.

[0006] In a first aspect, embodiments of this application provide a method for predicting fuel consumption based on vehicle parameters, the method comprising: Based on the actual test data of vehicle fuel consumption and the vehicle parameters corresponding to the test data, establish the correspondence between the actual test data of fuel consumption and the vehicle parameters; Correlation analysis was performed on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption. Based on the aforementioned correlation characteristics, regression analysis is used to optimize the correlation between vehicle parameters and actual fuel consumption test results, resulting in a correlation expression for predicting fuel consumption.

[0007] In conjunction with the first aspect, in one implementation, the step of performing correlation analysis on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption includes: The Pearson correlation coefficient method is used to calculate the correlation coefficient between each vehicle parameter and the actual test results of fuel consumption. The absolute value of the correlation coefficient represents the correlation strength, and the positive or negative value of the correlation coefficient represents the correlation direction, thereby clarifying the correlation influence characteristics of each vehicle parameter on fuel consumption.

[0008] In conjunction with the first aspect, in one implementation, the step of optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on the correlation characteristics to obtain a correlation expression for predicting fuel consumption includes: First, a preliminary correlation between a single vehicle parameter and fuel consumption is established through linear regression. Then, multiple linear regression is used to extend the correlation to multiple vehicle parameters. Finally, nonlinear regression is used to add square and interaction terms to adapt to the nonlinear correlation characteristics. The weights of the parameter terms are gradually adjusted to improve the fitting accuracy of the correlation to the actual test results of fuel consumption, thereby obtaining the correlation expression used to predict fuel consumption.

[0009] In conjunction with the first aspect, in one implementation, the step of optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on the correlation characteristics to obtain a correlation expression for predicting fuel consumption includes: Based on a preset threshold of the maximum design mass of the vehicle, the actual test data of fuel consumption of heavy commercial vehicles and the corresponding vehicle parameters are divided into a first data group and a second data group. Then, for the first data group and the second data group, the correlation between vehicle parameters and fuel consumption within each group is combined with the correlation characteristics of each group. Regression analysis is used to optimize the correlation relationship of each group, resulting in the first group correlation relationship expression and the second group correlation relationship expression, which are used as correlation relationship expressions for predicting fuel consumption.

[0010] In conjunction with the first aspect, in one implementation, after optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on the aforementioned correlation characteristics to obtain a correlation expression for predicting fuel consumption, the method further includes: The calculation result of the correlation expression is compared with the actual fuel consumption measurement data to calculate the relative error between the calculated value of the expression and the actual measurement value. If the relative error exceeds the preset accuracy range, the application method of the regression analysis method or the weight of the parameter items in the correlation relationship is adjusted, and the correlation relationship between vehicle parameters and fuel consumption is re-optimized until the relative error of the expression calculation result meets the accuracy requirements, and the verified and optimized correlation relationship expression is obtained.

[0011] In conjunction with the first aspect, in one implementation, the following steps are also included: Obtain vehicle parameters for different models of the same vehicle type, substitute these parameters into the verified and optimized correlation expression, and calculate the predicted fuel consumption values ​​for the different models of the same vehicle type.

[0012] In conjunction with the first aspect, in one embodiment, the vehicle parameters include a constant term for the vehicle's coasting resistance coefficient, a first-order term for the vehicle's coasting resistance coefficient, a second-order term for the vehicle's coasting resistance coefficient, the vehicle's maximum design mass, and the engine's rated power.

[0013] Secondly, embodiments of this application provide a fuel consumption prediction device based on vehicle parameters, the fuel consumption prediction device based on vehicle parameters includes: The parameter association construction module is used to establish the correspondence between the actual fuel consumption test data and the vehicle parameters based on the actual fuel consumption test data of the vehicle and the vehicle parameters corresponding to the test data. The correlation characteristic analysis module is used to perform correlation analysis on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption. The correlation optimization module is used to optimize the correlation between vehicle parameters and actual fuel consumption test results based on the correlation characteristics using regression analysis methods, so as to obtain a correlation expression for predicting fuel consumption.

[0014] Thirdly, this application provides a fuel consumption prediction device based on vehicle parameters. The fuel consumption prediction device based on vehicle parameters includes a processor, a memory, and a fuel consumption prediction program based on vehicle parameters stored in the memory and executable by the processor. When the fuel consumption prediction program based on vehicle parameters is executed by the processor, it implements the steps of the fuel consumption prediction method based on vehicle parameters as described in the above embodiments.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium storing a fuel consumption prediction program based on vehicle parameters, wherein when the fuel consumption prediction program based on vehicle parameters is executed by a processor, it implements the steps of the fuel consumption prediction method based on vehicle parameters as described in the above embodiments.

[0016] The beneficial effects of the technical solutions provided in this application include: By building a foundation of association based on source data of different models of heavy-duty commercial vehicles of the same type and clarifying the association characteristics through correlation analysis, the association expression obtained by regression analysis can accurately characterize the intrinsic relationship between parameters and fuel consumption of different models of the same vehicle type. This eliminates the need to accumulate data through extensive real-vehicle testing for each model of the same vehicle type. The fuel consumption of different models of the same vehicle type can be predicted through this association expression, meeting the need for rapid prediction of fuel consumption of different models of the same vehicle type during the vehicle development stage. This provides timely guidance for the design optimization of different models of the same vehicle type to improve R&D efficiency, while avoiding the high cost and time investment caused by conducting extensive real-vehicle testing for each model. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the first embodiment of the fuel consumption prediction method based on vehicle parameters in this application; Figure 2 This is a schematic diagram of the hardware structure of the fuel consumption prediction device based on vehicle parameters involved in the embodiments of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0019] With the continuous upgrading of global requirements for energy conservation and emission reduction in automobiles, fuel consumption has become a key indicator for heavy-duty commercial trucks, which are core equipment for logistics transportation. It is also a crucial consideration for vehicles to meet national environmental regulations and reduce operating costs. Currently, the heavy-duty commercial truck industry is facing increasingly stringent fuel consumption limits. Manufacturers need to predict fuel consumption performance in advance during vehicle development to avoid problems such as R&D rework and increased costs due to failure to meet standards in later testing. Therefore, the demand for accurate and efficient fuel consumption prediction technology is becoming increasingly urgent.

[0020] Some fuel consumption prediction solutions rely on big data collection, requiring extensive real-vehicle testing of the target vehicle to accumulate data, and then using data-driven models to predict fuel consumption.

[0021] However, solutions that rely on a large amount of real-vehicle test data require significant investment in testing costs and time, which contradicts the need for rapid prediction and early optimization during the vehicle development phase. This approach fails to provide timely and accurate guidance for vehicle design optimization, thus limiting R&D efficiency.

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0023] In a first aspect, embodiments of this application provide a method for predicting fuel consumption based on vehicle parameters.

[0024] In one embodiment, reference is made to Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the fuel consumption prediction method based on vehicle parameters in this application. Figure 1 As shown, methods for predicting fuel consumption based on vehicle parameters include: S100: Based on the actual test data of the vehicle's fuel consumption and the vehicle parameters corresponding to the test data, establish the correspondence between the actual test data of fuel consumption and the vehicle parameters; S200: Perform correlation analysis on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption; S300: Based on the aforementioned correlation characteristics, a regression analysis method is used to optimize the correlation between vehicle parameters and actual fuel consumption test results, resulting in a correlation expression for predicting fuel consumption.

[0025] In this embodiment, each set of actual fuel consumption test data and its corresponding vehicle parameters are derived from different models of heavy-duty commercial vehicles of the same type. By associating the actual fuel consumption test data of different models of heavy-duty commercial vehicles of the same type with their corresponding vehicle parameters, a correspondence is established between the two to form a correlation dataset. Correlation analysis is then performed on this correspondence to clarify the correlation characteristics between each vehicle parameter and the actual fuel consumption test results. Based on the obtained correlation characteristics, regression analysis is used to optimize the correlation between vehicle parameters and the actual fuel consumption test results, ultimately obtaining a correlation expression for predicting fuel consumption. Through the above method, relying on different models of heavy-duty commercial vehicles of the same type… By constructing a foundation of associations based on the same source data of vehicles and combining it with correlation analysis to clarify the association characteristics, the association expression obtained by regression analysis can accurately characterize the intrinsic relationship between parameters and fuel consumption of different models under the same vehicle model. This eliminates the need to rely on accumulating data through extensive real-vehicle testing for each different model under the same vehicle model. The fuel consumption of different models under the same vehicle model can be predicted through this association expression, meeting the need for rapid prediction of fuel consumption of different models under the same vehicle model during the vehicle development stage. This provides timely guidance for the design optimization of different models under the same vehicle model to improve R&D efficiency, while avoiding the high cost and time investment caused by conducting extensive real-vehicle testing for each different model.

[0026] Furthermore, in one embodiment, step S200 includes the following steps: S201: The Pearson correlation coefficient calculation method is adopted to obtain the correlation coefficient between each vehicle parameter and the actual test results of fuel consumption. The absolute value of the correlation coefficient represents the correlation strength, and the positive or negative value of the correlation coefficient represents the correlation direction, thereby clarifying the correlation influence characteristics of each vehicle parameter on fuel consumption.

[0027] In this embodiment, during the correlation analysis of the correspondence between actual fuel consumption test data and vehicle parameters, the Pearson correlation coefficient calculation method is specifically adopted. The correlation coefficient between each vehicle parameter and the actual fuel consumption test results is calculated. The absolute value of the correlation coefficient represents the strength of the correlation between each vehicle parameter and fuel consumption, and the positive or negative sign of the correlation coefficient represents the direction of the correlation. This clarifies the correlation influence characteristics of each vehicle parameter on fuel consumption. Based on the mathematical characteristics of the Pearson correlation coefficient calculation method, the correlation attributes between each vehicle parameter and fuel consumption can be quantitatively defined. This provides a clear basis for subsequent steps to optimize the correlation relationship through regression analysis based on the correlation characteristics. This ensures that subsequent regression analysis can specifically focus on vehicle parameters that have a clear correlation influence on fuel consumption, reducing the interference of uncorrelated or weakly correlated parameters on the optimization process. This makes the final correlation expression for predicting the fuel consumption of different models of heavy commercial vehicles of the same type more accurately match the intrinsic correlation between vehicle parameters and fuel consumption, further improving the accuracy of fuel consumption prediction and better meeting the needs of rapid prediction and design optimization of fuel consumption for different models of the same type during the vehicle development stage.

[0028] Furthermore, in one embodiment, step S300 includes the following steps: S301: First, a preliminary correlation between a single vehicle parameter and fuel consumption is established through linear regression. Then, multiple linear regression is used to extend the correlation to multiple vehicle parameters. Finally, nonlinear regression is used to add square terms and interaction terms to adapt to the nonlinear correlation characteristics. The weights of the parameter terms are gradually adjusted to improve the fitting accuracy of the correlation to the actual test results of fuel consumption, thereby obtaining the correlation expression used to predict fuel consumption.

[0029] In this embodiment, in the process of optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on correlation characteristics, a preliminary correlation between a single vehicle parameter and fuel consumption is first constructed through linear regression. Then, the correlation dimension is expanded to a collaborative correlation of multiple vehicle parameters through multiple linear regression. Finally, nonlinear regression is used to add square terms and interaction terms to the correlation to adapt to the nonlinear correlation characteristics between parameters and fuel consumption. Furthermore, the weights of each parameter are gradually adjusted during the progressive process of the regression analysis to continuously improve the fitting accuracy of the correlation to the actual fuel consumption test results, ultimately yielding a method for predicting different models of the same vehicle. The correlation expression for fuel consumption of heavy-duty commercial vehicles is derived through the progressive application of regression analysis and the gradual optimization of parameter weights. This allows the obtained correlation expression to not only cover the synergistic effects of multiple vehicle parameters but also adapt to nonlinear correlation characteristics. It more accurately reproduces the inherent correlation between vehicle parameters and fuel consumption of different models of the same type of heavy-duty commercial vehicle, further ensuring the accuracy of fuel consumption prediction results. This provides more reliable support for rapid prediction of fuel consumption of different models of the same type of vehicle during the vehicle development stage, offering precise data references for the design optimization of such vehicles. Simultaneously, it continuously reduces reliance on large amounts of real-vehicle test data, further controlling R&D costs and time investment.

[0030] Furthermore, in one embodiment, step S300 includes the following steps: S302: Based on a preset threshold of the maximum design mass of the vehicle, the collected actual test data of fuel consumption of heavy commercial vehicles and the corresponding vehicle parameters are divided into a first data group and a second data group. S303: For the first data group and the second data group, the correlation characteristics between vehicle parameters and fuel consumption within each group are combined, and the regression analysis method is used to optimize the corresponding correlation relationship of each group to obtain the first group correlation relationship expression and the second group correlation relationship expression, which are used as the correlation relationship expression for predicting fuel consumption.

[0031] In this embodiment, during the process of optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on correlation characteristics, the actual fuel consumption test data and corresponding vehicle parameters of different models of heavy-duty commercial vehicles of the same type are first divided into a first data group and a second data group based on a preset threshold of the maximum design mass of the vehicle. Then, for the first and second data groups, regression analysis is used to optimize the correlation between vehicle parameters and fuel consumption within each group, and finally, the first and second data group correlation expressions are obtained as correlation expressions for predicting the fuel consumption of different models of heavy-duty commercial vehicles of the same type. This is achieved by setting a preset threshold based on the maximum design mass of the vehicle. Value grouping ensures greater consistency in core mass parameters for vehicles within each group, adapting to the differentiated characteristics of different models of the same vehicle at maximum design mass. This allows each group's regression analysis to specifically match the correlation between vehicle parameters and fuel consumption within the corresponding mass range, reducing the interference of mixed data from different mass ranges on the optimization process. It also improves the fitting accuracy of each group's correlation expression to actual test data within the corresponding mass range, thereby enabling accurate fuel consumption predictions for different models of the same vehicle across different mass ranges. This more comprehensively meets the fuel consumption prediction and design optimization needs of different models of the same vehicle across various mass ranges during the vehicle development stage, while maintaining a low dependence on a large amount of real-vehicle test data, ensuring R&D efficiency and cost control.

[0032] Furthermore, in one embodiment, after S300, there is S400, which includes the following steps: S401: Compare the calculation result of the correlation expression with the actual fuel consumption measurement data, and calculate the relative error between the calculated value of the expression and the actual measurement value; S402: If the relative error exceeds the preset accuracy range, adjust the application method of the regression analysis method or the weight of the parameter items in the correlation relationship, and re-optimize the correlation relationship between vehicle parameters and fuel consumption until the relative error of the expression calculation result meets the accuracy requirements, and obtain the verified and optimized correlation relationship expression.

[0033] In this embodiment, after obtaining the correlation expression for predicting fuel consumption, the calculation result of the correlation expression is further compared with the actual fuel consumption measurement data to calculate the relative error between the calculated value and the actual measurement value. If the calculated relative error exceeds the preset accuracy range, the application method of the regression analysis method or the weight of the parameter items in the correlation is adjusted, and the correlation between vehicle parameters and fuel consumption is re-optimized until the relative error of the correlation expression calculation result meets the preset accuracy requirement, thus obtaining the verified and optimized correlation expression. By comparing the correlation expression with actual measurement data and verifying the error, and by making targeted adjustments and optimizations for cases that do not meet the accuracy requirements, it is ensured that the verified and optimized correlation expression can more accurately match the inherent correlation between vehicle parameters and fuel consumption of different models of heavy commercial vehicles of the same type, further improving the reliability of fuel consumption prediction results. This provides a more accurate basis for fuel consumption prediction and design optimization of different models of vehicles of the same type during the vehicle development stage, while avoiding the adverse impact of prediction deviations caused by insufficient expression accuracy on R&D decisions.

[0034] Furthermore, in one embodiment, the method further includes the following steps: S403: Obtain vehicle parameters for different models of the same vehicle type, substitute the vehicle parameters for different models of the same vehicle type into the verified and optimized correlation expression, and calculate the predicted fuel consumption value for different models of the same vehicle type.

[0035] In this embodiment, vehicle parameters of different models of the same vehicle model are obtained, and these parameters are substituted into the verified and optimized correlation expression to calculate the predicted fuel consumption values ​​for different models of the same vehicle model. Based on the verified and optimized correlation expression that adapts to the correlation patterns of this vehicle model, fuel consumption prediction results can be quickly obtained simply by acquiring the vehicle parameters of different models of the same vehicle model. This eliminates the need for extensive real-vehicle testing of different models of the same vehicle model, ensuring the accuracy of the prediction results to match the anticipated needs of the vehicle development stage, and significantly shortening the fuel consumption evaluation cycle for different models of the same vehicle model. This provides timely and reliable fuel consumption references for the design optimization of different models of the same vehicle model, further improving R&D efficiency and reducing R&D testing costs.

[0036] Furthermore, in one embodiment, the vehicle parameters include a constant term for the vehicle's coasting drag coefficient, a first-order term for the vehicle's coasting drag coefficient, a second-order term for the vehicle's coasting drag coefficient, the vehicle's maximum design mass, and the engine's rated power.

[0037] In this embodiment, the vehicle parameters used specifically include the constant term of the vehicle's coasting resistance coefficient, the first term of the vehicle's coasting resistance coefficient, the second term of the vehicle's coasting resistance coefficient, the maximum design mass of the vehicle, and the rated power of the engine. These parameters are all core parameters directly related to the fuel consumption of different models of heavy-duty commercial vehicles of the same type. In the process of establishing the correspondence between actual fuel consumption test data and vehicle parameters, conducting correlation analysis to clarify the correlation characteristics, and subsequently performing regression analysis to optimize the correlation, using these core parameters as the analysis objects allows the entire correlation construction process to focus on key factors that have a substantial impact on fuel consumption, reducing the interference introduced by irrelevant parameters. This allows the obtained correlation expression to more accurately capture the inherent correlation between core parameters and fuel consumption, thereby improving the accuracy of fuel consumption prediction for different models of heavy-duty commercial vehicles of the same type. This provides a more targeted parameter adjustment basis for the design optimization of such vehicles during the vehicle development stage, while maintaining a low dependence on a large amount of real vehicle test data, ensuring R&D efficiency and cost control.

[0038] In summary, the complete technical solution for predicting fuel consumption based on vehicle parameters is outlined and explained below: I. Overview of Technical Solution This technical solution is applicable to different models of heavy-duty commercial vehicles of the same type. Its core objective is to construct an accurate fuel consumption prediction model through a complete process of "data collection - correlation analysis - relationship optimization - verification - prediction," addressing the problems of existing technologies that rely on extensive real-vehicle testing, resulting in high costs and low efficiency. This provides timely guidance for design optimization during the vehicle development phase. The solution uses "vehicle core parameters" as the core input, and through correlation analysis, progressive regression optimization, grouping adaptation, and accuracy verification, ultimately achieves rapid and accurate fuel consumption prediction for different models of the same type of vehicle.

[0039] II. Complete Technical Process and Details Step 1: Parameter Collection and Correlation Construction Operation content: Collect "actual fuel consumption test data (Y)" and the corresponding 5 vehicle parameters (X1~X5) of different models of heavy commercial vehicles of the same type; associate each set of "Y-X1~X5" data to establish the correspondence between "fuel consumption-vehicle parameters" and form a basic dataset.

[0040] Data characteristics: Each set of data comes from different models of the same vehicle type, ensuring the consistency of the core architecture and reducing interference from unrelated variables.

[0041] Step 2: Correlation Feature Analysis Core method: The Pearson correlation coefficient method is used to quantify the correlation characteristics between various vehicle parameters and fuel consumption; Calculation logic: The formula for calculating the Pearson correlation coefficient (r) is as follows:

[0042] Where X is a certain vehicle parameter (any one of X1~X5), Y is the actual test value of the corresponding fuel consumption, and n is the number of test samples; Defining the correlation characteristics: The absolute value of r represents the "correlation strength" (the closer the absolute value is to 1, the stronger the correlation), and the sign of r represents the "correlation direction" (positive correlation: X increases → Y increases; negative correlation: X increases → Y decreases), clarifying the correlation influence characteristics of X1~X5 on Y.

[0043] Step 3: Data Grouping Grouping criteria: The grouping is based on a preset threshold of the vehicle's maximum design mass (X4). Operation: Divide the basic dataset into two groups—the first data group (X4 ≤ preset threshold) and the second data group (X4 > preset threshold). Core objective: To ensure the consistency of core vehicle quality parameters within each data set and reduce the interference of data from different quality ranges on subsequent optimization; or based on GB / T38146.2-2019 China Automotive Driving Conditions Part 2: Heavy Commercial Vehicles, Chinese trucks are tested under the CHTC-LT condition (1652 seconds) with a GVW ≤ 5500kg and a CHTC-HT condition (1800 seconds) with a GVW > 5500kg.

[0044] Step 4: Optimize Relationships This step is divided into "basic optimization logic" and "group optimization logic". Group optimization is an extension of basic optimization, as detailed below: 4.1 Basic Optimization Logic (Ungrouped Scenarios) The "progressive regression analysis" is used to gradually improve the accuracy of the correlation fit. The steps are as follows: Initial Linear Regression Setup: For a single parameter with a high correlation strength (such as X3), construct an initial linear correlation relationship: ( For a single core parameter, such as X3) in For constant terms, The weights of the parameter terms are calculated using the least squares method to minimize the fitting error. Multiple linear regression extension: Introducing residual parameters (X1~X5) to construct multi-parameter synergistic relationships:

[0045] Adjusted by stepwise regression method The weights are adjusted to accommodate the synergistic effects of multiple parameters. Nonlinear regression adaptation: For parameters with nonlinear correlations (such as X3), add squared terms and interaction terms to optimize the relationship into a nonlinear one.

[0046] X3 2 X2 and X3 are the squared terms, and X2 and X3 are the interaction terms. All weights are recalculated. Minimize the fitting error to obtain the initial correlation expression; For example, Y=1.923+0.0098X1+0.302X2+10.567X3+0.786X4+0.029X5+0.00012X1 2 -0.0045X2²+0.234X3 2 +0.0034X4X5.

[0047] 4.2 Grouping Optimization Logic (Grouped Scenarios) Perform the progressive regression analysis described in section 4.1 on both the first and second data groups to obtain two independent association expressions: First set of association expressions (fitting X4 ≤ preset threshold):

[0048] Second set of association expressions (adapting to X4 > preset threshold):

[0049] in , Each group has independent weights.

[0050] For example, when X4 ≤ 5.5, Y1=1.234+0.0145X1+0.278X2+15.678X3+0.031X5-0.0000035X1 2 +0.00134X2X3+0.000172X1X3+0.00212X2 2 -0.0000085X3X 5； When X4 > 5.5, Y2=2.123+0.0078X1+0.312X2+10.456X3+0.678X4+0.0178X5-0.0000022X1 2 +0.00086X2X3+0.000072X1X3+0.000032X1X4-0.000016X4X5+0.167X3X4+0.00042X2X4-0.0000035X1X5+0.00124X2 2 -0.00000085X3X1X4+0.00012X32 X4.

[0051] Step 5: Expression Validation Optimization Error calculation: Compare the calculated value of the initial correlation expression (or grouped Y1, Y2) with the corresponding actual test value Y, and calculate the relative error:

[0052] Accuracy verification: If the relative error exceeds the preset accuracy range (e.g., 5%), adjust the regression analysis method (e.g., change the combination of nonlinear terms) or the weight of the parameter terms, and repeat the regression optimization process in step 4. Output results: Until the relative error meets the accuracy requirements, the verified and optimized correlation expression (single or two groups) is obtained.

[0053] Step 6: Fuel consumption prediction for the new model of the same car Parameter Acquisition: Obtain vehicle parameters (X1~X5) for the new models of the same car model. Grouping judgment (if grouped): Compare the new X4 of the same model with the preset threshold to determine its data group (first group or second group). Predictive calculation: Substitute the new models X1~X5 of the same vehicle type into the "verified and optimized correlation expression" of the corresponding group to calculate the predicted fuel consumption value of the new models of the same vehicle type.

[0054] Secondly, embodiments of this application also provide a fuel consumption prediction device based on vehicle parameters. The device includes: a parameter association construction module, used to establish a correspondence between the actual fuel consumption test data and the vehicle parameters based on actual fuel consumption test data and the vehicle parameters corresponding to the test data; an association characteristic analysis module, used to perform correlation analysis on the correspondence to determine the association characteristics between each vehicle parameter and the actual fuel consumption test results; and an association relationship optimization module, used to optimize the association relationship between the vehicle parameters and the actual fuel consumption test results using regression analysis based on the association characteristics, to obtain an association relationship expression for predicting fuel consumption.

[0055] The functions of each module in the above-mentioned fuel consumption prediction device based on vehicle parameters correspond to the steps in the above-mentioned fuel consumption prediction method embodiment based on vehicle parameters, and their functions and implementation processes will not be described in detail here.

[0056] Thirdly, embodiments of this application provide a fuel consumption prediction device based on vehicle parameters. The fuel consumption prediction device based on vehicle parameters can be a personal computer (PC), a laptop computer, a server, or other device with data processing capabilities.

[0057] Reference Figure 2 , Figure 2 This is a schematic diagram of the hardware structure of a fuel consumption prediction device based on vehicle parameters involved in an embodiment of this application. In this embodiment, the fuel consumption prediction device based on vehicle parameters may include a processor, a memory, a communication interface, and a communication bus.

[0058] The communication bus can be of any type and is used to interconnect the processor, memory, and communication interface.

[0059] The communication interface includes input / output (I / O) interfaces, physical interfaces, and logical interfaces used for interconnecting internal components of the vehicle parameter-based fuel consumption prediction device, as well as interfaces used for interconnecting the device with other devices (such as other computing devices or user equipment). Physical interfaces can be Ethernet interfaces, fiber optic interfaces, ATM interfaces, etc.; user equipment can be displays, keyboards, etc.

[0060] Memory can be various types of storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile RAM (NVRAM), flash memory, optical storage, hard disk, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), etc.

[0061] The processor can be a general-purpose processor, which can call a fuel consumption prediction program based on vehicle parameters stored in memory and execute the fuel consumption prediction method based on vehicle parameters provided in the embodiments of this application. For example, the general-purpose processor can be a central processing unit (CPU). The method executed when the fuel consumption prediction program based on vehicle parameters is called can be referred to in the various embodiments of the fuel consumption prediction method based on vehicle parameters of this application, and will not be repeated here.

[0062] Those skilled in the art will understand that Figure 2 The hardware structure shown does not constitute a limitation of this application and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0063] Fourthly, embodiments of this application also provide a readable storage medium.

[0064] This application has a readable storage medium storing a fuel consumption prediction program based on vehicle parameters, wherein when the fuel consumption prediction program based on vehicle parameters is executed by a processor, it implements the steps of the fuel consumption prediction method based on vehicle parameters as described above.

[0065] The method implemented when the fuel consumption prediction program based on vehicle parameters is executed can be referred to in various embodiments of the fuel consumption prediction method based on vehicle parameters in this application, and will not be repeated here.

[0066] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0067] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0068] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0069] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0070] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0071] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0072] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for predicting fuel consumption based on vehicle parameters, characterized in that, The method for predicting fuel consumption based on vehicle parameters includes: Based on the actual test data of vehicle fuel consumption and the vehicle parameters corresponding to the test data, establish the correspondence between the actual test data of fuel consumption and the vehicle parameters; Correlation analysis was performed on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption. Based on the aforementioned correlation characteristics, regression analysis is used to optimize the correlation between vehicle parameters and actual fuel consumption test results, resulting in a correlation expression for predicting fuel consumption.

2. The fuel consumption prediction method based on vehicle parameters as described in claim 1, characterized in that, The correlation analysis performed on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual fuel consumption test results includes: The Pearson correlation coefficient method is used to calculate the correlation coefficient between each vehicle parameter and the actual test results of fuel consumption. The absolute value of the correlation coefficient represents the correlation strength, and the positive or negative value of the correlation coefficient represents the correlation direction, thereby clarifying the correlation influence characteristics of each vehicle parameter on fuel consumption.

3. The fuel consumption prediction method based on vehicle parameters as described in claim 1, characterized in that, Based on the aforementioned correlation characteristics, regression analysis is used to optimize the correlation between vehicle parameters and actual fuel consumption test results, resulting in a correlation expression for predicting fuel consumption, including: First, a preliminary correlation between a single vehicle parameter and fuel consumption is established through linear regression. Then, multiple linear regression is used to extend the correlation to multiple vehicle parameters. Finally, nonlinear regression is used to add square and interaction terms to adapt to the nonlinear correlation characteristics. The weights of the parameter terms are gradually adjusted to improve the fitting accuracy of the correlation to the actual test results of fuel consumption, thereby obtaining the correlation expression used to predict fuel consumption.

4. The fuel consumption prediction method based on vehicle parameters as described in claim 1, characterized in that, Based on the aforementioned correlation characteristics, regression analysis is used to optimize the correlation between vehicle parameters and actual fuel consumption test results, resulting in a correlation expression for predicting fuel consumption, including: Based on a preset threshold of the maximum design mass of the vehicle, the actual test data of fuel consumption of heavy commercial vehicles and the corresponding vehicle parameters are divided into a first data group and a second data group. Then, for the first data group and the second data group, the correlation between vehicle parameters and fuel consumption within each group is combined with the correlation characteristics of each group. Regression analysis is used to optimize the correlation relationship of each group, resulting in the first group correlation relationship expression and the second group correlation relationship expression, which are used as correlation relationship expressions for predicting fuel consumption.

5. The fuel consumption prediction method based on vehicle parameters as described in claim 1, characterized in that, After optimizing the correlation between vehicle parameters and actual fuel consumption test results using regression analysis based on the aforementioned correlation characteristics to obtain a correlation expression for predicting fuel consumption, the method further includes: The calculation result of the correlation expression is compared with the actual fuel consumption measurement data to calculate the relative error between the calculated value of the expression and the actual measurement value. If the relative error exceeds the preset accuracy range, the application method of the regression analysis method or the weight of the parameter items in the correlation relationship is adjusted, and the correlation relationship between vehicle parameters and fuel consumption is re-optimized until the relative error of the expression calculation result meets the accuracy requirements, and the verified and optimized correlation relationship expression is obtained.

6. The fuel consumption prediction method based on vehicle parameters as described in claim 5, characterized in that, It also includes the following steps: Obtain vehicle parameters for different models of the same vehicle type, substitute these parameters into the verified and optimized correlation expression, and calculate the predicted fuel consumption values ​​for the different models of the same vehicle type.

7. The fuel consumption prediction method based on vehicle parameters as described in claim 1, characterized in that, The vehicle parameters include a constant term for the vehicle's coasting resistance coefficient, a first-order term for the vehicle's coasting resistance coefficient, a second-order term for the vehicle's coasting resistance coefficient, the vehicle's maximum design mass, and the engine's rated power.

8. A fuel consumption prediction device based on vehicle parameters, characterized in that, The fuel consumption prediction device based on vehicle parameters includes: The parameter association construction module is used to establish the correspondence between the actual fuel consumption test data and the vehicle parameters based on the actual fuel consumption test data of the vehicle and the vehicle parameters corresponding to the test data. The correlation characteristic analysis module is used to perform correlation analysis on the correspondence to determine the correlation characteristics between each vehicle parameter and the actual test results of fuel consumption. The correlation optimization module is used to optimize the correlation between vehicle parameters and actual fuel consumption test results based on the correlation characteristics using regression analysis methods, so as to obtain a correlation expression for predicting fuel consumption.

9. A fuel consumption prediction device based on vehicle parameters, characterized in that, The vehicle parameter-based fuel consumption prediction device includes a processor, a memory, and a vehicle parameter-based fuel consumption prediction program stored in the memory and executable by the processor, wherein when the vehicle parameter-based fuel consumption prediction program is executed by the processor, it implements the steps of the vehicle parameter-based fuel consumption prediction method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a fuel consumption prediction program based on vehicle parameters, wherein when the fuel consumption prediction program based on vehicle parameters is executed by a processor, it implements the steps of the fuel consumption prediction method based on vehicle parameters as described in any one of claims 1-7.

Images