Test method, device and host computer for predicting energy consumption performance of extended-range hybrid vehicles

Abstract

The present invention relates to the field of vehicle technology, and more particularly to a test method, device, and host computer for predicting the energy consumption performance of an extended-range hybrid vehicle. The method comprises: identifying operating condition information for multiple road sections in navigation information; predicting the energy consumption of the multiple road sections based on the operating condition information; generating torque control instructions based on the energy consumption of the multiple road sections and operating information of a vehicle model of the extended-range hybrid vehicle; using the torque control instructions to control a target test bench to conduct a simulation experiment, wherein a driver model and vehicle model on the target test bench respond to the torque control instructions and simulate driving on the multiple road sections; and generating energy consumption performance prediction results for the extended-range hybrid vehicle based on the simulation experiment data. This method solves the problem that the existing technology has low accuracy in energy consumption prediction, which in turn affects vehicle energy management.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a test method, device and host computer for predicting energy consumption performance of an extended-range hybrid vehicle. Background Art

[0002] With the development of intelligent transportation systems, automakers are constantly exploring how to more effectively manage the energy use of new energy vehicles, particularly extended-range hybrid vehicles (R-EHVs). These vehicles combine a battery-driven electric motor with a small internal combustion engine (i.e., a range extender) to extend pure electric driving range and reduce emissions. However, energy management for R-EHVs faces numerous challenges. Predicting vehicle energy consumption in advance is crucial for energy management. This ensures sufficient charge for pure electric driving when needed most, while also utilizing the internal combustion engine to supplement energy under appropriate conditions, thereby maximizing overall energy efficiency. Accurate energy consumption prediction can also help avoid premature or excessive activation of the R-EHV, reducing unnecessary fuel consumption and emissions.

[0003] Existing technologies mainly use static or semi-static methods to predict energy consumption, that is, calculating energy consumption under different driving conditions based on historical data or theoretical formulas. However, this method is difficult to accurately reflect the complex situations during actual driving, resulting in low prediction accuracy and subsequent impact on vehicle energy management. Summary of the Invention

[0004] The present invention provides a method, device and host computer for testing the energy consumption performance of an extended-range hybrid vehicle, so as to solve the problem that the energy consumption prediction accuracy of the existing technology is low, which in turn affects the energy management of the vehicle.

[0005] An embodiment of the first aspect of the present invention provides a test method for predicting the energy consumption performance of an extended-range hybrid vehicle, comprising the following steps: identifying operating condition information of multiple road sections in navigation information; predicting the energy consumption of the multiple road sections based on the operating condition information of the multiple road sections; generating torque control instructions based on the energy consumption of the multiple road sections and operating information of a vehicle model of the extended-range hybrid vehicle, and using the torque control instructions to control a target test bench to perform a simulation experiment, wherein a driver model and a vehicle model on the target test bench respond to the torque control instructions and simulate driving on multiple road sections; and generating energy consumption performance prediction results of the extended-range hybrid vehicle based on the data of the simulation experiment.

[0006] Optionally, the multiple road sections include current sections and future sections, and the energy consumption of the multiple road sections is predicted based on the working condition information of the multiple road sections, including: inputting the working condition information of the future road sections into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future road sections.

[0007] Optionally, before predicting the energy consumption of multiple road sections based on the operating condition information of multiple road sections, it also includes: if the current road section is a congested road section, the vehicle model of the extended-range hybrid vehicle travels in pure electric mode; if the current road section is a smooth road section, the energy consumption of future road sections is predicted based on the operating condition information of multiple road sections.

[0008] Optionally, a torque control instruction is generated based on the energy consumption of multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle, including: adjusting the SOC (State of Charge) balance point of the vehicle model of the extended-range hybrid vehicle according to the energy consumption of the future road section; adjusting the operating state of the range extender based on the adjusted SOC balance point and the operating information; and generating the torque control instruction based on the adjusted SOC balance point and the operating state of the range extender.

[0009] Optionally, adjusting the SOC balance point of the vehicle model of the extended-range hybrid vehicle based on the energy consumption of multiple road sections includes: determining an unobstructed road section in the future road section that is closest to the current road section as a target road section; and predicting the charging energy consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section, wherein the calculation formula for the charging energy consumption is: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ The predicted energy consumption of each road section after the target road section; the target incremental SOC of the battery power of the extended-range hybrid vehicle is calculated based on the supplementary power consumption, the battery self-discharge efficiency and the total energy of the extended-range hybrid vehicle, and the SOC balance point of the vehicle model of the extended-range hybrid vehicle is adjusted based on the target incremental SOC.

[0010] Optionally, the operating information includes at least one of a current SOC and a current vehicle speed, and adjusting the operating state of the range extender based on the adjusted SOC balance point and the operating information includes: calculating a difference between the current SOC and the adjusted SOC balance point, and selecting a power generation power of the range extender on a target operating curve of the range extender based on the difference and the current vehicle speed; and determining a power generation timing of the range extender based on the power generation power, the current SOC and the adjusted SOC balance point.

[0011] A second aspect of the present invention provides a test device for predicting the energy consumption performance of an extended-range hybrid vehicle, comprising: an identification module for identifying operating condition information of multiple road sections in navigation information; a prediction module for predicting the energy consumption of multiple road sections based on the operating condition information of the multiple road sections; a first generation module for generating torque control instructions based on the energy consumption of the multiple road sections and operating information of a vehicle model of the extended-range hybrid vehicle, and using the torque control instructions to control a target test bench to perform a simulation experiment, wherein a driver model and a vehicle model on the target test bench respond to the torque control instructions to simulate driving on multiple road sections; and a second generation module for generating energy consumption performance prediction results of the extended-range hybrid vehicle based on data from the simulation experiment.

[0012] Optionally, the multiple road sections include a current road section and a future road section, and the prediction module is further used to: input the working condition information of the future road section into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future road section.

[0013] Optionally, it also includes: a judgment module, which is used to, before predicting the energy consumption of multiple road sections based on the operating condition information of multiple road sections, if the current road section is a congested road section, then the vehicle model of the extended-range hybrid vehicle travels in pure electric mode; if the current road section is a smooth road section, then predicting the energy consumption of future road sections based on the operating condition information of multiple road sections.

[0014] Optionally, the first generation module is further used to: adjust the SOC balance point of the vehicle model of the extended-range hybrid vehicle according to the energy consumption of the future road section; adjust the working state of the range extender based on the adjusted SOC balance point and operating information; and generate a torque control instruction based on the adjusted SOC balance point and the working state of the range extender.

[0015] Optionally, the first generation module is further configured to: determine a target road section as a clear road section in the future road section that is closest to the current road section; and predict the charging energy consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section, wherein the charging energy consumption is calculated as follows: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ The predicted energy consumption of each road section after the target road section; the target incremental SOC of the battery power of the extended-range hybrid vehicle is calculated based on the supplementary power consumption, the battery self-discharge efficiency and the total energy of the extended-range hybrid vehicle, and the SOC balance point of the vehicle model of the extended-range hybrid vehicle is adjusted based on the target incremental SOC.

[0016] Optionally, the operating information includes at least one of a current SOC and a current vehicle speed, and the first generating module is further used to: calculate a difference between the current SOC and an adjusted SOC balance point, and select a power generation power of the range extender on a target operating curve of the range extender based on the difference and the current vehicle speed; and determine a power generation timing of the range extender based on the power generation power, the current SOC and the adjusted SOC balance point.

[0017] A third aspect of the present invention provides a host computer, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to perform a test method for predicting energy consumption performance of an extended-range hybrid vehicle as described in the above embodiment.

[0018] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program or instruction stored thereon, which is executed by a processor to perform a test method for predicting energy consumption performance of an extended-range hybrid vehicle as described in the above embodiment.

[0019] A fifth aspect of the present invention provides a computer program product, including a computer program or instructions. When the computer program or instructions are executed, the method for testing the predicted energy consumption performance of an extended-range hybrid vehicle as described in the above embodiment is implemented.

[0020] Therefore, the present invention has at least the following beneficial effects:

[0021] The embodiment of the present invention can predict the energy consumption of multiple road sections based on the operating condition information of multiple road sections in the navigation information, and generate torque control instructions based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle. The torque control instructions are used to control the target test bench to perform simulation experiments, and then generate energy consumption performance prediction results of the extended-range hybrid vehicle based on the simulation experiment data, thereby achieving a prediction of the vehicle's energy consumption performance. The target test bench is used to simulate the real driving environment, improving the accuracy of the simulation experiment, eliminating the need for actual vehicle testing, and reducing the cost and risk of actual vehicle testing. By simulating various driving situations, the dependence on actual vehicles is reduced, reducing testing costs and potential safety risks, and thus improving the accuracy of energy management optimization. This solves the technical problems of the existing technology such as the low accuracy of energy consumption prediction, which in turn affects the energy management of the vehicle.

[0022] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 A flowchart of a method for predicting energy consumption performance of an extended-range hybrid vehicle according to an embodiment of the present invention;

[0025] Figure 2 The training process of the neural network energy consumption prediction model provided by the embodiment of the present invention;

[0026] Figure 3 A schematic diagram of a prediction of a neural network energy consumption model provided according to an embodiment of the present invention;

[0027] Figure 4 A structural diagram of a test system for predicting energy consumption performance of an extended-range hybrid vehicle provided in an embodiment of the present invention;

[0028] Figure 5 A flowchart of an energy management optimization strategy provided according to an embodiment of the present invention;

[0029] Figure 6 This is an example diagram of a test device for predicting energy consumption performance of an extended-range hybrid vehicle according to an embodiment of the present invention;

[0030] Figure 7 The figure is a schematic diagram of the structure of a host computer according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0032] The following describes a method, device, and host computer for predicting energy consumption performance of an extended-range hybrid vehicle according to an embodiment of the present invention with reference to the accompanying drawings. In response to the prior art mentioned in the background art, which primarily predicts energy consumption using a static or semi-static approach, namely, calculating energy consumption under different driving conditions based on historical data or theoretical formulas, this method struggles to accurately reflect the complexities of actual driving, resulting in low prediction accuracy and, in turn, impacting vehicle energy management. The present invention provides a testing method for predicting the energy consumption performance of an extended-range hybrid vehicle. In this method, energy consumption for multiple road sections can be predicted based on operating condition information for the multiple road sections in navigation information. Torque control commands are generated based on the energy consumption of the multiple road sections and operating information of a vehicle model of the extended-range hybrid vehicle. The torque control commands are used to control a target test bench for simulation experiments. Based on the simulation experiment data, prediction results for the energy consumption performance of the extended-range hybrid vehicle are generated, thereby achieving a prediction of the vehicle's energy consumption performance. Furthermore, the target test bench is used to simulate a real driving environment, improving the accuracy of the simulation experiments. This eliminates the need for actual vehicle testing, reducing the cost and risk of actual vehicle testing. By simulating various driving conditions, reliance on actual vehicles is reduced, reducing testing costs and potential safety risks, and thereby improving the accuracy of energy management optimization. This solves the problem that the existing technology has low accuracy in energy consumption prediction, which in turn affects the energy management of the vehicle.

[0033] Specifically, Figure 1 A flow chart of a method for predicting energy consumption performance of an extended-range hybrid vehicle provided by an embodiment of the present invention.

[0034] like Figure 1 As shown, the test method for predicting the energy consumption performance of the extended-range hybrid vehicle includes the following steps:

[0035] In step S101 , operating condition information of a plurality of road sections in navigation information is identified.

[0036] Among them, the multiple road sections include current road sections and future road sections; the working condition information includes road section congestion information, average road section speed, road section length, etc.

[0037] In step S102 , energy consumption of the multiple road sections is predicted based on the operating condition information of the multiple road sections.

[0038] It is understandable that the embodiment of the present invention can predict the energy consumption of multiple road sections based on the working condition information of multiple road conditions. The specific prediction method is as follows.

[0039] In an embodiment of the present invention, the energy consumption of multiple road sections is predicted based on the working condition information of the multiple road sections, including: inputting the working condition information of the future road sections into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future road sections.

[0040] It is understandable that the embodiment of the present invention can input the working condition information of the future road section into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future time period.

[0041] It should be noted that the neural network energy consumption prediction model is an existing technology. Before using the neural network energy consumption prediction model to output the predicted energy consumption in the future period, the neural network energy consumption prediction model needs to be trained through the historical information collected by the actual vehicle. The training process is as follows: Figure 2 As shown in the figure, the number of input layer nodes is set to 3, and the input is the road congestion situation, the average speed of the road section, and the length of the road section; the hidden layer is set to two layers, each with 25 nodes; the number of output layer nodes is 1, and the output is energy consumption. Among them, the training function uses the trainlm function, and the normalization function uses the mapminmax function. The process of online prediction of the neural network energy consumption prediction model is as follows Figure 3 As shown in the figure, when the energy consumption of each road section is predicted online, the trained model receives the map matrix information and predicts the energy consumption matrix information of the future road section, where v i represents the average speed of the i-th road section, s i Represents the distance of the i-th road segment, m i represents the congestion information of the i-th road section, E i Represents the predicted energy consumption information of the i-th road section.

[0042] In an embodiment of the present invention, before predicting the energy consumption of multiple road sections based on the operating condition information of multiple road sections, it also includes: if the current road section is a congested road section, the vehicle model of the extended-range hybrid vehicle travels in pure electric mode; if the current road section is a smooth road section, the energy consumption of future road sections is predicted based on the operating condition information of multiple road sections.

[0043] It will be appreciated that, before predicting the energy consumption of multiple road sections based on the operating condition information of the multiple road sections, embodiments of the present invention may first determine whether the current road section is congested. If the current road section is congested, since congested urban roads often involve frequent starts and stops and low-speed driving, the internal combustion engine (i.e., the range extender) has low operating efficiency, poor fuel economy, and high emissions. Therefore, the range-extended hybrid vehicle can be directly driven in pure electric mode. This prevents the internal combustion engine from operating under adverse conditions, thereby reducing fuel consumption and pollutant emissions, while providing a quieter and smoother driving experience. Furthermore, the battery electric drive system is more efficient at low speeds and is therefore more suitable for navigating traffic congestion. If the current road section is unobstructed, that is, when road conditions are good and the vehicle can maintain a high average speed, the internal combustion engine can operate in a more efficient operating range. Therefore, navigation information is used to predict the energy consumption of future road sections, so as to help determine the optimal time to start charging the range extender and ensure sufficient power to support continued pure electric mode driving in possible congested sections.

[0044] In step S103, a torque control instruction is generated based on the energy consumption of multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle. The torque control instruction is used to control a target test bench to perform a simulation experiment, wherein the driver model and vehicle model on the target test bench respond to the torque control instruction and simulate driving on multiple road sections.

[0045] The operating information includes dynamic response information such as the current SOC of the battery and the current vehicle speed; the target test bench may be a HIL (Hardware-in-the-Loop) test bench.

[0046] It can be understood that the embodiment of the present invention can generate torque control instructions based on the energy consumption of multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle, and use the torque control instructions to control the target test bench to perform simulation experiments and simulate driving on multiple road sections.

[0047] In an embodiment of the present invention, generating a torque control command based on energy consumption of multiple road sections and operating information of a vehicle model of an extended-range hybrid vehicle includes: adjusting the SOC balance point of the vehicle model of the extended-range hybrid vehicle based on the energy consumption of a future road section; adjusting the operating state of the range extender based on the adjusted SOC balance point and the operating information; and generating the torque control command based on the adjusted SOC balance point and the operating state of the range extender.

[0048] The operating status of the range extender includes the power generation capacity and the timing of power generation of the range extender.

[0049] It can be understood that the embodiments of the present invention can adjust the SOC balance point according to the energy consumption of the future road section, and adjust the operating state of the range extender based on the adjusted balance point and the operating information of the extended-range hybrid vehicle, and then generate a torque control instruction based on the adjusted SOC balance point and the operating state of the range extender to ensure that the vehicle maintains optimal energy consumption efficiency throughout the entire driving process.

[0050] In an embodiment of the present invention, the SOC balance point of a vehicle model of an extended-range hybrid vehicle is adjusted according to the energy consumption of multiple road sections, including: determining an unobstructed road section in a future road section that is closest to a current road section as a target road section; predicting the supplementary power consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section; calculating a target incremental SOC of the battery power of the extended-range hybrid vehicle based on the supplementary power consumption, the battery self-discharge efficiency and the total energy of the extended-range hybrid vehicle, and adjusting the SOC balance point of the vehicle model of the extended-range hybrid vehicle based on the target incremental SOC.

[0051] The future road section includes at least one road section.

[0052] It can be understood that the embodiment of the present invention can determine the unobstructed section in the future section that is closest to the current section as the target section, and then predict the charging energy consumption of the future congested section based on the predicted energy consumption of each section in the future section and the target section, calculate the target incremental SOC of the battery power of the extended-range hybrid vehicle based on the charging energy consumption, the battery self-discharge efficiency and total energy of the extended-range hybrid vehicle, and adjust the SOC balance point of the vehicle model of the extended-range hybrid vehicle based on the target incremental SOC.

[0053] The calculation formula for supplementary power consumption is: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ Predicted energy consumption for each road segment after the target road segment.

[0054] It should be noted that section k is the unobstructed section closest to the current section. The purpose of the embodiment of the present invention is to ensure that the vehicle can travel in pure electric mode on congested sections. Therefore, only the energy consumption required for the short section and the section after section k needs to be considered.

[0055] Specifically, the process of dynamically adjusting the SOC balance point is:

[0056] First, mark the unobstructed road section closest to the current road section as the k road section (i.e. the target road section), and make an estimated replenishment energy consumption prediction based on the k road section. , the specific algorithm is as follows:

[0057] ;

[0058] is the penalty coefficient, The size of depends on the ratio of the number of smooth sections in the subsequent sections of section k to the total number of subsequent sections. , specifically, The expression is as follows:

[0059] ;

[0060] If all subsequent sections are clear sections, =1, at this time , that is, at this time, the prediction of future power replenishment demand energy consumption only considers the congested sections before section k; if all subsequent sections are congested sections, that is ,at this time =0.5, at this time, the power replenishment demand of the current section should not only meet the energy consumption of the congested section in front of section k, but also appropriately supplement a part of the energy consumption of the congested section behind section k, to prevent the actual power replenishment of section k from failing to meet the power replenishment demand of subsequent congested road conditions.

[0061] Secondly, after obtaining the energy consumption required for replenishment of electricity in the future congested road section, the energy consumption is converted into battery power (Target incremental SOC):

[0062] ;

[0063] in, is the battery discharge efficiency, is the total energy of the battery.

[0064] The calculation formula for dynamically adjusting the SOC balance point is as follows:

[0065] ;

[0066] in, The original SOC balance point is the preset original SOC balance point. The original SOC balance point is based on the default or user-defined power conservation threshold value of the test calibration. is the adjusted SOC balance point.

[0067] In addition, the SOC balance point will be adjusted according to driving conditions, driving mode, user needs and environmental factors, and the adjusted SOC balance point in the embodiment of the present invention takes into account the energy consumption requirements of future road sections and is optimized based on the energy management strategy.

[0068] In an embodiment of the present invention, adjusting the operating state of the range extender based on the adjusted SOC balance point and the operating information includes: calculating the difference between the current SOC and the adjusted SOC balance point, and selecting the power generation power of the range extender on the target operating curve of the range extender based on the difference and the current vehicle speed; and determining the power generation timing of the range extender based on the power generation power, the current SOC, and the adjusted SOC balance point.

[0069] The target operating curve is a preset optimal operating curve of the range extender; the operating state of the range extender includes the power generation and the power generation timing.

[0070] It is understood that the embodiment of the present invention can calculate the difference between the current SOC and the adjusted SOC balance point, and select the power generation of the range extender on the target operating curve of the range extender based on the difference and the current vehicle speed; and determine the power generation timing of the range extender based on the power generation, the current SOC and the adjusted SOC balance point. Specifically, the process of adjusting the operating state of the range extender is as follows:

[0071] Calculate the balance point between current SOC and adjusted SOC ( ) :

[0072] ;

[0073] Combined with the difference between the current SOC and the adjusted balance point and the current vehicle speed, the charging power is selected on the preset optimal working curve of the range extender. (Also known as power generation), where the power generation can be directly obtained by querying a pre-calibrated table. A three-dimensional table is constructed based on the required power, current vehicle speed, and SOC deviation to jointly determine the power generation (it is also possible to query a two-dimensional table without considering the required power of the entire vehicle). , is the power demand of the vehicle at the current moment.

[0074] At the same time, the selection of power generation timing should satisfy the following formula:

[0075] ;

[0076] in, t is the estimated time to pass the current road section, is the charging power, is the total energy of the battery, For the replenishment power.

[0077] In other words, the time required to replenish the battery to the adjusted SOC balance point is calculated as ,

[0078] ;

[0079] The estimated passing time of the current road section can be expressed as:

[0080] ;

[0081] in, is the total length of the current road section, is the average speed of the current road section, The time spent traveling on the current road segment.

[0082] In order to ensure sufficient battery power when entering congested sections and cope with random changes in future working conditions, a charging buffer time is defined. , generally, The value range of is (5, 10). As the map information is dynamically updated, when the following formula is satisfied, the range extender performs a charging operation. When the following formula is not satisfied, it searches for the next unobstructed road section for a charging operation.

[0083] .

[0084] In step S104 , an energy consumption performance prediction result of the extended-range hybrid vehicle is generated based on the data of the simulation experiment.

[0085] It can be understood that the embodiments of the present invention can generate energy consumption performance prediction results of extended-range hybrid vehicles based on the data of simulation experiments, realize the prediction of vehicle energy consumption performance, and use the HIL test bench to simulate the real driving environment. The neural network energy consumption prediction model is used to predict the vehicle energy consumption status in real time and with high precision, thereby improving the accuracy of simulation experiments, reducing the cost and risk of actual vehicle testing, and reducing dependence on actual vehicles by simulating various driving conditions, thereby reducing testing costs and potential safety risks.

[0086] It should be noted that the test method for predicting energy consumption performance of an extended-range hybrid vehicle of the present invention is carried out on a test system. The specific structure of the overall test system is as follows: Figure 4 As shown, the system comprises a vehicle navigation system, a vehicle control unit (VCU), a HIL test bench, and a host computer. Generally speaking, the vehicle navigation system sends map information to the VCU. This map information includes congestion information for the current road segment and N upcoming road segments, average vehicle speed, and segment length, and is dynamically updated with a step size of ∆t. The HIL test bench simulates driver behavior and vehicle dynamic response, including battery SOC, speed, power demand, and engine torque. Based on the map information and vehicle dynamic information provided by the HIL test bench, the VCU calculates the dynamic SOC equilibrium point and selects the range extender operating point for torque control. This system significantly improves the accuracy of simulation experiments while also reducing the risks and costs associated with real-world road data acquisition experiments.

[0087] The method for testing the predicted energy consumption performance of a range-extended hybrid vehicle according to an embodiment of the present invention specifically includes the following steps:

[0088] S1: Obtain the working condition information of the next N road sections through navigation information (such as the AutoNavi API (Application Programming Interface)): road congestion, average speed, road distance, etc.

[0089] S2: Build an intelligent energy management model, including offline training of BP (Back Propagation Neural Network) neural network and online application for energy consumption prediction.

[0090] S3: Build a complete driver model and vehicle model on the HIL bench.

[0091] The driver model is designed to mimic real-world driver behavior, including reaction time and acceleration / deceleration pedal openings. The vehicle model includes dynamics, electric drive system, battery management system, braking system, tire, aerodynamic, and thermal management models. Data signals interact based on energy transfer between these models, simulating the various characteristics of a real vehicle.

[0092] S4: Energy consumption prediction and dynamic adjustment.

[0093] The operating condition matrix in S1 is fed into S2's BP neural network. The neural network outputs a predicted energy consumption matrix, which is fed into the energy management module to adjust the dynamic SOC balance point and the range extender's operating state. S2 sends torque control commands to the vehicle model in S3 for control. Simultaneously, S3 provides real-time feedback on vehicle dynamics to S2's intelligent energy management system. Through HIL bench simulation, the optimized results of vehicle energy consumption are more accurately reflected.

[0094] Specifically, the specific process of the energy management optimization strategy of the embodiment of the present invention is as follows: Figure 5 As shown, including:

[0095] Receive online map information and determine whether the current road section is congested. If it is a congested section, maintain pure electric mode; if it is an unobstructed section, enter the smart range-extended mode to calculate the dynamic SOC balance point and determine the working status of the range extender.

[0096] First, mark the unobstructed road section closest to the current road section as section k, and make an estimated power consumption prediction based on section k. , the specific algorithm is as follows:

[0097] ;

[0098] is the penalty coefficient, The size of depends on the ratio of the number of smooth sections in the subsequent sections of section k to the total number of subsequent sections. , specifically, The expression is as follows:

[0099] ;

[0100] If all subsequent sections are clear sections, =1, at this time , that is, at this time, the prediction of future power replenishment demand energy consumption only considers the congested sections before section k; if all subsequent sections are congested sections, that is ,at this time =0.5, at this time, the power replenishment demand of the current section should not only meet the energy consumption of the congested section in front of section k, but also appropriately supplement a part of the energy consumption of the congested section behind section k, to prevent the actual power replenishment of section k from failing to meet the power replenishment demand of subsequent congested road conditions.

[0101] Secondly, after obtaining the energy consumption required for replenishment of electricity in the future congested road section, the energy consumption is converted into battery power :

[0102] ;

[0103] in, is the battery discharge efficiency, is the total energy of the battery.

[0104] The calculation formula for dynamically adjusting the SOC balance point is as follows:

[0105] ;

[0106] in, It is the preset original SOC balance point.

[0107] Calculate the difference between SOC and SOC balance point :

[0108] ;

[0109] Combined with the difference between the current SOC and the balance point and the current vehicle speed, the charging efficiency is selected on the preset optimal working curve of the range extender. At the same time, the selection of power generation timing should satisfy the following formula:

[0110] ;

[0111] in, t is the estimated time to pass the current road section, is the charging power.

[0112] As map information is continuously updated, the present invention can dynamically acquire map information and adjust and optimize the SOC balance point on the HIL test bench. On the premise that the remaining SOC does not meet the remaining mileage of pure electric driving and ensures the NVH of the vehicle, the SOC balance point can be dynamically changed, and the range extender's high-efficiency area can be used for charging in unobstructed sections of the road, and pure electric driving can be achieved in congested low-speed sections, so as to achieve the effect of energy conservation and emission reduction, and realize dynamic regulation of the range extender's working timing and working time to achieve the effect of optimizing energy consumption.

[0113] According to the test method for predicting the energy consumption performance of an extended-range hybrid vehicle proposed in an embodiment of the present invention, the energy consumption of multiple road sections can be predicted based on the operating condition information of the multiple road sections in the navigation information, and torque control instructions can be generated based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle. The torque control instructions are used to control the target test bench to perform a simulation experiment, and then the energy consumption performance prediction results of the extended-range hybrid vehicle are generated based on the data of the simulation experiment, thereby realizing the prediction of the vehicle's energy consumption performance. The target test bench is used to simulate the real driving environment to improve the accuracy of the simulation experiment. There is no need for actual vehicle testing, which reduces the cost and risk of actual vehicle testing. By simulating various driving conditions, the dependence on the actual vehicle is reduced, the testing cost and potential safety risks are reduced, and the accuracy of energy management optimization can be improved.

[0114] Next, a test device for predicting energy consumption performance of an extended-range hybrid vehicle proposed in accordance with an embodiment of the present invention will be described with reference to the accompanying drawings.

[0115] Figure 6 It is a block diagram of a test device for predicting energy consumption performance of an extended-range hybrid vehicle according to an embodiment of the present invention.

[0116] like Figure 6 As shown, the test device 10 for predicting the energy consumption performance of an extended-range hybrid vehicle includes: an identification module 100 , a prediction module 200 , a first generation module 300 and a second generation module 400 .

[0117] Among them, the identification module 100 is used to identify the working condition information of multiple road sections in the navigation information; the prediction module 200 is used to predict the energy consumption of multiple road sections based on the working condition information of multiple road sections; the first generation module 300 is used to generate torque control instructions based on the energy consumption of multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle, and use the torque control instructions to control the target test bench to perform simulation experiments, wherein the driver model and vehicle model on the target test bench respond to the torque control instructions and simulate driving on multiple road sections; the second generation module 400 is used to generate energy consumption performance prediction results of the extended-range hybrid vehicle based on the data of the simulation experiment

[0118] In an embodiment of the present invention, the multiple road sections include the current road section and the future road section, and the prediction module 200 is further used to: input the working condition information of the future road section into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future road section.

[0119] In the embodiment of the present invention, the test device 10 for predicting energy consumption performance of an extended-range hybrid vehicle according to the embodiment of the present invention further includes: a judgment module.

[0120] Among them, the judgment module is used to predict the energy consumption of multiple road sections based on the operating condition information of multiple road sections. If the current road section is a congested road section, the vehicle model of the extended-range hybrid vehicle travels in pure electric mode; if the current road section is a smooth road section, the energy consumption of future road sections is predicted based on the operating condition information of multiple road sections.

[0121] In an embodiment of the present invention, the first generation module 300 is further used to: adjust the SOC balance point of the vehicle model of the extended-range hybrid vehicle according to the energy consumption of the future road section; adjust the operating state of the range extender based on the adjusted SOC balance point and operating information; and generate a torque control command based on the adjusted SOC balance point and the operating state of the range extender.

[0122] In this embodiment of the present invention, the first generation module 300 is further configured to: determine the unobstructed road section closest to the current road section in the future road section as the target road section; and predict the charging energy consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section, wherein the charging energy consumption is calculated as follows: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ The predicted energy consumption of each road section after the target road section; the target incremental SOC of the battery power of the extended-range hybrid vehicle is calculated based on the supplementary power consumption, the battery self-discharge efficiency and the total energy of the extended-range hybrid vehicle, and the SOC balance point of the vehicle model of the extended-range hybrid vehicle is adjusted based on the target incremental SOC.

[0123] In an embodiment of the present invention, the operating information includes at least one of a current SOC and a current vehicle speed. The first generating module 300 is further configured to: calculate a difference between the current SOC and an adjusted SOC balance point, and select a power generation power of the range extender on a target operating curve of the range extender based on the difference and the current vehicle speed; and determine a power generation timing of the range extender based on the power generation power, the current SOC, and the adjusted SOC balance point.

[0124] It should be noted that the above explanation of the embodiment of the test method for predicting the energy consumption performance of an extended-range hybrid vehicle is also applicable to the test device for predicting the energy consumption performance of an extended-range hybrid vehicle in this embodiment, and will not be repeated here.

[0125] According to the test device for predicting the energy consumption performance of an extended-range hybrid vehicle proposed in an embodiment of the present invention, the energy consumption of multiple sections can be predicted based on the operating condition information of the multiple sections in the navigation information, and torque control instructions can be generated based on the energy consumption of the multiple sections and the operating information of the vehicle model of the extended-range hybrid vehicle. The torque control instructions are used to control the target test bench to perform a simulation experiment, and then the energy consumption performance prediction result of the extended-range hybrid vehicle is generated based on the data of the simulation experiment, thereby realizing the prediction of the vehicle's energy consumption performance. The target test bench is used to simulate the real driving environment to improve the accuracy of the simulation experiment. There is no need for actual vehicle testing, which reduces the cost and risk of actual vehicle testing. By simulating various driving conditions, the dependence on the actual vehicle is reduced, the testing cost and potential safety risks are reduced, and the accuracy of energy management optimization can be improved.

[0126] Figure 7 A schematic diagram of the structure of the host computer provided in an embodiment of the present invention. The host computer may include:

[0127] A memory 701 , a processor 702 , and a computer program stored in the memory 701 and executable on the processor 702 .

[0128] When the processor 702 executes the program, the method for testing the predicted energy consumption performance of the extended-range hybrid vehicle provided in the above embodiment is implemented.

[0129] Furthermore, the host computer also includes:

[0130] The communication interface 703 is used for communication between the memory 701 and the processor 702 .

[0131] The memory 701 is used to store computer programs that can be run on the processor 702 .

[0132] The memory 701 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0133] If the memory 701, processor 702, and communication interface 703 are implemented independently, the communication interface 703, memory 701, and processor 702 can be interconnected via a bus to communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0134] Optionally, in a specific implementation, if the memory 701, the processor 702 and the communication interface 703 are integrated on a chip, the memory 701, the processor 702 and the communication interface 703 can communicate with each other through an internal interface.

[0135] The processor 702 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0136] An embodiment of the present invention further provides a computer-readable storage medium having a computer program or instruction stored thereon. When the computer program or instruction is executed by a processor, the above-mentioned test method for predicting energy consumption performance of an extended-range hybrid vehicle is implemented.

[0137] An embodiment of the present invention further provides a computer program product, including a computer program or instructions, which, when executed, implements the above-mentioned test method for predicting energy consumption performance of an extended-range hybrid vehicle.

[0138] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0139] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "N" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0140] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N executable instructions for implementing a custom logical function or step of a process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

[0141] It should be understood that various components of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0142] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A method for predicting energy consumption performance of an extended-range hybrid vehicle, characterized in that: The following steps are involved: Identify the working condition information of multiple road sections in the navigation information; Predicting energy consumption of the multiple road sections according to the operating condition information of the multiple road sections, wherein the multiple road sections include current road sections and future road sections; A torque control instruction is generated based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle, and the torque control instruction is used to control a target test bench to perform a simulation experiment, wherein the driver model and the vehicle model on the target test bench respond to the torque control instruction and simulate driving on the multiple road sections; the generating of the torque control instruction based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle includes: determining that the unobstructed road section closest to the current road section in the future road section is the target road section; and predicting the supplementary power energy consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section, wherein the calculation formula for the supplementary power energy consumption is: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ predicting energy consumption for each road section after the target road section; calculating a target incremental SOC of battery power of the extended-range hybrid vehicle based on the supplemental energy consumption, the battery self-discharge efficiency of the extended-range hybrid vehicle, and the total energy; and adjusting an SOC balance point of a vehicle model of the extended-range hybrid vehicle based on the target incremental SOC; adjusting an operating state of a range extender based on the adjusted SOC balance point and the operating information; and generating a torque control command based on the adjusted SOC balance point and the operating state of the range extender; The energy consumption performance prediction result of the extended-range hybrid vehicle is generated based on the data of the simulation experiment.

2. The method for predicting energy consumption performance of an extended-range hybrid vehicle according to claim 1, characterized in that: The predicting the energy consumption of the plurality of road sections according to the operating condition information of the plurality of road sections includes: The working condition information of the future road section is input into a pre-trained neural network energy consumption prediction model, and the neural network energy consumption prediction model outputs the energy consumption of the future road section.

3. The method for predicting energy consumption performance of an extended-range hybrid vehicle according to claim 2, characterized in that: Before predicting the energy consumption of the multiple road sections according to the operating condition information of the multiple road sections, the method further includes: If the current road section is a congested road section, the vehicle model of the extended-range hybrid vehicle travels in a pure electric mode; If the current road section is a smooth road section, the energy consumption of the future road section is predicted according to the working condition information of the multiple road sections.

4. The method for predicting energy consumption performance of an extended-range hybrid vehicle according to claim 1, characterized in that: The operating information includes at least one of a current SOC and a current vehicle speed, and adjusting the operating state of the range extender based on the adjusted SOC balance point and the operating information includes: calculating a difference between a current SOC and the adjusted SOC balance point, and selecting a power generation power of the range extender on a target operating curve of the range extender based on the difference and a current vehicle speed; A power generation timing of the range extender is determined based on the power generation power, the current SOC, and the adjusted SOC balance point.

5. A test device for predicting energy consumption performance of an extended-range hybrid vehicle, characterized in that: include: An identification module, used to identify working condition information of multiple road sections in navigation information; a prediction module, configured to predict energy consumption of the plurality of road sections according to the operating condition information of the plurality of road sections, wherein the plurality of road sections include a current road section and a future road section; The first generation module is configured to generate a torque control instruction based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle, and use the torque control instruction to control a target test bench to perform a simulation experiment, wherein the driver model and the vehicle model on the target test bench respond to the torque control instruction and simulate driving on the multiple road sections. The generation of the torque control instruction based on the energy consumption of the multiple road sections and the operating information of the vehicle model of the extended-range hybrid vehicle includes: determining that the unobstructed road section closest to the current road section in the future road section is the target road section; and predicting the supplementary power consumption of the extended-range hybrid vehicle based on the predicted energy consumption of each road section in the future road section and the target road section, wherein the calculation formula for the supplementary power consumption is: , To make up for the power consumption, For the target road section, is the penalty coefficient, is the total number of road sections, ~ is the predicted energy consumption of each section from the current section to the target section, ~ predicting energy consumption for each road section after the target road section; calculating a target incremental SOC of battery power of the extended-range hybrid vehicle based on the supplemental energy consumption, the battery self-discharge efficiency of the extended-range hybrid vehicle, and the total energy; and adjusting an SOC balance point of a vehicle model of the extended-range hybrid vehicle based on the target incremental SOC; adjusting an operating state of a range extender based on the adjusted SOC balance point and the operating information; and generating a torque control command based on the adjusted SOC balance point and the operating state of the range extender; The second generation module is used to generate the energy consumption performance prediction result of the extended-range hybrid vehicle based on the data of the simulation experiment.

6. A host computer, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for testing the energy consumption performance of an extended-range hybrid vehicle as described in any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the test method for predicting energy consumption performance of an extended-range hybrid vehicle as described in any one of claims 1 to 4.

8. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed, the method for testing the predicted energy consumption performance of an extended-range hybrid vehicle as described in any one of claims 1 to 4 is implemented.

Images