CN119669066B - Software and hardware decoupling simulation test system - Google Patents

Software and hardware decoupling simulation test system

Info

Publication number
CN119669066B
CN119669066B CN202411730164.XA CN202411730164A CN119669066B CN 119669066 B CN119669066 B CN 119669066B CN 202411730164 A CN202411730164 A CN 202411730164A CN 119669066 B CN119669066 B CN 119669066B
Authority
CN
China
Prior art keywords
simulation
vehicle
pid
module
control
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411730164.XA
Other languages
Chinese (zh)
Other versions
CN119669066A (en
Inventor
陈博谦
叶宇
周东凯
陈建勇
朱赛春
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangxi Xingwang Zhiyun Technology Co ltd
Original Assignee
Guangxi Xingwang Zhiyun Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangxi Xingwang Zhiyun Technology Co ltd filed Critical Guangxi Xingwang Zhiyun Technology Co ltd
Priority to CN202411730164.XA priority Critical patent/CN119669066B/en
Publication of CN119669066A publication Critical patent/CN119669066A/en
Application granted granted Critical
Publication of CN119669066B publication Critical patent/CN119669066B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Feedback Control In General (AREA)

Abstract

本发明公开了一种软硬件解耦仿真模拟测试系统，属于车辆仿真模拟测试技术领域，解决传统测试系统过度从理论角度考虑，往往会忽略运行过程中的实际情况的技术问题。系统包括：环境仿真模块，作为通过模拟仿真技术实现汽车虚拟研发的一体化工具与平台，将汽车行驶环境模型、车载环境传感模型与交通模型集于一体，提供了三维数字虚拟试验场景建模与编辑功能；车辆动力学仿真模块，提供车辆动力学仿真、场景构建、传感器构建、数据interface构建；评测指标与评测软件模块，用于接收环境仿真模块、车辆动力学仿真模块输出的结果，并输出报告。本发明着重模拟仿真实车工况、路况和情景来测试设计好的算法模型、软件、硬件，从而尽早发现问题，解决问题。

This invention discloses a hardware-software decoupled simulation testing system, belonging to the field of vehicle simulation testing technology. It addresses the problem that traditional testing systems, which often focus excessively on theoretical aspects and neglect actual operational conditions, suffer from limitations. The system includes: an environment simulation module, serving as an integrated tool and platform for virtual automotive R&D through simulation technology, integrating a vehicle driving environment model, an onboard environmental sensing model, and a traffic model, providing 3D digital virtual test scene modeling and editing functions; a vehicle dynamics simulation module, providing vehicle dynamics simulation, scene construction, sensor construction, and data interface construction; and an evaluation index and software module, used to receive the results from the environment simulation module and the vehicle dynamics simulation module and output reports. This invention emphasizes simulating real-world vehicle operating conditions, road conditions, and scenarios to test the designed algorithm models, software, and hardware, thereby identifying and resolving problems as early as possible.

Description

Software and hardware decoupling simulation test system
Technical Field
The invention relates to the technical field of vehicle simulation test, in particular to a software and hardware decoupling simulation test system.
Background
The related closed Loop test system is designed from three layers of MIL (Model in the Loop, model in ring)/SIL (software in the Loop, software in ring)/HiL (Hardware-in-the-Loop, hardware in ring) in the conventional whole vehicle and spare part laboratory verification system. Because the functional requirements of MIL/SIL/HIL are generally considered separately from the initial design, the independent MIL/SIL/HIL test systems are built, and the requirements of different layers of engineers (algorithm engineers, software engineers and system engineers) are often met, the whole engineering system is split, the test requirements of different layers and the whole engineering requirements are difficult to be organically combined, and the test system is comprehensively and systematically built.
In the process of building a test system, the traditional method focuses on the test design around a kinematic model and a dynamic model from the theoretical point of view, and the performance of the model under different working conditions and road conditions is verified. Over-theorized, the actual conditions during operation are often ignored.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide a software and hardware decoupling simulation test system which can highly fit an actual scene, and the design is optimized by verifying the performances of the design in different fitting scenes from the actual scene.
The technical scheme of the invention is that the software and hardware decoupling simulation test system comprises:
The environment simulation module is used as an integrated tool and platform for realizing virtual research and development of the automobile through an analog simulation technology, integrates an automobile driving environment model, an on-board environment sensing model and a traffic model, can be seamlessly linked with Matlab/Simulink, supports offline and real-time simulation functions, and provides three-dimensional digital virtual test scene modeling and editing functions;
The vehicle dynamics simulation module is used for providing vehicle dynamics simulation, scene construction, sensor construction and data interface construction, constructing a control algorithm through a Simulink platform, realizing dynamics simulation through connecting hardware, software and images, wherein the images are automatically generated through the environment simulation module;
the evaluation index and evaluation software module is used for receiving the perception result output by the environment simulation module, receiving the planning target track, the vehicle speed, the control state quantity and the control execution quantity output by the vehicle dynamics simulation module, defining the evaluation index and the target function, outputting the model algorithm capability report, and outputting the algorithm module and the strategy algorithm parameter to be optimized aiming at the report.
As a further improvement, the environment simulation module designs a plurality of scene libraries according to different working conditions and ground conditions, and the operation coefficient K of the scene type can be calculated according to the following linear formula:
K=α* K1+β* K2+γ*K3+δ*K4;
Wherein alpha is ground condition consideration specific gravity, K1 is ground comprehensive coefficient, beta is weather condition consideration specific gravity, K2 is weather comprehensive coefficient, gamma is crop growth condition consideration specific gravity, K3 is crop growth condition comprehensive coefficient, delta is operation scene consideration specific gravity, and K4 is operation scene comprehensive coefficient.
Further, the vehicle dynamics simulation module comprises a power unit module, a chassis unit module and an intelligent driving unit module;
the power unit module is used for simulating the driving process of the power system, and the power output is calculated by adopting the following formula:
P=2π×T×n/60;
wherein P is power, T is torque, and n is rotation speed;
the chassis unit module is used for calibrating energy loss k generated in the power transmission process of the engine and calculating a final power output value;
P1=P*(1-k);
Wherein P1 is output power;
The intelligent driving unit module calculates and generates a control quantity according to a difference error between the target speed and the measured speed by using a PID formula, wherein the PID formula is as follows:
;
wherein, the For the target speed to be the same,In order to achieve a proportional gain,In order to integrate the gain,Is a differential gain.
Further, there is the following relationship between torque and speed:
T=F*L;
F=M*a;
v(t)=∫a(t)dt;
where F is force, L is force acting distance, M is vehicle mass, a is acceleration, and v (t) is speed.
Further, a data sharing interface is arranged among the power unit module, the chassis unit module and the intelligent driving unit module.
Further, the power system comprises a diesel engine system, an extended range hybrid system and a pure electric system.
Further, the KP, KI and KD of the PID controller are adaptively adjusted by adopting an adaptive PID adjustment strategy to adapt to each road section, and the adaptive PID adjustment strategy comprises:
The data-driven self-adaptive adjustment is that the historical data and the machine learning technology are utilized to analyze the performances of different vehicle types under different road conditions, and the training model predicts the optimal PID parameters;
the modularized PID control comprises the steps of configuring independent PID controller modules for each vehicle type and road condition, wherein each module is provided with self-adaptive adjustment logic;
Real-time road condition feedback, namely collecting road condition information in real time through a sensor, wherein the road condition information comprises road surface friction coefficient, gradient and curvature, and dynamically adjusting PID parameters according to the road condition information;
the vehicle dynamics model is used for establishing a detailed dynamics model for each vehicle type, simulating the behavior of each vehicle type under different road conditions, and adjusting PID parameters based on model prediction;
Implementing an adaptive control algorithm to dynamically adjust PID parameters according to the current and predicted errors;
The fuzzy logic system is used for processing multiple input variables and nonlinear system characteristics by using fuzzy logic and outputting adaptive PID parameters;
genetic algorithm optimization, namely optimizing PID parameters by applying a genetic algorithm, and finding out optimal parameters adapting to the current road section and vehicle type through an iterative process;
designing a layered control structure, wherein the bottom layer is responsible for real-time PID parameter adjustment, and the upper layer is responsible for selecting a control strategy according to the vehicle type and road conditions;
Simulating driving behaviors of different drivers in a simulation system, and adjusting PID parameters according to simulation results to adapt to different driving styles;
taking into consideration control targets which possibly conflict with different vehicle types and road conditions, balancing the targets by using a multi-target optimization method, and finding out the most suitable PID parameters;
reinforcement learning, namely using reinforcement learning algorithm to enable a control system to learn itself through interaction with the environment, and continuously optimizing PID parameters to obtain better control effect;
the system integration and coordination ensures that all modules can work cooperatively and share information so as to more comprehensively understand the state and environmental conditions of the vehicle and perform more effective PID parameter adjustment;
real-time monitoring and adjustment, namely implementing a real-time monitoring system, continuously evaluating control performance, and immediately adjusting PID parameters once performance degradation or specific trigger conditions are detected;
And the user self-defines setting, namely allowing the user to self-define an adjustment strategy of the PID parameters according to experience or specific requirements, and correspondingly adjusting the PID parameters according to user input by the system.
Advantageous effects
Compared with the prior art, the invention has the advantages that:
The invention emphasizes the simulation of the working condition, road condition and situation of the real vehicle, and ensures the transmission of data streams among the modules. According to the requirements of various test environments in the research and development process, related models are designed on the ring, software on the ring and hardware on the ring, so that the test environments are guaranteed to be highly similar to the actual vehicle conditions, and the designed algorithm models, software and hardware are tested, so that problems are found as soon as possible, and the problems are solved. The invention starts from a working scene, has the characteristics of coupling with actual scene data, highly sharing data among subsystems, decoupling software and hardware, modularization of the subsystems and suitability for flexible construction.
Drawings
FIG. 1 is a frame diagram of the present invention;
FIG. 2 is a block diagram of a PID controller.
Detailed Description
The invention will be further described with reference to specific embodiments in the drawings.
Referring to fig. 1-2, a software and hardware decoupling simulation test system comprises an environment simulation module, a vehicle dynamics simulation module, an evaluation index and an evaluation software module.
The environment simulation module is used as an integrated tool and platform for realizing virtual research and development of the automobile through an analog simulation technology, integrates an automobile driving environment model, an on-board environment sensing model and a traffic model, can be seamlessly linked with Matlab/Simulink, supports offline and real-time simulation functions, and provides modeling and editing functions of a three-dimensional digital virtual test scene.
The environment simulation module supports modeling and editing of the running environment of the automobile for roads, road textures, lane lines, traffic signs and facilities, weather and night scenes. The model establishment and setting of various types of sensors can be supported, including a fisheye camera, a monocular camera, a binocular camera, a millimeter wave radar, a laser radar, an ultrasonic radar, a V2X communication sensor, a lane line sensor and a target object identification sensor. The road model can be set and edited, the road model has the road database with gradient, curvature, side inclination and overhead, the parameterized road model is provided, the automatic test is supported, the non-paved road simulation is supported, and the high-precision map importing of the third-party map OSM/OpenDRIVE is supported. The environment model can be built, and comprises a pavement and roadside facility database, a traffic sign database, a building, a green belt database and a 3D model for supporting user definition. The method supports the creation and editing of road users, including cars, motorcycles, commercial vehicles, pedestrians, bicycles and test balloon vehicles. The method supports the construction of weather conditions such as weather, illumination and the like, and comprises the steps of creating daytime, night rainy and snowy weather, setting car lights and street lamps. The illumination model has sensor response characteristics. Uneven roads (e.g., deceleration strips, potholes) can be simulated, and the real road environment can be imported directly from the HERE map. The driver model can define the driving style (aggressive type and robust type), can support complex driving operation, has learning function, and can adapt to different vehicles and road characteristics. The traffic flow model may define an almost unlimited number of traffic participants, each of which may add a kinetic model, and may exercise fine control over the participants based on events.
The vehicle dynamics simulation module supports modeling and simulation analysis of large, medium and small cars in various typical driving types and suspension forms, is used for providing vehicle dynamics simulation, scene construction, sensor construction and data interface construction, builds a control algorithm through a Simulink platform, and realizes dynamics simulation through connecting hardware, software and images. The image is automatically generated by the environment simulation module. The hardware connection I/O relates to the communication between a singlechip of embedded system hardware and a PC system, CAN signal reading and real-time feedback of signals to a roll, pitch and yaw control system on a steering wheel and a base.
The evaluation index and evaluation software module is used for receiving the perception result output by the environment simulation module, receiving the planning target track, the vehicle speed, the control state quantity and the control execution quantity output by the vehicle dynamics simulation module, defining the evaluation index and the target function, outputting the model algorithm capability report, and outputting the algorithm module and the strategy algorithm parameter to be optimized aiming at the report. The output capability report comprises perception capability, planning capability, control capability, communication capability and intelligent driving comprehensive capability evaluation. And according to the model selection and evaluation indexes, the automatic test software and the test cases, performing optimization variable selection, optimization variable and constraint condition definition, and finally performing algorithm optimization on the tested object.
The environment simulation module designs a plurality of scene libraries according to different working conditions and ground conditions, and mainly comprehensively considers the ground conditions (the hardness of cultivated lands, the ground flatness and inclination, the ground friction and the adhesion), the weather conditions (the rain and snow conditions), the crop growth conditions and the operation scenes (the harvesting scenes, the seeding scenes, the field management scenes and the cultivated land scenes), and the operation coefficient K of the scene type can be calculated according to the following linear formula:
K=α* K1+β* K2+γ*K3+δ*K4;
Wherein alpha is ground condition consideration specific gravity, K1 is ground comprehensive coefficient, beta is weather condition consideration specific gravity, K2 is weather comprehensive coefficient, gamma is crop growth condition consideration specific gravity, K3 is crop growth condition comprehensive coefficient, delta is operation scene consideration specific gravity, and K4 is operation scene comprehensive coefficient. According to the above, a scene coefficient correspondence table is made in the format shown in table 1 below:
TABLE 1
The vehicle dynamics simulation module comprises a power unit module, a chassis unit module and an intelligent driving unit module, and the software and hardware are decoupled as follows:
The power unit module is used for simulating the driving process of a power system, the power system comprises a diesel engine system, a range-extending hybrid system and a pure electric system, and the power output is calculated by adopting the following formula:
P=2π×T×n/60;
wherein P is power, T is torque, and n is rotational speed.
The chassis unit module is used for calibrating energy loss k generated in the power transmission process of the engine and calculating a final power output value. According to the power output, the relation between the power output and the longitudinal acceleration and the longitudinal speed of the vehicle is calibrated according to the actual working condition, and the diesel engine system, the hybrid electric system and the pure electric system are distinguished through coefficients.
P1=P*(1-k);
Wherein P1 is the output power.
The intelligent driving unit module calculates and generates a control quantity according to the difference error between the target speed and the measured speed by using a PID formula, wherein the PID formula is as follows:
;
wherein, the For the target speed to be the same,In order to achieve a proportional gain,In order to integrate the gain,Is a differential gain.
The torque and speed have the following relationship:
T=F*L;
F=M*a;
;
Where F is force, L is force acting distance, M is vehicle mass, a is acceleration, and v (t) is speed. Therefore, the three modules of the power unit module, the chassis unit module and the intelligent driving unit module generate certain correlation through torque.
And a data sharing interface is arranged among the power unit module, the chassis unit module and the intelligent driving unit module so as to realize data sharing among the power unit module, the chassis unit module and the intelligent driving unit module and ensure that required data is transmitted among different modules or systems. For example, an acceleration output calculated from a simulation of the engine output power, is used in the simulation of actual parameters of the intelligent driving system, especially in PID control, to calibrate the difference between the measured speed and the target speed.
In this embodiment, the KP, KI, KD of the PID controller is adaptively adjusted to adapt to each road section by adopting an adaptive PID adjustment strategy. The adaptive PID tuning strategy includes:
1. And (3) data-driven self-adaptive adjustment, namely analyzing the performances of different vehicle types under different road conditions by utilizing historical data and a machine learning technology, and predicting the optimal PID parameters by a training model.
2. And (3) modular PID control, namely configuring independent PID controller modules for each vehicle type and road condition, wherein each module is provided with self-adaptive adjustment logic.
3. And (3) real-time road condition feedback, namely collecting road condition information in real time through a sensor, wherein the road condition information comprises road surface friction coefficient, gradient and curvature, and dynamically adjusting PID parameters according to the road condition information.
4. And the vehicle dynamics model is used for establishing a detailed dynamics model for each vehicle type, simulating the behavior of each vehicle type under different road conditions and adjusting PID parameters based on model prediction.
5. Adaptive control strategy-implementing an adaptive control algorithm, such as Model Predictive Control (MPC), dynamically adjusts PID parameters based on current and predicted errors.
6. Fuzzy logic system, which uses fuzzy logic to process multiple input variables (such as vehicle speed, steering angle, acceleration, etc.) and nonlinear system characteristics, and outputs adaptive PID parameters.
7. Genetic algorithm optimization, namely optimizing PID parameters by applying a genetic algorithm, and finding out optimal parameters adapting to the current road section and vehicle type through an iterative process.
8. And the hierarchical control structure is designed, wherein the bottom layer is responsible for real-time PID parameter adjustment, and the upper layer is responsible for selecting a control strategy according to the vehicle type and road conditions.
9. And (3) simulating the driving behaviors of different drivers in a simulation system, and adjusting PID parameters according to simulation results to adapt to different driving styles.
10. And (3) multi-objective optimization, namely taking control objectives which possibly conflict with different vehicle types and road conditions into consideration, balancing the objectives by using a multi-objective optimization method, and finding out the most suitable PID parameters.
11. Reinforcement learning, namely using reinforcement learning algorithm to enable the control system to learn itself through interaction with the environment, and continuously optimizing PID parameters to obtain better control effect.
12. System integration and collaboration, ensuring that all modules (e.g., sensing, decision, control) can work cooperatively, share information, so as to more fully understand vehicle status and environmental conditions, and thus make more efficient PID parameter adjustments.
13. And (3) real-time monitoring and adjustment, namely implementing a real-time monitoring system, continuously evaluating the control performance, and immediately adjusting the PID parameters once the performance degradation or the specific triggering condition is detected.
14. And the user self-defines setting, namely allowing the user to self-define an adjustment strategy of the PID parameters according to experience or specific requirements, and correspondingly adjusting the PID parameters according to user input by the system.
The system fits the actual scene to a high degree, starts from the actual scene, and optimizes the design by verifying the performances of the design in different fitting scenes. In terms of data application, part of the test pattern is more focused on independent application of data. Because the system focuses on virtual integration and data integration between different subsystems (a power unit module, a chassis unit module and a intelligent driving unit module), data are coupled in the different subsystems. The software and hardware of each system are decoupled, the data are shared, and the subsystems can be flexibly matched to serve different purposes.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present invention, and these do not affect the effect of the implementation of the present invention and the utility of the patent.

Claims (4)

1.一种软硬件解耦仿真模拟测试系统，其特征在于，包括：1. A hardware/software decoupling simulation and testing system, characterized in that it comprises: 环境仿真模块，作为通过模拟仿真技术实现汽车虚拟研发的一体化工具与平台，将汽车行驶环境模型、车载环境传感模型与交通模型集于一体，可与Matlab / Simulink 无缝链接并支持离线与实时仿真功能，提供了三维数字虚拟试验场景建模与编辑功能；The environment simulation module, as an integrated tool and platform for realizing virtual R&D of automobiles through simulation technology, integrates the vehicle driving environment model, the vehicle environment sensing model and the traffic model. It can be seamlessly linked with Matlab/Simulink and supports offline and real-time simulation functions. It provides three-dimensional digital virtual test scene modeling and editing functions. 车辆动力学仿真模块，用于提供车辆动力学仿真、场景构建、传感器构建、数据interface构建，通过Simulink平台构建控制算法，通过连接硬件、软件和图像实现动力学仿真，所述图像是通过所述环境仿真模块自动生成的；The vehicle dynamics simulation module is used to provide vehicle dynamics simulation, scene construction, sensor construction, and data interface construction. It constructs control algorithms through the Simulink platform and realizes dynamics simulation by connecting hardware, software, and images. The images are automatically generated by the environment simulation module. 评测指标与评测软件模块，用于接收所述环境仿真模块输出的感知结果，以及接收所述车辆动力学仿真模块输出的规划目标轨迹、车速、控制状态量、控制执行量，定义评测指标和目标函数，输出模型算法能力报告，针对报告输出需优化的算法模块及策略算法参数；The evaluation index and evaluation software module is used to receive the perception results output by the environment simulation module, as well as the planned target trajectory, vehicle speed, control state variables, and control execution variables output by the vehicle dynamics simulation module. It defines the evaluation index and objective function, outputs the model algorithm capability report, and outputs the algorithm modules and strategy algorithm parameters that need to be optimized based on the report. 所述环境仿真模块根据不同工况和地况设计若干场景库，场景类型的作业系数K根据如下线性公式计算：The environmental simulation module designs several scenario libraries based on different working conditions and site conditions. The operation coefficient K for each scenario type is calculated according to the following linear formula: K=α* K1+β* K2+γ*K3+δ*K4；K=α* K1+β* K2+γ*K3+δ*K4; 其中，α为地面情况考虑比重，K1为地面综合系数，β为天气情况考虑比重，K2为天气综合系数，γ为作物生长情况考虑比重，K3为作物生长情况综合系数，δ为作业场景考虑比重，K4为作业场景综合系数；Where α represents the weight of ground conditions, K1 represents the comprehensive ground coefficient, β represents the weight of weather conditions, K2 represents the comprehensive weather coefficient, γ represents the weight of crop growth conditions, K3 represents the comprehensive crop growth coefficient, δ represents the weight of the operational scenario, and K4 represents the comprehensive operational scenario coefficient. 所述车辆动力学仿真模块包括动力单元模块、底盘单元模块和智驾单元模块；The vehicle dynamics simulation module includes a power unit module, a chassis unit module, and an intelligent driving unit module; 所述动力单元模块用于模拟动力系统驱动过程，功力输出采用以下公式计算：The power unit module is used to simulate the driving process of a power system, and the power output is calculated using the following formula: P＝2π×T×n/60；P = 2π × T × n / 60; 其中，P为功率，T为扭矩，n为转速；Where P is power, T is torque, and n is rotational speed; 所述底盘单元模块用于对发动机功率传递过程中所产生的能量损耗k进行标定，并计算出最终功率输出值；The chassis unit module is used to calibrate the energy loss k generated during the engine power transmission process and calculate the final power output value. P1=P*（1-k）；P1 = P * (1 - k); 其中，P1为输出功率；Where P1 is the output power; 所述智驾单元模块利用PID公式根据目标速度和测量速度之间的差异error，进行计算并产生出控制量，PID公式如下：The intelligent driving unit module uses the PID formula to calculate and generate control input based on the difference (error) between the target speed and the measured speed. The PID formula is as follows: ； ; 其中，为目标速度，为比例增益，为积分增益，为微分增益；in, For the target speed, For proportional gain, For integral gain, This is the differential gain; 所述动力单元模块、底盘单元模块和智驾单元模块之间设有数据共享接口。The power unit module, chassis unit module, and intelligent driving unit module are provided with a data sharing interface. 2.根据权利要求1所述的一种软硬件解耦仿真模拟测试系统，其特征在于，扭矩和速度之间有以下关系：2. The hardware-software decoupling simulation test system according to claim 1, characterized in that the torque and speed have the following relationship: T=F*L；T = F * L; F=M*a；F = M * a; v(t)=∫a(t)dt；v(t) = ∫a(t)dt; 其中，F为力，L为力作用距离，M为车辆质量，a为加速度，v(t)为速度。Where F is force, L is the distance of force application, M is the mass of the vehicle, a is acceleration, and v(t) is velocity. 3.根据权利要求1所述的一种软硬件解耦仿真模拟测试系统，其特征在于，所述动力系统包括柴油机系统、增程式混动系统、纯电系统。3. The hardware and software decoupling simulation test system according to claim 1, wherein the power system includes a diesel engine system, a range-extended hybrid system, and a pure electric system. 4.根据权利要求1-3任意一项所述的一种软硬件解耦仿真模拟测试系统，其特征在于，采用自适应PID调整策略对PID控制器的KP、KI、KD进行自适应调整以适应各个路段，自适应PID调整策略包括：4. A hardware/software decoupling simulation test system according to any one of claims 1-3, characterized in that an adaptive PID adjustment strategy is used to adaptively adjust the KP, KI, and KD of the PID controller to adapt to each road segment, wherein the adaptive PID adjustment strategy includes: 数据驱动的自适应调整：利用历史数据和机器学习技术，分析不同车型在不同路况下的表现，训练模型预测最优的PID参数；Data-driven adaptive adjustment: Utilizing historical data and machine learning techniques, analyze the performance of different vehicle models under different road conditions, and train models to predict the optimal PID parameters; 模块化PID控制：为每个车型和路况配置独立的PID控制器模块，每个模块都有其自适应调整逻辑；Modular PID control: Each vehicle type and road condition is equipped with an independent PID controller module, and each module has its own adaptive adjustment logic; 实时路况反馈：通过传感器实时收集路况信息，路况信息包括路面摩擦系数、坡度、曲率，根据路况信息动态调整PID参数；Real-time traffic feedback: Traffic information is collected in real time through sensors, including road surface friction coefficient, slope, and curvature. PID parameters are dynamically adjusted based on the traffic information. 车辆动力学模型：为每种车型建立详细的动力学模型，模拟各车型在不同路况下的行为，基于模型预测来调整PID参数；Vehicle dynamics model: Detailed dynamics models are established for each vehicle type to simulate the behavior of each vehicle type under different road conditions, and PID parameters are adjusted based on model predictions; 自适应控制策略：实施自适应控制算法根据当前和预测的误差动态调整PID参数；Adaptive control strategy: Implement an adaptive control algorithm to dynamically adjust PID parameters based on current and predicted errors; 模糊逻辑系统：使用模糊逻辑处理多输入变量和非线性系统特性，输出自适应的PID参数；Fuzzy logic system: Uses fuzzy logic to process the characteristics of multi-input variables and nonlinear systems, and outputs adaptive PID parameters; 遗传算法优化：应用遗传算法来优化PID参数，通过迭代过程找到适应当前路段和车型的最佳参数；Genetic algorithm optimization: Applying a genetic algorithm to optimize PID parameters, finding the optimal parameters for the current road segment and vehicle type through an iterative process; 分层控制结构：设计一个分层控制结构，底层负责实时PID参数调整，上层负责根据车型和路况选择控制策略；Hierarchical control structure: Design a hierarchical control structure, with the bottom layer responsible for real-time PID parameter adjustment and the upper layer responsible for selecting control strategies based on vehicle type and road conditions; 驾驶员行为模拟：在仿真系统中模拟不同驾驶员的驾驶行为，根据模拟结果调整PID参数以适应不同驾驶风格；Driver behavior simulation: Simulate the driving behavior of different drivers in the simulation system, and adjust the PID parameters according to the simulation results to adapt to different driving styles; 多目标优化：考虑到不同车型和路况可能存在冲突的控制目标，使用多目标优化方法来平衡这些目标，找到最合适的PID参数；Multi-objective optimization: Considering the conflicting control objectives that may exist for different vehicle models and road conditions, a multi-objective optimization method is used to balance these objectives and find the most suitable PID parameters; 强化学习：使用强化学习算法让控制系统通过与环境的交互自我学习，不断优化PID参数以获得更好的控制效果；Reinforcement learning: Reinforcement learning algorithms are used to enable the control system to learn by interacting with the environment and continuously optimize PID parameters to achieve better control results; 系统集成与协同：确保所有模块能够协同工作，共享信息，以便更全面地理解车辆状态和环境条件，从而进行更有效的PID参数调整；System integration and collaboration: Ensure that all modules can work together and share information to gain a more comprehensive understanding of vehicle status and environmental conditions, thereby enabling more effective PID parameter adjustments; 实时监控与调整：实施实时监控系统，持续评估控制性能，一旦检测到性能下降或特定触发条件，立即调整PID参数；Real-time monitoring and adjustment: Implement a real-time monitoring system to continuously evaluate control performance, and immediately adjust PID parameters once performance degradation or specific triggering conditions are detected; 用户自定义设置：允许用户根据经验或特定需求自定义PID参数的调整策略，系统根据用户输入进行相应调整。User-defined settings: Allows users to customize the adjustment strategy of PID parameters based on experience or specific needs, and the system makes corresponding adjustments based on user input.
CN202411730164.XA 2024-11-29 2024-11-29 Software and hardware decoupling simulation test system Active CN119669066B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411730164.XA CN119669066B (en) 2024-11-29 2024-11-29 Software and hardware decoupling simulation test system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411730164.XA CN119669066B (en) 2024-11-29 2024-11-29 Software and hardware decoupling simulation test system

Publications (2)

Publication Number Publication Date
CN119669066A CN119669066A (en) 2025-03-21
CN119669066B true CN119669066B (en) 2025-12-09

Family

ID=94989094

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411730164.XA Active CN119669066B (en) 2024-11-29 2024-11-29 Software and hardware decoupling simulation test system

Country Status (1)

Country Link
CN (1) CN119669066B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120653945B (en) * 2025-05-28 2026-03-03 河南省科学院物理研究所 AI-based autonomous driving evaluation system
CN121455041A (en) * 2026-01-06 2026-02-03 重庆长安汽车股份有限公司 Hardware-in-loop calibration method and device, electronic equipment and vehicle

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110794810A (en) * 2019-11-06 2020-02-14 安徽瑞泰智能装备有限公司 Method for carrying out integrated test on intelligent driving vehicle
CN117631556A (en) * 2023-10-26 2024-03-01 武汉极目智能技术有限公司 Vehicle dynamics model and real vehicle joint simulation method, system, equipment and medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116467892A (en) * 2023-05-05 2023-07-21 东风汽车集团股份有限公司 Vehicle longitudinal dynamics modeling method and system for intelligent driving simulation test

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110794810A (en) * 2019-11-06 2020-02-14 安徽瑞泰智能装备有限公司 Method for carrying out integrated test on intelligent driving vehicle
CN117631556A (en) * 2023-10-26 2024-03-01 武汉极目智能技术有限公司 Vehicle dynamics model and real vehicle joint simulation method, system, equipment and medium

Also Published As

Publication number Publication date
CN119669066A (en) 2025-03-21

Similar Documents

Publication Publication Date Title
CN119669066B (en) Software and hardware decoupling simulation test system
US11755396B2 (en) Generating autonomous vehicle simulation data from logged data
Kaur et al. A survey on simulators for testing self-driving cars
CN114326696B (en) Automatic parameter adjustment framework for controller used in automatic driving vehicle
CN110406530B (en) An automatic driving method, apparatus, apparatus and vehicle
US20230365145A1 (en) Method, system and computer program product for calibrating and validating a driver assistance system (adas) and/or an automated driving system (ads)
US11415484B2 (en) Apparatus and method for testing automated vehicles via movable target body or electronic target simulator
CN108319249B (en) Comprehensive evaluation system and method for unmanned driving algorithm based on driving simulator
US20250111105A1 (en) Generating Perception Scenarios for an Autonomous Vehicle from Simulation Data
CN114755937A (en) Automatic driving simulation test method and system based on digital twinning
CN109147465A (en) A kind of automobile driving simulator test macro and control method
CN113076897A (en) Game dynamic driving safety measurement and control method and regulation and control terminal of intelligent networked automobile
CN112230659A (en) Method for accurately planning movement track, intelligent control equipment and automatic driving vehicle
Iclodean et al. Virtual Model
Catozzi Design of a NMPC system for automated driving and integration into the CARLA simulation environment
Dipalo Development of a NMPC system for autonomous vehicles: Integration into the CARLA simulation environment and validation in complex scenarios
Yilmaz-Niewerth et al. Calibration of Traffic Flow Simulation Towards Realistic Human Behavior
Ensbury et al. Virtual Proving Ground Testing: Deploying Dymola and Modelica to recreate Full Vehicle Proving Ground Testing Procedures.
US20260002786A1 (en) Vehicle operation
CN121859594A (en) A virtual simulation system and testing method for electric vehicles based on multidisciplinary collaboration
Piecha et al. Development with Radar Target Simulator and GNSS Spoofing at an Integration Testbed
Amelunxen et al. Detailed Simulation of Autonomous Systems for Off-highway Applications: Detailed Simulation of Autonomous Systems for Off-highway Applications
CN121254804A (en) Automatic driving test method and device, vehicle and storage medium
CN119247929A (en) An autonomous driving test system and method based on digital twin
CN121185636A (en) A closed-loop testing method and apparatus for intelligent driving systems based on driving simulators

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant