Scholarlink

<p>Controlling the lateral dynamics of intelligent articulated trucks (IATs) under extreme conditions necessitates the optimal utilization of tire force capacities. This study introduces an innovative control method that synergizes Model Predictive Control (MPC) and Radial Basis Function Neural Network-based Active Disturbance Rejection Control (RBFNN-ADRC) to mitigate jackknifing through active braking. Initially, dual 3 Degree-of-Freedom models of the tractor-trailer system are developed to aid in the controller design, and the nutcracker optimization algorithm is applied for precise model parameter optimization. Accurate estimation of critical variables such as yaw rate and sideslip angle is essential for ensuring vehicle control safety. It is achieved using a dual unscented kalman filter to estimate these unmeasured key variables accurately. The controller utilizes the discrepancy between the estimated values and ideal state values as input to generate additional yaw moments through differential braking, thereby effectively preventing jackknifing. Comprehensive hardware-in-the-loop experiments are conducted to validate the performance of the controller. The experimental results demonstrate that the integrated controller effectively addresses and mitigates the jackknifing issue in IATs, enhancing overall safety and stability. The results show that the proposed method reduces jackknifing risk by 38%, enhances yaw stability by 25<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation>, and improves trajectory tracking accuracy by 22<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mo>%</mo> </math></EquationSource> </InlineEquation>, compared to standalone MPC or ADRC controllers.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Predictive Control and Neural Network-Based Techniques for Enhancing Yaw Stability in Intelligent Articulated Trucks

  • 期刊论文

  • 发表日期：

    2026年1月7日

查看全文
  • Yang Tian,
  • He Ma,
  • Guilin Wen,
  • Xiangyu Wang,
  • Yahui Zhang,
  • Liang Li

摘要

Controlling the lateral dynamics of intelligent articulated trucks (IATs) under extreme conditions necessitates the optimal utilization of tire force capacities. This study introduces an innovative control method that synergizes Model Predictive Control (MPC) and Radial Basis Function Neural Network-based Active Disturbance Rejection Control (RBFNN-ADRC) to mitigate jackknifing through active braking. Initially, dual 3 Degree-of-Freedom models of the tractor-trailer system are developed to aid in the controller design, and the nutcracker optimization algorithm is applied for precise model parameter optimization. Accurate estimation of critical variables such as yaw rate and sideslip angle is essential for ensuring vehicle control safety. It is achieved using a dual unscented kalman filter to estimate these unmeasured key variables accurately. The controller utilizes the discrepancy between the estimated values and ideal state values as input to generate additional yaw moments through differential braking, thereby effectively preventing jackknifing. Comprehensive hardware-in-the-loop experiments are conducted to validate the performance of the controller. The experimental results demonstrate that the integrated controller effectively addresses and mitigates the jackknifing issue in IATs, enhancing overall safety and stability. The results show that the proposed method reduces jackknifing risk by 38%, enhances yaw stability by 25 \(\%\) % , and improves trajectory tracking accuracy by 22 \(\%\) % , compared to standalone MPC or ADRC controllers.