Statistical Learning and Stochastic Process for Robust Predictive Control of Vehicle Suspension Systems

Statistical Learning;Predictive Control;Robust Control;Uncertainty Quantification;Vehicle Suspension System Control

Mozaffari, Ahmadeddin ; advisor:Chenouri, Shoja'affiliation1:Faculty of Mathematics ; Chenouri, Shoja'eddin ;

University of Waterloo

关键词: Predictive Control;    Uncertainty Quantification;    Statistical Learning;    Master Thesis;    Robust Control;    Vehicle Suspension System Control;   

Others  :  https://uwspace.uwaterloo.ca/bitstream/10012/12369/3/Mozaffari_Ahmad.pdf

瑞士|英语

来源: UWSPACE Waterloo Institutional Repository

【 摘 要 】

Predictive controllers play an important role in today's industry because of their capabilityof verifying optimum control signals for nonlinear systems in a real-time fashion.Due to their mathematical properties, such controllers are best suited for control problemswith constraints. Also, these interesting controllers can be equipped with different typesof optimization and learning modules. The main goal of this thesis is to explore the potential of predictive controllers for a challenging automotive problem, known as active vehicle suspension control.In this context, it is intended to explore both modeling and optimization modulesusing different statistical methodologies ranging from statistical learning to random processcontrol. Among the variants of predictive controllers, learning-based model predictivecontroller (LBMPC) is becoming more and more interesting to the researchers of controlsociety due to its structural flexibility and optimal performance. The current investigationwill contribute to the improvement of LBMPC by adopting different statistical learningstrategies and forecasting methods to improve the efficiency and robustness of learningperformed in LBMPC. Also, advanced probabilistic tools such as reinforcement learning,absorbing state stochastic process, graphical modelling, and bootstrapping are used toquantify different sources of uncertainty which can affect the performance of the LBMPCwhen it is used for vehicle suspension control. Moreover, a comparative study is conductedusing gradient-based as well as deterministic and stochastic direct search optimizationalgorithms for calculating the optimal control commands.By combining the well-established control and statistical theories, a novel variant ofLBMPC is developed which not only affords stability and robustness, but also surpassesa wide range of conventional controllers for the vehicle suspension control problem. The findings of the current investigation can be interesting to the researchers of automotiveindustry (in particular those interested in automotive control), as several open issues regarding the potential of statistical tools for improving the performance of controllers forvehicle suspension problem are addressed.