Apresenta uma solução inovadora de controle por redes neurais artificiais aprendendo segundo a técnica de aprendizagem por reforço usando algoritmos genéticos para integrar múltiplos sistemas ativos no controle de estabilidade de um veículo. Estudo, restringido a um domínio de manobras, foi desenvolvido excluindo falhas e alterações da planta no tempo. Contribui para responder como o controlador de dinâmica veicular pode ser aperfeiçoado para atuação simultânea de múltiplos sistemas ativos. Contempla o desenvolvimento do neurocontrolador e algoritmo de aprendizagem na plataforma Matlab, de um modelo de dinâmica veicular em ambiente ADAMS e do modelo de referência, atuadores e observador com programação Matlab. Analisa a estabilidade da planta e define regiões de atuação do controlador. Apresenta um estudo e definição da técnica de controle de estabilidade em guinada para nortear a função de otimização, o treinamento e as simulações. Treinamento da rede neural para acomodar as não linearidades envolvidas na planta e para otimizar a integração dos múltiplos sistemas ativos focando nas especificações de desempenho do controlador e no domínio de situações a serem analisadas. Simulação de situações e manobras para validação e avaliação do desempenho do controlador com co-simulação entre Matlab e ADAMS. Resultados qualitativos e quantitativos do desempenho do controlador justificando a integração efetiva dos sistemas e o neurocontrolador não-linear. / Presents an innovative control solution with artificial neural networks learning using reinforcement learning by genetic algorithms to integrate multiple active systems to control yaw vehicle stability. Study restricted to a maneuver domain and excluding plant changes in time and failures. Contributes to answer how the vehicle dynamics controller can be improved for multiple simultaneous active systems. Development of the neurocontroller and learning algorithm in Matlab, vehicle dynamics model in ADAMS environment and reference model, actuators and observer with Matlab programming. Plant stability analysis and activation areas definition. Study and method definition for stability yaw control to guide the task of optimization, training and simulation. Training the neural network to accomplish the plant nonlinearity and to optimize the multiple active systems synergy targeting the controller performance specifications and the analyzed conditions domain. Conditions and maneuvers simulation to validate and evaluate the controller performance using cosimulation between Matlab and ADAMS. Qualitative and quantitative controller results justifying the effective systems integration and non-linear neurocontroller.

Apresenta uma solução inovadora de controle por redes neurais artificiais aprendendo segundo a técnica de aprendizagem por reforço usando algoritmos genéticos para integrar múltiplos sistemas ativos no controle de estabilidade de um veículo. Estudo, restringido a um domínio de manobras, foi desenvolvido excluindo falhas e alterações da planta no tempo. Contribui para responder como o controlador de dinâmica veicular pode ser aperfeiçoado para atuação simultânea de múltiplos sistemas ativos. Contempla o desenvolvimento do neurocontrolador e algoritmo de aprendizagem na plataforma Matlab, de um modelo de dinâmica veicular em ambiente ADAMS e do modelo de referência, atuadores e observador com programação Matlab. Analisa a estabilidade da planta e define regiões de atuação do controlador. Apresenta um estudo e definição da técnica de controle de estabilidade em guinada para nortear a função de otimização, o treinamento e as simulações. Treinamento da rede neural para acomodar as não linearidades envolvidas na planta e para otimizar a integração dos múltiplos sistemas ativos focando nas especificações de desempenho do controlador e no domínio de situações a serem analisadas. Simulação de situações e manobras para validação e avaliação do desempenho do controlador com co-simulação entre Matlab e ADAMS. Resultados qualitativos e quantitativos do desempenho do controlador justificando a integração efetiva dos sistemas e o neurocontrolador não-linear. / Presents an innovative control solution with artificial neural networks learning using reinforcement learning by genetic algorithms to integrate multiple active systems to control yaw vehicle stability. Study restricted to a maneuver domain and excluding plant changes in time and failures. Contributes to answer how the vehicle dynamics controller can be improved for multiple simultaneous active systems. Development of the neurocontroller and learning algorithm in Matlab, vehicle dynamics model in ADAMS environment and reference model, actuators and observer with Matlab programming. Plant stability analysis and activation areas definition. Study and method definition for stability yaw control to guide the task of optimization, training and simulation. Training the neural network to accomplish the plant nonlinearity and to optimize the multiple active systems synergy targeting the controller performance specifications and the analyzed conditions domain. Conditions and maneuvers simulation to validate and evaluate the controller performance using cosimulation between Matlab and ADAMS. Qualitative and quantitative controller results justifying the effective systems integration and non-linear neurocontroller.

The contact between the tire and the road is the key enabler of vehicle acceleration, deceleration and steering. However, under the circumstances of sudden changes to the road conditions, the driver`s ability to maintain control of the vehicle maybe at risk. In many cases, this requires intervention from the chassis control systems onboard the vehicle. Although these systems perform well in a variety of situations, their performance can be improved if a real-time estimate of the tire-road contact parameters (ranging from kinematic conditions of the tire to its dynamic properties) are available. At the present stage of development, tire-road contact parameters are indirectly estimated using observers based on vehicle dynamics measurements (acceleration, yaw and roll rates, suspension deflections, etc). Although these methods present a relatively accurate solution, they rely heavily on tire and vehicle kinematic formulations and break down in case of abrupt changes in the measured quantities. To address this problem, researchers have been developing certain sensor based advanced tire concepts for direct measurement of the tire-road contact parameters. Thus the new terms "Intelligent Tire" and "Smart Tire", which mean online tire monitoring are thus enjoying increasing popularity among automotive manufacturers and formed the motivation for this thesis to explore the possibility of developing an intelligent tire system. The development of the so called "intelligent tire/ smart tire system" is expected to spur the development of a new generation of vehicle control system with modified control strategies, leveraging information directly coming from the interface between the tire and the road, and in turn significantly reducing the risk of accidents. The specific contributions of this thesis include the following: • Development of an intelligent tire system, with a special attention to development of measurement and sensor feature extraction methodologies of acceleration signals coming from sensors fixed to the tire innerliner • Design of an integrated vehicle state estimator for application to global chassis control • Development of a model-based tire-road friction estimation algorithm • Development of an intelligent tire based adaptive wheel slip controller for anti-lock brake system (ABS) • Development of a piezoelectric vibration energy harvesting system with an adaptive frequency tuning mechanism for intelligent tires / Master of Science

The main goal of this work is to gain knowledge of how and to what extent state-of-the-artsimulation tools can be used in a conceptual development phase for vehicle dynamics control atVolvo Car Corporation (VCC).The first part of the thesis deals with an evaluation of vehicle dynamics simulation tools and theiruses. The three simulation tools selected for the study, namely Mechanical Simulation CarSim 8.2.1,IPG CarMaker 4.0.5, and VI-Grade CarRealTime V14, are briefly described and discussed. In order toevaluate and compare these tools with respect to application for vehicle dynamics control, a criterialist is developed covering aspects such as tool requirements and intended usage. Based on thecriteria list and certain identified drawbacks, a ranking of the tools is made possible. Furthermore,the process of developing vehicle models for the different tools is discussed in detail, along with theprocedure of validating the vehicle models.In the second part, the concept of Collision Avoidance Driver Assistance (CADA) function isintroduced and possible approaches for developing CADA functions are discussed in brief. It isimportant to note that the CADA functions in this work are based on cornering the vehicle i.e.maneuvering around the threat, rather than solely reducing vehicle speed. A number ofimplementations of the functions are developed in Simulink. A frequency analysis of a simplifiedlinear vehicle model is performed to investigate the influence of steering, differential braking, andtheir combination on the resultant lateral displacement of the vehicle during an evasive maneuver.The developed CADA functions are then simulated using the vehicle simulation tools. Two specificmetrics - Lateral Displacement gain and DeltaX - are formulated to evaluate the effectiveness of theCADA functions. Based on these metrics, the assistance obtained due to the functions for a specificevasive maneuver is compared.From the evaluation process of the three tools, two were considered suitable for the purpose ofsimulating collision avoidance functions. The evaluation of the CADA functions demonstrates thatcombined assistive steering with differential braking provides considerable assistance in order toavoid collisions. The simulation results also present interesting trends which provide a usefuldirection regarding the conditions for intervention by such collision avoidance functions during anevasive maneuver. The use of simulation tools makes it possible to observe these trends and utilizethem in the development process of the functions.

Vehicle Dynamics Control (VDC) systems (also known as Active Chassis systems) are mechatronic systems developed for improving vehicle comfort, handling and/or stability. Traditionally, most of these systems have been individually developed and manufactured by various suppliers and utilised by automotive manufacturers. These decentralised control systems usually improve one aspect of vehicle performance and in some cases even worsen some other features of the vehicle. Although the benefit of the stand-alone VDC systems has been proven, however, by increasing the number of the active systems in vehicles, the importance of controlling them in a coordinated and integrated manner to reduce the system complexity, eliminate the possible conflicts as well as expand the system operational envelope, has become predominant. The subject of Integrated Vehicle Dynamics Control (IVDC) for improving the overall vehicle performance in the existence of several VDC active systems has recently become the topic of many research and development activities in both academia and industries Several approaches have been proposed for integration of vehicle control systems, which range from the simple and obvious solution of networking the sensors, actuators and processors signals through different protocols like CAN or FlexRay, to some sort of complicated multi-layered, multi-variable control architectures. In fact, development of an integrated control system is a challenging multidisciplinary task and should be able to reduce the complexity, increase the flexibility and improve the overall performance of the vehicle. The aim of this thesis is to develop a low-cost control scheme for integration of Electric Power-Assisted Steering (EPAS) system with Enhanced Stability Program (ESP) system to improve driver comfort as well as vehicle safety. In this dissertation, a systematic approach toward a modular, flexible and reconfigurable control architecture for integrated vehicle dynamics control systems is proposed which can be implemented in real time environment with low computational cost. The proposed control architecture, so named “Integrated Vehicle Control System (IVCS)”, is customised for integration of EPAS and ESP control systems. IVCS architecture consists of three cascade control loops, including high-level vehicle control, low-level (steering torque and brake slip) control and smart actuator (EPAS and EHB) control systems. The controllers are designed based on Youla parameterisation (closed-loop shaping) method. A fast, adaptive and reconfigurable control allocation scheme is proposed to coordinate the control of EPAS and ESP systems. An integrated ESP & ESP HiL/RCP system including the real EPAS and Electro Hydraulic Brake (EHB) smart actuators integrated with a virtual vehicle model (using CarMaker/HiL®) with driver in the loop capability is designed and utilised as a rapid control development platform to verify and validate the developed control systems in real time environment. Integrated Vehicle Dynamic Control is one of the most promising and challenging research and development topics. A general architecture and control logic of the IVDC system based on a modular and reconfigurable control allocation scheme for redundant systems is presented in this research. The proposed fault tolerant configuration is applicable for not only integrated control of EPAS and ESP system but also for integration of other types of the vehicle active systems which could be the subject of future works.