Search Results

A neural network model of a full car has been developed here on the basis of ADAMS simulation results. The model basically intended for roll control studies, is a completely non-liner model and has 104 degrees of freedom. ADAMS software has been used to determine the model behavior to specific steering inputs. The out put of the simulation program was then used to train a neural network constructed to approximate the model for controller design and real time studies of control action. Specific time delayed feedback inputs to the neural network resulted an efficient approximate model with good accuracy for control tasks.

Design of a fuzzy controller for active suspension of a compact car is the topic of this article. The car dynamic model used for this purpose is very large and completely nonlinear. A large part of this model namely the car basic dynamics is constructed in ADAMS software which in excess of considering the components in their real working conditions, it includes parameters such as flexibility of parts and joints. The hydraulic system of the active suspension system is modeled in Matlab and the two softwares are linked to form the complete car model. Using control methods on the basis of neural network and fuzzy logic, a controller is designed that can eliminate roll over of the car in sever driving conditions.