Intelligent cruise control using an efficient pid model neural network

Servomotor systems are known to have nonlinear parameters and dynamic factors, such as backlash, dead zone and Coulomb friction, making the system hard to control using conventional control methods as PID controllers. Also, the dynamics of the system will change when changing the load, which will add more complexity and nonlinearity to the system. Nontraditional, intelligent control techniques such as Neural Networks (NN), Genetic Algorithms and Fuzzy Logic methods have been used in many applications in order to solve the problem related to these nonlinear systems. This paper presents a NN controller for intelligent cruise control (ICC) of vehicles, in which the model of a servomotor is used as the base for its implementation. In particular, we are using a multilayer neural network to build a model that mimics the function of a DC servomotor system; also we are using a second neural network to control the modeled network. The main objective of the ICC is to achieve automatic vehicle speed control in a safe, reliable and smooth way. The proposed NN controller will be able to deal with the nonlinear parameters and dynamic factors involved in the system and hence the proper control of the servomotor output speed and position. Off-line simulation using MATLAB is used to show final results, and to compare them with a conventional PID controller results for the same model. Dynamic Publishers, Inc.