Fault diagnosis and fault tolerant control of mobile robot based on neural networks

This paper presents a method based on neural networks for achieving fault diagnosis and fault tolerant control of the mobile robot control. The neural network state observer is trained by real nonlinear control system. From the residual difference between outputs of actual system and neural network observer, the fault of control system is detected and determined. Fault tolerant control is realized by using compensation controller and can guarantee the stability and performance. As an example of the application, a tracking control problem for the speed and azimuth of a mobile robot driven by two independent wheels is solved by using the controller. The results of simulation show the effectiveness of the proposed method with scaling location of the fault and the time of occurrence, and eliminating the noise and offering high robustness.