Switched time delay control based on neural network for fault detection and compensation in robot

Fault detection in robotic manipulators is necessary for their monitoring and represents an effective support to use them as independent systems. This present study investigates enhanced method representation of the faultless system behavior a robot manipulator based on multi-layer perceptron (MLP) neural network learning model which produces same real dynamic manipulator. The was generation residue by contrasting actual output with those network; Then, time delay control (TDC) applied compensate fault, typical sliding mode command used delete estimate produced belated signal order obtain strong performances. results simulations performed SCARA arm manipulator, showed good trajectory tracking fast convergence speed presence faults sensors. In addition, completely independent, both TDC MLP network, major advantage proposed command.