Fault detection and fault tolerance methods for industrial robot manipulators based on hybrid intelligent approach

Abstract

Fault tolerance is increasingly important in modern industrial robotic manipulators, especially those operated in remote and hazardous environment. Faults in robotic manipulator can cause economic and serious damages. So the robots need the ability to detect as well as tolerate failures, allow effectively coping with internal failures and continue performing designated tasks without the need for immediate human intervention. This saves time and cost involved in repairing the robot. This type of autonomous fault tolerance is also useful for industrial robots in that it decreases down-time by tolerating failures, identifies faulty components or subsystems to speed up the repair process and prevents the robot from damaging the products being manufactured. To support these fault tolerant capabilities, methods of detecting and tolerating failures must be perfected in robot manipulator. A number of researchers have proposed fault detection/tolerance architectures for robotic manipulators using the model based analytical, and redundancy approach. One of the main issues in the design of fault detection system is to model the rigid link robotic manipulators with modeling uncertainties. In this paper, a new approach hybrid intelligence based fault detection/tolerance for robot manipulators is discussed. A learning architecture, with neural network as on-line approximates the off-nominal system behavior, which is used for monitoring the robotic system for the faults. This generates the residual by comparing the actual output from robot. Fuzzy inference system is applied to identify and tolerate the faults which provide the adoptive threshold under the varying conditions. The new concepts discussed were validated through simulation study using a Scorbot ER 5plus manipulator robot mat lab toolbox.