A hybrid fuzzy logic artificial neural network algorithm-based fault detection and isolation for industrial robot manipulators

Abstract

The adoption of an efficient online Fault Detection and Isolation (FDI) tool is becoming of utmost importance for robots, especially for those operating in remote or hazardous environments, where a high degree of safety and self-diagnostics capabilities are required. This saves time and cost in repairing the robot. A number of researchers have proposed fault diagnosis architectures for robotic manipulators using the model-based analytical and redundancy approach. One of the main issues in the design of fault detection systems is how to model the rigid-link robotic manipulators with modelling uncertainties. In this paper, a new approach ? hybrid intelligence-based fault detection and isolation for robot manipulators ? is discussed. A learning architecture with neural network approximates the off-nominal system behaviour, which is used for monitoring the robotic system for the faults. This generates the residual by comparing the actual output from the robot. The fuzzy inference system is applied to identify and isolate the faults which provide the adoptive threshold under varying conditions. The concepts discussed are validated through a simulation study using a Scorbot-ER 5Plus manipulator to illustrate the ability of the neuro fuzzy-based fault-diagnosis scheme to detect and isolate faults.