Intelligence Decision Making of Fault Detection and Fault Tolerances Method for Industrial Robotic Manipulators

FD methods are usually based on the residual generation and analysis concept. A mathematical model is used to reproduce the dynamic behavior of the fault-free system; the deviation of the output predicted by the model from actual output measurements forms the so-called residuals. Which, when properly analyzed, provides valuable information about failure. Based on the failure an intelligent decision is taken with the help of the neuro fuzzy fault diagnosis system. The main aim of this work is the introduction of a new algorithm for robots fault detection which forms part of a proposed intelligent decision making framework for fault tolerance in robotic manipulator. In developing the model, this work explores the affects of failures in an example robot using a technique called Neuro-Fuzzy Approach. The robot components critical to fault detection are revealed using a Neuro-Fuzzy (NF) approach. To evaluate our NF based fault detection and tolerance method we performed an extensive simulation study with a Scorbot ER 5u plus robot manipulator. In this research work we considered all faults possible to occur in robot manipulator. The Scorbot ER 5u plus model was developing in robotics toolbox for MATLAB using the NF algorithms