Fault Detection and Isolation for Robotic Manipulators

This paper deals with the problem of detecting and isolating sensor faults in industrial robot manipulators. To the purpose, an analytical redundancy approach has been pursued, based on a bank of state observers for residual generation. An extended H_infin approach is adopted to build the bank of residual generators; the compensation of poorly known dynamics in each observer is improved by the use of a neural network. The synthesis of the observer gains is achieved by solving an LMI feasibility problem, where constraint on the position of the estimation error linearized dynamics poles in the complex plane are taken into account Finally, in order to test the effectiveness of the proposed approach, a case study is presented, based on experimental data collected on a six-degree-of-freedom Comau Smart-3 S industrial manipulator