Model-based fault detection and isolation method using ART2 neural network

Abstract

This article presents a model-based fault diagnosis method to detect and isolate faults in the robot arm control system. The proposed algorithm is composed functionally of three main parts: parameter estimation, fault detection, and isolation. When a change in the system occurs, the errors between the system output and the estimated output cross a predetermined threshold, and once a fault in the system is detected, the estimated parameters are transferred to the fault classifier by the adaptive resonance theory 2 neural network (ART2 NN) with uneven vigilance parameters for fault isolation. The simulation results show the effectiveness of the proposed ART2 NN-based fault diagnosis method.

Model-Based FDI Schemes For Robot Manipulators Using Soft Computing Techniques

“…Terra and Tinós used some different types of NN structures for both residual generation and evaluation (Terra & Tinós, 2001). Lee et al tried to use parameter identification methods for fault detection and ART type NNs for fault isolation on component and sensor type faults (Lee et al, 2003). Datta et al tried to classify coefficients obtained from discrete wavelet transform (DWT) using a NN (Datta et al, 2007).…”

Distributed sensor analysis for fault detection in tightly-coupled multi-robot team tasks

“…The most popular method for providing fault detection in robot systems is based on motion control modeling [8], [12], which compares the values estimated by the motion model and the current measurements, in order to detect a fault. Another widely used computer fault detection method is voting based on modular redundancy [9], [4], which is commonly used in highly reliable systems in which more than one module works redundantly to perform the same task given the same input data and the faulty module is voted out according to the module results.…”

Design and performance improvements for fault detection in tightly-coupled multi-robot team tasks

“…The most popular method for providing fault detection in robot systems is based on motion control [7], [14], [11]. Other widely used computer fault detection methods include voting based modular redundancy [16], [3], analytical redundancy [12], [8], [5] and particle filter techniques [4], [18], [2].…”