Dual neural classification for robust fault diagnosis in robotic manipulators

A fault, if undetected, could have catastrophic consequences (in systems such as aircraft, robotic systems and nuclear reactors) and could incur financial losses (such as in a production process). In this paper the artificial neural networks are used for both residual generation and residual analysis. A Multilayer Perceptron (MLP) is employed to reproduce the dynamics of the robotic manipulator. Its outputs are compared with actual position and velocity measurements, generating the so-called residual vector. The residuals, when properly analyzed, provide an indication of the status of the robot (normal or faulty operation). The ANN architecture employed in the residual analysis is also a multilayer perceptron (MLP) or a radial basis function network (RBFN) which uses the residuals of position and velocity to perform fault identification. Simulations employing a SCARA robotic manipulator are showed demonstrating that the system can detect and isolate correctly faults that can occur during the performance of its task. We opted in our study on fault diagnosis for a dual neural classification. Thus, the architecture of the proposed approach is based on two types of classifiers: Firstly a classifier consisting only of one neural network (MLP or RBF) followed by a comparison of the results of detection and localization. Secondly a classifier consisting of two neural networks (RBF and MLP) and is followed by a final decision system.