Reliable Algebraic Fault Detection and Identification of Robots
Alexander Lomakin, Joachim Deutscher
Abstract
This paper presents a reliable algebraic method for fault detection and identification for rigid robots considering additive faults and external forces. The presented method is based on the reconstruction of a residual or the fault by nonlinear differential algebraic expressions using the polynomial approximation operator. Furthermore, it is shown how the filter parameters and the noise suppression properties of the resulting filter can be parameterized for reliable fault diagnosis according to the characteristics of the fault signals in the frequency domain. The presented method provides an evaluable expression that can be used to explicitly estimate the influence of measurement noise, quantization, numerical errors, and parameter uncertainties in terms of computable error bounds, thus ensuring reliable fault diagnosis. Based on a SCARA robot, a comparison of the method with the generalized momentum observer is performed, highlighting the advantages of the presented approach. Furthermore, it is applied to a real-world application of a delta robot with parallel kinematics for the identification of additive faults while considering interactions due to the application. For this purpose, the appropriate parameterization of the filter is determined and then the feasibility of the method is verified by the implementation on a real-time controller.