A novel neural second-order sliding mode observer for robust fault diagnosis in robot manipulators

Abstract

This paper investigates an algorithm for fault diagnosis in robot manipulators using a novel neural second-order sliding mode observer. Differently from the conventional neural network observer and first-order sliding mode observer for the robust fault estimation schemes, the second-order sliding mode observer is first designed and compared with them. Although the second-order sliding mode observer converges faster and with less error than each of the neural network and the first-order sliding mode observer does, it requires prior knowledge of the upper bound of the fault function. Because of this disadvantage, a neural second-order sliding mode observer is designed, which combines the second-order sliding mode observer with the neural network observer. The resulting observer not only preserves the features of the second-order sliding mode observer but also can improve it by removing the need for prior knowledge of the fault function upper bound. Computer simulation results for a PUMA560 industrial robot are also shown to verify the effectiveness of the proposed strategy.