Fault diagnosis of industrial robot gearbox using joint interclass and intraclass mappings

Abstract

Due to complex structure and harsh operating conditions, it remains challenging to accurately diagnose industrial robot gearbox fault patterns. For this reason, a joint interclass and intraclass mappings (JIIM) strategy is presented in this paper to enhance the performance of industrial robot gearbox fault diagnosis. To this end, an echo state network (ESN) is first adopted to map the training data into their class centers for minimizing the interclass distance. Meanwhile, the maximization of interclass distance in the data space is achieved by equalizing the distance between class centers. For the mapped data, another ESN is proposed to classify the fault patterns. The proposed JIIM method is evaluated by fault-diagnosis experiments for industrial robot gearboxes. Improvements owing to minimizing the intraclass distance and equalizing the interclass distance are discussed in detail. Results show that the presented JIIM can efficiently improve the performance of industrial robot gearbox fault diagnosis.