A Multilevel Branch Neural Network With Self-Evolution for Condition Monitoring of Industrial Equipment Under Incomplete Training Data Set Scenario

Abstract

It has been widely recognized that the practical application of deep learning (DL) to condition monitoring of industrial equipment relies heavily on having comprehensive coverage of essential features in the training data set, i.e., the data collected should include all potential feature modes under various operating conditions. Given this limitation, this article proposes a multilevel branch neural network (MLBNN) with self-evolution capability. In particular, the MLBNN structure can be updated online when emerging fault modes or operating conditions are encountered during equipment operation. Two case studies employing an industrial robot arm joint bearing and a motor bearing fault diagnosis data set demonstrate the efficacy of MLBNN. We then demonstrate that MLBNN is suitable for deployment under cloud-edge computing architecture, which can further improve the speed of model update operations during self-evolution process and model inference to meet online condition monitoring requirements. Finally, the performance of MLBNN is compared to classical DL and transfer learning approaches under an incomplete training data set scenario, and results show that the accuracy of MLBNN is superior to others.