Unsupervised adversarial domain adaptive for fault detection based on minimum domain spacing

Abstract

The deep learning model has gradually matured in the detection of mechanical faults. However, due to the changes in the mechanical operating environment and the application of new sensors in real work, the effect of the training model is not ideal in field applications. The key of this problem is the deviation of feature space mapping between training source domain and application target domain. This paper proposes an unsupervised adversarial domain adaptive fault diagnosis transfer learning model based on the minimum domain spacing to reduce the deviation. In adversarial network training, by training the weight parameters of the classifier, some features extracted by the composed classifier are added to the feature distribution of the target domain through weight changes, which reduces the feature distribution difference between the source domain and the target domain. It is reflected on the reduction of the maximum mean difference distance (MMD) between the two domains, and the fitting features of the data distribution are improved. Finally, through two experimental platforms of rolling bearing and planetary gearbox dataset, the results of six diagnostic tasks show that the new model reduces the amount of parameters by 33.66% and keeps accuracy more than 99% compared with the DANN model under the condition.