A new deep domain adaptation method with joint adversarial training for online detection of bearing early fault

For online early fault detection of rolling bearings in non-stop scenarios, one of the main concerns is the model bias caused by the distribution shift between offline and online working conditions. Under such concern, how to improve the feature sensitivity to early faults and the robustness of detection model has become a key challenge of improving the effectiveness of online detection. To solve this problem, a new online early fault detection method is proposed in this paper based on a strategy of deep transfer learning. First, a new robust state assessment method is presented. By introducing priori degradation information in the anomaly detection process of the isolated forest algorithm, this method can accurately assess the normal state and early fault state under noise interference. Second, a new deep domain adaptation algorithm is proposed. The algorithm uses the results of state assessment as output labels, and designs a deep domain adaptation neural network for joint adversarial training at feature level and model level simultaneously. Then a domain-invariant feature representation can be extracted from the data of different working conditions, and an online detection model can then be constructed. Comparative experiments are run on two bearing datasets IEEE PHM Challenge 2012 and XJTU-SY, and the results verifies the effectiveness of the proposed method in false alarm number and detection location.