Adversarial adaptive 1-D convolutional neural networks for bearing fault diagnosis under varying working condition
This addresses a domain-specific problem for industrial maintenance by enabling more reliable fault diagnosis in real-world scenarios with changing conditions, though it is incremental as it builds on existing adversarial domain adaptation methods.
The paper tackles the problem of bearing fault diagnosis under varying working conditions, where traditional methods fail due to distribution shifts between training and testing data, and proposes A2CNN, an adversarial adaptive 1-D CNN that achieves high accuracy by learning domain-invariant features.
Traditional intelligent fault diagnosis of rolling bearings work well only under a common assumption that the labeled training data (source domain) and unlabeled testing data (target domain) are drawn from the same distribution. However, in many real-world applications, this assumption does not hold, especially when the working condition varies. In this paper, a new adversarial adaptive 1-D CNN called A2CNN is proposed to address this problem. A2CNN consists of four parts, namely, a source feature extractor, a target feature extractor, a label classifier and a domain discriminator. The layers between the source and target feature extractor are partially untied during the training stage to take both training efficiency and domain adaptation into consideration. Experiments show that A2CNN has strong fault-discriminative and domain-invariant capacity, and therefore can achieve high accuracy under different working conditions. We also visualize the learned features and the networks to explore the reasons behind the high performance of our proposed model.