Distribution Adaptation and Manifold Alignment for complex processes fault diagnosis

Highlights：

• We learn two projection matrices that map the monitoring data of source domain (labeled data) and target domain (unlabeled data) into two low-dimensional subspaces where the distributional shift and structural shift are reduced simultaneously.

• We introduce manifold alignment into unsupervised domain adaptation. We dig deep into the intrinsic structure of the data itself by using the graph Laplacian matrix to approach the local manifold of the data in order to make the distance of the corresponding points in the projection coordinates as close as possible.

• It is also suitable for the complex process with nonlinear trait.

• To our knowledge, it is a pioneering work to apply domain adaptation methods to the field of fault diagnosis.