Sparse Gaussian Feature Learning for Nonlinear Industrial Fault Diagnosis

With the increasing complexity of modern industrial processes, the high-dimensional industrial data exhibits strong nonlinearity, bringing considerable challenges to the fault diagnosis of processes. To efficiently extract deep meaningful features that are crucial for fault diagnosis, a sparse Gaussian feature extractor(SGFE) is designed to learn a nonlinear mapping that projects the raw data into the feature space with the fault label dimension. The feature space is described by the one-hot encoding of the fault category label as an orthogonal basis. In this way, the sparse Gaussian features related to fault categories can be gradually learned from the raw data by SGFE. In the feature space, the sparse Gaussian (SG) loss function is designed to constrain the distribution of features to multiple sparse multivariate Gaussian distributions. The sparse Gaussian features are linearly separable in the feature space, which can improve the accuracy of the downstream fault classification task. The effectiveness of the proposed SGFE is verified by the Tennessee–Eastman (TE) benchmark process.