Industrial Process Fault Detection Based on Incremental Isometric Mapping and Double Local Density Method

Abstract

To address the nonlinearity and dynamics of industrial processes, an incremental isometric mapping (IISOMAP) in combination with double local density (DLD) is proposed as a fault detection method (IISOMAP-DLD) based on stream shape learning. First, IISOMAP is used to map the raw data into a low-dimensional manifold feature subspace and a residual subspace. Then, the double local density method is introduced in the two subspaces respectively to construct statistics to monitor the process. Finally, the IISOMAP-DLD method is applied to the Tennessee-Eastman (TE) process, and the experimental results show that IISOMAP-DLD has a higher fault detection rate than the other methods. IISOMAP preserves the intrinsic characteristics of the data and solves the nonlinear problems of the process, while the double local density method can eliminate the dynamic of the process.

Keywords

• manifold learning
• isometric mapping (isomap)
• local density
• fault detection
• dynamic