Canonical correlation analysis-based fault detection methods with application to alumina evaporation process

• Different from the well-established principal component analysis (PCA) and partial least squares (PLS) methods, the core of the proposed methods is to build residual signals by means of the CCA technique for detecting faults in a process with input and output data.
• To develop CCA-based schemes for monitoring static and dynamic processes.
• To apply these proposed methods to a real industrial simulation of alumina evaporation process.

In this paper, canonical correlation analysis (CCA)-based fault detection methods are proposed for both static and dynamic processes. Different from the well-established process monitoring and fault diagnosis systems based on multivariate analysis techniques like principal component analysis and partial least squares, the core of the proposed methods is to build residual signals by means of the CCA technique for the fault detection purpose. The proposed methods are applied to an alumina evaporation process, and the achieved results show that both methods are applicable for fault detection, while the dynamic one delivers better detection performance.