Adaptive LII-RMPLS based data-driven process monitoring scheme for quality-relevant fault detection

Abstract

The partial least squares (PLS) method has been successfully applied for fault diagnosis in industrial production. Compared with the traditional PLS methods, the modified PLS (MPLS) approach is available for slow-time-varying data processing and quality-relevant fault detecting. However, it encounters heavy computational load in model updating, and the static control limits often lead to the low fault detection rate (FDR) or high false alarm rate (FAR). In this article, we first introduce the recursive MPLS (RMPLS) method for quality-relevant fault detection and computational complexity reducing, and then combine the local information increment (LII) method to obtain the time-varying control limits. First, the proposed LII-RMPLS method is capable of quality-relevant faults detection. Second, the adaptive threshold leads to higher FDRs and lower FARs compared with traditional methods. Third, the adaptive parameter-matrices-based model updating approach ensures that the proposed method has better robustness and lower computational complexity when dealing with time-varying factors.