Multiscale PCA (MSPCA) is a well-established fault-detection and isolation (FDI) technique. It utilizes wavelet analysis and PCA to extract important features from process data. This study demonstrates limitations in the conventional MSPCA fault detection algorithm, thereby proposing an enhanced MSPCA (EMSPCA) FDI algorithm that uses a new wavelet thresholding criterion. As such, it improves the projection of faults in the residual space and the threshold estimation of the fault detection statistic. When tested with a synthetic model, EMSPCA resulted in a 30% improvement in detection rate with equal false alarm rates. The EMSPCA algorithm also relies on the novel application of reconstruction-based fault isolation at multiple scales. The proposed algorithm reduces fault smearing and consequently improves fault isolation performance. The paper will further investigate the use of soft vs. hard wavelet thresholding, decimated vs. undecimated wavelet transforms, the choice of wavelet decomposition depth, and their implications on FDI performance.The FDI performance of the developed EMSPCA method was illustrated for sensor faults. This undertaking considered synthetic data, the simulated data of a continuously stirred reactor (CSTR), and experimental data from a packed-bed pilot plant. The results of these examples show the advantages of EMSPCA over existing techniques.

Multiclass fault classification in complex processes is challenging due to many classes, nonlinear dynamics, overlapping fault signatures, and expanding fault taxonomies. Traditional machine learning models often struggle in such settings. The goal of this paper is to develop a model-agnostic, extensible framework. The proposed methodology aims to boost any base classifier via optimization, interval-based feature selection, and intelligent binary decomposition. By restructuring a multiclass task into hierarchies of binary subproblems and linking each boundary to automatically selected statistical features, the developed method improves diagnostic accuracy and generalization. Experimental results on a large-scale dataset demonstrate improved performance compared to existing methods, achieving a high accuracy rate. Although the approach increases the computation time, the notable improvements in accuracy make the balance between precision and computation time advantageous for real-world use.