A Review on Data‐Driven Learning Approaches for Fault Detection and Diagnosis in Chemical Processes

Abstract

Fault detection and diagnosis for process plants has been an active area of research for many years. This review presents a concise overview on supervised and unsupervised data‐driven approaches for fault detection and diagnosis in chemical processes. Methods based on supervised and unsupervised data‐driven techniques are reviewed, and the challenges in the field of fault detection and diagnosis have also been highlighted. It is observed that most of the data‐driven approaches are application specific, in that no single method can be used to obtain a generalized solution for nearly all purposes. The methods reviewed differ significantly from one to the other, and hence it is difficult to generalize any key similarity. The majority of the works proposed in the literature focused mainly on single fault detection, and do not cover the root‐cause diagnosis of the detected faults. In cases where both detection and diagnosis are performed, the focus is mainly for a single fault. In addition, majority of the articles do not extend to the diagnosis of the root cause for multiple and simultaneous faults.

Review of Multiscale Methods for Process Monitoring, With an Emphasis on Applications in Chemical Process Systems

“…Taqvi et al [41] Process industries Overview and categorize data-driven approaches in fault detection and diagnosis in process industries. 2021…”

Multiscale Principal Component Analysis-Signed Directed Graph Based Process Monitoring and Fault Diagnosis

“…Its vital contribution is introducing a process monitoring method based on multiscale PCA-SDG. Fault diagnostic techniques based on multiscale PCA-SDG are effective for convenient accuracy and easy diagnosis, and it allows operators to respond to strange events at an early stage . The multiscale PCA-SDG diagnostics framework leads to early identification and diagnosis of unusual circumstances that may react to measured variable contribution changes in correlation information.…”

Simultaneous fault diagnosis based on multiple kernel support vector machine in nonlinear dynamic distillation column

“…SVM has gained much attention due to its generalization ability and becomes a familiar machine-learning and classification tool as compared to the neural network. 35 SVM has been used in various applications including pattern recognition, face detection, text detection, prediction, and classification. In 2004, a fault diagnosis technique using the Fisher discriminant analysis (FDA) and comparison with SVM were done by Chaing.…”