Deep Learning-based Fault Detection in the Tennessee Eastman Process

Nowadays, every sector has at least one fault that must be detected and diagnosed promptly to ensure appropriate monitoring. Numerous Fault Detection and Diagnostic (FDD) techniques have been proposed and implemented. In recent years, it has been shown that using Machine Learning (ML) to conduct FDD more precisely and effectively has been demonstrated. Deep Learning (DL) is one such application of machine learning. DL is a set of approaches for modeling data with a complex architecture by combining non-linear processes. The Tennessee Eastman Process (TEP) was used to demonstrate the aforementioned suggested approach.