Application case study of machine learning techniques towards a fault diagnosis system for a manufacturing plant environment

Abstract

Fault diagnosis is a vital problem in process engineering. It is the fundamental component of anomalous event management (AEM) which has attracted a lot of attention over recent years. AEM deals with the timely detection, diagnosis and correction of abnormal conditions of faults in a process. Early detection and diagnosis of process faults while the plant is still operating in a controllable region can help avoid anomalous event evolution, improve uptime and reduce efficiency loss. There is a great quantity of literature on process fault diagnosis ranging from analytical methods to artificial intelligence and statistical approaches. From a modeling perspective, there are methods that require accurate process models, semi-quantitative models, or qualitative models. At the other end of the gamut, there are methods that do not assume any form of model information and rely only on historical process data. In this paper we present the performance of few approaches of data driven modeling /machine learning techniques on the simulated data from a distillation column.

Enhancing Fault Detection in CNC Machinery: A Deep Learning and Genetic Algorithm Approach

“…A particular case study conducted by Rao et al [13] put forth a machine learning approach for diagnosing faults in industrial equipment. In this research, the authors utilized support vector machines (SVMs) and artificial neural networks (ANNs) to classify varying types of faults.…”