Change Detection in a Distillation Column Based on the Generalized Likelihood Ratio Approach

Yahya Chetouani

doi:10.4172/2157-7048.1000115

Abstract

With increasing demands for efficiency, product quality, reliability and process safety, the field of fault detection (FD) plays an important role in chemical industries. This paper deals with a FD method based on the combination of Generalized Likelihood Ration Test (GLRT) and Artificial Neural Networks (ANNs). A reliable neural model in normal conditions, under all regimes (i.e. steady-state and dynamic conditions), is found by means of a NARX (Nonlinear Auto-Regressive with eXogenous input) model and by an experimental design. The efficiency of the combination of these two approaches used for detecting faults has been tested under real anomalous conditions on a real plant as a distillation column. From the experimental results, it is observed that the proposed FD is able to detect the process status effectively.

Highlights

Detection of occurrence of an abnormal event, fault or failure in an operating plant is vital for ensuring plant safety and maintaining product quality in chemical industries
The necessity to improve fault detection (FD) methods is further underlined by the finding that about 70% of industrial accidents are caused by human errors [1]
Artificial Neural Networks (ANNs) have an adaptive behavior i.e. they are able to adjust and to modify their behavior according to nonlinear dynamics of processes

Summary

Introduction

Detection of occurrence of an abnormal event, fault or failure in an operating plant is vital for ensuring plant safety and maintaining product quality in chemical industries. In modern process industry, there is a demand for data-based methods because of the complexity and the limited availability of the nonlinear models in chemical units. ANNs can be trained to learn new associations, complex modelling, functional dependencies and new patterns [2]. Owing to their inherent nature to model and learn complexities, ANNs have been successfully applied in medicine and biomedical studies [3]. They have found wide applications in various areas of chemical engineering [4,5]

Objectives

Results

Conclusion