Fault Detection of Complex Processes Using nonlinear Mean Function Based Gaussian Process Regression: Application to the Tennessee Eastman Process

摘要

Process monitoring or fault detection and diagnosis have gained tremendous attention over the past decade in order to achievebetter product quality, minimise downtime and maximise profit in process industries. Among various process monitoringtechniques, data-based machine learning approaches have become immensely popular in the past decade.However, a promisingmachine learning technique Gaussian process regression has not yet received adequate attention for process monitoring. Inthis work, Gaussian process regression (GPR)-based process monitoring approach is applied to the benchmark TennesseeEastman challenge problem. Effect of various GPR hyper-parameters onmonitoring efficiency is also thoroughly investigated.The results of GPR model is found to be better than many other techniques which is reported in a comparative study in thiswork.