摘要：AbstractAccurate modeling of industrial processes is an important topic in process systems engineering for further anomaly detection and fault diagnosis. Dynamics is inevitable in these processes, and several dynamic variants were proposed in the literature to extract both cross-correlations and auto-correlations between process variables and quality variables. However, all of them focus on the auto-correlations in process variables only, while the valuable auto-regressive information between collected quality variables is ignored. In this paper, a new dynamic auto-regressive partial least squares (DAPLS) method is proposed to capture the auto-correlations of both process and quality variables as well as the cross-correlations between them. In DAPLS, quality-relevant dynamics are exploited by maximizing the covariance between current quality sample and the weighted combinations of both past process and quality samples. Its inner modeling objective is also explicit and consistent with its outer model. The case studies with the numerical simulations and the Tennessee Eastman process have demonstrated the effectiveness of the proposed model.
关键词：KeywordsDynamic partial least squaresauto-regressive exogenoussupervised modeling
