An online operating performance evaluation approach using probabilistic fuzzy theory for chemical processes with uncertainties

Operating performance evaluation (OPE) has been playing an essential role to ensure the effective operations of chemical processes. However, most of previous research focused on the deterministic evaluation strategies, without consideration of uncertainties in the evaluation indicators of OPE. Based on probabilistic fuzzy theory, an online OPE scheme is proposed by considering the uncertainties in chemical processes. In the modeling step, on the basis of just-in-time learning and probabilistic principal component regression, a prediction model is proposed and applied to estimate the probability distribution of the evaluation indicators in real time; and a weighted cosine Mahalanobis-Taguchi system for variable selection is developed to improve the prediction accuracy of the evaluation indicators. In the evaluation step, a probabilistic fuzzy inference method is proposed to improve the accuracy of evaluation results by considering the uncertainty of evaluation indicators. The effectiveness of the proposed approach is finally tested on an industrial hydrocracking process. (C) 2020 Elsevier Ltd. All rights reserved.

Automated summary

The study proposed an online OPE scheme based on probabilistic fuzzy theory to consider uncertainties in chemical processes, including methods for establishing prediction models, improving prediction accuracy of evaluation indicators, and a probabilistic fuzzy inference method to enhance evaluation results by considering uncertainty of evaluation indicators.