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.

操作绩效评估（OPE）一直在确保化学过程的有效运营中发挥重要作用。但是，以往的大多数研究都集中在确定性评估策略上，而不考虑OPE评估指标的不确定性。基于概率模糊理论，提出了一种基于化学过程不确定性的在线OPE方案。在建模步骤中，在实时学习和概率主成分回归的基础上，提出了预测模型，并将其应用于实时评估评估指标的概率分布。开发了加权余弦Mahalanobis-Taguchi变量选择系统，以提高评估指标的预测准确性。在评估步骤中，提出了一种概率模糊推理方法，通过考虑评估指标的不确定性来提高评估结果的准确性。最后，在工业加氢裂化工艺上测试了该方法的有效性。