Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, PR China.
Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education, East China University of Science and Technology, Shanghai 200237, PR China.
ISA Trans. 2019 Jan;84:247-261. doi: 10.1016/j.isatra.2018.10.011. Epub 2018 Oct 15.
Recently, based on the powerful capability of feature extraction, deep learning technique has been applied to the field of process monitoring, and usually, the researches utilize all the abstract features to establish the detection model and detect or classify the fault. However, whether all the extracted features are valid and beneficial for process monitoring have never been researched and discussed. If there are some features that are adverse for process monitoring, the detection performance of the model would be reduced once they are considered in the model, and utilized the features that are advantageous for process monitoring could ameliorate the performance of detection model. Motivated by this, a feasibility analysis on each feature captured by deep belief network for process monitoring is executed and the conception of active features (AFs) which have active expression for the occurrence of the fault is proposed. Based on AFs, utilized Euclidean metric to calculate the dissimilarity between the test sample and the training sample, and moving average technique is employed to reduce the effect of the burst noise in measurement variables on the result. Finally, the comparison of fault detection rate with other advanced methods on a numerical process and TE process demonstrate the feasibility and superiority of the proposed method, AF-DBN in this study.
最近，基于强大的特征提取能力，深度学习技术已经应用于过程监测领域，通常，研究人员利用所有抽象特征来建立检测模型，并进行故障检测或分类。然而，对于过程监测而言，所有提取的特征是否都是有效的和有益的，这一点从未被研究和讨论过。如果存在一些对过程监测不利的特征，那么一旦在模型中考虑到这些特征，模型的检测性能就会降低，而利用对过程监测有利的特征可以改善检测模型的性能。受此启发，对深度置信网络捕捉到的每个特征进行了过程监测的可行性分析，并提出了主动特征（AF）的概念，该概念对故障的发生具有积极的表达。基于 AF，利用欧几里得度量来计算测试样本和训练样本之间的相似度，并采用移动平均技术来减少测量变量中的突发噪声对结果的影响。最后，通过在数值过程和 TE 过程上与其他先进方法的故障检测率比较，验证了所提出的方法（AF-DBN）的可行性和优越性。
