基于TE-DS的半监督化工过程故障诊断方法

针对现有基于深度学习的化工过程故障诊断方法通常需要完备的标签数据才能构建故障诊断模型等局限,提出一种基于时间集成—双重学生模型(temporal ensembling-dual student, TE-DS)的半监督化工过程故障诊断方法。该方法首先以双重学生模型为基础,通过分类项约束、稳定性约束和一致性约束条件指导相互训练,有效地缓解了误差累积情况的发生;然后利用时间集成(temporal ensembling)将多个先前网络评估的预测集成作为一致性正则化对象,达到缓解预测值噪声、降低模型训练时间的目的,以提高分类性能,实现故障诊断;最后通过田纳西—伊斯曼(Tennessee-Eastman)化工过程基准数据进行故障诊断实验,验证提出方法的有效性和可行性,并与BNLSTM、DCNN和MCLSTM等有监督方法进行比较,证明了TE-DS算法对故障诊断的优越性。

Semi-supervised fault diagnosis method for chemical process based on TE-DS

Aiming at the limitation that the existing chemical process fault diagnosis methods based on deep learning usually need complete labeled data to build a fault diagnosis model, this paper proposed a semi-supervised fault diagnosis method for chemical process based on temporal ensembling-dual student model. Firstly, based on the dual student model, the method guided the mutual training through the classification constraint, the stability constraint and the consistency constraint, which effectively alleviated the error accumulation. Then it used temporal ensembling to integrate the prediction of multiple previous network evaluations as consistent regularization objects to alleviate the prediction noise and reduce the training time of the model, so as to improve the classification performance and realize fault diagnosis. Finally, this paper verified the validity and feasibility of the proposed method by the Tennessee-Eastman chemical process benchmark data. Compared with supervised methods such as BNLSTM, DCNN and MCLSTM, it is proved that TE-DS algorithm is superior to fault diagnosis.