基于SSAE的非线性系统故障分类方法  

Fault Classification Method of Nonlinear Systems Based on Stacked Sparse Autoencoders

作　　者：杨泽宇 王培良[1,2] 叶晓丰 YANG Ze-yu;WANG Pei-liang;YE Xiao-feng(School of Electronic Information,Hangzhou Dianzi University,Hangzhou 310018,China;School of Engineering,Huzhou University,Huzhou 313000,China)

机构地区：[1]杭州电子科技大学电子信息学院,杭州310018 [2]湖州师范学院工学院,浙江湖州313000

出　　处：《控制工程》2018年第11期2003-2009,共7页Control Engineering of China

基　　金：国家自然科学基金资助项目(61573137)

摘　　要：针对核独立成分分析（KICA）方法虽能对非线性非高斯过程数据有很好的处理能力,但是却不能有效地进行故障分类的问题,提出了一种将堆叠稀疏自动编码器（SSAE）与KICA方法结合的复杂系统故障分类方法。首先利用KICA提取数据的主导独立成分,然后通过SSAE和softmax分类器所构成的完整SSAE分类算法建立模型,该模型采用非监督逐层贪婪训练算法初始化网络权重,并使用有限内存拟牛顿（L-BFGS）算法进行反向微调各参数,最后将过程数据输入到该训练好的模型,实现故障分类。TE过程的实验结果表明,KICA-SSAE算法的故障平均分类精度较高,表现出良好的分类效果。The multivariate statistics based on kernel independent component analysis（KICA） is mainly used for fault detection of industrial processes. While, it is not effective in fault classification. For this reason, a fault classification method of complex systems with stacked sparse auto encoder（SSAE） and the softmax classifier is proposed. First of all, the KICA is utilized to extract the leading independent component among the data set, and then model is set up on the training data according to the complete SSAE algorithm. Meanwhile, greedy layer-wise unsupervised learning algorithm is used to initialize the weights of the network and L-BFGS algorithm is adopted to optimize the parameters of the network. Finally, the test data is fed to the trained model to realize fault classification. According to the experimental result on Tennessee Eastman（TE） simulation platform, the average classification rate of KICA-SSAE is higher, showing a better classification effect.

关 键 词：堆叠稀疏自动编码器 核独立成分分析 softmax分类器 故障分类 TE过程 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]