文献类型：期刊文献

英文题名：Self-Adaption AAE-GAN for Aluminum Electrolytic Cell Anomaly Detection

作者：Cao, Danyang[1,2];Liu, Di[1];Ren, Xu[1];Ma, Nan[3]

第一作者：Cao, Danyang

通讯作者：Cao, DY[1];Cao, DY[2]

机构：[1]North China Univ Technol, Sch Informat Sci & Technol, Beijing 100144, Peoples R China;[2]Beijing Key Lab Integrat & Anal Large Scale Strea, Beijing 100144, Peoples R China;[3]Beijing Union Univ, Coll Robot, Beijing 100101, Peoples R China

第一机构：North China Univ Technol, Sch Informat Sci & Technol, Beijing 100144, Peoples R China

通讯机构：[1]corresponding author), North China Univ Technol, Sch Informat Sci & Technol, Beijing 100144, Peoples R China;[2]corresponding author), Beijing Key Lab Integrat & Anal Large Scale Strea, Beijing 100144, Peoples R China.

年份：2021

卷号：9

起止页码：100991-101002

外文期刊名：IEEE ACCESS

收录：;EI(收录号：20213010675666);Scopus(收录号：2-s2.0-85110789396);WOS:【SCI-EXPANDED(收录号:WOS:000675189000001)】；

基金：This work was supported in part by the Yuyou Talent Support Plan of North China University of Technology under Grant 107051360019XN132/017, and in part by the Fundamental Research Funds for Beijing Universities under Grant 110052971803/037.

语种：英文

外文关键词：Anomaly detection; Time series analysis; Aluminum; Production; Generative adversarial networks; Image reconstruction; Generators; Aluminum electrolytic cell; anomaly detection; AAE-GAN; multivariate time series; imbalanced industrial time series

摘要：Nowadays, the anomaly detection of aluminum electrolysis cell is a big problem in the aluminum electrolysis industry. The problem of unbalanced time series samples is common in industrial applications. The number of samples under normal conditions is much larger than that under abnormal conditions. In the electrolytic aluminum industry, this problem is even more serious, it is very difficult to find abnormal samples in industrial production because experts do not have a clear criterion to judge abnormalities. In traditional machine learning algorithms, such as support vector machine (SVM) and convolutional neural network (CNN), it is difficult to obtain high classification accuracy on the problem of class imbalance, and these methods tend to be more biased towards positive samples. In recent years, generative adversarial network (GAN) has become more and more popular in the field of anomaly detection. However, these methods need to find the best mapping from the actual space to the latent space in the anomaly detection stage, and the optimization process may bring new errors and take a long time. In this article, we use the ability of GAN to model complex high-dimensional image distribution, and propose a self-adaption AAE-GAN network based on adaptive changes of input samples. This time series anomaly detection method converts multi-dimensional time series data into a two-dimensional matrix, and only normal samples are needed in the training process, which effectively solves the above problems. The method we proposed is to use encoder and decoder to constitute a generator and a discriminator. During the training process, the generator and the discriminator are trained jointly and confrontationally, so that the mapping ability of the encoder can be fully reflected. In the anomaly detection stage, we determine whether the sample is abnormal according to the size of the reconstruction difference. Experimental results show that the detection accuracy and speed of this method are very high.