An Anomaly Detection Method for Nonlinear Industrial Process Using Sparse Stacked Denoising Autoencoder - Details

author：

Yang, Mingwei (Yang, Mingwei.) ^[1] | Liu, YanHua (Liu, YanHua.) ^[2] (Scholars：刘延华) | Chen, Hong (Chen, Hong.) ^[3] | Lin, Jiefei (Lin, Jiefei.) ^[4] | Lin, Haoqiang (Lin, Haoqiang.) ^[5]

Indexed by：

Abstract：

With　the　increasing　complexity　of　industrial　systems,　new　challenges　are　posed　to　the　monitoring　of　industrial　process　data,　which　often　appear　to　be　characterized　by　nonlinear　and　strong　feature　correlation.　Therefore,　a　sparse　stacked　denoise　autoencoder(SSDAE)　based　anomaly　detection　model　is　proposed　in　the　paper,　which　uses　the　autoencoder　model　to　capture　the　nonlinear　feature　structure　in　the　industrial　data,　and　we　extract　the　feature　space　and　the　residual　space　to　build　a　statistic　to　capture　the　system　changes,　and　finally　use　the　KDE　to　determine　the　threshold　to　detect　the　anomalies.　In　this　paper,　using　the　Tennesse-Eastman　dataset,　method　validation　is　carried　out　and　compared　with　algorithms　such　as　PCA,　DAE　and　LRAE,　which　verifies　the　effectiveness　of　the　algorithm,　improves　the　detection　rate　of　faults,　and　is　able　to　identify　more　faults.　©　2023　IEEE.

Keyword：

Anomaly detection Learning systems Process monitoring

Community：

[ 1 ] [Yang, Mingwei]Fuzhou University, College of Computer and Data Science, Fuzhou, China
[ 2 ] [Liu, YanHua]Fuzhou University, College of Computer and Data Science, Fuzhou, China
[ 3 ] [Chen, Hong]State Grid Info-Telecom Great Power Science and Technology CO.,LTD, Fuzhou; 350000, China
[ 4 ] [Lin, Jiefei]State Grid Info-Telecom Great Power Science and Technology CO.,LTD, Fuzhou; 350000, China
[ 5 ] [Lin, Haoqiang]State Grid Info-Telecom Great Power Science and Technology CO.,LTD, Fuzhou; 350000, China