An LSTM auto-encoder based anomaly detection for industrial system
In the context of the industrial internet,automatic and effective anomaly detection methods are of great significance to the safe and stable production of industrial systems.Traditional anomaly detection methods have the disadvantages of requiring a large number of labeled samples,and not adapting t...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2020-07-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020188/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841530670530166784 |
|---|---|
| author | Xiaojun SHEN Yanan GE Zhihao SHEN Yangdan NI Mingqi LV Zhengqiu WENG |
| author_facet | Xiaojun SHEN Yanan GE Zhihao SHEN Yangdan NI Mingqi LV Zhengqiu WENG |
| author_sort | Xiaojun SHEN |
| collection | DOAJ |
| description | In the context of the industrial internet,automatic and effective anomaly detection methods are of great significance to the safe and stable production of industrial systems.Traditional anomaly detection methods have the disadvantages of requiring a large number of labeled samples,and not adapting to high-dimensional time series data.Aiming at these limitations,an industrial system anomaly detection method based on LSTM (long short-term memory)auto-encoder was proposed.Firstly,to address the limitation of relying on labeled samples,an encoder used to learn the features and patterns of a large number of normal samples in an unsupervised manner.Then,anomaly detection was performed via reconstructing samples and calculating the reconstruction error.Secondly,to adapt to high-dimensional time series data,a BiLSTM (bidirectional LSTM) was used as an encoder,and then the potential characteristics of multi-dimensional time series data were mined.Experiments based on a real paper industry data set which demonstrate this method has improved the existing unsupervised anomaly detection methods in various indicators,and the overall accuracy of the detection has reached 93.4%. |
| format | Article |
| id | doaj-art-63ced06f910f4ee7819ff4524abb98b6 |
| institution | Kabale University |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2020-07-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-63ced06f910f4ee7819ff4524abb98b62025-01-15T03:00:28ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012020-07-013613614559582303An LSTM auto-encoder based anomaly detection for industrial systemXiaojun SHENYanan GEZhihao SHENYangdan NIMingqi LVZhengqiu WENGIn the context of the industrial internet,automatic and effective anomaly detection methods are of great significance to the safe and stable production of industrial systems.Traditional anomaly detection methods have the disadvantages of requiring a large number of labeled samples,and not adapting to high-dimensional time series data.Aiming at these limitations,an industrial system anomaly detection method based on LSTM (long short-term memory)auto-encoder was proposed.Firstly,to address the limitation of relying on labeled samples,an encoder used to learn the features and patterns of a large number of normal samples in an unsupervised manner.Then,anomaly detection was performed via reconstructing samples and calculating the reconstruction error.Secondly,to adapt to high-dimensional time series data,a BiLSTM (bidirectional LSTM) was used as an encoder,and then the potential characteristics of multi-dimensional time series data were mined.Experiments based on a real paper industry data set which demonstrate this method has improved the existing unsupervised anomaly detection methods in various indicators,and the overall accuracy of the detection has reached 93.4%.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020188/abnormal detectionindustrial Internetauto-encoderLSTM |
| spellingShingle | Xiaojun SHEN Yanan GE Zhihao SHEN Yangdan NI Mingqi LV Zhengqiu WENG An LSTM auto-encoder based anomaly detection for industrial system Dianxin kexue abnormal detection industrial Internet auto-encoder LSTM |
| title | An LSTM auto-encoder based anomaly detection for industrial system |
| title_full | An LSTM auto-encoder based anomaly detection for industrial system |
| title_fullStr | An LSTM auto-encoder based anomaly detection for industrial system |
| title_full_unstemmed | An LSTM auto-encoder based anomaly detection for industrial system |
| title_short | An LSTM auto-encoder based anomaly detection for industrial system |
| title_sort | lstm auto encoder based anomaly detection for industrial system |
| topic | abnormal detection industrial Internet auto-encoder LSTM |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2020188/ |
| work_keys_str_mv | AT xiaojunshen anlstmautoencoderbasedanomalydetectionforindustrialsystem AT yanange anlstmautoencoderbasedanomalydetectionforindustrialsystem AT zhihaoshen anlstmautoencoderbasedanomalydetectionforindustrialsystem AT yangdanni anlstmautoencoderbasedanomalydetectionforindustrialsystem AT mingqilv anlstmautoencoderbasedanomalydetectionforindustrialsystem AT zhengqiuweng anlstmautoencoderbasedanomalydetectionforindustrialsystem AT xiaojunshen lstmautoencoderbasedanomalydetectionforindustrialsystem AT yanange lstmautoencoderbasedanomalydetectionforindustrialsystem AT zhihaoshen lstmautoencoderbasedanomalydetectionforindustrialsystem AT yangdanni lstmautoencoderbasedanomalydetectionforindustrialsystem AT mingqilv lstmautoencoderbasedanomalydetectionforindustrialsystem AT zhengqiuweng lstmautoencoderbasedanomalydetectionforindustrialsystem |