An LSTM auto-encoder based anomaly detection for industrial system

Xiaojun SHEN; Yanan GE; Zhihao SHEN; Yangdan NI; Mingqi LV; Zhengqiu WENG

doi:10.11959/j.issn.1000-0801.2020188

您当前的位置：

首页 >

文章列表页 >

An LSTM auto-encoder based anomaly detection for industrial system

Operation Technology | 更新时间：2024-06-05

- An LSTM auto-encoder based anomaly detection for industrial system
- Telecommunications Science Vol. 36, Issue 7, Pages: 136-145(2020)
- 作者机构：
  
  1. 国网浙江省电力有限公司，浙江杭州 310007
  2. 浙江工业大学，浙江杭州 310023
  3. 温州职业技术学院，浙江温州 325035
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2020188
  CLC： TN929.5
- Published Online：2020-07，
  
  Published：20 July 2020
- 稿件说明：
移动端阅览
Xiaojun SHEN, Yanan GE, Zhihao SHEN, et al. An LSTM auto-encoder based anomaly detection for industrial system[J]. Telecommunications science, 2020, 36(7): 136-145.
DOI：

Xiaojun SHEN, Yanan GE, Zhihao SHEN, et al. An LSTM auto-encoder based anomaly detection for industrial system[J]. Telecommunications science, 2020, 36(7): 136-145. DOI： 10.11959/j.issn.1000-0801.2020188.

摘要

在工业互联网的环境下，自动有效的异常检测方法对工业系统的安全、稳定生产具有重要的意义。传统的异常检测方法存在需要大量标注样本、不适应高维度时序数据等不足，提出一种基于LSTM自动编码机的工业系统异常检测方法。为克服现有方法依赖标注样本的不足，提出采用自动编码机，通过无监督的方式学习大量正常样本的特征和模式，在此基础上通过对样本进行重构和计算重构误差的方式进行异常检测。其次，为克服现有方法不适应高维度时序数据的不足，提出采用双向LSTM作为编码器，进而挖掘多维时序数据的潜在特征。基于一个真实造纸工业的数据集的实验表明，所提方法在各项指标上都对现有无监督异常检测方法有一定的提升，检测的总体精度达到了93.4%。

Abstract

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%.

关键词

Keywords

references

ZHOU L Y , GUO H Q . Anomaly detection methods for IoT Networks [C ] // Proceedings of 2018 IEEE International Conference on Service Operations and Logistics,and Informatics (SOLI) . Piscataway:IEEE Press , 2018 : 214 - 219 .

GENGE B , PIROSKA H , CALIN E . Anomaly detection in aging industrial internet of things [J ] . IEEE Access , 2019 ( 99 ):1.

WONG T , LUO Z . Recurrent auto-encoder model for large-scale industrial sensor signal analysis [C ] // Proceedings of International Conference on Engineering Applications of Neural Networks . Berlin:Springer , 2018 : 203 - 216

HUANG H K . Real-time fault-detection for IoT facilities using GBRBM-based DNN [J ] . IEEE Internet of Things Journal , 2019 ( 10 ): 1 - 1 .

RIEGER T , . Fast predictive maintenance in industrial internet of things (IIoT) with deep learning (DL):a review [C ] // Proceedings of 2019 Collaborative European Research Conference (CERC2019).[S.l.:s.n] . 2019 : 69 - 79 .

KANAWADAY A , SANE A . Machine learning for predictive maintenance of industrial machines using IoT sensor data [C ] // Proceedings of 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS) . Piscataway:IEEE Press , 2017 : 107 - 110 .

ABU A , HANEEN A . Effects of distance measure choice on K-nearest neighbor classifier performance:a review [J ] . Big Data , 2019 ( 7 ): 221 - 248 .

BREUNING M , . LOF:identifying density-based local outliers [C ] // Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data . New York:ACM Press , 2000 , 29 ( 2 ): 93 - 104 .

TANG J , . Enhancing effectiveness of outlier detections for low density patterns [C ] // Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining . Berlin:Springer , 2002 .

GRIFFIN J M , DOBERTI A J , VALBORT H , et al . Multiple classification of the force and acceleration signals extracted during multiple machine processes:part 1 intelligent classification from an anomaly perspective [J ] . International Journal of Advanced Manufacturing Technology , 2017 ( 93 ): 1 - 13 .

NANDURI A , SHERRY L . Anomaly detection in aircraft data using recurrent neural networks (RNN) [C ] // Proceedings of 2016 Integrated Communications Navigation and Surveillance (ICNS) . Piscataway:IEEE Press , 2016 .

JANSSENS O . Convolutional neural network based fault detection for rotating machinery [J ] . Journal of Sound and Vibration , 2016 ( 377 ): 331 - 345 .

AMRUTHNATH N , TARUN G . A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance [C ] // Proceedings of 2018 5th International Conference on Industrial Engineering and Applications (ICIEA) . Piscataway:IEEE Press , 2018 : 355 - 361 .

DIEZ-OLIVAN A , RUBIO J A P . Kernel-based support vector machines for automated health status assessment in monitoring sensor data [J ] . The International Journal of Advanced Manufacturing Technology , 2018 , 95 ( 1-4 ): 327 - 340 .

JOSHI S , PHOHA V . Investigating hidden Markov models capabilities in anomaly detection [C ] // Proceedings of the 43rd Annual Southeast Regional Conference . New York:ACM Press , 2005 : 98 - 103 .

FENG T Z , DU Z H , SUN Y K , et al . Real-time anomaly detection of short-time-scale gwac survey light curves [C ] // Proceedings of 2017 IEEE International Congress on Big Data (BigData Congress) . Piscataway:IEEE Press , 2017 : 224 - 231 .

SERDIO F , LUGHOFER E , PICHLER K , et al . Residual-based fault detection using soft computing techniques for condition monitoring at rolling mills [J ] . Information Sciences , 2014 ( 259 ): 304 - 320 .

KINGMA D P . Auto-encoding variational bayes [J ] . arXiv:1312.6114 . 2013

LU C , WANG Z Y , QIN W L , et al . Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification [J ] . Signal Processing , 2016 ( 130 ): 377 - 388 .

HOCHREITER S , SCHMIDHUBER J . Long short-term memory [J ] . Neural computation , 1997 ( 9 ): 1735 - 1780 .

RANJAN C . Dataset:rare event classification in multivariate time series [J ] . arXiv:1809.10717 . 2018

SCHOLKOPF B , WILLIAMSONET R , et al . Support vector method for novelty detection [C ] // Proceedings of the 12th International Conference on Neural Information Processing Systems . Cambridge:MIT Press , 1999 : 582 - 588 .

LIU F T , TING K M , ZHOU Z H . Isolation-based anomaly detection [J ] . ACM Transactions on Knowledge Discovery from Data (TKDD) , 2012 , 6 ( 1 ): 1 - 39 .

MALHOTRA P . LSTM-based encoder-decoder for multi-sensor anomaly detection [J ] . arXiv:1607.00148 . 2016

Views

1538

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analysis and research on the impact of medium voltage power line carrier communication

Deterministic service level agreement: indicator classification in private networks for vertical industry

A survey on redundancy mechanisms in time-sensitive networking

Research on 5G core network service model intelligent prediction

An industrial internet business management platform that supports the cloud-native

Related Author

SU Yuzhong

ZHAO Tonghan

SHOU Guochu

HU Yihong

LIU Yaqiong

LI Xiaoliang

WANG Ke

LI Hongxing

Related Institution

Guyuan Power Supply Company, State Grid Ningxia Electric Power Co., Ltd.

China Mobile Group Design Institute Co., Ltd.

China Academy of Information and Communications Technology

Beijing University of Posts and Telecommunications

Beijing Key Laboratory of Network System Architecture and Convergence

⁰