Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering
The coal pulverizing system is an important auxiliary system in thermal power generation systems. The working condition of a coal pulverizing system may directly affect the safety and economy of power generation. Prognostics and health management is an effective approach to ensure the reliability of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/11/3271 |
| _version_ | 1797565773287260160 |
|---|---|
| author | Zian Chen Zhiyu Yan Haojun Jiang Zijun Que Guozhen Gao Zhengguo Xu |
| author_facet | Zian Chen Zhiyu Yan Haojun Jiang Zijun Que Guozhen Gao Zhengguo Xu |
| author_sort | Zian Chen |
| collection | DOAJ |
| description | The coal pulverizing system is an important auxiliary system in thermal power generation systems. The working condition of a coal pulverizing system may directly affect the safety and economy of power generation. Prognostics and health management is an effective approach to ensure the reliability of coal pulverizing systems. As the coal pulverizing system is a typical dynamic and nonlinear high-dimensional system, it is difficult to construct accurate mathematical models used for anomaly detection. In this paper, a novel data-driven integrated framework for anomaly detection of the coal pulverizing system is proposed. A neural network model based on gated recurrent unit (GRU) networks, a type of recurrent neural network (RNN), is constructed to describe the temporal characteristics of high-dimensional data and predict the system condition value. Then, aiming at the prediction error, a novel unsupervised clustering algorithm for anomaly detection is proposed. The proposed framework is validated by a real case study from an industrial coal pulverizing system. The results show that the proposed framework can detect the anomaly successfully. |
| first_indexed | 2024-03-10T19:17:45Z |
| format | Article |
| id | doaj.art-3410d558f15144efa18281f0e410eff0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T19:17:45Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3410d558f15144efa18281f0e410eff02023-11-20T03:13:11ZengMDPI AGSensors1424-82202020-06-012011327110.3390/s20113271Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and ClusteringZian Chen0Zhiyu Yan1Haojun Jiang2Zijun Que3Guozhen Gao4Zhengguo Xu5College of Control Science and Engineering, Zhejiang University, Hangzhou 310000, ChinaCollege of Control Science and Engineering, Zhejiang University, Hangzhou 310000, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou 310000, ChinaCollege of Control Science and Engineering, Zhejiang University, Hangzhou 310000, ChinaCollege of Control Science and Engineering, Zhejiang University, Hangzhou 310000, ChinaCollege of Control Science and Engineering, Zhejiang University, Hangzhou 310000, ChinaThe coal pulverizing system is an important auxiliary system in thermal power generation systems. The working condition of a coal pulverizing system may directly affect the safety and economy of power generation. Prognostics and health management is an effective approach to ensure the reliability of coal pulverizing systems. As the coal pulverizing system is a typical dynamic and nonlinear high-dimensional system, it is difficult to construct accurate mathematical models used for anomaly detection. In this paper, a novel data-driven integrated framework for anomaly detection of the coal pulverizing system is proposed. A neural network model based on gated recurrent unit (GRU) networks, a type of recurrent neural network (RNN), is constructed to describe the temporal characteristics of high-dimensional data and predict the system condition value. Then, aiming at the prediction error, a novel unsupervised clustering algorithm for anomaly detection is proposed. The proposed framework is validated by a real case study from an industrial coal pulverizing system. The results show that the proposed framework can detect the anomaly successfully.https://www.mdpi.com/1424-8220/20/11/3271anomaly detectiongated recurrent unittemporalclustering |
| spellingShingle | Zian Chen Zhiyu Yan Haojun Jiang Zijun Que Guozhen Gao Zhengguo Xu Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering Sensors anomaly detection gated recurrent unit temporal clustering |
| title | Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering |
| title_full | Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering |
| title_fullStr | Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering |
| title_full_unstemmed | Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering |
| title_short | Detecting Coal Pulverizing System Anomaly Using a Gated Recurrent Unit and Clustering |
| title_sort | detecting coal pulverizing system anomaly using a gated recurrent unit and clustering |
| topic | anomaly detection gated recurrent unit temporal clustering |
| url | https://www.mdpi.com/1424-8220/20/11/3271 |
| work_keys_str_mv | AT zianchen detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering AT zhiyuyan detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering AT haojunjiang detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering AT zijunque detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering AT guozhengao detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering AT zhengguoxu detectingcoalpulverizingsystemanomalyusingagatedrecurrentunitandclustering |