Open Access

ARTICLE

Key Process Protection of High Dimensional Process Data in Complex Production

He Shi^1,2,3,4, Wenli Shang^1,2,3,4,*, Chunyu Chen^1,2,3,4, Jianming Zhao^1,2,3,4, Long Yin^{1, 2, 3, 4}
1 University of Chinese academy of sciences, Beijing, China.
2 Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China.
3 Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang, China.
4 Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China.
* Corresponding Author: Wenli Shang. Email: .

Computers, Materials & Continua 2019, 60(2), 645-658. https://doi.org/10.32604/cmc.2019.05648

Abstract

In order to solve the problem of locating and protecting key processes and detecting outliers efficiently in complex industrial processes. An anomaly detection system which is based on the two-layer model fusion frame is designed in this paper. The key process is located by using the random forest model firstly, then the process data feature selection, dimension reduction and noise reduction are processed. Finally, the validity of the model is verified by simulation experiments. It is shown that this method can effectively reduce the prediction accuracy variance and improve the generalization ability of the traditional anomaly detection model from the experimental results.

---

Keywords

Industrial control system, outlier detection, anomaly detection system, rule tree model

---