Detecting Outliers in Electric Arc Furnace under the Condition of Unlabeled, Imbalanced, Non-stationary and Noisy Data

Measurement and Control - Tập 51 Số 3-4 - Trang 83-93 - 2018
Zhizhong Mao1
1Department of Control Theory and Control Engineering, Northeastern University, Shenyang, China

Tóm tắt

The presence of outliers is the main reason leading to ineffectiveness of advanced data-driven control methods in electric arc furnace systems. This paper proposes a hybrid method dedicated to detecting outliers in electric arc furnace systems, where process data are characterized as unlabeled, imbalanced, non-stationary and noisy. First, the raw data are divided into certain number of clusters. Then, with each cluster, a one-class classifier can be trained. So with these well-trained sub-models, new test points can be investigated. Those points that are rejected by all sub-models will be labeled as outliers. With the combination of one-class classification and clustering technique, the intricate data in electric arc furnace can be processed effectively. In addition, the detector will be updated with a specific strategy to enhance its adaptiveness. A series of experiments are carried out, and comparative results have shown the effectiveness of our method.

Từ khóa


Tài liệu tham khảo

Billings SA, 1979, Automatica, 15, 137, 10.1016/0005-1098(79)90065-7

Mao Z, 1996, Journal of Northeastern University, 17, 65

Parsapoor A, International conference on control, automation and systems

Srdic S, 2011, IEEE Transactions on Industrial Electronics, 58, 3349, 10.1109/TIE.2010.2089941

Bekker JG, 2000, Control Engineering Practice, 8, 445, 10.1016/S0967-0661(99)00163-X

Rashid MM, 2016, Journal of Process Control, 40, 50, 10.1016/j.jprocont.2015.12.012

Khoshkhoo H, 2011, Computers & Mathematics with Applications, 62, 4391, 10.1016/j.camwa.2011.10.009

Li L, 2012, Neurocomputing, 82, 91, 10.1016/j.neucom.2011.10.020

10.1177/0142331210397571

Jia MX, 2007, Journal of Northeastern University, 28, 1221

Dehghan Marvasti F, 2015, International Transactions on Electrical Energy Systems, 24, 1419, 10.1002/etep.1783

Park B, 2010, Electric Power Systems Research, 80, 7, 10.1016/j.epsr.2009.12.005

Chandola V, 2009, ACM Computing Surveys, 41, 15, 10.1145/1541880.1541882

Tax DMJ, 2004, Machine Learning, 54, 45, 10.1023/B:MACH.0000008084.60811.49

Bicego M, 2009, Pattern Recognition, 42, 27, 10.1016/j.patcog.2008.07.004

Žliobaitė I, 2014, Neurocomputing, 150, 240, 10.1016/j.neucom.2014.05.084

Thông tin
Thông tin xuất bản

Measurement and Control

Tập 51 Số 3-4

83-93

Thông tin tác giả