Abstract
Steel markets are very competitive and demand greater gauge precision and higher production rates. These growing requirements result in tandem rolling mill, which is of substantial interest to the steel industry, in order to improve quality and productivity. In such an environment, it is important to construct appropriate condition monitoring, which can lead to achieving the highest economic efficiency and avoiding equipment damage. This paper proposes a comprehensive condition monitoring methodology based on statistical feature extraction technique to increase the efficiency of feature extraction from high-dimensional feature space. It is examined that one can explore easily the effective features by using three-dimensional feature space for the condition monitoring. The method has been applied on condition monitoring of the stationary rolling in steel industry.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asch A, Hohn W (1999) Monitoring system for roll stand drives using strain gage technology. In: Proceedings of international federation of automatic control: automation in mining, mineral, and metal processing, pp 159–164
Cerv H, Kefller H, Luckmann F, Mackel J (1998) Mill diagnostic system (MiDaS)—a monitoring system with quality and maintenance-related diagnostic functions. Aluminium 74(3):148–154
Vinod DT, Jayant PM, Girish DM (2011) Vibration based condition monitoring of rolling mill. Int J Sci Eng Res 2(12):2229–5518
Donkle LB (1999) Fifth-octave chatter problem solved using vibration analysis. AISE Steel Technol 76(11):40–45
Mohammad RN, Mohammad RF, Mahmud S, Mohsen K (2012) Frequency analysis of chatter vibrations in tandem rolling mills. J VibroEng 14(2):1392–8716
Kimmura Y, Sodani Y, Nishiura N, Ikeuchi N, Mihara Y (2003) Analysis of chatter in tandem cold rolling mills. ISIJ Int 43(1):77–84
Widodo A, Yang BS (2007) Application of nonlinear feature extraction and support vector machines for fault diagnosis of induction motors. Expert Syst Appl 33(1):241–250
Yang BS, Han T, Hwang WW (2005) Application of multi-class support vector machines for fault diagnosis of rotating machinery. J Mech Sci Technol 19(3):845–858
Srilatha C, Ajith A, Johnson PT (2004) Feature deduction and ensemble design of intrusion detection systems. Comput Secur 24(4):295–307
Mandokht M, Glenn F, Jennifer GD (2010) From transformation-based dimensionality reduction to feature selection, appearing. In: Proceedings of the 27 the international conference on machine learning
Zhu Y, Shan X, Guo J (2005) Feature selection method based on variable similarity in intrusion detection system. Microelectron Comput 22(10):34–36
Widodo A, Yang BS, Han T (2007) Combination of independent component analysis and multi-class support vector machines for fault diagnosis of induction motors. Expert Syst Appl 32(2):299–312
Widodo A, Kim EY, Son JD, Yang BS, Tan CC, Gu DS, Choi BK, Mathew J (2009) Fault diagnosis of low speed bearing based on relevance vector machine and support vector machine. Expert Syst Appl 36(3):7252–7261
Hwang WW, Yang BS (2004) Fault diagnosis of rotating machinery using multi-class support vector machines. Trans Korean Soc Noise Vibr Eng 14(12):1233–1240
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Oh, JS., Kim, HE. (2015). A Case Study on Condition Monitoring Based on Statistical Feature for Coil Break on Tandem Cold Rolling. In: Lee, W., Choi, B., Ma, L., Mathew, J. (eds) Proceedings of the 7th World Congress on Engineering Asset Management (WCEAM 2012). Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-319-06966-1_43
Download citation
DOI: https://doi.org/10.1007/978-3-319-06966-1_43
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-02461-5
Online ISBN: 978-3-319-06966-1
eBook Packages: EngineeringEngineering (R0)