Steel Plate Faults Diagnosis with S-MTS

S-MTS를 이용한 강판의 표면 결함 진단

  • Kim, Joon-Young (Plant SE Team, Institute for Advanced Engineering (IAE)) ;
  • Cha, Jae-Min (Plant SE Team, Institute for Advanced Engineering (IAE)) ;
  • Shin, Junguk (Plant SE Team, Institute for Advanced Engineering (IAE)) ;
  • Yeom, Choongsub (Plant SE Team, Institute for Advanced Engineering (IAE))
  • 김준영 (고등기술연구원 플랜트 SE팀) ;
  • 차재민 (고등기술연구원 플랜트 SE팀) ;
  • 신중욱 (고등기술연구원 플랜트 SE팀) ;
  • 염충섭 (고등기술연구원 플랜트 SE팀)
  • Received : 2016.11.17
  • Accepted : 2016.12.25
  • Published : 2017.03.31


Steel plate faults is one of important factors to affect the quality and price of the steel plates. So far many steelmakers generally have used visual inspection method that could be based on an inspector's intuition or experience. Specifically, the inspector checks the steel plate faults by looking the surface of the steel plates. However, the accuracy of this method is critically low that it can cause errors above 30% in judgment. Therefore, accurate steel plate faults diagnosis system has been continuously required in the industry. In order to meet the needs, this study proposed a new steel plate faults diagnosis system using Simultaneous MTS (S-MTS), which is an advanced Mahalanobis Taguchi System (MTS) algorithm, to classify various surface defects of the steel plates. MTS has generally been used to solve binary classification problems in various fields, but MTS was not used for multiclass classification due to its low accuracy. The reason is that only one mahalanobis space is established in the MTS. In contrast, S-MTS is suitable for multi-class classification. That is, S-MTS establishes individual mahalanobis space for each class. 'Simultaneous' implies comparing mahalanobis distances at the same time. The proposed steel plate faults diagnosis system was developed in four main stages. In the first stage, after various reference groups and related variables are defined, data of the steel plate faults is collected and used to establish the individual mahalanobis space per the reference groups and construct the full measurement scale. In the second stage, the mahalanobis distances of test groups is calculated based on the established mahalanobis spaces of the reference groups. Then, appropriateness of the spaces is verified by examining the separability of the mahalanobis diatances. In the third stage, orthogonal arrays and Signal-to-Noise (SN) ratio of dynamic type are applied for variable optimization. Also, Overall SN ratio gain is derived from the SN ratio and SN ratio gain. If the derived overall SN ratio gain is negative, it means that the variable should be removed. However, the variable with the positive gain may be considered as worth keeping. Finally, in the fourth stage, the measurement scale that is composed of selected useful variables is reconstructed. Next, an experimental test should be implemented to verify the ability of multi-class classification and thus the accuracy of the classification is acquired. If the accuracy is acceptable, this diagnosis system can be used for future applications. Also, this study compared the accuracy of the proposed steel plate faults diagnosis system with that of other popular classification algorithms including Decision Tree, Multi Perception Neural Network (MLPNN), Logistic Regression (LR), Support Vector Machine (SVM), Tree Bagger Random Forest, Grid Search (GS), Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The steel plates faults dataset used in the study is taken from the University of California at Irvine (UCI) machine learning repository. As a result, the proposed steel plate faults diagnosis system based on S-MTS shows 90.79% of classification accuracy. The accuracy of the proposed diagnosis system is 6-27% higher than MLPNN, LR, GS, GA and PSO. Based on the fact that the accuracy of commercial systems is only about 75-80%, it means that the proposed system has enough classification performance to be applied in the industry. In addition, the proposed system can reduce the number of measurement sensors that are installed in the fields because of variable optimization process. These results show that the proposed system not only can have a good ability on the steel plate faults diagnosis but also reduce operation and maintenance cost. For our future work, it will be applied in the fields to validate actual effectiveness of the proposed system and plan to improve the accuracy based on the results.

강판 표면 결함은 강판의 품질과 가격을 결정하는 중요한 요인 중 하나로, 많은 철강 업체는 그동안 검사자의 육안으로 강판 표면 결함을 확인해왔다. 그러나 시각에 의존한 검사는 통상 30% 이상의 판단 오류가 발생함에 따라 검사 신뢰도가 낮은 문제점을 갖고 있다. 따라서 본 연구는 Simultaneous MTS (S-MTS) 알고리즘을 적용하여 보다 지능적이고 높은 정확도를 갖는 새로운 강판 표면 결함 진단 시스템을 제안하였다. S-MTS 알고리즘은 단일 클래스 분류에는 효과적이지만 다중 클래스 분류에서 정확도가 떨어지는 기존 마할라노비스 다구찌시스템 알고리즘(Mahalanobis Taguchi System; MTS)의 문제점을 해결한 새로운 알고리즘이다. 강판 표면 결함 진단은 대표적인 다중 클래스 분류 문제에 해당하므로, 강판 표면 결함 진단 시스템 구축을 위해 본 연구에서는 S-MTS 알고리즘을 채택하였다. 강판 표면 결함 진단 시스템 개발은 S-MTS 알고리즘에 따라 다음과 같이 진행하였다. 첫째, 각 강판 표면 결함 별로 개별적인 참조 그룹 마할라노비스 공간(Mahalanobis Space; MS)을 구축하였다. 둘째, 구축된 참조 그룹 MS를 기반으로 비교 그룹 마할라노비스 거리(Mahalanobis Distance; MD)를 계산한 후 최소 MD를 갖는 강판 표면 결함을 비교 그룹의 강판 표면 결함으로 판단하였다. 셋째, 강판 표면 결함을 분류하는 데 있어 결함 간의 차이점을 명확하게 해주는 예측 능력이 높은 변수를 파악하였다. 넷째, 예측 능력이 높은 변수만을 이용해 강판 표면 결함 분류를 재수행함으로써 최종적인 강판 표면 결함 진단 시스템을 구축한다. 이와 같은 과정을 통해 구축한 S-MTS 기반 강판 표면 결함 진단 시스템의 정확도는 90.79%로, 이는 기존 검사 방법에 비해 매우 높은 정확도를 갖는 유용한 방법임을 보여준다. 추후 연구에서는 본 연구를 통해 개발된 시스템을 현장 적용하여, 실제 효과성을 검증할 필요가 있다.



Supported by : Korea Institute of Energy Technology Evaluation and Planning (KETEP), Ministry of Trade, Industry & Energy (MI)


  1. Ahmet, S, S. Jagannathan, C. Saygin, "Mahalanobis Taguchi System (MTS) as a Prognostics Tool for Rolling Element Bearing Failures", Journal of Manufacturing Science and Engineering, Vol.132, No.5(2010)
  2. Cha, J. M., J. Y. Kim, J. U. Shin, and C. S. Yeom, "A Method for Improving Multiclass Classification Performance of Mahalanobis Taguchi System", Proceedings of the Korea Society of IT Service Conference, Vol.2016, (2016), 411-414.
  3. Fakhr, M. and A. M. Elsayad, "Steel plates faults diagnosis with data mining models", Journal of Computer Science, Vol.8, No.4(2012), 506-514.
  4. Hong, J. E., "Diagnosis of Spondylopathy Using Mahalanobis Taguchi System", Journal of Society of Korea Industrial and Systems Engineering, Vol.35, No.4(2012), 10-15.
  5. Jin, X. and T. W. S. Chow, "Anomaly Detection of Cooling Fan and Fault Classification of Induction Motor using Mahalanobis-Taguchi System", Expert Systems and Applications, Vol.40, (2013), 5787-5795.
  6. Kim, C. H., S. H. Choi, W. J. Joo, and G. B. Kim, "Classification of Surface Detect on Steel Strip by KNN Classifier", Journal of the Korean Society for Precision Engineering, Vol.23, No.8(2006), 80-88.
  7. Moon, C. I., S. H. Choi, W. J. Joo, G. B. Kim, and H. K. Kim, "Development of a Neural Network Classifier for the Classification of Surface Defects of Cold Rolled Strips", Journal of the Korean Society for Precision Engineering, Vol.24, No.4(2007), 76-83.
  8. Park, S. G., W. S. Park, Y. Y. Lee, D. S. Kim, and J. E. Oh, "A Fault Diagnosis on the Rotating Machinery Using MTS", Transactions of the Korean Society for Noise and Vibration Engineering, Vol.18, No.6(2008), 619-623.
  9. Ren, J., Y., Cai, X., Xing, and J., Chen, "A method of multi-class faults classification based-on Mahalanobis-Taguchi system using vibration signals", Proceedings of 9th IEEE International Conference on Reliability, Maintainability and Safety (ICRMS), Vol.2011, (2011), 1015-1020.
  10. Semeion, Steel Plates Faults Diagnosis Dataset, UCI Repository of machine learning databases, Irvine, CA: University of California, Department of Information and Computer Science, 2016. Available at (Downloaded 1 September, 2016).
  11. Simic, D., V. Svircevic, and S. Simic, "An Approach of Steel Plates Fault Diagnosis in Multiple Classes Decision Making", Hybrid Artificial Intelligence Systems, Vol.8480, (2014), 86-97.
  12. Song, S. J., H. J. Kim, S. H. Choi, and J. H. Lee, "Classification of Surface Defects on Cold Rolled Strips by Probabilistic Neural Networks", Journal of the Korean Society for Nondestructive Testing, Vol.17, No.3(1997), 162-173.
  13. Su, C.T. and Y.H., Hsiao, "Multiclass MTS for simultaneous feature selection and classification", IEEE Transactions on Knowledge and Data Engineering, Vol.21, No.2(2009), 192-205.
  14. Taguchi, G., and R. Jugulum, The Mahalanobis-Taguchi Stretegy: A Pattern Technology System, John Wiley & Sons, New York, 2002.
  15. Tian, Y., M. Fu, and F. Wu, "Steel plates fault diagnosis on the basis of support vector machines", Neurocomputing, Vol.151, (2015), 296-303.