신경망 이론과 Mahalanobis Distance 이상치 탐색방법을 이용한 고강도 콘크리트 강도 예측 모델 개발에 관한 연구
Modeling of Strength of High Performance Concrete with Artificial Neural Network and Mahalanobis Distance Outlier Detection Method
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
High-performance concrete (HPC) is a new terminology used in concrete construction industry. Several studies have shown that concrete strength development is determined not only by the water-to-cement ratio but also influenced by the content of other concrete ingredients. HPC is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed at demonstrating the possibilities of adapting artificial neural network (ANN) to predict the comprresive strength of HPC. Mahalanobis Distance (MD) outlier detection method used for the purpose increase prediction ability of ANN. The detailed procedure of calculating Mahalanobis Distance (MD) is described. The effects of outlier compared with before and after artificial neural network training. MD outlier detection method successfully removed existence of outlier and improved the neural network training and prediction perfomance.
Abstract
High-performance concrete (HPC) is a new terminology used in concrete construction industry. Several studies have shown that concrete strength development is determined not only by the water-to-cement ratio but also influenced by the content of other concrete ingredients. HPC is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed at demonstrating the possibilities of adapting artificial neural network (ANN) to predict the comprresive strength of HPC. Mahalanobis Distance (MD) outlier detection method used for the purpose increase prediction ability of ANN. The detailed procedure of calculating Mahalanobis Distance (MD) is described. The effects of outlier compared with before and after artificial neural network training. MD outlier detection method successfully removed existence of outlier and improved the neural network training and prediction perfomance.
참고문헌 (10)
- Wu,Y, "Pattern Recognition using Mahalanobis Distance", TPD Symposium, pp.1~14 (1996)
- "Mahalanobis Distance:A Theoretical and Practical Approach"[URL]
- I.C.Yeh, "Modeling of Strength of High-Perfprmance Concrete Using Artificial Neural Networks", Cement and Concrete Research, 28(12), pp.1797~1808 (1998)
- 최희복, "재생골재 적용 콘크리트의 강도예측 -신경망 기법과 적산온도방식 강도예측-", 대한건축학회논문집 구조계, 21(6), pp.49~55 (2005), 대한건축학회
- Taguchi,G, "New Trends in Multivariate Diagnosis", Indian Journal of Statistics, 62(B, 2), pp.233~248 (2000)
- Taguchi,G, "The Mahalanobis-Taguchi Strategy : A Pattern Technology System" (2002), John Wiley and Sons, Inc.
- Hayashi,S, "A New Manufacturing Control System using Mahalanobis Distance for Maximizing Productivity", IEEE Transactions, pp.59~62 (2001)
- Hong, Jung-Eui, "A Comparison study of Mahalanobis Taguchi System and nueral network for multivariate pattern recognition", ASME IMECE Proceedings (2005)
- E.A.Cudney, "An Evaluation of Mahalanobis Taguchi System and Neural Network for Multivariate Pattern Recognition", Journal of Industrial and System Engineering, 1(2), pp.139~150 (2007)
- R.Jugulum, "Comparison between Mahalanobis-Taguchi-System and Artificial Neural Networks", Journal of Quality Engineering Society, 10(1), pp.60~73 (2002)