Information-Based Hybrid Modeling Framework on the Systematic use ofArtificial Neural-Networks
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this study, a new information-based hybrid modeling framework is proposed. In the hybrid framework, a conventional mathematical model is complemented by the informational methods. The basic premise of the proposed hybrid methodology is that not all features of system response are amenable to mathematical modeling, hence considering informational alternatives. This may be because (i) the underlying theory is not available or not sufficiently developed, or (ii) the existing theory is too complex and therefore not suitable for modeling within building frame analysis. The role of informational methods is to model aspects that the mathematical model leaves out. Autoprogressive algorithm and self-learning simulation extract the missing aspects from a system response. In a hybrid framework, experimental data is an integral part of modeling, rather than being used strictly for validation processes. The potential of the hybrid methodology is illustrated through modeling complex hysteretic behavior of beam-to-column connections.
Abstract
In this study, a new information-based hybrid modeling framework is proposed. In the hybrid framework, a conventional mathematical model is complemented by the informational methods. The basic premise of the proposed hybrid methodology is that not all features of system response are amenable to mathematical modeling, hence considering informational alternatives. This may be because (i) the underlying theory is not available or not sufficiently developed, or (ii) the existing theory is too complex and therefore not suitable for modeling within building frame analysis. The role of informational methods is to model aspects that the mathematical model leaves out. Autoprogressive algorithm and self-learning simulation extract the missing aspects from a system response. In a hybrid framework, experimental data is an integral part of modeling, rather than being used strictly for validation processes. The potential of the hybrid methodology is illustrated through modeling complex hysteretic behavior of beam-to-column connections.
참고문헌 (10)
- Bernuzzi, C., "Experimental Analysis and Modelling of Semi-Rigid Steel Joints under Cyclic Reversal Loading", Journal of Constructional Steel Research, 38(2), pp.95~123 (1996)
- Ghaboussi, J., "Material Modeling with Neural Networks", Proceedings of the International Conference on Numerical Methods in Engineering: Theory and Applications, pp.701~717 (1990)
- Ghaboussi J., "Knowledge-based Modeling of Material Behavior with Neural Networks", Journal of Engineering Mechanics, 117(1), pp.132~153 (1991)
- Ghaboussi J., "Nested Adaptive Neural Network: A NewArchitecture", Proceedings of International conferenceon Artificial Neural Networks in Engineering,ANNIE97 (1997)
- Ghaboussi J., "New Nested Adaptive Neural Networks (NANN) for Constitutive Modeling", Computers and Geotechnics, 22(1), pp.29~52 (1998)
- Ghaboussi, J., "Autoprogressive Training of Neural Network Constitutive Models", International Journal for Numerical Methods in Engineering, 42(1), pp.105~126 (1998)
- Hashash, Y.M.A., "Systematic Update of a Deep Excavation Model Using Field Performance Data", Computers and Geotechnics, 30(6), pp.477~488 (2003)
- Hashash, Y.M.A, "Novel Approach to Integration of Numerical Modeling and Field Observations for Deep Excavations", Journal of Geotechnical and Geoenvironmental Engineering, 132(8), pp.1019~1031 (2006)
- Kim, J.H., "Mechanical and Informational Modeling of Steel Beam-to-Column Connections", Engineering Structures, 32(2), pp.449~458 (2010)
- Shin, H.S., "On self-learning Finite Element Codes Based on Monitored Response of Structures", Computers and Geotechnics, 27(3), pp.161~178 (2000)