Machine learning for combinatorial optimization of brace placement of steel frames
Authors:
Open Access
- 20 August 2018
- journal article
- research article
- Published by Wiley in JAPAN ARCHITECTURAL REVIEW
- Vol. 1 (4) , 419-430
Abstract
A method is presented for optimal placement of braces of plane frames using machine learning. The frame is subjected to static horizontal loads representing seismic loads. We consider the process of seismic retrofit by attaching braces. Therefore, the maximum value of additional stresses in the existing beams and columns and the maximum interstory drift angle are incorporated in the optimization problem. Characteristics of approximate optimal solutions and nonoptimal solutions are extracted using machine learning based on support vector machine and binary decision tree. Convolution and pooling are used for defining the features characterizing the solutions while reducing the number of variables. Optimization is carried out using a heuristic algorithm called simulated annealing based on local search. It is shown in the numerical examples that the computational cost is successfully reduced by avoiding costly structural analysis for a solution judged by machine learning as nonoptimal, and the important features in approximate optimal and nonoptimal solutions are identified.Keywords
Funding Information
- Japan Society for the Promotion of Science (16H03014, 16H04449)
This publication has 26 references indexed in Scilit:
- Neural network based prediction schemes of the non-linear seismic response of 3D buildingsAdvances in Engineering Software, 2012
- Recent advances in surrogate-based optimizationProgress in Aerospace Sciences, 2009
- Optimal placement of braces for steel frames with semi-rigid joints by scatter searchComputers & Structures, 2008
- TOPOLOGY OPTIMIZATION OF DISCRETE STRUCTURES BY INTEGRATION OF HEURISTICS AND NONLINEAR PROGRAMMINGJournal of Structural and Construction Engineering (Transactions of AIJ), 2008
- Topology Mining for Optimization of Framed StructuresJournal of Advanced Mechanical Design, Systems, and Manufacturing, 2008
- Pattern Recognition and Machine Learning2006
- Evaluating machine learning models for engineering problemsArtificial Intelligence in Engineering, 1999
- Learning to set up numerical optimizations of engineering designsArtificial Intelligence for Engineering Design, Analysis and Manufacturing, 1998
- Empirical performance comparison of selective and constructive inductionEngineering Applications of Artificial Intelligence, 1996
- A neural dynamics model for structural optimization—TheoryComputers & Structures, 1995