Design-objective space exploration and multi-objective optimization of initial structural design alternatives via machine learning

Date

2020-9

Author

Yetkin, Ozan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

303
views

0
downloads

Increasing implementations of digital workflows within design processes generate exponentially growing data in each phase. Therefore, decision making within a design space with growing complexity is expected to be a great challenge for designers in the future. Hence, this research aimed to seek the potentials of complex relations between data within design space and objective space of structural design problems for proposing a novel approach to augment capabilities of digital tools by artificial intelligence. As a method, a machine learning-based framework was proposed that can help designers to understand the trade-offs between initial structural design alternatives to make informed decisions. The proposed framework was tested in three stages: probabilistic, deterministic, and integrated; all of which allow users to conduct optimization studies with the help of different machine learning models. Finally, the proposed approaches were presented in case studies, and potentials/limitations of the models were discussed including future projections.

Subject Keywords

Design Space, Objective Space, Structural Analysis, Multi-Objective Optimization, Artificial Intelligence, Machine Learning

URI

https://hdl.handle.net/11511/69230

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Design Space Exploration of Initial Structural Design Alternatives via Artificial Neural Networks Yetkin, Ozan; Sorguç, Arzu (2019-09-13) Increasing implementation of digital tools within a design process generates exponentially growing data in each phase, and inevitably, decision making within a design space with increasing complexity will be a great challenge for the designers in the future. Hence, this research aimed to seek potentials of captured data within a design space and solution space of a truss design problem for proposing an initial novel approach to augment capabilities of digital tools by artificial intelligence where designers...
Layout optimization of trusses using simulated annealing Hasançebi, Oğuzhan (2000-09-08) This paper addresses to the development of a simulated annealing (SA) based solution algorithm which is automated to achieve the simultaneous optimum design of truss type structures with respect to size, shape and topology design variables. The proposed algorithm is designed in such a way that together with applicability to practical design problems, it is also aimed at producing efficient and improved design solutions for the problems of interest. From the practicality point of view, the task is chosen as ...
Improving forecasting accuracy of time series data using a new ARIMA-ANN hybrid method and empirical mode decomposition Buyuksahin, Umit Cavus; Ertekin Bolelli, Şeyda (Elsevier BV, 2019-10-07) Many applications in different domains produce large amount of time series data. Making accurate forecasting is critical for many decision makers. Various time series forecasting methods exist that use linear and nonlinear models separately or combination of both. Studies show that combining of linear and nonlinear models can be effective to improve forecasting performance. However, some assumptions that those existing methods make, might restrict their performance in certain situations. We provide a new Au...
Performance-based parametric design explorations: A method for generating appropriate building components Ercan, Burak; Elias Özkan, Soofia Tahira (2015-05-01) Performance-based parametric design explorations depend on formulating custom-designed workflows that require reading, writing, interpreting and manipulating databases, as part of the design process. The possibilities of customization and parameterization offered by the user-friendly interfaces of advanced building-performance simulation software and digital design tools have now enabled architects to carry out performance-based design explorations without the help of simulation experts. This paper presents...
Optimum design of steel frames using stochastic search techniques based on natural phenomena: A review Saka, M. P. (2007-09-21) Recent developments in optimization techniques that deal with finding the solution of combinatorial optimization problems has provided steel designers with new capabilities. These new optimization techniques use nature as a source of inspiration to develop new procedures for solving complex engineering problems. Among these, evolutionary algorithms mimic evolutionary biology and make use of the principle of the survival of the fittest to establish a numerical search algorithm. In the immune system algorithm...

Citation Formats

O. Yetkin, “Design-objective space exploration and multi-objective optimization of initial structural design alternatives via machine learning,” M.S. - Master of Science, Middle East Technical University, 2020.