Meta Models for Real-Time Design Assessment Within an Integrated Information and Numerical Modelling Framework

Ninic, Jelena; Koch, Christian; Tizani, Walid

Abstract

© Springer International Publishing AG, part of Springer Nature 2018. In situations where rapid decisions are required or a large number of design alternatives is to be explored, numerical predictions of construction processes have to be performed in near real-time. For the design assessment of complex engineering problems such as mechanised tunnelling, simple numerical and analytical models are not able to reproduce all complex 3D interactions. To overcome this problem, in this paper a novel concept for on-demand design assessment for mechanized tunnelling using simulation-based meta models is proposed. This concept includes: (i) the generation of enhanced simulation-based meta models; (ii) real-time meta model-based design assessment in the design tool, and; (iii) the implementation within a unified numerical and information modelling platform called SATBIM. The capabilities of this concept are demonstrated through an example for the evaluation of tunnel alignment design and the assessment of the impact of tunnelling on existing infrastructure. Moreover, meta models are used for fast forward calculation in sensitivity analyses for the evaluation of the importance of model parameters. The concept proved its efficiency by assessing the design alternatives in real-time with the prediction error of less than 3% compared to complex numerical simulation in presented example.

Citation

Ninic, J., Koch, C., & Tizani, W. (2018, June). Meta Models for Real-Time Design Assessment Within an Integrated Information and Numerical Modelling Framework. Presented at 25th EG-ICE International Workshop 2018, Lausanne, Switzerland

• Presentation Conference Type: Edited Proceedings
• Conference Name: 25th EG-ICE International Workshop 2018
• Start Date: Jun 10, 2018
• End Date: Jun 13, 2018
• Acceptance Date: Mar 22, 2018
• Online Publication Date: May 19, 2018
• Publication Date: 2018
• Deposit Date: Apr 27, 2018
• Publicly Available Date: May 19, 2018
• Publisher: Springer Verlag
• Volume: 10836
• Pages: 201-218
• Series Title: Lecture Notes in Computer Science
• Series ISSN: 1611-3349
• Book Title: Advanced Computing Strategies for Engineering
• ISBN: 9783319916347
• DOI: https://doi.org/10.1007/978-3-319-91635-4_11
• Keywords: Building Information Modelling, Numerical analysis, Meta models, Level of Detail, Soil-structure interaction, Real-time prediction
• Public URL: https://nottingham-repository.worktribe.com/output/947094
• Publisher URL: https://doi.org/10.1007/978-3-319-91635-4_11
• Additional Information: Also published as: Advanced computing strategies for engineering : 25th International Workshop 2018, EG-ICE 2018, Lausanne, Switzerland, June 10-13, 2018 : proceedings, part I / Smith, Ian F. C., Domer, Bernd (Eds.).