A general framework of high-performance machine learning algorithms: application in structural mechanics

Salvato in:
Dettagli Bibliografici
Pubblicato in:Computational Mechanics vol. 73, no. 4 (Apr 2024), p. 705
Autore principale: Markou, George
Altri autori: Bakas, Nikolaos P., Chatzichristofis, Savvas A., Papadrakakis, Manolis
Pubblicazione:
Springer Nature B.V.
Soggetti:
Accesso online:Citation/Abstract
Full Text - PDF
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!

MARC

LEADER 00000nab a2200000uu 4500
001 3033927894
003 UK-CbPIL
022 |a 0178-7675 
022 |a 1432-0924 
024 7 |a 10.1007/s00466-023-02386-9  |2 doi 
035 |a 3033927894 
045 2 |b d20240401  |b d20240430 
100 1 |a Markou, George  |u University of Pretoria, Civil Engineering Department, Pretoria, South Africa (GRID:grid.49697.35) (ISNI:0000 0001 2107 2298) 
245 1 |a A general framework of high-performance machine learning algorithms: application in structural mechanics 
260 |b Springer Nature B.V.  |c Apr 2024 
513 |a Journal Article 
520 3 |a Data-driven models utilizing powerful artificial intelligence (AI) algorithms have been implemented over the past two decades in different fields of simulation-based engineering science. Most numerical procedures involve processing data sets developed from physical or numerical experiments to create closed-form formulae to predict the corresponding systems’ mechanical response. Efficient AI methodologies that will allow the development and use of accurate predictive models for solving computational intensive engineering problems remain an open issue. In this research work, high-performance machine learning (ML) algorithms are proposed for modeling structural mechanics-related problems, which are implemented in parallel and distributed computing environments to address extremely computationally demanding problems. Four machine learning algorithms are proposed in this work and their performance is investigated in three different structural engineering problems. According to the parametric investigation of the prediction accuracy, the extreme gradient boosting with extended hyper-parameter optimization (XGBoost-HYT-CV) was found to be more efficient regarding the generalization errors deriving a 4.54% residual error for all test cases considered. Furthermore, a comprehensive statistical analysis of the residual errors and a sensitivity analysis of the predictors concerning the target variable are reported. Overall, the proposed models were found to outperform the existing ML methods, where in one case the residual error was decreased by 3-fold. Furthermore, the proposed algorithms demonstrated the generic characteristic of the proposed ML framework for structural mechanics problems. 
653 |a Machine learning 
653 |a Data processing 
653 |a Artificial intelligence 
653 |a Sensitivity analysis 
653 |a Prediction models 
653 |a Mechanics (physics) 
653 |a Algorithms 
653 |a Structural engineering 
653 |a Mathematical models 
653 |a Mechanical analysis 
653 |a Mechanics 
653 |a Statistical analysis 
653 |a Distributed processing 
653 |a Computer networks 
700 1 |a Bakas, Nikolaos P.  |u National Infrastructures for Research and Technology – GRNET, Athens, Greece (GRID:grid.9067.8); The American College of Greece, School of Liberal Arts and Sciences, Technology & AI Lab, Deree, Greece (GRID:grid.461970.d) (ISNI:0000 0001 2216 0572) 
700 1 |a Chatzichristofis, Savvas A.  |u Neapolis University Pafos, Intelligent Systems Lab and Department of Computer Science, Pafos, Cyprus (GRID:grid.449420.f) (ISNI:0000 0004 0478 0358) 
700 1 |a Papadrakakis, Manolis  |u National Technical University of Athens, Department of Civil Engineering, Athens, Greece (GRID:grid.4241.3) (ISNI:0000 0001 2185 9808) 
773 0 |t Computational Mechanics  |g vol. 73, no. 4 (Apr 2024), p. 705 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3033927894/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3033927894/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch