Al-DeMat: A web-based expert system platform for computationally expensive models in materials design. (February 2023)

• Record Type: Journal Article
• Authors: Liu, Bokai; Vu-Bac, Nam; Zhuang, Xiaoying; Lu, Weizhuo; Fu, Xiaolong; Rabczuk, Timon
• Is Part Of: Advances in engineering software. Volume 176(2023)
• Publication Date: 2023-02
• Subjects: Machine learning -- Data-driven modeling -- Decision support systems (DSS) -- R shiny -- Web-based platform; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2022.103398
• Languages: English
• ISSNs: 0965-9978

Abstract

Abstract: We present a web-based framework based on the R shiny package with functional back-end server in machine learning methods. A 4-tiers architecture is programmed to achieve users' interactive design and visualization via a web browser. Many data-driven methods are integrated into this framework, namely Random Forest, Gradient Boosting Machine, Artificial and Deep neural networks. Moreover, a robust gradient-free optimization technique, the Particle Swarm Optimization, is used to search optimal values in hyper-parameters tuning. K-fold Cross Validation is applied to avoid over-fitting. R 2 and RMSE are considered as two key factors to evaluate the trained models. The contributions to the expert system in materials design are: (1) A systematic framework that can be applied in materials prediction with machine learning approaches, (2) A user-friendly web-based platform that is easy and flexible to use and (3) integrated optimization and visualization into the framework with pre set algorithms. This computational framework is designed for researchers and materials engineers who would like to do the preliminary designs before experimental studies. Finally, we demonstrate the performance of the web-based framework through 2 case studies. Highlights: A web-based framework is presented based on the R shiny package with functional back-end server in machine learning methods. A 4-tiers architecture is programmed with many data-driven methods to achieve users' interactive design and visualization via a web browser. A systematic framework that can be applied in materials prediction with machine learning approaches. A user-friendly web-based platform that is easy and flexible to operate. Optimization and visualization are Integrated into the framework with preset algorithms.