Hierarchical Deep Learning Neural Network (HiDeNN): An artificial intelligence (AI) framework for computational science and engineering

• Published in: Computer methods in applied mechanics and engineering 2021-01, Vol.373, p.113452, Article 113452
• Main Authors: Saha, Sourav, Gan, Zhengtao, Cheng, Lin, Gao, Jiaying, Kafka, Orion L., Xie, Xiaoyu, Li, Hengyang, Tajdari, Mahsa, Kim, H. Alicia, Liu, Wing Kam
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial intelligence; Data-driven discovery; Deep learning; Finite element method; Machine learning; Mathematical analysis; Multiscale analysis; Multiscale simulation; Neural networks; Reduced order model; Stress concentration
• ISSN: 0045-7825; 1879-2138
• DOI: 10.1016/j.cma.2020.113452

In this work, a unified AI-framework named Hierarchical Deep Learning Neural Network (HiDeNN) is proposed to solve challenging computational science and engineering problems with little or no available physics as well as with extreme computational demand. The detailed construction and mathematical elements of HiDeNN are introduced and discussed to show the flexibility of the framework for diverse problems from disparate fields. Three example problems are solved to demonstrate the accuracy, efficiency, and versatility of the framework. The first example is designed to show that HiDeNN is capable of achieving better accuracy than conventional finite element method by learning the optimal nodal positions and capturing the stress concentration with a coarse mesh. The second example applies HiDeNN for multiscale analysis with sub-neural networks at each material point of macroscale. The final example demonstrates how HiDeNN can discover governing dimensionless parameters from experimental data so that a reduced set of input can be used to increase the learning efficiency. We further present a discussion and demonstration of the solution for advanced engineering problems that require state-of-the-art AI approaches and how a general and flexible system, such as HiDeNN-AI framework, can be applied to solve these problems. •An AI system framework for generally challenging problems in computational science and engineering.•Demonstrating how to build HiDeNN from hierarchically assembled deep neural networks.•Application of HiDeNN to capture stress concentration and solve multiscale problem.•Discovery of non-dimensional number with HiDeNN based on experimental data.•Vision on how to deploy HiDeNN for three examples of challenging problems.