Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Modelling
Special Issues
Synthesis of Computational Mechanics and Machine Learning
share announcement

Synthesis of Computational Mechanics and Machine Learning

A special issue of Modelling (ISSN 2673-3951).

Deadline for manuscript submissions: closed (30 October 2022) | Viewed by 6301

Special Issue Editors

Dr. Miguel A. Bessa

E-Mail Website
Guest Editor
School of Engineering, Brown University, Providence, RI 02912, USA
Interests: development of numerical methods; machine learning and optimization; multi-scale modeling of materials and structures
Prof. Dr. Günther Meschke

E-Mail Website
Guest Editor
Institute for Structural Mechanics, Ruhr-Universität Bochum, Bochum, Germany
Interests: research in theoretical and applied research in computational structural mechanics with emphasis on tunneling and subsurface engineering; model- and data-driven methods for the steering support of construction processes; machine learning methods and uncertainty modeling in engineering; integration of BIM and computational simulation; robust optimization of steel- and fiber-reinforced concrete structures; durability mechanics; life-time analyses of reinforced concrete structures; modeling of excavation and fragmentation processes
Special Issues, Collections and Topics in MDPI journals
Dr. Jithender J. Timothy

E-Mail Website
Guest Editor
Department of Materials Engineering, TUM School of Engineering and Design, Technical University of Munich, 81245 Munich, Germany
Interests: model-based material characterization and design; analytical and computational modeling of structure-property relations (stiffness, diffusivity, conductivity, permeability); biomaterials; cementitous materials; geomaterials
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Recognizing the potential of using data generated in engineering applications, e.g., from laboratory testing or during the monitoring of structures or engineering processes, traditional methods of computational mechanics have recently expanded towards an integration of data, leading to hybrid formats of data- and model-based prognosis models. Different procedures, ranging from methods of data-driven mechanics to enrich physics-based models by synthetic data to support of the training of machine-learning algorithms using methods of computational simulation, are currently being investigated. Exploiting the complementary advantages of physics-based modelling and data-driven learning opens new perspectives on the generation of digital twins as the backbone of the steering of engineering processes.

This Special Issue welcomes contributions from both researchers and practitioners describing recent advancements in the combination of methods of computational mechanics with methods of machine-learning targeted towards applications in engineering.

Dr. Miguel A. Bessa
Prof. Dr. Günther Meschke
Dr. Jithender J. Timothy
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Modelling is an international peer-reviewed open access quarterly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Physics-informed AI
  • Mechanistic machine learning
  • Data-driven computational mechanics
  • Big-data
  • Digital-twin

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 2711 KiB  
Article
High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics
by Diana A. Bistrian
Modelling 2022, 3(3), 314-332; https://0-doi-org.brum.beds.ac.uk/10.3390/modelling3030020 - 21 Jul 2022
Cited by 1 | Viewed by 1774
Abstract
The purpose of this paper is the identification of high-fidelity digital twin data models from numerical code outputs by non-intrusive techniques (i.e., not requiring Galerkin projection of the governing equations onto the reduced modes basis). In this paper the author defines the concept [...] Read more.
The purpose of this paper is the identification of high-fidelity digital twin data models from numerical code outputs by non-intrusive techniques (i.e., not requiring Galerkin projection of the governing equations onto the reduced modes basis). In this paper the author defines the concept of the digital twin data model (DTM) as a model of reduced complexity that has the main feature of mirroring the original process behavior. The significant advantage of a DTM is to reproduce the dynamics with high accuracy and reduced costs in CPU time and hardware for settings difficult to explore because of the complexity of the dynamics over time. This paper introduces a new framework for creating efficient digital twin data models by combining two state-of-the-art tools: randomized dynamic mode decomposition and deep learning artificial intelligence. It is shown that the outputs are consistent with the original source data with the advantage of reduced complexity. The DTMs are investigated in the numerical simulation of three shock wave phenomena with increasing complexity. The author performs a thorough assessment of the performance of the new digital twin data models in terms of numerical accuracy and computational efficiency. Full article
(This article belongs to the Special Issue Synthesis of Computational Mechanics and Machine Learning)
►▼ Show Figures

Figure 1

15 pages, 9831 KiB  
Article
Numerical Simulation-Based Damage Identification in Concrete
by Giao Vu, Jithender J. Timothy, Divya S. Singh, Leslie A. Saydak, Erik H. Saenger and Günther Meschke
Modelling 2021, 2(3), 355-369; https://0-doi-org.brum.beds.ac.uk/10.3390/modelling2030019 - 06 Aug 2021
Cited by 7 | Viewed by 3492
Abstract
High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using [...] Read more.
High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks. Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens is performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN-based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks) with an overall accuracy of 77%. The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%. Full article
(This article belongs to the Special Issue Synthesis of Computational Mechanics and Machine Learning)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop