Special Issue: Computers & Structures:
Machine Learning for Computational Mechanics
Guest Edited by: A. Bahreininejad, S. Freitag, K. Khandelwal,
Final Deadline for papers 15th January 2023
J. Lee and B.H.V. Topping
Aims and Scope:
The potential applications for machine learning and related soft computing techniques in computational mechanics is extremely wide. Current machine learning techniques may be categorised into the following types: supervised learning; semi-supervised learning; self-supervised learning; unsupervised learning; reinforcement learning; clustering rule generation; and dimensionality reduction.
Recently the emergence of deep learning, (a subset of machine learning), has fundamentally changed the landscape of solving highly complex and nonlinear engineering problems.
Machine learning also involves creating a model, which is trained on some data. For example by using data of laboratory experiments, in-situ measurements or numerical simulations, but also by adding physical knowledge to the machine learning model (physics informed machine learning). The machine learning model can then be used to process additional data to make predictions. Models can be created using a wide range of techniques that include: artificial neural networks; decision tree learning; support-vector machines; regression analysis; Bayesian networks; ontology based systems; federated learning; ensemble methods; often integrated with or assisted by genetic algorithms and other heuristic methods.
Authors using the above mentioned learning and model creation techniques or other machine learning techniques to solve new problems in the many branches of computational mechanics (solids, structures and fluids) are invited to submit papers to the special issue. Problems addressed could include (but not confined to): model pre-processing; enhanced and assisted modelling techniques; post processing capabilities; material modelling and multi-scale simulations, model substitution in optimization, diagnosis of structural behaviour and faults; inverse problems in computational mechanics; as well as design and optimization systems and procedures.
Please read the "Guide for Authors" by following the link on the journal home page.
- The journal home page of the International Journal of Computers & Structures (CAS) is
Please prepare your submission using information from the journal home page but see the following important
In case of problems please contact Professor Barry Topping using the email "jou1 AT bhvt.uk"
please put "VSI: Machine Learning" in the subject of the email.
- Ensure that your paper is in a final state and no modifications need to be made before submitting it for review.
- Please prepare a submission letter that the paper has not been submitted elsewhere for publication (at the same time) and that the paper is for the special issue. Nothing else is needed all information about the paper should be in the highlights, abstract and the paper.
- At the begining of the submission process please select the article type "VSI: Machine Learning".
- Do number the lines of your paper.
- Do number the pages of your paper.
- Do NOT use a double column layout - (DCL makes review more difficult - many reviewers do not like DCL.)
- Please make sure that the english of your paper is as perfect as you can make it - reviewers who find lots of mistakes in the english - simply give up and will not review a paper that requires corrections. It is not a good strategy to expect a reviewer to correct english.
- Please recognise that the abstract and highlights are very important - if these are not good your paper will not pass initial checks.
- In the abstract make sure that you DO NOT include text that should be in the introduction. Do make sure that the abstract provides the reader with a clear statement of what is new and what contribution to the state of the art has been made in the paper. Do not write about objectives - do not write about research - relate the abstract to the paper - explain what is important in the paper.
- The highlights should be short numbered bullet points that indicate why the author should read your paper - they should clearly and briefly state what is new in the paper - they should NOT be long sentences - they should not be information that should be in either the abstract or introduction - they should not be a direct copy of the abstract - they should NOT be keywords - keywords should be in the keyword field. For details on the physical restrictions on the number and character length of highlights please follow the journal home page: Guide for Authors link.
- Acronyms: These should be avoided in the title, keywords, abstract and highlights. Acronyms should not be defined in the title, keywords, abstract and highlights. Acronyms should be defined where first used in the body of the paper.
- Advice on selecting referees: The authors of submissions must suggest at least six potential reviewers through the Editorial Manager system please could you do this but consider the following. Please ensure that the reviewers are not conflicted. You should not have published papers or books with the persons proposed. Ideally two of the persons should be members of the journal editorial board (see the journal home page) if at all possible. (Please note you can have more than six reviewer proposals). The reviewers should not be Editors of the journal. The reviewers should generally not come from the same country or be of the same nationality as any of the authors (except in the case of editorial board members). The journals are international and therefore international referees are required. Do not select editors of CAS, ADES or other journals as they are usually overloaded and do not have time to review.
- The link for making the submission can be found on the journal home page.
Thank you for your interest in the journal and the conferences.
Professor Barry H V Topping
Computers and Structures
Advances in Engineering Software