I'm looking for some guidance and advise in the subject of "Machine Learning," which I'll utilize for my research interests in computational mechanics and structural vibration control.
An area of interest is the computation speed and type of precision used for higher efficiency. For this, please check Deep Learning that is a subset of machine learning and its applications to the Computational Mechanics.
Thanks for your valuable suggestion. Are there any literature available for machine learning which is used in computational mechanics or structural vibration control?
I appreciate your response and this interesting discussion. I'm only aware of the computational mechanics.
Yagawa, Genki, and Atsuya Oishi. Computational Mechanics with Neural Networks. Cham, Switzerland: Springer, 2021. Print.
These are open access or available online
Fritzen, Felix, and David Ryckelynck. Machine Learning, Low-Rank Approximations and Reduced Order Modeling in Computational Mechanics. MDPI, 2019. Web.
Oishi, Atsuya, and Genki Yagawa. “Computational Mechanics Enhanced by Deep Learning.” Computer methods in applied mechanics and engineering 327 (2017): 327–351. Web.
Another to consider in general
Favorskaya, Margarita N et al. “Recent Advances in Numerical Methods, Machine Learning, and Computer Science.” Smart Modelling for Engineering Systems. Singapore: Springer Singapore, 2021. 1–5. Web.
There are several ways that machine learning could be applied to research in computational mechanics and structural vibration control. Here are a few examples:
Developing predictive models for the behavior of structures under dynamic loading: Machine learning algorithms can be used to analyze large datasets of structural responses to dynamic loading, such as from finite element simulations or experimental testing, to develop predictive models that can be used to estimate the behavior of similar structures under different loading conditions.
Identifying patterns in structural responses to dynamic loading: Machine learning algorithms can be used to analyze large datasets of structural responses to identify patterns and trends that may not be immediately apparent to a human observer. This can be helpful in understanding the mechanisms of structural response under different loading conditions and in identifying potential failure modes.
Developing control algorithms for structural vibration suppression: Machine learning algorithms can be used to develop control algorithms that can be used to actively suppress structural vibrations. For example, machine learning algorithms could be used to analyze the structural responses to different control inputs and to identify the control strategies that are most effective at reducing vibrations.
Predicting the fatigue life of structures: Machine learning algorithms can be used to analyze large datasets of structural responses under cyclic loading to predict the fatigue life of structures. This can be particularly useful for identifying fatigue-sensitive locations in a structure and for optimizing the design of structures to improve fatigue performance.