Empowering engineering with data, machine learning and artificial intelligence: a short introductive review

Abstract

Simulation-based engineering has been a major protagonist of the technology of the last century. However, models based on well established physics fail sometimes to describe the observed reality. They often exhibit noticeable differences between physics-based model predictions and measurements. This difference is due to several reasons: practical (uncertainty and variability of the parameters involved in the models) and epistemic (the models themselves are in many cases a crude approximation of a rich reality). On the other side, approaching the reality from experimental data represents a valuable approach because of its generality. However, this approach embraces many difficulties: model and experimental variability; the need of a large number of measurements to accurately represent rich solutions (extremely nonlinear or fluctuating), the associate cost and technical difficulties to perform them; and finally, the difficulty to explain and certify, both constituting key aspects in most engineering applications. This work overviews some of the most remarkable progress in the field in recent years.

Optimal trajectory planning combiningmodel-based and data-driven hybrid approaches

“…It is here that artificial intelligence and machine learning methods come into play [14]. In order to speed-up optimal decisions, reinforcement learning is increasingly considered, as commented before, in particular for autonomous system applications [9].…”

Data-Completion and Model Correction by Means of Evanescent Regularization

“…Multiple novel applications are appearing on a daily basis. A combination of data-driven modeling and the more experienced physics-based modeling, to enhance diagnosis and prognosis, taking the best of both paradigms, is also an active research topic [1]. Multiple data-driven approaches, combined with physical modeling, are used and referred to as hybrid models [2].…”

A parametric metamodel of the vehicle frontal structure accounting for material properties and strain-rate effect: application to full frontal rigid barrier crash test

“…This work primarily focuses on snapshots-based reduced-order modeling (a subject that is extensively discussed in [2] ) and, particularly, on the Proper Orthogonal Decomposition —POD— and on the sparse Proper Generalized Decomposition —sPGD—. Extensive reviews and investigations on such techniques can be found in [4] , [5] , [6] , [7] , [8] , [9] , [10] , [11] , [12] . In particular, in the recent work [10] , the authors deal with parametric metamodeling of curves, based on POD, PGD, data alignment, data clustering and data classification, with emphasis in computational materials science.…”