A machine-learning-based surrogate modeling method for distributed fluid systems is proposed in this paper, where a dimensionality reduction technique used to reduce the flowfield dimension and regression model predict reduced coefficients from input parameters. The specifically designed tackle involving aerodynamic structures, its performance illustrated by application on wake flow around wind...

A transient model of an induction machine (IM) is developed in this work using artificial neural network (ANN) surrogate model. The suitable to be used for direct-on-line IMs. finite-element (FE)-based IM generate the training, validation, and testing datasets. Different inputs configurations are investigated find optimal solution developing proposed digital twin services since it can estimate ...

The use of supporting fluids to stabilize excavations is a common technique adopted in the construction industry. Rapid detection incipient collapse for deep and timely decision making are crucial ensure safety during construction. This paper explores hybrid framework forecasting fluid-supported circular by combining physics-based data-driven modeling. Finite-element limit analysis first used d...

This paper investigates the characterization of the uncertainty in the prediction of surrogate models. In the practice of engineering, where predictive models are pervasively used, the knowledge of the level of modeling error in any region of the design space is uniquely helpful for design exploration and model improvement. The lack of methods that can explore the spatial variation of surrogate...

Parametrized surrogate models are used in alloy modeling to quickly obtain otherwise expensive properties such as quantum mechanical energies, and thereafter used to optimize, or simply compute, some alloy quantity of interest, e.g., a phase transition, subject to given constraints. Once learned on a data set, the surrogate can compute alloy properties fast, but with an increased uncertainty co...

Often, the performance on a supervised machine learning task is evaluated with a task loss function that cannot be optimized directly. Examples of such loss functions include the classification error, the edit distance and the BLEU score. A common workaround for this problem is to instead optimize a surrogate loss function, such as for instance cross-entropy or hinge loss. In order for this rem...

Engineering systems form the basis on which our day-to-day lives depend on. In many cases, designers are interested in identifying an optimal design of an engineering system. However, very often, the process of engineering design optimization is complex and involves time-expensive simulations or the need to satisfy not just one, but multiple objectives. This thesis aims to explore the area of e...

The fidelity of surrogate models remains one of the primary concerns in their application to represent complex system behavior. Appropriate sampling of training points is one of the primary factors affecting the fidelity of surrogate models. This paper investigates the relative advantage of probability-based uniform sampling over distance-based uniform sampling, in training surrogate models who...