Abstract
Surrogate Modeling (SM) is often used to reduce the computational burden of time-consuming system simulations. However, continuous advances in Artificial Intelligence (AI) and the spread of embedded sensors have led to the creation of Digital Twins (DT), Design Mining (DM), and Soft Sensors (SS). These methodologies represent a new challenge for the generation of surrogate models since they require the implementation of elaborated artificial intelligence algorithms and minimize the number of physical experiments measured. To reduce the assessment of a physical system, several existing adaptive sequential sampling methodologies have been developed; however, they are limited in most part to the Kriging models and Kriging-model-based Monte Carlo Simulation. In this paper, we integrate a distinct adaptive sampling methodology to an automated machine learning methodology (AutoML) to help in the process of model selection while minimizing the system evaluation and maximizing the system performance for surrogate models based on artificial intelligence algorithms. In each iteration, this framework uses a grid search algorithm to determine the best candidate models and perform a leave-one-out cross-validation to calculate the performance of each sampled point. A Voronoi diagram is applied to partition the sampling region into some local cells, and the Voronoi vertexes are considered as new candidate points. The performance of the sample points is used to estimate the accuracy of the model for a set of candidate points to select those that will improve more the model’s accuracy. Then, the number of candidate models is reduced. Finally, the performance of the framework is tested using two examples to demonstrate the applicability of the proposed method.
Highlights
Many science and engineering fields rely on computer simulations to replace expensive physical experimentation to analyze and improve the quality of different designs, methodologies, or products.The continuous research of numerical simulations has reduced the gap between the physical system and its model
While Design Mining (DM) considers rapid prototyping as a fundamental part of the exploration of the design space, surrogate modeling has been proposed as the main alternative to reduce the cost related to this methodology [10,11,12]
Adaptive sampling algorithms have been proven to be useful in reliability analysis for traditional surrogate models like the Kriging method, but the growing demand for algorithms to translate the surrogate models into applications such as digital twinning, design mining or soft sensors has generated the need to transfer adaptive sampling methods into machine learning models
Summary
Many science and engineering fields rely on computer simulations to replace expensive physical experimentation to analyze and improve the quality of different designs, methodologies, or products. The continuous research of numerical simulations has reduced the gap between the physical system and its model. This improvement comes with a cost in time due to the complexity of such numerical models. Surrogate modeling has become a solution for approximating the expensive numerical simulations of complex systems used to solve heavily iterative problems, such as optimization problems, and achieve acceptable accuracy at a low computational cost. Surrogate modeling has been incorporated in multiple fields. In [1], the authors develop a multi-fidelity surrogate model for a microwave component. In [2] the authors use a surrogate Kriging
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
