Augustin Persoons
YOU?
Author Swipe
View article: A new approach to combine physics-based and data-driven models using a localised trustworthiness metric
A new approach to combine physics-based and data-driven models using a localised trustworthiness metric Open
Artificial Neural Networks (ANNs) can solve many (un)supervised learning tasks by virtue of the universal approximation theorem. In the context of on-line process control for manufacturing processes, ANNs are an ideal approach for e.g., on…
View article: Near-real-time online process control using grey-box models
Near-real-time online process control using grey-box models Open
Conference paper for 14th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP14), 2023, Dublin, Ireland. A scheme is presented with the goal to enable near-real time reliable and robust proces…
View article: A self-learning Digital Twin for Process Control of fast processes under Uncertainty
A self-learning Digital Twin for Process Control of fast processes under Uncertainty Open
Conference paper for the 5th International Conference on Uncertainty Quantification in Computational Science and Engineering (UNCECOMP 2023), Athens, Greece. Methodology to perform reliable process control for fast and highly complex proce…
View article: Robust Design Optimization of Expensive Stochastic Simulators Under Lack-of-Knowledge
Robust Design Optimization of Expensive Stochastic Simulators Under Lack-of-Knowledge Open
Robust design optimization of stochastic black-box functions is a challenging task in engineering practice. Crashworthiness optimization qualifies as such problem especially with regards to the high computational costs. Moreover, in early …
View article: A new scheme combining adaptive Kriging with adaptative variance-reduction using Gaussian mixture importance sampling
A new scheme combining adaptive Kriging with adaptative variance-reduction using Gaussian mixture importance sampling Open
This article describes a new adaptive Kriging method designed to alleviate the limitations of other related approaches encounter in cases of extremely rare failure events. The main idea is to iteratively reduce both surrogate modelling err…
View article: Accuracy of physics informed neural network used to model the elastic response of a material
Accuracy of physics informed neural network used to model the elastic response of a material Open
Choosing between theoretical or data-driven models can be a challenge when trying to build accurate and robust physical models. Instead of a clear-cut choice, an interesting approach, called grey-box modelling, consists in combining the tw…
View article: QUANTIFYING UNCERTAINTY OF PHYSICS-INFORMED NEURAL NETWORKS FOR CONTINUUM MECHANICS APPLICATIONS
QUANTIFYING UNCERTAINTY OF PHYSICS-INFORMED NEURAL NETWORKS FOR CONTINUUM MECHANICS APPLICATIONS Open
Physics-informed neural networks (PINNs) are a relatively new technique that has gained significant attention in recent years as a versatile and robust way to solve a wide range of physical problems, including continuum mechanics. One of t…
View article: A SELF-LEARNING DIGITAL TWIN FOR PROCESS CONTROL OF FAST PROCESSES UNDER UNCERTAINTY
A SELF-LEARNING DIGITAL TWIN FOR PROCESS CONTROL OF FAST PROCESSES UNDER UNCERTAINTY Open
With the recent developments of sensor technologies appear new opportunities for conducting increasingly efficient and close control of industrial processes.This paper proposes a new scheme for near real-time process control of extremely f…
View article: ROBUST DESIGN OPTIMIZATION UNDER EPISTEMIC UNCERTAINTY USING ADAPTIVE KRIGING AND EXTREME VALUE DISTRIBUTIONS
ROBUST DESIGN OPTIMIZATION UNDER EPISTEMIC UNCERTAINTY USING ADAPTIVE KRIGING AND EXTREME VALUE DISTRIBUTIONS Open
This article proposes a method to solve robust optimization problems under interval uncertainties.The goal of such a problem is to find the set of design variables minimizing the amplitude of performance variations due to the uncertain var…
View article: Active learning in grey-box models for near-real-time online monitoring of dynamic processes
Active learning in grey-box models for near-real-time online monitoring of dynamic processes Open
Near-real-time monitoring of dynamical processes in a production line can aid greatly in increasing the products quality and reliability, leading to an overall extended lifetime and reduced costs. It enables timely intervention in case of …
View article: Active learning in grey-box models for near-real-time online monitoring of dynamic processes
Active learning in grey-box models for near-real-time online monitoring of dynamic processes Open
Near-real-time monitoring of dynamical processes in a production line can aid greatly in increasing the products quality and reliability, leading to an overall extended lifetime and reduced costs. It enables timely intervention in case of …