arXiv subjects

Laura Boca de Giuli

Publications and source records attributed to Laura Boca de Giuli.

4 recordsLinked to original sources

arXiv2026

Learning, fast and slow: a two-fold data-based model adaptation algorithm for processes under varying operating conditions

This article proposes a novel two-fold learning framework to maintain the accuracy of data-based process models, typically affected by two types of uncertainty. Out-of-domain uncertainty arises when the modelled process operates under conditions not represented in the training dataset, in-domain uncertainty results from real-world plant variability. To handle out-of-domain uncertainty, a slow learning component learns system dynamics under unexplored operating conditions; it consists of an ensemble of neural network models, featuring (i) a combination rule that weights individual models based on the statistical proximity between their training data and the current operating condition, and (ii) a monitoring algorithm based on statistical control charts that supervises the ensemble's performance and triggers the offline training and integration of a new model when a new operating condition is detected. To address in-domain uncertainty, a fast learning component continuously compensates in real time for the mismatch of the slow learning model using Gaussian processes. The proposed methodology is tested on an energy process system referenced in the literature, demonstrating that the combined use of slow and fast learning components improves model accuracy compared to standard adaptation approaches.

eess.SY↗

arXiv2026

Model Predictive Control and Moving Horizon Estimation using Statistically Weighted Data-Based Ensemble Models

This paper presents a model predictive control (MPC) framework leveraging an ensemble of data-based models to optimally control complex systems under multiple operating conditions. A novel combination rule for ensemble models is proposed, based on the statistical Mahalanobis distance, enabling the ensemble weights to suitably vary across the prediction window based on the system input. In addition, a novel state observer for ensemble models is developed using moving horizon estimation (MHE). The effectiveness of the proposed methodology is demonstrated on a benchmark energy system operating under multiple conditions.

eess.SY↗

arXiv2026

Goal-oriented safe active learning for predictive control using Bayesian recurrent neural networks

A key challenge in learning-based model predictive control (MPC) is to collect informative data online for model adaptation while ensuring safety and without penalising control performance. In this paper, we propose an online model adaptation scheme embedded within an MPC framework in which the last-layer parameters of a recurrent neural network are recursively updated via Bayesian learning. This is achieved by means of a goal-oriented safe active learning algorithm that alternates between an exploration phase, where the MPC actively explores system dynamics to collect informative data for model adaptation while still pursuing the main control objective, and a goal-reaching phase, where it focuses exclusively on the main control objective. The algorithm is complemented with theoretical guarantees of (i) recursive feasibility, (ii) safety, (iii) termination of exploration in finite time, and (iv) close-to-optimal performance. Simulation results on a benchmark energy system demonstrate that the proposed framework achieves economic performance comparable to that of an MPC with full system knowledge, while progressively improving model accuracy and respecting operational safety constraints with high probability.

eess.SY↗

arXiv2023

Physics-informed Neural Network Modelling and Predictive Control of District Heating Systems

This paper addresses the data-based modelling and optimal control of District Heating Systems (DHSs). Physical models of such large-scale networked systems are governed by complex nonlinear equations that require a large amount of parameters, leading to potential computational issues in optimizing their operation. A novel methodology is hence proposed, exploiting operational data and available physical knowledge to attain accurate and computationally efficient DHSs dynamic models. The proposed idea consists in leveraging multiple Recurrent Neural Networks (RNNs) and in embedding the physical topology of the DHS network in their interconnections. With respect to standard RNN approaches, the resulting modelling methodology, denoted as Physics-Informed RNN (PI-RNN), enables to achieve faster training procedures and higher modelling accuracy, even when reduced-dimension models are exploited. The developed PI-RNN modelling technique paves the way for the design of a Nonlinear Model Predictive Control (NMPC) regulation strategy, enabling, with limited computational time, to minimize production costs, to increase system efficiency and to respect operative constraints over the whole DHS network. The proposed methods are tested in simulation on a DHS benchmark referenced in the literature, showing promising results from the modelling and control perspective.

eess.SY↗