no code implementations • 31 Jan 2024 • Marcello Farina, Giancarlo Ferrari-Trecate, Riccardo Scattolini
This report presents three Moving Horizon Estimation (MHE) methods for discrete-time partitioned linear systems, i. e. systems decomposed into coupled subsystems with non-overlapping states.
no code implementations • 28 Sep 2023 • Fabio Bonassi, Alessio La Bella, Marcello Farina, Riccardo Scattolini
This brief addresses the design of a Nonlinear Model Predictive Control (NMPC) strategy for exponentially incremental Input-to-State Stable (ISS) systems.
no code implementations • 28 Jun 2023 • Stefano Spinelli, Marcello Farina, Andrea Ballarino
A hierarchical architecture for the optimal management of an ensemble of steam generators is presented.
no code implementations • 6 Apr 2023 • Fabio Bonassi, Alessio La Bella, Giulio Panzani, Marcello Farina, Riccardo Scattolini
The aim of this work is to investigate the use of Incrementally Input-to-State Stable ($\delta$ISS) deep Long Short Term Memory networks (LSTMs) for the identification of nonlinear dynamical systems.
no code implementations • 18 Oct 2022 • William D'Amico, Alessio La Bella, Marcello Farina
This paper proposes a novel sufficient condition for the incremental input-to-state stability of a generic class of recurrent neural networks (RNNs).
no code implementations • 13 Oct 2022 • Jing Xie, Fabio Bonassi, Marcello Farina, Riccardo Scattolini
This paper presents a robust Model Predictive Control (MPC) scheme that provides offset-free setpoint tracking for systems described by Neural Nonlinear AutoRegressive eXogenous (NNARX) models.
no code implementations • 8 Aug 2022 • Fabio Bonassi, Jing Xie, Marcello Farina, Riccardo Scattolini
This paper proposes a method for lifelong learning of Recurrent Neural Networks, such as NNARX, ESN, LSTM, and GRU, to be used as plant models in control system synthesis.
no code implementations • 30 Mar 2022 • Fabio Bonassi, Jing Xie, Marcello Farina, Riccardo Scattolini
This paper deals with the design of nonlinear MPC controllers that provide offset-free setpoint tracking for models described by Neural Nonlinear AutoRegressive eXogenous (NNARX) networks.
no code implementations • 28 Feb 2022 • William D'Amico, Marcello Farina
To show the generality and effectiveness of our approach, we apply it to two of the most widely used yet simple control schemes, i. e., where tracking is achieved thanks to (i) a static feedforward action and (ii) an integrator in closed-loop.
no code implementations • 26 Nov 2021 • Fabio Bonassi, Marcello Farina, Jing Xie, Riccardo Scattolini
This paper aims to discuss and analyze the potentialities of Recurrent Neural Networks (RNN) in control design applications.
no code implementations • 3 Mar 2021 • William D'Amico, Marcello Farina, Giulio Panzani
The capability of this class of regulators of constraining the control variable is pointed out and an advanced control scheme that allows to achieve zero steady-state error is presented.
no code implementations • 16 Feb 2021 • Enrico Terzi, Lorenzo Fagiano, Marcello Farina, Riccardo Scattolini
This note extends a recently proposed algorithm for model identification and robust MPC of asymptotically stable, linear time-invariant systems subject to process and measurement disturbances.
no code implementations • 7 Dec 2020 • Fabio Bonassi, Marcello Farina, Riccardo Scattolini
The idea of using Feed-Forward Neural Networks (FFNNs) as regression functions for Nonlinear AutoRegressive eXogenous (NARX) models, leading to models herein named Neural NARXs (NNARXs), has been quite popular in the early days of machine learning applied to nonlinear system identification, owing to their simple structure and ease of application to control design.
no code implementations • 13 Nov 2020 • Fabio Bonassi, Marcello Farina, Riccardo Scattolini
The goal of this paper is to provide sufficient conditions for guaranteeing the Input-to-State Stability (ISS) and the Incremental Input-to-State Stability ({\delta}ISS) of Gated Recurrent Units (GRUs) neural networks.