One-shot backpropagation for multi-step prediction in physics-based system identification -- EXTENDED VERSION

2023/10/31 by Cesare Donati, Martina Mammarella, Donati, Cesare +7
Computer Science · Engineering · #Control Systems and Identification #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Machine Learning (cs.LG) #Structural Health Monitoring Techniques #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2310.20567

openalex publication_date 2023/10/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The aim of this paper is to present a novel physics-based framework for the identification of dynamical systems, in which the physical and structural insights are reflected directly into a backpropagation-based learning algorithm. The main result is a method to compute in closed form the gradient of a multi-step loss function, while enforcing physical properties and constraints. The derived algorithm has been exploited to identify the unknown inertia matrix of a space debris, and the results show the reliability of the method in capturing the physical adherence of the estimated parameters.

Related

• Combining Off-White and Sparse Black Models in Multi-step Physics-based Systems Identification -- EXTENDED VERSION
• An algorithm for discovering Lagrangians automatically from data
• Physics-Informed Machine Learning for Characterizing System Stability
• Backpropagation and gradient descent for an optimized dynamic mode decomposition
• Dynamics-Encoded Deep Learning for Robust System Identification and Parameter Estimation