One-shot learning in hybrid system identification: a new modular paradigm

Identification of hybrid systems requires learning models that capture both discrete transitions and continuous dynamics from observational data. Traditional approaches follow a stepwise process, separating trace segmentation and mode-specific regression, which often leads to inconsistencies due to unmodeled interdependencies. In this paper, we propose a new iterative learning paradigm that jointly optimizes segmentation and flow function identification. The method incrementally constructs a hybrid model by evaluating and expanding candidate flow functions over observed traces, introducing new modes only when existing ones fail to explain the data. The approach is modular and agnostic to the choice of the regression technique, allowing the identification of hybrid systems with varying levels of complexity. Empirical results on benchmark examples demonstrate that the proposed method produces more compact models compared to traditional techniques, while supporting flexible integration of different regression methods. By favoring fewer, more generalizable modes, the resulting models are not only likely to reduce complexity but also simplify diagnostic reasoning, improve fault isolation, and enhance robustness by avoiding overfitting to spurious mode changes.

Subjects

Hybrid System

Model Learning

Symbolic Regression

DDC Class

519: Applied Mathematics, Probabilities

006.3: Artificial Intelligence

658: General Managament

Funding(s)

Automatische Generierung von Modellen für Prädikation, Testen und Monitoring cyber-physischer Systeme

Publication version

publishedVersion

Name

OASIcs.DX.2025.7.pdf

Type

Main Article

Size

1.08 MB

Format

Adobe PDF

Options

One-shot learning in hybrid system identification: a new modular paradigm