Identification of Probability weighted ARX models with arbitrary domains

TL;DR

This paper introduces a novel probabilistic mixture model approach for identifying arbitrary domain PieceWise Auto Regressive with eXogenous input (NPWARX) models, leveraging neural networks and Expectation Maximization for improved hybrid system modeling.

Contribution

It proposes a new method combining neural networks and mixture models for identifying NPWARX models with arbitrary, discontinuous regions, extending beyond polyhedral domains.

Findings

Successfully modeled a nonlinear piecewise problem with discontinuous maps.

Demonstrated the effectiveness of the approach on complex hybrid systems.

Achieved concurrent estimation of submodels and classifiers using EM.

Abstract

Hybrid system identification is a key tool to achieve reliable models of Cyber-Physical Systems from data. PieceWise Affine models guarantees universal approximation, local linearity and equivalence to other classes of hybrid system. Still, PWA identification is a challenging problem, requiring the concurrent solution of regression and classification tasks. In this work, we focus on the identification of PieceWise Auto Regressive with eXogenous input models with arbitrary regions (NPWARX), thus not restricted to polyhedral domains, and characterized by discontinuous maps. To this end, we propose a method based on a probabilistic mixture model, where the discrete state is represented through a multinomial distribution conditioned by the input regressors. The architecture is conceived following the Mixture of Expert concept, developed within the machine learning field. To achieve nonlinear partitioning, we parametrize the discriminant function using a neural network. Then, the parameters of both the ARX submodels and the classifier are concurrently estimated by maximizing the likelihood of the overall model using Expectation Maximization. The proposed method is demonstrated on a nonlinear piece-wise problem with discontinuous maps.