A machine-learning approach to synthesize virtual sensors for parameter-varying systems

DOI10.1016/J.EJCON.2021.06.005MaRDI QIDQ2235477zbMATH OpenOpenAlexFDO

Authors Daniele Masti, D. Bernardini, A. Bemporad

Publication date 21 October 2021

Published in European Journal of Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2103.12324

zbMATH Keywords

parameter estimationstate estimationmachine learning algorithmsvirtual sensors

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonlinear systems in control theory (93C10) Adaptive control/observation systems (93C40) Estimation and detection in stochastic control theory (93E10)

Abstract: This paper introduces a novel model-free approach to synthesize virtual sensors for the estimation of dynamical quantities that are unmeasurable at runtime but are available for design purposes on test benches. After collecting a dataset of measurements of such quantities, together with other variables that are also available during on-line operations, the virtual sensor is obtained using machine learning techniques by training a predictor whose inputs are the measured variables and the features extracted by a bank of linear observers fed with the same measures. The approach is applicable to infer the value of quantities such as physical states and other time-varying parameters that affect the dynamics of the system. The proposed virtual sensor architecture - whose structure can be related to the Multiple Model Adaptive Estimation framework - is conceived to keep computational and memory requirements as low as possible, so that it can be efficiently implemented in embedded hardware platforms. The effectiveness of the approach is shown in different numerical examples, involving the estimation of the scheduling parameter of a nonlinear parameter-varying system, the reconstruction of the mode of a switching linear system, and the estimation of the state of charge (SoC) of a lithium-ion battery.

Recommendations

• Virtual sensors for the functional diagnosis of nonlinear systems
• Virtual sensors for semiconductor manufacturing: A nonparametric approach -- exploiting information theoretic learning and kernel machines
• Low-complexity piecewise-affine virtual sensors: theory and design
• Synthesis of virtual measurements in nonlinear observation problem

Cites work

• scientific article; zbMATH DE number 44406 (Why is no real title available?)
• scientific article; zbMATH DE number 3997615 (Why is no real title available?)
• Absolute diameters and codiameters
• Advanced Lectures on Machine Learning
• Fault diagnosis and fault-tolerant control strategies for non-linear systems. Analytical and soft computing approaches
• Fitting jump models
• Least squares quantization in PCM
• Modeling and identification of linear parameter-varying systems
• Multiple-model estimation with variable structure
• Random forests
• Reducing the Dimensionality of Data with Neural Networks
• Some remarks on the chi-squared test with both margins fixed
• Switching in systems and control
• System identification. An introduction.
• The filter design from data (FD2) problem: nonlinear set membership approach

Cited in

(2)

• Low-complexity piecewise-affine virtual sensors: theory and design
• Virtual sensors for semiconductor manufacturing: A nonparametric approach -- exploiting information theoretic learning and kernel machines

This page was built for publication: A machine-learning approach to synthesize virtual sensors for parameter-varying systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2235477)