Modelling and control of dynamic systems using Gaussian process models
I cite description of the book given by the author: In Preface: ``...this book is written with purpose of demonstrating a type of nonparametric model, coming mainly from the machine-learning community, for use in the applications of the engineering community. ``The emphasis is on guidelines for working solutions and on practical advice for their implementation. ...it shows the potential of the selected modeling method for use in dynamic-systems identification and control design. It is not written in a theorem/proof style. The mathematics is kept to a minimum. In Introduction: ``This book deals with the topic of nonlinear system identification using Gaussian Process (GP) models and their role in the design of the control of dynamic systems. ``Mathematical models of dynamic systems are used for prediction, control design, fault detection, etc. These models can be further divided by the type of modeling. One example is the white-box models, which are obtained from theoretical modeling based on physical, chemical or other basic principles. The alternative is black-box models, which are obtained from experimental modeling or identification. The author enumerates where the GP model was used in the course of time: in the field of geostatistics; to solve a regression problem; in machine-learning community; in artificial neural networks. ``...we are taking the position of a practical user of nonlinear, black-box models. The book complements other books where GP models have been described in detail from the theoretical point of view, for example, [\textit{C. E. Rasmussen} and \textit{C. K. I. Williams}, Gaussian processes for machine learning. Cambridge, MA: MIT Press (2006; Zbl 1177.68165)], [\textit{J. Q. Shi} and \textit{T. Choi}, Gaussian process regression analysis for functional data. Boca Raton, FL: CRC Press (2011; Zbl 1273.60005)]. In the last chapter 6 are presented ``GP model applications for dynamic systems modeling and control in practice: 6.1 Gas-Liquid Separator Modeling and Control 6.2 Faulty Measurements Detection and Reconstruction in Urban Traffic 6.3 Prediction of Ozone Concentration in the Air References are voluminous, they contain in particular a lot of books and conference articles of the recent time. The author himself has a lot of articles in engineering and biological applications journals, and they are sufficiently cited.
- Online model learning of buildings using stochastic hybrid systems based on Gaussian processes
- Hybrid Gaussian process modeling applied to economic stochastic model predictive control of batch processes
- Consistent online Gaussian process regression without the sample complexity bottleneck
- High-probability stable Gaussian process-supported model predictive control for Lur'e systems
- A stochastic variational framework for recurrent Gaussian processes models
- A flexible state-space model for learning nonlinear dynamical systems
- Distributed predictive control based on Gaussian process models
- Gaussian process internal model control
- Gaussian process model identification: a process engineering case study
- Finite-Dimensional Gaussian Approximation with Linear Inequality Constraints
- scientific article; zbMATH DE number 2150211 (Why is no real title available?)
- Fixed-structure Gaussian process model
- Switching and Learning in Feedback Systems
- Switching and Learning in Feedback Systems
- Dynamic systems identification with Gaussian processes
- scientific article; zbMATH DE number 7686968 (Why is no real title available?)
- Online learning‐based model predictive control with Gaussian process models and stability guarantees
- A framework for machine learning of model error in dynamical systems
- Learning for predictive control: a dual Gaussian process approach
- A GP-enhanced MPC framework with information-driven adaptation and risk-awareness for UAV trajectory tracking
This page was built for publication: Modelling and control of dynamic systems using Gaussian process models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q896718)
