Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

State-of-the-art methods for data-driven modelling of non-linear dynamical systems typically involve interactions with an expert user. In order to partially automate the process of modelling physical systems from data, many EA-based approaches have been proposed for model-structure selection, with special focus on non-linear systems. Recently, an approach for data-driven modelling of non-linear dynamical systems using Genetic Programming (GP) was proposed. The novelty of the method was the modelling of noise and the use of Tree Adjoining Grammar to shape the search-space explored by GP. In this paper, we report results achieved by the proposed method on three case studies. Each of the case studies considered here is based on real physical systems. The case studies pose a variety of challenges. In particular, these challenges range over varying amounts of prior knowledge of the true system, amount of data available, the complexity of the dynamics of the system, and the nature of non-linearities in the system. Based on the results achieved for the case studies, we critically analyse the performance of the proposed method.

LanguageEnglish
Title of host publication2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages2673-2680
Number of pages8
ISBN (Electronic)978-1-7281-2153-6
DOIs
StatePublished - 1 Jun 2019
Event2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Wellington, New Zealand
Duration: 10 Jun 201913 Jun 2019

Conference

Conference2019 IEEE Congress on Evolutionary Computation, CEC 2019
CountryNew Zealand
CityWellington
Period10/06/1913/06/19

Fingerprint

Nonlinear dynamical systems
Genetic programming
Genetic Programming
Data-driven
Grammar
Data structures
Dynamical systems
Dynamical system
Computer systems programming
Model structures
Modeling
Nonlinear Dynamical Systems
Nonlinear systems
Physical Modeling
Prior Knowledge
Search Space
Nonlinear Systems
Nonlinearity
Interaction
Range of data

Keywords

  • genetic programming
  • system identification
  • tree adjoining grammar

Cite this

Khandelwal, D., Schoukens, M., & Toth, R. (2019). Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming. In 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings (pp. 2673-2680). [8790250] Piscataway: Institute of Electrical and Electronics Engineers. DOI: 10.1109/CEC.2019.8790250
Khandelwal, Dhruv ; Schoukens, Maarten ; Toth, Roland. / Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming. 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Piscataway : Institute of Electrical and Electronics Engineers, 2019. pp. 2673-2680
@inproceedings{5736e68b58a84b5b87a5c6eacda6acb4,
title = "Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming",
abstract = "State-of-the-art methods for data-driven modelling of non-linear dynamical systems typically involve interactions with an expert user. In order to partially automate the process of modelling physical systems from data, many EA-based approaches have been proposed for model-structure selection, with special focus on non-linear systems. Recently, an approach for data-driven modelling of non-linear dynamical systems using Genetic Programming (GP) was proposed. The novelty of the method was the modelling of noise and the use of Tree Adjoining Grammar to shape the search-space explored by GP. In this paper, we report results achieved by the proposed method on three case studies. Each of the case studies considered here is based on real physical systems. The case studies pose a variety of challenges. In particular, these challenges range over varying amounts of prior knowledge of the true system, amount of data available, the complexity of the dynamics of the system, and the nature of non-linearities in the system. Based on the results achieved for the case studies, we critically analyse the performance of the proposed method.",
keywords = "genetic programming, system identification, tree adjoining grammar",
author = "Dhruv Khandelwal and Maarten Schoukens and Roland Toth",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/CEC.2019.8790250",
language = "English",
pages = "2673--2680",
booktitle = "2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Khandelwal, D, Schoukens, M & Toth, R 2019, Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming. in 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings., 8790250, Institute of Electrical and Electronics Engineers, Piscataway, pp. 2673-2680, 2019 IEEE Congress on Evolutionary Computation, CEC 2019, Wellington, New Zealand, 10/06/19. DOI: 10.1109/CEC.2019.8790250

Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming. / Khandelwal, Dhruv; Schoukens, Maarten; Toth, Roland.

2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Piscataway : Institute of Electrical and Electronics Engineers, 2019. p. 2673-2680 8790250.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming

AU - Khandelwal,Dhruv

AU - Schoukens,Maarten

AU - Toth,Roland

PY - 2019/6/1

Y1 - 2019/6/1

N2 - State-of-the-art methods for data-driven modelling of non-linear dynamical systems typically involve interactions with an expert user. In order to partially automate the process of modelling physical systems from data, many EA-based approaches have been proposed for model-structure selection, with special focus on non-linear systems. Recently, an approach for data-driven modelling of non-linear dynamical systems using Genetic Programming (GP) was proposed. The novelty of the method was the modelling of noise and the use of Tree Adjoining Grammar to shape the search-space explored by GP. In this paper, we report results achieved by the proposed method on three case studies. Each of the case studies considered here is based on real physical systems. The case studies pose a variety of challenges. In particular, these challenges range over varying amounts of prior knowledge of the true system, amount of data available, the complexity of the dynamics of the system, and the nature of non-linearities in the system. Based on the results achieved for the case studies, we critically analyse the performance of the proposed method.

AB - State-of-the-art methods for data-driven modelling of non-linear dynamical systems typically involve interactions with an expert user. In order to partially automate the process of modelling physical systems from data, many EA-based approaches have been proposed for model-structure selection, with special focus on non-linear systems. Recently, an approach for data-driven modelling of non-linear dynamical systems using Genetic Programming (GP) was proposed. The novelty of the method was the modelling of noise and the use of Tree Adjoining Grammar to shape the search-space explored by GP. In this paper, we report results achieved by the proposed method on three case studies. Each of the case studies considered here is based on real physical systems. The case studies pose a variety of challenges. In particular, these challenges range over varying amounts of prior knowledge of the true system, amount of data available, the complexity of the dynamics of the system, and the nature of non-linearities in the system. Based on the results achieved for the case studies, we critically analyse the performance of the proposed method.

KW - genetic programming

KW - system identification

KW - tree adjoining grammar

UR - http://www.scopus.com/inward/record.url?scp=85071329584&partnerID=8YFLogxK

U2 - 10.1109/CEC.2019.8790250

DO - 10.1109/CEC.2019.8790250

M3 - Conference contribution

SP - 2673

EP - 2680

BT - 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Khandelwal D, Schoukens M, Toth R. Data-driven modelling of dynamical systems using tree adjoining grammar and genetic programming. In 2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings. Piscataway: Institute of Electrical and Electronics Engineers. 2019. p. 2673-2680. 8790250. Available from, DOI: 10.1109/CEC.2019.8790250