Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles
This paper proposes a novel hybrid physics-data-driven framework for system modelling by integrating a physical model and an online learning data model to improve model accuracy, interpretability, and generalization. Taking an in-wheel Motor Driven Vehicle (IMDV) as an example, two hybrid representa...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/164354 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-164354 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1643542023-01-17T05:46:04Z Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles Chen, Hao Lou, Shanhe Lv, Chen School of Mechanical and Aerospace Engineering Engineering::Mechanical engineering Hybrid Modelling Physics-Data-Driven Method This paper proposes a novel hybrid physics-data-driven framework for system modelling by integrating a physical model and an online learning data model to improve model accuracy, interpretability, and generalization. Taking an in-wheel Motor Driven Vehicle (IMDV) as an example, two hybrid representations, i.e. the Dynamic Linearization Data Model (DLDM) and Recurrent High-Order Neural Network (RHONN) are introduced for the planar dynamics modelling of the electric vehicle. However, it is difficult to obtain the statistical information of the operation process and measurement noise when the weight vectors of the data-driven model is updated online. To address this issue, a H∞-based learning algorithm is adopted. The stability and convergence rate are elaborated and compared with an existing Extended Kalman Filter (EKF)-based method. Finally, we compare four methods, including the physics-based, data-based and two hybrid models, to evaluate their performances of modelling the IMDV's dynamics. The feasibility test and comparison studies are conducted in simulations and on a Hardware-in-the-Loop (HiL) test rig. The results demonstrated that the proposed H∞-based hybrid method, which does not make any assumption on measurement noise, has better generalization ability and robustness in practical implementations, compared to other baseline methods. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University Submitted/Accepted version This work was supported in part by A*STAR AME Young Individual Research Grant (No. A2084c0156), and the Start-Up Grant of Nanyang Technological University, Singapore. 2023-01-17T05:46:04Z 2023-01-17T05:46:04Z 2023 Journal Article Chen, H., Lou, S. & Lv, C. (2023). Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles. Mechanical Systems and Signal Processing, 185, 109791-. https://dx.doi.org/10.1016/j.ymssp.2022.109791 0888-3270 https://hdl.handle.net/10356/164354 10.1016/j.ymssp.2022.109791 2-s2.0-85138471963 185 109791 en Mechanical Systems and Signal Processing © 2022 Elsevier Ltd. All rights reserved. This paper was published in Mechanical Systems and Signal Processing and is made available with permission of Elsevier Ltd. application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Mechanical engineering Hybrid Modelling Physics-Data-Driven Method |
spellingShingle |
Engineering::Mechanical engineering Hybrid Modelling Physics-Data-Driven Method Chen, Hao Lou, Shanhe Lv, Chen Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
description |
This paper proposes a novel hybrid physics-data-driven framework for system modelling by integrating a physical model and an online learning data model to improve model accuracy, interpretability, and generalization. Taking an in-wheel Motor Driven Vehicle (IMDV) as an example, two hybrid representations, i.e. the Dynamic Linearization Data Model (DLDM) and Recurrent High-Order Neural Network (RHONN) are introduced for the planar dynamics modelling of the electric vehicle. However, it is difficult to obtain the statistical information of the operation process and measurement noise when the weight vectors of the data-driven model is updated online. To address this issue, a H∞-based learning algorithm is adopted. The stability and convergence rate are elaborated and compared with an existing Extended Kalman Filter (EKF)-based method. Finally, we compare four methods, including the physics-based, data-based and two hybrid models, to evaluate their performances of modelling the IMDV's dynamics. The feasibility test and comparison studies are conducted in simulations and on a Hardware-in-the-Loop (HiL) test rig. The results demonstrated that the proposed H∞-based hybrid method, which does not make any assumption on measurement noise, has better generalization ability and robustness in practical implementations, compared to other baseline methods. |
author2 |
School of Mechanical and Aerospace Engineering |
author_facet |
School of Mechanical and Aerospace Engineering Chen, Hao Lou, Shanhe Lv, Chen |
format |
Article |
author |
Chen, Hao Lou, Shanhe Lv, Chen |
author_sort |
Chen, Hao |
title |
Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
title_short |
Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
title_full |
Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
title_fullStr |
Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
title_full_unstemmed |
Hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
title_sort |
hybrid physics-data-driven online modelling: framework, methodology and application to electric vehicles |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/164354 |
_version_ |
1756370564548657152 |