A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions

Abstract Accurate and practical modelling of the scroll expander is essential to improve energy conversion efficiency and reduce energy losses. To improve the generalizability and physical consistency of the data-driven models for the scroll expander under noisy and data scarcity conditions, a novel...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoshuang Lv, Xin Ma, Wei Peng, Ke Li, Chengdong Li
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-02059-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225802512596992
author Xiaoshuang Lv
Xin Ma
Wei Peng
Ke Li
Chengdong Li
author_facet Xiaoshuang Lv
Xin Ma
Wei Peng
Ke Li
Chengdong Li
author_sort Xiaoshuang Lv
collection DOAJ
description Abstract Accurate and practical modelling of the scroll expander is essential to improve energy conversion efficiency and reduce energy losses. To improve the generalizability and physical consistency of the data-driven models for the scroll expander under noisy and data scarcity conditions, a novel mechanism-guided residual network (MGResNet) model is proposed in this study. Firstly, the overall framework of MGResNet is presented. This framework is based on the architecture of residual network, where the mechanistic laws are embedded as constraints in the training of the network through an improved loss function. Then, a hybrid optimization algorithm is detailed, which can achieve efficient and accurate updating of the parameters of the network and mechanistic equations. Finally, comparative prediction experiments are carried out to validate the proposed MGResNet. It has the ability to incorporate mechanistic constraints within the data-driven approach, setting it apart from conventional machine learning and deep learning methods that often disregard underlying physical laws. Experimental results demonstrate that MGResNet significantly outperforms traditional models, achieving over 14.324% improvement in volume flow rate prediction and 3.937% in torque prediction under noisy conditions. Even with a 90% reduction in training data, MGResNet maintains superior accuracy, showing up to 45.983% better performance than other models. This proves that the proposed MGResNet exhibits better forecasting accuracy and stronger robustness in the noisy environments and data sparse conditions due to embedded mechanistic constraints, while generating outputs consistently with physical laws.
format Article
id doaj-art-dea7c824dc174cb9960da32ef787b3f3
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-dea7c824dc174cb9960da32ef787b3f32025-08-24T12:02:18ZengSpringerComplex & Intelligent Systems2199-45362198-60532025-08-01111011810.1007/s40747-025-02059-5A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditionsXiaoshuang Lv0Xin Ma1Wei Peng2Ke Li3Chengdong Li4School of Information and Electrical Engineering, Shandong Jianzhu UniversitySchool of Information and Electrical Engineering, Shandong Jianzhu UniversitySchool of Information and Electrical Engineering, Shandong Jianzhu UniversitySchool of Control Science and Engineering, Shandong UniversitySchool of Information and Electrical Engineering, Shandong Jianzhu UniversityAbstract Accurate and practical modelling of the scroll expander is essential to improve energy conversion efficiency and reduce energy losses. To improve the generalizability and physical consistency of the data-driven models for the scroll expander under noisy and data scarcity conditions, a novel mechanism-guided residual network (MGResNet) model is proposed in this study. Firstly, the overall framework of MGResNet is presented. This framework is based on the architecture of residual network, where the mechanistic laws are embedded as constraints in the training of the network through an improved loss function. Then, a hybrid optimization algorithm is detailed, which can achieve efficient and accurate updating of the parameters of the network and mechanistic equations. Finally, comparative prediction experiments are carried out to validate the proposed MGResNet. It has the ability to incorporate mechanistic constraints within the data-driven approach, setting it apart from conventional machine learning and deep learning methods that often disregard underlying physical laws. Experimental results demonstrate that MGResNet significantly outperforms traditional models, achieving over 14.324% improvement in volume flow rate prediction and 3.937% in torque prediction under noisy conditions. Even with a 90% reduction in training data, MGResNet maintains superior accuracy, showing up to 45.983% better performance than other models. This proves that the proposed MGResNet exhibits better forecasting accuracy and stronger robustness in the noisy environments and data sparse conditions due to embedded mechanistic constraints, while generating outputs consistently with physical laws.https://doi.org/10.1007/s40747-025-02059-5Machine learningPhysics-informed neural networkResidual networkScroll expander modeling
spellingShingle Xiaoshuang Lv
Xin Ma
Wei Peng
Ke Li
Chengdong Li
A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
Complex & Intelligent Systems
Machine learning
Physics-informed neural network
Residual network
Scroll expander modeling
title A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
title_full A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
title_fullStr A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
title_full_unstemmed A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
title_short A novel mechanism-guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
title_sort novel mechanism guided residual network for accurate modelling of scroll expander under noisy and sparse data conditions
topic Machine learning
Physics-informed neural network
Residual network
Scroll expander modeling
url https://doi.org/10.1007/s40747-025-02059-5
work_keys_str_mv AT xiaoshuanglv anovelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT xinma anovelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT weipeng anovelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT keli anovelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT chengdongli anovelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT xiaoshuanglv novelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT xinma novelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT weipeng novelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT keli novelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions
AT chengdongli novelmechanismguidedresidualnetworkforaccuratemodellingofscrollexpanderundernoisyandsparsedataconditions