Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains

The locomotive autonomous operation system is characterized by its inherent nonlinear and time-varying nature. Operating trains encounter a diverse range of track conditions, which necessitates not only predictive control but also the dynamic adjustment of controller parameters to adapt to these var...

Full description

Saved in:
Bibliographic Details
Main Authors: YI Jie, JIANG Fan, LUO Yuan, ZHANG Zhengfang, BAI Jinlei, ZHONG Puhua
Format: Article
Language:zho
Published: Editorial Office of Control and Information Technology 2024-08-01
Series:Kongzhi Yu Xinxi Jishu
Subjects:
Online Access:http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2024.04.005
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224677907496960
author YI Jie
JIANG Fan
LUO Yuan
ZHANG Zhengfang
BAI Jinlei
ZHONG Puhua
author_facet YI Jie
JIANG Fan
LUO Yuan
ZHANG Zhengfang
BAI Jinlei
ZHONG Puhua
author_sort YI Jie
collection DOAJ
description The locomotive autonomous operation system is characterized by its inherent nonlinear and time-varying nature. Operating trains encounter a diverse range of track conditions, which necessitates not only predictive control but also the dynamic adjustment of controller parameters to adapt to these varying conditions. To address these challenges, this paper presents a fuzzy adaptive model predictive control (FAMPC) approach specifically for heavy-haul trains. Based on the establishment of a nonlinear multi-mass model for heavy-haul trains, a model predictive control system framework was constructed, to incorporate optimization processes that consider multiple objectives and operational constraints. This model aims to predict and dynamically adjust the operational states of trains. To mitigate the inadaptability associated with fixed controller parameters in response to changing track conditions, this paper integrates fuzzy control with model predictive control methods, to facilitate the adaptive optimization control for trains running on different railways, by enabling the adaptive tuning of weight coefficients within their model predictive controllers. Simulation results revealed the good control performance of the integrated controller configuration, highlighting its ability to ensure the stable train operation while achieving accurate train control within speed errors of ±1 km/h.
format Article
id doaj-art-c6829e75b1d54d4389d29e746ab4043e
institution Kabale University
issn 2096-5427
language zho
publishDate 2024-08-01
publisher Editorial Office of Control and Information Technology
record_format Article
series Kongzhi Yu Xinxi Jishu
spelling doaj-art-c6829e75b1d54d4389d29e746ab4043e2025-08-25T06:57:16ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272024-08-01364368496716Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul TrainsYI JieJIANG FanLUO YuanZHANG ZhengfangBAI JinleiZHONG PuhuaThe locomotive autonomous operation system is characterized by its inherent nonlinear and time-varying nature. Operating trains encounter a diverse range of track conditions, which necessitates not only predictive control but also the dynamic adjustment of controller parameters to adapt to these varying conditions. To address these challenges, this paper presents a fuzzy adaptive model predictive control (FAMPC) approach specifically for heavy-haul trains. Based on the establishment of a nonlinear multi-mass model for heavy-haul trains, a model predictive control system framework was constructed, to incorporate optimization processes that consider multiple objectives and operational constraints. This model aims to predict and dynamically adjust the operational states of trains. To mitigate the inadaptability associated with fixed controller parameters in response to changing track conditions, this paper integrates fuzzy control with model predictive control methods, to facilitate the adaptive optimization control for trains running on different railways, by enabling the adaptive tuning of weight coefficients within their model predictive controllers. Simulation results revealed the good control performance of the integrated controller configuration, highlighting its ability to ensure the stable train operation while achieving accurate train control within speed errors of ±1 km/h.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2024.04.005heavy-haul trainlocomotive automatic operationadaptive model predictive controlfuzzy control
spellingShingle YI Jie
JIANG Fan
LUO Yuan
ZHANG Zhengfang
BAI Jinlei
ZHONG Puhua
Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
Kongzhi Yu Xinxi Jishu
heavy-haul train
locomotive automatic operation
adaptive model predictive control
fuzzy control
title Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
title_full Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
title_fullStr Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
title_full_unstemmed Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
title_short Research on Fuzzy Adaptive Model Predictive Control Methodology for Heavy-Haul Trains
title_sort research on fuzzy adaptive model predictive control methodology for heavy haul trains
topic heavy-haul train
locomotive automatic operation
adaptive model predictive control
fuzzy control
url http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2024.04.005
work_keys_str_mv AT yijie researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains
AT jiangfan researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains
AT luoyuan researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains
AT zhangzhengfang researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains
AT baijinlei researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains
AT zhongpuhua researchonfuzzyadaptivemodelpredictivecontrolmethodologyforheavyhaultrains