Data-driven approaches for modeling train control models : Comparison and case studies
Copyright © 2019 ISA. Published by Elsevier Ltd. All rights reserved..
In railway systems, the train dynamics are usually affected by the external environment (e.g., snow and wind) and wear-out of on-board equipment, leading to the performance degradation of automatic train control algorithms. In most existing studies, the train control models were derived from the mechanical analyzation of train motors and wheel-track frictions, which may require many times of field trials and high costs to validate the model parameters. To overcome this issue, we record the explicit train operation data in Beijing Metro within three years and develop three data-driven approaches, involving a linear regression-based model (LAM), a nonlinear regression-based model (NRM), and furthermore a deep neural network based (DNN) model, where the LAM and NRM can act as benchmarks for evaluating DNN. To improve the training efficiency of DNN model, we especially customize the input and output layers of DNN, batch normalization based layers and network parameter initialization techniques according to the unique characteristics of railway train models. From the model training and testing results with field data, we observe that DNN significantly enhances the predicting accuracy for the train control model by using our customized network structure compared with LAM and NRM models. These data-driven approaches are successfully applied to Beijing Metro for designing efficient train control algorithms.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2020 |
|---|---|
| Erschienen: |
2020 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:98 |
|---|---|
| Enthalten in: |
ISA transactions - 98(2020) vom: 20. März, Seite 349-363 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Yin, Jiateng [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Artificial neural networks |
|---|
| Anmerkungen: |
Date Revised 16.03.2020 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
|---|
| doi: |
10.1016/j.isatra.2019.08.024 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM300608500 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM300608500 | ||
| 003 | DE-627 | ||
| 005 | 20231225102902.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2020 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.isatra.2019.08.024 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1002.xml |
| 035 | |a (DE-627)NLM300608500 | ||
| 035 | |a (NLM)31451233 | ||
| 035 | |a (PII)S0019-0578(19)30360-X | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yin, Jiateng |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Data-driven approaches for modeling train control models |b Comparison and case studies |
| 264 | 1 | |c 2020 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ƒaComputermedien |b c |2 rdamedia | ||
| 338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Date Revised 16.03.2020 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status PubMed-not-MEDLINE | ||
| 520 | |a Copyright © 2019 ISA. Published by Elsevier Ltd. All rights reserved. | ||
| 520 | |a In railway systems, the train dynamics are usually affected by the external environment (e.g., snow and wind) and wear-out of on-board equipment, leading to the performance degradation of automatic train control algorithms. In most existing studies, the train control models were derived from the mechanical analyzation of train motors and wheel-track frictions, which may require many times of field trials and high costs to validate the model parameters. To overcome this issue, we record the explicit train operation data in Beijing Metro within three years and develop three data-driven approaches, involving a linear regression-based model (LAM), a nonlinear regression-based model (NRM), and furthermore a deep neural network based (DNN) model, where the LAM and NRM can act as benchmarks for evaluating DNN. To improve the training efficiency of DNN model, we especially customize the input and output layers of DNN, batch normalization based layers and network parameter initialization techniques according to the unique characteristics of railway train models. From the model training and testing results with field data, we observe that DNN significantly enhances the predicting accuracy for the train control model by using our customized network structure compared with LAM and NRM models. These data-driven approaches are successfully applied to Beijing Metro for designing efficient train control algorithms | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Artificial neural networks | |
| 650 | 4 | |a Data-driven approaches | |
| 650 | 4 | |a Field test | |
| 650 | 4 | |a Train control models | |
| 700 | 1 | |a Su, Shuai |e verfasserin |4 aut | |
| 700 | 1 | |a Xun, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Tang, Tao |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Ronghui |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t ISA transactions |d 1971 |g 98(2020) vom: 20. März, Seite 349-363 |w (DE-627)NLM001336894 |x 1879-2022 |7 nnns |
| 773 | 1 | 8 | |g volume:98 |g year:2020 |g day:20 |g month:03 |g pages:349-363 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.isatra.2019.08.024 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 98 |j 2020 |b 20 |c 03 |h 349-363 | ||