Blockchain-based federated learning for intelligent control in Heavy Haul Railway
Author
dc.contributor.author
Gaofeng, Hua
Author
dc.contributor.author
Zhu, Li
Author
dc.contributor.author
Wu, Jinsong
Author
dc.contributor.author
Shen, Chunzi
Author
dc.contributor.author
Zhou, Lingyan
Author
dc.contributor.author
Lin, Qingqing
Admission date
dc.date.accessioned
2021-01-27T19:37:51Z
Available date
dc.date.available
2021-01-27T19:37:51Z
Publication date
dc.date.issued
2020
Cita de ítem
dc.identifier.citation
IEEE Access, vol. 8, pp. 176830-176839
es_ES
Identifier
dc.identifier.other
10.1109/ACCESS.2020.3021253
Identifier
dc.identifier.uri
https://repositorio.uchile.cl/handle/2250/178366
Abstract
dc.description.abstract
Due to the long train marshaling and complex line conditions, the operating modes in heavy haul rail systems frequently change when trains travel. Improper traction or braking operation made by drivers will increase the longitudinal impact force to trains and causes the train decoupling, severely affecting the safe operations of trains. It is quite desirable to replace the manual control with intelligent control in heavy haul rail systems. Traditional machine learning-based intelligent control methods suffer from insufficient data. Due to lacking effective incentives and trust, data from different rail lines or operators cannot be shared directly. In this paper, we propose an approach on blockchain-based federated learning to implement asynchronous collaborative machine learning between distributed agents that own data. This method performs distributed machine learning without a trusted central server. The blockchain smart contract is used to realize the management of the entire federated learning. Using the historical driving data collected from real heavy haul rail systems, the learning agent in the federated learning method adopts a support vector machine (SVM) based intelligent control model. To deal with the imbalanced traction and braking data, we optimize the classic SVM model via assigning different penalty factors to the majority and minority classes. The data set are mapped to a high dimension using kernel functions to make it linearly separable. We construct a mixing kernel function composed of polynomial and radial basis function (RBF) kernel functions, which uses a dynamic weight factor changing with train speeds to improve the model accuracy. The simulation results demonstrate the efficiency and accuracy of our proposed intelligent control method.
es_ES
Patrocinador
dc.description.sponsorship
National Natural Science Foundation of China (NSFC)
61973026
Beijing Science and Technology Commission
Z191100010818001
Beijing Education Commission
I20H100010
I19H100010
Beijing Natural Science Foundation
L181004
Fundamental Research Funds for the Central Universities
2018JBZ002
Hunan Provincial Nature Science Foundation
2018JJ2535
Chile Comisión Nacional de Investigación Científica y Tecnológica (CONICYT) Fondo Nacional de Desarrollo Científico y Tecnológico (FONDECYT)
1181809
Chile CONICYT Fondo de Fomento al Desarrollo Científico y Tecnológico (FONDEF)
ID16I10466
es_ES
Lenguage
dc.language.iso
en
es_ES
Publisher
dc.publisher
Institute of Electrical and Electronics Engineers (IEEE)