A novel brain-inspired approach based on spiking neural network for cooperative control and protection of multiple trains

The ongoing challenge of addressing critical issues related to intelligent cooperative control and active protection persists due to the absence of a comprehensive and efficient integrated solution. To address this challenge, this paper introduces a brain-inspired controller that emulates the collab...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Engineering applications of artificial intelligence Ročník 127; s. 107252
Hlavní autoři: Zhang, Zixuan, Song, Haifeng, Wang, Hongwei, Tan, Ligang, Dong, Hairong
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.01.2024
Témata:
Brain-inspired control
Cooperative operation
Railway train control
Spiking neural networks
Brain-inspired control
Cooperative operation
Railway train control
Spiking neural networks
ISSN:0952-1976, 1873-6769
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The ongoing challenge of addressing critical issues related to intelligent cooperative control and active protection persists due to the absence of a comprehensive and efficient integrated solution. To address this challenge, this paper introduces a brain-inspired controller that emulates the collaborative functionalities of various brain regions, harnessing the power of spiking neural networks. The controller’s primary tasks include reference velocity tracking, cooperative control, and active protection, with a special focus on cooperative protection within distinct operational modes. Furthermore, the fundamental principles of incorporating spiking neural networks into train control, such as coding and decoding mechanisms, are expounded. The overarching controller is partitioned into two principal functional segments. The first segment involves emulating the prefrontal cortex (PFC) for reference velocity tracking and active protection against overspeed and collisions through motor control and movement planning. The second segment employs a cerebellum-inspired network for cooperative control. Additionally, the brain-inspired network introduced in this study undergoes training utilizing biologically-inspired mechanisms, incorporating dopamine and pertinent teaching signals to facilitate realistic synaptic modifications. Simulation results in several scenarios validate the proposed approach.
ISSN:0952-1976
1873-6769
DOI:10.1016/j.engappai.2023.107252