[1]吴乐华,于东洋.基于脉冲神经网络的数字车辆数据处理研究[J].机械与电子,2026,44(08):18-25.
　WU Lehua,YU Dongyang.Research on Digital Vehicle Data Processing Based on Spiking Neural Network[J].Machinery & Electronics,2026,44(08):18-25.
点击复制

基于脉冲神经网络的数字车辆数据处理研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年08期
页码:
18-25
栏目:
研究与设计
出版日期:
2026-08-25

文章信息/Info

Title:
Research on Digital Vehicle Data Processing Based on Spiking Neural Network
文章编号:
1001-2257(2026)08-0018-08
作者:
吴乐华1; 于东洋2
1.中国铁路南昌局集团有限公司,江西 南昌 330009; 2.北京京天威科技发展有限公司,北京 100080
Author(s):
WU Lehua1; YU Dongyang2
(1.China Railway Nanchang Group Co.,Ltd.,Nanchang 330009,China; 2.Beijing Jingtianwei Technology Development Co.,Ltd.,Beijing 100080,China)
关键词:
铁路数字化管理; 数字车辆; 脉冲神经网络; 实时数据流处理; 脉冲编码
Keywords:
railway digital management; digital vehicle; spiking neural networks; real-time data stream processing; spike coding
分类号:
TP183
文献标志码:
A
摘要:
针对数字车辆综合信息管理平台中多源实时数据处理资源消耗大、响应延迟高等问题,提出了一种基于脉冲神经网络的处理方法。通过脉冲编码将来自车速、位置、温度等多种传感器的实时数据转化为脉冲信号,结合脉冲时序依赖可塑性(STDP)学习规则与多层网络架构,实现对时序数据的深度挖掘。实验结果表明,该模型处理实时数据流准确率达92.5%,响应时间为35 ms,能够有效满足铁路运输系统中大规模实时数据流的处理需求。
Abstract:
To address the high resource consumption and long response latency of multi-source real-time data processing in the digital vehicle integrated information management platform,a processing method based on spiking neural networks is proposed.Real-time data from various sensors,including vehicle speed,position,and temperature,are first converted into spike trains through spike encoding.The Spike-Timing Dependent Plasticity (STDP) learning rule is then combined with a multi-layer network architecture to enable deep mining of temporal data.Experimental results demonstrate that the proposed model performs effectively in processing real-time data streams,achieving an accuracy of 92.5% and a response time of 35 ms,thereby effectively satisfying the demands of large-scale real-time data stream processing in railway transportation systems.

参考文献/References:

[1] 刘淼,崔妍.基于数据中台的重载铁路智能化应用研究[J].铁路计算机应用,2023,32(12):67-72. [2] 宋宗莹,丁辉,王兴中,等.基于列车群组运行的重载铁路运输组织研究综述[J].铁道运输与经济,2024,46(10):73-81. [3] 魏中华.突发事故干扰背景下的铁路运输实时调度方法设计[J].工程建设与设计,2024(17):91-93. [4] Liu Huan,Wang Shilei,Jing Guoqing,et al.Combined CNN and RNN neural networks for GPR detection of railway subgrade diseases [J].Sensors,2023,23(12):5383. [5] Feng Yang,Zhao Chunfa,Liang Xin,et al.SNN-based surrogate modeling of electromagnetic force and its application in maglev vehicle dynamics simulation[J]Actuators,2025,14(3):112. [6] Dampfhoffer M,Mesquida T,Valentian A,et al.Backpropagation-based learning techniques for deep spiking neural networks:a survey[J].IEEE Transactions on Neural Networks and Learning Systems,2023,35(9):11906-11921. [7] Safa A,Ocket I,Bourdoux A,et al.STDP-driven development of attention-based people detection in spiking neural networks[J].IEEE Transactions on Cognitive and Developmental Systems,2022,16(1):380-387. [8] 陈祖快,李靖,沈玉文,等.基于脉冲神经网络的低压交流串联故障电弧识别方法研究[J].电器与能效管理技术,2025(4):7-14. [9] 张永强,刘健章,李向南.基于脉冲神经网络的铁路接触线异物检测研究[J].软件工程,2025,28(3):51-56. [10] Liang Yu,Wei Wenjie,Belatreche A,et al.Towards accurate binary spiking neural networks:learning with adaptive gradient modulation mechanism[C]∥ Proceedings of the AAAI Conference on Artificial Intelligence,2025:1402-1410. [11] Rathi N,Roy K.DIET SNN:a low-latency spiking neural network with direct input encoding and leakage and threshold optimization[J].IEEE Transactions on Neural Networks and Learning Systems,2023,34(6):3174-3182. [12] Botalb A,Moinuddin M,Al-Saggaf U M,et al.Contrasting convolutional neural network (CNN) with multi-layer perceptron (MLP) for big data analysis [C]∥2018 International Conference on Intelligent and Advanced System (ICIAS).New York:IEEE,2018:1-5. [13] Rahman M S A,Jamaludin N A A,Zainol Z,et al.Enhancing project completion date prediction using a hybrid model:rule-based algorithm and machine learning algorithm[J].International Journal on Advanced Science,Engineering and Information Technology,2025,15(4):1047-1059. [14] Danach K,Khalaf A H,Rammal A,et al.Enhancing DDBMS performance through RFO-SVM optimized data fragmentation:a strategic approach to machine learning enhanced systems[J].Applied Sciences,2024,14(14):6093. [15] Agarwal H,Mahajan G,Shrotriya A,et al.Predictive data analysis:leveraging RNN and LSTM techniques for time series dataset[J].Procedia Computer Science,2024,235:979-989.

备注/Memo

备注/Memo:
收稿日期:2026-05-09 基金项目:国铁集团科技创新项目(CRNCJ2024073) 作者简介:吴乐华 (1972-),男,福建福州人,高级工程师,研究方向为铁道车辆技术与装备应用;于东洋 (1976-),男,山东掖县人,高级工程师,研究方向为计算数学及应用软件开发。
更新日期/Last Update: 2026-08-28