nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo journalinfonormal searchdiv searchzone qikanlogo popupnotification paper paperNew
2025, 02, v.52 25-33+80
高速列车转向架设计仿真验证知识图谱构建及应用研究
基金项目(Foundation): 四川省自然科学基金(2022NSFSC0038)
邮箱(Email): zhanghaizhu@swjtu.edu.cn;
DOI:
发布时间: 2025-02-15
出版时间: 2025-02-15
移动端阅读
摘要:

高速列车转向架设计仿真验证是保证列车运行品质和安全的重要手段。针对转向架设计仿真验证过程中知识缺乏统一表达、管理和重用的问题,提出一种高速列车转向架设计仿真验证知识图谱构建及应用技术框架。首先,在转向架设计仿真验证知识分析的基础上构建知识本体,基于BERT-BiLSTM-CRF模型完成知识抽取,并构建转向架设计仿真验证知识图谱,结合Neo4j实现知识的表达、管理与存储;其次,分别基于TransR算法与相似度计算和Cypher语句实现知识推理和知识检索,进而实现知识重用;最后,开发转向架设计仿真验证知识管理系统,实现高速列车转向架设计仿真验证知识的有效管理,以转向架运行安全性需求为仿真目标案例,实现仿真知识重用并搭建仿真模型,验证所提方法的可行性。

Abstract:

Simulation & verification of high-speed train bogie design are an important means to ensure the quality and safety of train operation. Aiming at the problem of lack of unified expression, management and reuse of knowledge in the simulation & verification process of bogie design, this paper proposed a technology framework of knowledge graph construction and application for simulation & verification of high-speed train bogie design. Firstly, the knowledge ontology was constructed based on the knowledge analysis of bogie design simulation & verification, and accomplished knowledge extraction based on the BERT-BiLSTM-CRF model,and the knowledge graph of simulation &verification for bogie design was constructed, and the expression,management and storage of knowledge were realized by combining Neo4j. Then, knowledge reasoning and knowledge retrieval were realized based on TransR algorithm, similarity calculation and Cypher statement respectively, so as to realize knowledge reuse. Finally, the knowledge management system of simulation & verification for bogie design was developed, which realized the effective management of high-speed train bogie design simulation verification knowledge. Taking the safety requirements of bogie operation as the simulation target case, the simulation knowledge reuse was realized and the simulation model was built, which verified the feasibility of the method proposed in this paper.

参考文献

[1]陈晓波,熊光楞,柴旭东.仿真在复杂产品设计中的应用及面临的挑战[J].系统仿真学报,2002(8):1034-1039.

[2]李传迎,李鹏,吴兴文,等.基于刚柔耦合动力学的高速列车转向架构架振动疲劳研究[J].机械,2023,50(1):20-28.

[3]贾鹏,池茂儒,李浩天,等.扭转刚度和扭转阻尼对虚拟轨道车辆性能的影响分析[J].机械,2019,46(10):22-30.

[4]施国强,刘泽伟,林廷宇,等.面向复杂产品建模与仿真系统的开放式云架构设计[J].系统仿真学报,2022,34(3):442-451.

[5]邱晓刚,段红,谢旭,等.仿真学科知识体系的若干问题研究[J].系统仿真学报,2021,33(4):753-762.

[6]XIONG S,ZHU F,YAO Y,et al. A description method of cloud simulation model resources based on knowledge graph:2019 IEEE4th International Conference on Cloud Computing and Big Data Analysis(ICCCBDA)[C]. IEEE,2019.

[7]刘怀远,文晶,陈兴雷,等.知识驱动的大电网仿真分析知识建模方法及其在潮流智能调整问题中的应用[J].中国电机工程学报,2023,43(5):1843-1855.

[8]刘营,张霖,赖李媛君.复杂系统仿真的模型重用研究[J].中国科学:信息科学,2018,48(7):743-766.

[9]LISTL F G, FISCHER J, BEYER D, et al. Knowledge Representation in Modeling and Simulation:A survey for the production and logistic domain:2020 25th IEEE International conference on emerging technologies and factory automation(ETFA)[C]. IEEE,2020.

[10]AMIT S. Introducing the knowledge graph[R]. America:Official Blog of Google,2012.

[11]李佳静,黎荣,武浩远,等.面向多领域的转向架知识本体表达及重用研究[J].机械设计与制造,2019(4):55-58.

[12]王昊琪,李浩,文笑雨,等.本体驱动的复杂产品系统设计信息重用框架[J].计算机集成制造系统,2021,27(6):1662-1672.

[13]郭恒,黎荣,张海柱,等.多域融合的高速列车维修性设计知识图谱构建[J].中国机械工程,2022,33(24):3015-3023.

[14]舒世泰,李松,郝晓红,等.知识图谱嵌入技术研究进展[J].计算机科学与探索,2021,15(11):2048-2062.

[15]LIN Y,LIU Z,SUN M,et al. Learning entity and relation embeddings for knowledge graph completion:Proceedings of the AAAI conference on artificial intelligence[C]. AAAI,2015.

[16]中华人民共和国国家市场监督管理总局,中国国家标准化管理委员会.机车车辆动力学性能评定及试验鉴定规范:GB/T 5599-2019[S].北京:中国标准出版社,2019.

基本信息:

中图分类号:TP391.1;U270.33

引用信息:

[1]廖杨,黎荣,张海柱,等.高速列车转向架设计仿真验证知识图谱构建及应用研究[J].机械,2025,52(02):25-33+80.

基金信息:

四川省自然科学基金(2022NSFSC0038)

发布时间:

2025-02-15

出版时间:

2025-02-15

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文
检 索 高级检索