Although urban rail transit provides significant daily assistance to users, traffic risk remains. Turn‐back faults are a common cause of traffic accidents. To address turn‐back faults, machines are able to learn the complicated and detailed rules of the train’s internal communication codes, and engineers must understand simple external features for quick judgment. Focusing on turn‐back faults in urban rail, in this study we took advantage of related accumulated data to improve algorithmic and human diagnosis of this kind of fault. In detail, we first designed a novel framework combining rules and algorithms to help humans and machines understand the fault characteristics and collaborate in fault diagnosis, including determining the category to which the turn‐back fault belongs, and identifying the simple and complicated judgment rules involved. Then, we established a dataset including tabular and text data for real application scenarios and carried out corresponding analysis of fault rule generation, diagnostic classification, and topic modeling. Finally, we present the fault characteristics under the proposed framework. Qualitative and quantitative experiments were performed to evaluate the proposed method, and the experimental results show that (1) the framework is helpful in understanding the faults of trains that occur in three types of turn‐back: automatic turn‐back (ATB), automatic end change (AEC), and point mode end change(PEC); (2) our proposed framework can assist in diagnosing turn‐back faults.
项目组人员：
马思琦 2018级信息管理与信息系统，王笑辰2018级信息管理与信息系统专业，王鑫 2018级信息管理与信息系统专业项目
指导教师：张润彤
推荐级别：国家级
研究背景：
城市轨道交通持续发展，积累大量的列车折返故障数据，使得如何及时有效地理解和分析这些数据成为一个难题。折返中发生的故障会带来较大的交通风险，除了机器自动诊断故障外，还需要人工判断和监督。对于折返故障，机器适合学习大量复杂的列车内部通信码特征，而测试人员需要了解简单的外部特征，以便快速做出决策。
实验过程：
本项目旨在研究一种结合规则生成与分类算法的方法，以帮助测试人员与机器合作学习折返故障的特征：例如，发生的故障属于哪种折返类别，涉及到哪些关键的判断规则？为此，本项目建立一个贴合真实应用场景的数据集（包含表格形式的列车通信码数据和文本形式的测试人员工作日报数据），并进行故障规则生成、诊断分类和主题建模的仿真实验。结果表明，该方法有助于从算法和人工相结合的角度理解列车在无人自动折返（ATB），自动换端（AEC），和点式换端（PEC）时发生的三种折返故障。
应用：
本研究结合领域知识对实验结果中的故障特征进一步分析，从而为交通安全和城市轨道领域的研究做出贡献。城市轨道交通的管理者可以应用这个方法来管理和诊断折返故障。
未来展望：
在现有基础上建立城市轨道列车折返故障系统。
项目创新点：
1.建立有价值的数据集：建立了比较有价值的数据集，包含完整的三种折返故障，数据量足够大，别且故障类别的比例分布与现实场景保持一致。
2.算法与人结合：框架中将智能算法与人工监督相结合，兼顾准确性与风险排查，适用于交通安全场景。
3.规则与算法结合：特征工程方面结合了故障规则的先验知识，使算法有比较好的可解释性。
项目成果：
1：Siqi Ma, Xin Wang, Xiaochen Wang, Hanyu Liu, and Runtong Zhang, A Framework for Diagnosing Urban Rail Train Turn‐Back, Applied Science [J], 2021. 4, Vol. 11, Iss. 8, no. 3347. SCI. https://doi.org/10.3390/app11083347
2：Siqi Ma; Runtong Zhang; Xiaochen Wang; Xin Wang, A Turn-back Fault Diagnosis Method for Urban Rail System Based on Spark, 2020 6th International Conference on Big Data and Information Analytics (BigDIA) [100]. EI. https://doi.org/10.1109/BigDIA51454.2020.00066
3：基于机器故障和文本主题分析的城轨折返故障诊断方法，马思琦，王鑫，王笑辰，刘涵宇，赵步天，张润彤，发明专利，202110340750.3
