The invention belongs to the technical field of unmanned driving application, and particularly relates to an unmanned vehicle fault diagnosis method based on deep reinforcement learning and an expert knowledge base. According to the method, through deep fusion of deep reinforcement learning and expert knowledge, the advantages of the deep reinforcement learning and the expert knowledge can be better exerted in the field of unmanned vehicle fault diagnosis. According to the technical scheme, based on an expert knowledge base and a complete training sample, model training is carried out through a deep reinforcement learning algorithm, and a deep reinforcement learning knowledge system is obtained; according to a deep reinforcement learning knowledge system and an expert knowledge base, establishing an explanation library between fault names and diagnosis data; according to the invention, the method achieves the diagnosis of the preprocessed unmanned vehicle data based on a deep reinforcement learning knowledge system, outputs a fault name through an explanation library, and updates the knowledge system and the explanation library if the fault has no solution, thereby effectively improving the detection range of the fault, and reducing the safety accidents caused by the fault of the unmanned vehicle.

    本发明属于无人驾驶应用技术领域,尤其涉及一种基于深度强化学习和专家知识库的无人车故障诊断方法。本发明通过深度强化学习和专家知识的深度融合,使二者在无人车故障诊断领域更好地发挥其优势。本发明技术方案中,基于专家知识库和完整的训练样本,通过深度强化学习算法进行模型训练,得到深度强化学习知识系统;根据深度强化学习知识系统和专家知识库,建立故障名称和诊断数据之间的解释库;基于深度强化学习知识系统实现对预处理后的无人车数据的诊断,并通过解释库输出故障名称,若该故障无解则更新知识系统和解释库,从而有效提升了故障的检测范围,减少了无人车因故障引起的安全事故的发生。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Unmanned vehicle fault diagnosis method based on deep reinforcement learning and expert knowledge base


    Weitere Titelangaben:

    基于深度强化学习和专家知识库的无人车故障诊断方法


    Beteiligte:
    FENG XUAN (Autor:in) / XU RONGGE (Autor:in) / LAN WEI (Autor:in) / MA WENBO (Autor:in) / GUO QIANG (Autor:in)

    Erscheinungsdatum :

    2023-01-31


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Hydrogen fuel unmanned aerial vehicle energy management method based on deep reinforcement learning

    WU YU / ZHANG MINGXUAN / WANG YUYANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff



    Fault diagnosis equipment for unmanned aerial vehicle

    FU WENZHONG / LIU JIANFENG / HUANG JINGLIN | Europäisches Patentamt | 2023

    Freier Zugriff