一种基于大数据的接触网验损缺陷数据管理方法及系统

• Format: Patent
• Language: Chinese
• Published: 03.01.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

本发明公开了一种基于大数据的接触网验损缺陷数据管理方法及系统，包括以下步骤：利用预先建立的缺陷类别识别模型对接触网验损缺陷数据流进行缺陷数据的归类得到多组依缺陷类别区分的验损缺陷数据集，所述接触网验损缺陷数据为在接触网中获取用于表征接触网验损部位缺陷特征的特征数据；基于所述验损缺陷数据集构建定向识别模型。本发明基于所述验损缺陷数据集构建定向识别模型，以实现根据用户自定义选择进行接触网缺陷的定向识别，提高用户体验，构建位置缺陷测算模型，以实现根据接触网位置进行缺陷类别测算的智能分析，构建位置缺陷关联模型，以实现根据缺陷类别进行接触网位置关联的智能分析，提供管理智能化程度。 The invention discloses a big data-based contact network damage inspection defect data management method and system, and the method comprises the following steps: carrying out the classification of defect data of a contact network damage inspection defect data flow through a pre-established defect type recognition model, and obtaining a plurality of groups of damage inspection defect data sets which are distinguished according to defect types, the catenary damage inspection defect data is characteristic data which is obtained in a catenary and is used for representing defect characteristics of a catenary damage inspection part; and constructing a directional recognition model based on the damage inspection defect data set. Ac