Escalator fault early warning method and system based on transfer learning

• Main Authors: TANG ZHUKUAN, ZHANG YAN, CHENG ZHISHANG, DING HAOCHENG, XU LEI, LIU WENQIN
• Format: Patent
• Language: Chinese; English
• Published: 19.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELEVATORS; ESCALATORS OR MOVING WALKWAYS; HANDLING RECORD CARRIERS; HAULING; HOISTING; LIFTING; PERFORMING OPERATIONS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; TRANSPORTING

The invention discloses an escalator fault early warning method and system based on transfer learning, and the method comprises the steps: collecting to-be-analyzed feature data of a target escalator, the to-be-analyzed feature data comprising vibration data, temperature data and noise data; inputting the to-be-analyzed feature data into a fault early warning identification model for analysis and identification, and determining a fault trend level; and when the fault trend level exceeds a preset early warning threshold value, outputting fault early warning data to carry out fault risk early warning. The method is high in stability, high in accuracy and low in cost, and can be widely applied to the technical field of escalator management systems. 本发明公开了一种基于迁移学习的自动扶梯故障预警方法及系统，方法包括：采集目标扶梯的待分析特征数据，所述待分析特征数据包括振动数据、温度数据和噪声数据；将所述待分析特征数据输入故障预警识别模型进行分析识别，确定故障趋势等级；当所述故障趋势等级超过预设的预警阈值时，输出故障预警数据进行故障风险预警。本发明稳定性高、准确率高且成本低，可广泛应用于扶梯管理系统技术领域。