摘要
电梯安全运维面临“数据孤岛”、风险评估静态化、维保资源分配低效等挑战。本研究提出一种基于人工智能(Artificial Intelligence,AI)与多源数据融合的电梯检验与维保协同优化方法,构建了AI大模型驱动的“数据融合-动态风险评估-检验/维保决策优化-反馈迭代”闭环模型。该模型实现了高风险电梯精准识别、检验重点智能推荐、维保单位质量分级评价与薄弱环节分析,显著提升了电梯安全管理的智能化水平和效率,为资源配置优化提供了系统解决方案。
Elevator safety operation and maintenance face challenges such as data silos,static risk assessment,and inefficient allocation of maintenance resources.This study proposes an artificial intelligence(AI)and multi-source data fusion-based collaborative optimization method for elevator inspection and maintenance,constructing a closed-loop model driven by AI large-scale models:"from data fusion to dynamic risk assessment,and from inspection/maintenance decision optimization to feedback iteration".The model achieves precise identification of high-risk elevators,intelligent recommendation of inspection priorities,quality grading evaluation of maintenance providers,and weak-point analysis.It significantly enhances the intelligence level and efficiency of elevator safety management,providing a systematic solution for resource allocation optimization.
作者
欧阳徕
李刚
张巍
莫绍孟
罗永通
OUYANG Lai;LI Gang;ZHANG Wei;MO Shaomeng;LUO Yongtong(Guangzhou Special Equipment Inspection and Research Institute,Guangzhou,510180)
出处
《中国特种设备安全》
2025年第S1期34-38,共5页
China Special Equipment Safety
关键词
人工智能
数据融合
检验
维保
协同
Artificial intelligence
Data fusion
Inspection
Maintenance
Collaboration
