基于深度学习的风机机组运行故障自动化监测系统  

Automated monitoring system for wind turbine units operation faults based on deep learning

作　　者：闫浩伟 YAN Haowei(Datang Shanxi Renewable Power Company,Taiyuan 030000,China)

机构地区：[1]大唐山西新能源公司,山西太原030000

出　　处：《电子设计工程》2025年第7期95-98,共4页Electronic Design Engineering

摘　　要：为了获得更优的风机机组故障监测结果,设计基于深度学习的风机机组运行故障自动化监测系统。采集风机机组运行高清图像,利用改进Stentiford视觉模型提取巡视图像的感兴趣区域,并迅速定位巡视图像的重要信息;通过基于DenseNet网络设计风机机组运行故障诊断模型,实现运行故障智能诊断,仿真实验结果表明,该文系统的风机机组运行故障正确率超过95%,能够直观、可视化展示运行故障监测情况,具有较高的实际应用价值。In order to obtain better fault monitoring results for wind turbine units,a deep learning based automatic monitoring system for wind turbine unit operation faults is designed.Collect high-definition images of the operation of the fan unit,use an improved Stentiford visual model to extract regions of interest from the inspection image,and quickly locate important information in the inspection image;By designing a fault diagnosis model for wind turbine operation based on DenseNet network,intelligent diagnosis of operation faults is achieved.Simulation results show that the accuracy of the wind turbine operation faults in this system exceeds 95%,which can intuitively and visually display the monitoring situation of operation faults and has high practical application value.

关 键 词：深度学习 风机机组 运行故障监测 感兴趣区域 DenseNet网络 

分 类 号：TN911[电子电信—通信与信息系统]