工业设备状态监测系统的视觉辅助策略与实现

Vision aided strategy and implementation in equipment status monitoring system

视觉辅助的工业设备状态监测系统用视频流数据作为补充的现场信息来源,基于远程客户端展示车间各个设备的实时状态,为现场维护工程师和远程的机械专家协同工作提供更丰富的现场支持.为了准确识别视频中的设备,建立设备图像和设备实体的映射关系,提出一种基于图像分析的主动式设备ID识别方法,设备标签通过LED可见光源的周期性闪烁发送设备ID信息,IoT2000网关提取图像中的LED光斑形状特征变化,进而识别相应设备的ID信息.系统实验结果证明该方法能准确、可靠地识别设备标签信息.

A vision aided equipment status monitoring system is presented in this paper.With real-time video streaming data as the complementary data from industrial field,the system can intuitively show the real-time status of equipment in each workshop,and can better support the co-work between field maintenance engineers and remote mechanical engineers.The difficulty of the system implementation is how to recognize the equipment in the image,and setup the mapping between equipment unity and its image.An active method of equipment identity recognition is proposed based on vision processing.An equipment tag sends the equipment ID by blinking LED light source.An IoT2000 gateway recognizes the feature changing of LED lighting spots,and transforms to the equipment ID correspondingly.The experimental results proves the reliability and efficiency of the proposed method.