基于改进SSD算法的两相把手式开关识别

Two-phase Handle Switch Recognition Based on Improved SSD Algorithm

为协助操作人员准确判断设备开关状态,越来越多的配电站房引入智能巡检机器人进行设备状态监测。在智能巡检机器人参与采集图像数据的硬件基础上,提出了一种改进单激发多框探测器(SSD)图像识别算法,实现了对两相把手式开关的识别。改进SSD算法通过将基于卷积块的注意机制(CBAM)嵌入到SSD算法中,从通道和空间维度中选择有效的特征,抑制不相关的特征,提高模型的识别精度。实验结果表明,改进SSD算法对开关状态目标检测的平均精度(AP)在98.66%以上,平均精度均值(mAP)为99.10%。相较于传统的SSD算法,改进的SSD算法能更好地识别开关状态,提高变电站智能化水平。

To assist operators in accurately determining the status of equipment switches,more and more intelligent inspection robots are introduced into distribution station buildings for equipment status monitoring,This article proposes a Single Shot MultiBox Detector image recognition algorithm based on the hardware of intelligent inspection robots participating in collecting image data,to achieve recognition of two-phase handle switches.Improving the algorithm by embedding the Convolutional Block Attention Module into the SSD algorithm,selects effective features from channel and spatial dimensions,suppresses irrelevant features,and improves the recognition accuracy of the model.The experimental results show that the AP values for detecting switch status targets are all above 98.66%,the mAP of the improved algorithm is 99.10%,which can better identify switch status compared to traditional SSD algorithms and improve the intelligence level of substations.