接触网支持装置不良状态检测方法浅析

为准确检测接触网支持装置中开口销脱落、开口角度不足等缺陷,提出一种接触网支持装置不良状态的检测方法。首先根据接触网支持装置三大关键连接处的图像特征,通过Hough变换对斜腕臂进行边缘检测,再基于金字塔词袋模型,精确定位接触网支持装置的各连接处区域;结合开口销自身图像特征,采用图像增强和分割技术实现开口销图像的精确提取;最后分析不同状态下开口销非连通处的分布规律,制定不良状态判据,判别开口销所处的状态。实验结果表明,该方法能够有效判别开口销的状态,对于接触网维护和高速铁路安全运营具有重要意义。

With regard to the missing,the opening angle insufficiency of the split pins for the supporting devices of overhead contact line,the paper puts forward a detecting method of the supporting device with defective state.Firstly,based on the three image features at the key joints in the support device,the edge detection of the oblique cantilever tube is performed by Hough transform,and then the pyramid word bag model is used to obtain the precise positioning of the joints of the support device.Combining the image characteristics of the split pin itself,the image processing technology is used to achieve accurate extraction of the split pin image.Finally,according to the distribution law of the non-connection of the split pin,the defective state criterion is established to realize the detection of the defective state of the split pin.The experimental results show that the proposed method can accurately identify the three states in which the split pin is located,which has good application value for OCL maintenance and high speed railway operation and safety operation.