No abstract

When a high-speed train is running, it is easy for foreign objects like rail-side plastic bags to enter bottom bogies, cables and equipment gaps, which affects the safety of driving. At present, the detection accuracy of such foreign objects is low. To solve this problem, the present study used the latest deep learning based object detection networks, such as SSD and Faster R-CNN, which combined with different feature extractors to build a detection network. Through data augmentation of a sample, the number of sizes was expanded. By the idea of transfer learning, the COCO dataset was used as the source data to transfer features to the new detection network and then retrained to build a train bottom plastic bag detection network based on deep learning. It was shown that through data augmentation, the precision of each combination significantly improved. Moreover, the results using combination of SSD and MobileNet obtained the fastest detection speed with an average time of 41 ms and a precision rate of 81.3%. The accuracy using combination of SSD + Inception V2 combination reached to 89.7%, with an average time of 53 ms. INDEX TERMS Deep learning, foreign matter on underbody, transfer learning, data augmentation, highspeed train.

To solve data processing for the train multiple monitoring and control devices, a multi-protocol data acquisition gateway based on the embedded Linux system was designed. The principle of the gateway was proposed. The gateway’s communication abilities of RS485 network and Ethernet as well as RS485 network based on HDLC protocol and Ethernet were demonstrated by delay analysis for data propagation. The implementation of data acquisition and retransmission for the LKJ and TCMS provides support for achieving the aims of remote monitoring and fault diagnosis for rail transit train.