Search

In view of the defects of existing longitudinal tearing monitoring system of conveyor belt, such as few monitoring points, poor expansibility, and still need to be on duty, a remote monitoring system for longitudinal tearing of conveyor belt suitable for multi -point monitoring based on cloud technology was designed. The system consists of a word line laser, embedded processing terminal, area array CMOS camera, cloud server, PC monitoring software and mobile phone monitoring software.The embedded processing terminal drives area array CMOS camera to collect laser fringe projected by the laser onto lower surface of the conveyor belt, and analyzes each frame of collected image, extracts the laser fringe skeleton, and calculates the distortion value.When the distortion value is greater than the preset threshold value, it indicates that the conveyor belt has longitudinal tear and the embedded processing terminal drives the alarm with voice alarm.When the distortion value is less than the threshold value, it indicates that the conveyor belt works normally.The embedded processing terminal transfers image to PC via file transfer protocol and saves it locally.PC monitoring software uses secure file transfer protocol to send the received image information to the cloud server. Mobile phone monitoring software uses the Web server provided by Tomcat to access the cloud server and obtain the image information in real time.The experimental results show that the system can realize a full range of remote real -time monitoring of longitudinal tearing of conveyor belts on site, PC terminal and mobile terminal, and can monitor the running condition of the conveyor belt at any monitoring point in anytime and at anywhere.

For problems of existing pedestrian detection methods based on deep learning such as large computation, detection efficiency relying on hardware performance heavily and so on, the pedestrian detection method based on SSD network was improved. A lightweight convolutional neural network based on DenseNet network is designed as basic network of SSD network to meet real-time detection requirements of underground video pedestrian, and an auxiliary network based on ResNet network is designed to strengthen feature extraction ability and improve correctness of pedestrian detection. An underground video pedestrian detection method based on the improved SSD network has been arranged in embedded platform Jetson TX2 for experiments. The results show that detection accuracy rate of the method for underground video pedestrian is 87.9% as well as nearly 100% for underground low-density pedestrian scene, and calculation speed achieves 48 frames per second, which is about 4.4 times as quick as the pedestrian detection method based on SSD network and meets real-time detection requirements of underground pedestrian.