Research On Deep Learning Coal Flow Detection And Belt Speed Control Method

During actual coal mining process,large power loss will be caused due to the operation of belt conveyor without coal or with little coal at a high speed for a long time.Therefore,it is important to study intelligent coal mining based on the automatic control of belt conveyor speed of coal quantity monitoring system.An improved YOLOv5 real-time coal flow detection algorithm was proposed in the paper to save the loss caused by conveyor belt under well.The Swin Transfomer attention mechanism was introduced to improve the limitation of traditional convolution receptive field.In addition,a weighted splicing method was introduced to splice the features extracted from the backbone network.In this way,the overall information of the feature picture was accessible to the network,which helped to effectively improve detection ability.The experiment results indicated that there was an increase of 2.1%in coal flow detection mAP and decline of 10.6%in detection time compared with YOLOv5 algorithm.The method can help to quickly and accurately detect the coal flow of the conveyor belt in real time.The adaptive speed regulation control system for coal belt conveyor was designed in the paper based on intelligent detection technology of coal flow and adaptive speed regulation technology of belt conveyor.The speed was classified into three grades regarding(0～15%)slow,(15%～50%)intermediate and(over 50%)fast according to the proportion of coal flow of conveyor belt and no-load belt so as to adjust the operation speed of belt by grade.The system,which allows adjusting belt speed automatically based on the change of coal flow in the belt conveyor,has a significant energy-saving effect.It is applicable to the needs of coal mine production.