在实际煤炭采集过程中，长时间在无煤或少煤情况下高速运转皮带运输机会造成大量电能损耗，因此根据煤量监测系统自动调控带式输送机速率以实现智能化采煤是一项重要研究工作。

为了节省井下传送皮带造成的损耗,本文提出一种改进的YOLOv5实时煤流量检测算法。通过引入Swin Transfomer注意力机制，用以改善传统卷积感受野受限问题，同时引入一种加权的拼接方法，对主干网络提取的特征进行加权拼接，使网络能够获取特征图的全局信息，有效提高检测能力。实验结果表明，与YOLOv5算法相比，煤流量检测mAP提升2.1%，且检测时间减少10.6%，能够快速准确的对传送带煤流量进行实时检测。

本文在煤流量智能检测技术和带式输送机自适应调速技术的基础上，设计实现了煤炭带式运输机自适应调速控制系统。 根据输送带煤流量与空载皮带的占比情况，分为（0~15%）慢速、（15%~50%）中速、（大于50%）快速三个等级，从而分档次调整皮带的运行速度。该系统可根据带式输送机中运输煤流量的大小变化自动调节带速，节能效果明显，适于煤矿生产需求。

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.

[1]王福斌, 孙海洋, TU Paul. 边缘扩展的皮带撕裂支持向量机视觉检测[J]. 中国机械工程, 2019, 30(4):455-460.

[2]杨祥, 田慕琴, 李璐,等. 带式输送机输送带故障检测技术研究[J]. 煤矿机械, 2019, 40(2):133-136.

[3]朱立平, 蒋卫良. 适用于我国煤矿带式输送机典型机型的研究状[J]. 煤矿学报, 2010, (11): 1916-1920.

[4]赵玉文. 带式输送机的现状和发展趋势[J]. 煤矿机械, 2004, 2.

[5]宋伟刚, 王丹. 7.6km长距离带式输送机系统动力学的计算机仿真[J]. 煤炭学报, 2004, 29(2):249-253.

[6]孙伟, 王慧, 杨海群. 带式输送机变频调速节能控制系统研究[J]. 工矿自动化, 2013, 39(4):98-101.

[7]田原. 浅谈机器视觉技术在煤矿中的应用前景[J]. 工矿自动化, 2010, 36(5):30-32.

[8]任中全, 王淼. 带式输送机节能调速控制系统设计[J]. 煤炭技术, 2016, 35(5):245-246.

[9]丁秀明. 煤矿能耗调研分析和节能措施[J]. 煤炭技术, 2010, 29(3):243-245.

[10]代伟, 赵杰, 杨春雨,等. 基于双目视觉深度感知的带式输送机煤量检测方法[J]. 煤炭学报, 2017, 42(S2):547-555.

[11]唐守锋, 史可, 仝光明,等. 一种矿井低照度图像增强算法[J]. 工矿自动化, 2021, 47(10):5.

[12]孟凡芹, 王耀才. 煤矿井下带式输送机煤流图像识别方法的研究[J]. 煤炭学报, 2003, 28(1):23-24.

[13]杨小彬, 周世禄, 李娜,等. 深度学习及其在煤矿安全领域的应用[J]. 煤矿安全, 2019, 50(1):261-264.

[14]王森, 伍星, 张印辉,等. 基于深度学习的全卷积网络图像裂纹检测[J]. 计算机辅助设计与图形学学报, 2018, 30(5):115-123.

[15]Pouyanfar S, Sadiq S, Yan Y,et al. A Survey on Deep Learning: Algorithms, Techniques, and Applications[J]. Acm Computing Surveys, 2019, 51(5):92.1-92.36.

[16]Sermanet P, Eigen D, Zhang X,et al. OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks[J]. Eprint Arxiv, 2013.

[17]崔维玉. 基于数据挖掘的水轮机异常预警方法研究[D]. 山东:山东大学, 2018.

[18]韩慧. 基于深度学习的工业缺陷检测方法研究[D]. 重庆:重庆邮电大学,2019.

[19]Frizzi S, Kaabi R, Bouchouicha M,et al. Convolutional neural network for video fire and smoke detection[C]// Conference of the IEEE Industrial Electronics Society. IEEE, Florence, Italy, 2016: 877-882.

[20]Tao C, Jian Z, Pan W. Smoke Detection Based on Deep Convolutional Neural Networks[C]// International Conference on Industrial Informatics - Computing Technology. IEEE, Wuhan, China, 2017: 150-153.

[21]Zhang P, Shen H, Hui Z. Machine Learning Topological Invariants with Neural Networks[J]. Physical Review Letters, 2017, 120(6).

[22]张铮, 王艳平, 薛桂香. 数字图像处理与机器视觉[M]. 北京: 人民邮电出版社, 2010:340-379.

[23]余文勇, 石绘. 机器视觉自动检测技术[M]. 北京: 化学工业出版社, 2013:5-8.

[24]Suga T, Muto K, Yagi K,et al. Relation between Image Detection Time and Thumbnail Image Size for Satellite-based Telemedicine[J]. Procedia Computer Science, 2014, 35:1513-1518.

[25]Tong J H, Li J B, Jiang H Y. Machine vision techniques for the evaluation of seedling quality based on leaf area[J]. Biosystems Engineering, 2013, 115(3): 369–379.

[26]赵永强, 饶元, 董世鹏,等. 深度学习目标检测方法综述[J]. 中国图象图形学报, 2020, 25(4):629-654.

[27]Guo Z H, Jie W, Lu H Y, et al. A case study on a hybrid wind speed forecasting method using BP neural network[J]. Knowledge-Based Systems, 2011, 24(7): 1048-1056.

[28]周俊宇, 赵艳明. 卷积神经网络在图像分类和目标检测应用综述[J]. 计算机工程与应用, 2017, 53(13): 34-41.

[29]Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks[C]// Advances in neural information processing systems. 2012: 1097-1105.

[30]Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition[J]. Computer Science, 2014: 1409-1556.

[31]Szegedy C, Liu W, Jia Y, et al. Going Deeper with Convolutions[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 1-9.

[32]He K, Zhang X, Ren S, et al. Deep Residual Learning for Image Recognition[C]// Proceedings of the IEEE conference on computer vision and pattern recogniton. 2016: 770-778.

[33]Girshick R, Donahue J, Darrell T, et al. Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2014: 580-587.

[34]Girshick R. Fast r-cnn[C]// Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

[35]Ren S, He K, Girshick R, et al. Faster r-cnn: Towards real-time object detection with region proposal networks[C]// Advances in neural information processing systems. 2015: 91-99.

[36]Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection[C]// Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.

[37]Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]// European conference on computer vision. Springer, Cham. 2016: 21-37.

[38]Lindeberg T. Scale Invariant Feature Transform[M]. Scholarpedia,2012: 5.

[39]Kaothanthong N, Theeramunkong T, Chun J. Improving Thai Optical Character Recognition Using Circular-Scan Histogram[C]// IAPR International Conference on Document Analysis & Recognition. IEEE, 2018.

[40]Redmon J, Farhadi A. YOLO9000: Better, Faster, Stronger[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 7263-7271.

[41]Redmon J, Farhadi A. YOLOv3: An Incremental Improvement[J]. arXiv preprint arXiv: 1804.02767, 2018.

[42]Bochkovskiy A, Wang C Y, Liao H. YOLOv4: Optimal Speed and Accuracy of Object Detection[J]. 2020.

[43]Tan M, Pang R, Le Q V. EfficientDet: Scalable and Efficient Object Detection[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE Press, 2020: 10781-70790.

[44]Yun S, Han D, Chun S, et al. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 6023-6032.

[45]Wang C Y, Liao H, Wu Y H, et al. CSPNet: A New Backbone that can Enhance Learning Capability of CNN[C]// 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2020: 1911.11929.

[46]LIN T Y, DOLLAR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition. 2017: 936-944.

[47]Liu S, Qi L, Qin H, et al. Path Aggregation Network for Instance Segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 8759-8768.

[48]Kaiming, He, Xiangyu, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2015, 37(9): 1904-1916.

[49]Rahman M A, Yang W. Optimizing Intersection-Over-Union in Deep Neural Networks for Image Segmentation[C]// Proceedings of the International Symposium on Visual Computing. Switzerland: Springer, Cham, 2016: 234-244.

[50]Zheng Z, Wang P, Liu W, et al. Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression[C]// In Proceedings of the AAAI Conferrnce on Artificial Intelligence(AAAI), 2020, 34(07): 12993-13000.

[51]Bahdanau D, Cho K, Bengio Y. Neural Machine Translation by Jointly Learning to Align and Translate[J]. Computer Science, 2014: 1-15.

[52]Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[J]. arXiv preprint arXiv: 1706.03762, 2017.

[53]Dosovitskiy A, Beyer L, Kolesnikov A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[J]. arXiv preprint arXiv: 2010.11929, 2020.

Liu Z, Lin Y, Cao Y, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows[J]. arXiv preprint arXiv: 2013. 14030, 2021