全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于智能感知和深度学习的养蚕管理系统设计
Design on Highly Efficient Silkworm Rearing Technology Based on Intelligent Perception and Processing

DOI: 10.12677/AIRR.2022.112021, PP. 192-199

Keywords: 智能感知,深度学习,养蚕管理系统,设计
Intelligent Perception
, Deep Learning, Silkworm Rearing Technique, Design

Full-Text   Cite this paper   Add to My Lib

Abstract:

新阶段,智能化、装备化养蚕成为现代蚕业高质量发展的必然趋势,但以往的养蚕仍然面临着劳力紧张、装备老旧、控制复杂、标准不高、规范不严等现实问题,急需变革养蚕方式。在养蚕环境智能监控研究的基础上,探讨研制基于智能感知和深度学习的养蚕管理系统,结合自动化、省力化养蚕实景,依托物联网智能感知技术,对养蚕环境要素和蚕体发育状态进行智能感知、识别、传输、处理,精准掌握养蚕发育进程和环境状况,运用深度残差神经网络算法(DRCNN),对多特征数据提取和分级融合处理,及时校正养蚕数据标准,实时监控养蚕生产流程、输出技术方案,提供自动化养蚕决策,为打造智能化、装备化养蚕兼容平台提供参考。
In the new phase, intelligent and equipped sericulture has become an inevitable trend of high-quality development of modern sericulture; however, the management of Silkworm rearing in the past still faced such practical problems as labor shortage, old equipment, complicated control, low standard and lax regulation, and so on. It is urgent to reform the mode of production of silkworm rearing. Based on the research of intelligent monitoring and control of Sericulture Environment, this paper discusses the development of sericulture management system based on intelligent perception and deep learning; combining the real scene of automatic and labor-saving sericulture production, relying on the intelligent perception technology of Internet of things, the intelligent perception, recognition, transmission and processing of the environmental factors and the developmental state of the silkworm are carried out; the development process and the environmental state of the Silkworm are accurately mastered; depth residual neural network Algorithm (DRCNN) is used; the multi-feature data are extracted and classified and fused; the data standard of sericulture should be corrected in time; the production process and output technical scheme should be monitored in real time; and the automatic decision of sericulture should be provided.

References

[1]  吴文福, 张娜, 李姝峣, 等. 5T智慧农场管理系统构建与应用探索[J]. 农业工程学报, 2021, 37(9): 340-349.
[2]  李奇峰, 李嘉位, 马为红, 等. 畜禽养殖疾病诊断智能传感技术研究进展[J]. 中国农业科学, 2021(11): 2445-2463.
[3]  吴阳阳, 彭广德, 吴相飞. 基于LeNet-5 改进的卷积神经网络图像识别方法[J]. 信息与电脑, 2018(7): 127-130.
[4]  Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: NIPS, Research in Astronomy and Astrophysics, Beijing, 1097-1105.
[5]  Simonyan, K. and Zisserman, A. (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. Computer Science, 30, 330-335.
[6]  He, K., Zhang, X., Ren, S. and Sun, J. (2016) Deep Residual Learning for Image Recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90
[7]  赵凯旋, 何东健. 基于卷积神经网络的奶牛个体身份识别方法[J]. 农业工程学报, 2015, 31(5): 181-187.
[8]  肖占军, 赵志杰, 王大海. 浅论面向大数据高效特征选择与学习算法[J]. 科研, 2019(1): 162-163.
[9]  赵德安, 刘晓洋, 孙月平, 等. 基于机器视觉的水下河蟹识别方法[J]. 农业机械学报, 2019(3): 151-158.
[10]  孙孝龙, 吴德余, 徐森, 等. 基于机器学习的智能养蚕管理系统设计[J]. 安徽农业科学, 2020, 48(23): 260-262.
[11]  李家俊, 范英, 樊祺超, 等. 基于单片机智能养殖控制系统设计与实现[J]. 电子测试, 2020(16): 28-30.
[12]  于秋玉. 基于改进YOLOv4的虾苗智能识别算法研究[J]. 河南科技, 2021(6): 25-28.
[13]  孙浩, 陈进, 雷琳, 等. 深度卷积神经网络图像识别模型对抗鲁棒性技术综述[J]. 雷达学报, 2021, 10(4): 571-594.
[14]  范松伟, 林翔瑜, 周平. 基于改进的卷积神经网络的虾苗自动计数研究[J]. 渔业现代化, 2020(6): 35-41.
[15]  杨寿勇, 张海阳, 李成, 等. 基于卷积神经网络模型的微藻种类识别[J]. 环境科学与技术, 2020, 43(S2): 158-164.
[16]  刘莫尘, 许荣浩, 李法德, 等. 基于颜色与面积特征的方格蔟蚕茧分割定位算法与试验[J]. 农业机械学报, 2018, 49(3): 43-50.
[17]  孟令森, 吴胜, 王永娟. 仿蚕机器人的运动特性分析和仿真研究机械科学与技术[J]. 2018, 37(8): 1161-1166.
[18]  陈浩, 杨磊, 陈霞, 等. 机器视觉在茧形态检验中的应用研究[J]. 中国纤检, 2020(1): 74-77.
[19]  孙孝龙, 徐森, 周卫阳, 等. 基于物联网和深度学习的养蚕智能监控系统设计[J]. 江苏农业科学, 2020(21): 241-244.
[20]  孙孝龙, 吴德余, 徐森, 等. 规模化养蚕智能监控系统设计[J]. 蚕桑通报, 2020, 51(3): 29-32.
[21]  王婷. 基于PLC的智能农业现场监控系统设计分析[J]. 南方农业, 2020(27): 198-199.
[22]  陈太阳. 基于卷积神经网络多特征融合的复杂背景字符识别[J]. 电脑知识与技术, 2021, 17(10): 192-193.
[23]  陈彦彤, 陈伟楠, 张献中, 等. 基于深度卷积神经网络的蝇类面部识别[J]. 光学精密工程, 2020, 28(7): 1558-1567.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133