摘要
【目的】设计一款柑橘叶片氮磷含量高光谱检测系统。【方法】基于SR-GRU网络训练构建氮磷含量反演模型,获取柑橘叶片光谱数据和叶片氮磷含量。设计基于云边端架构的柑橘叶片氮磷含量检测系统,对易受户外光线干扰的光谱信号提出改进iForest-SAM算法进行异常光谱检验剔除,对波段多、体积大、传输慢的光谱数据提出基于过完备学习字典的稀疏LoRa报文进行快速传输。系统边缘端在柑橘园内作为LoRa网关,移动终端使用稀疏LoRa报文经边缘端发送至云端加载反演模型进行预测。【结果】SR-GRU反演模型对柑橘叶片氮磷元素含量的反演效果最佳,模型的决定系数分别为0.929和0.865,归一化均方根误差分别为0.083和0.079。系统单次柑橘叶片氮磷含量检测耗时均在1 s以内,LoRa节点连接稳定,基于互联网的Web程序运行稳定,页面平均加载时间在0.5 s以内。【结论】该系统满足对柑橘叶片氮磷含量及时检测的实际应用需求。
【Objective】To design a hyperspectral detection system for nitrogen and phosphorus contents in citrus leaves.【Method】Based on SR-GRU network training,an inversion model of nitrogen and phosphorus contents was constructed to obtain the spectral data of citrus leaves and corresponding nitrogen and phosphorus contents.A detection system of nitrogen and phosphorus contents in citrus leaves based on cloud edge-to-end architecture was designed.An improved iForest-SAM algorithm was proposed for outlier spectra test and rejection of spectral signals which were easily disturbed by outdoor light.The sparse LoRa message based on over-complete learning dictionary was proposed for fast transmission of spectral data with multiple bands,large size and slow transmission.The edge end of the system was acted as a LoRa gateway in the citrus orchard,and at the mobile terminal end,the sparse LoRa messages were sent to the cloud end via the edge end to load the inversion model for prediction.【Result】The SR-GRU inversion model had the best inversion effect on the contents of nitrogen and phosphorus in citrus leaves,with the determination coefficients of 0.929 and 0.865 respectively,and the normalized root mean square error of 0.083 and 0.079 respectively.The system took less than 1 s to detect nitrogen and phosphorus contents of citrus leaves once,and the LoRa node was connected stably.The web program based on the internet ran stably,and the average page loading time was less than 0.5 s.【Conclusion】The system meets the practical application requirements for timely detection of nitrogen and phosphorus contents in citrus leaves.
作者
高昌伦
张方任
唐婷
吴伟斌
段雨欣
罗青
林华瑞
高婷
GAO Changlun;ZHANG Fangren;TANG Ting;WU Weibin;DUAN Yuxin;LUO Qing;LIN Huarui;GAO Ting(College of Engineering,South China Agricultural University,Guangzhou 510642,China;Guangdong E&T Research Center for Mountainous,Orchard Machinery,Guangzhou 510642,China;College of Natural Resources and Environment,South China Agricultural University,Guangzhou 510642,China)
出处
《华南农业大学学报》
北大核心
2025年第2期278-286,共9页
Journal of South China Agricultural University
基金
广东省(深圳)数字智能农业服务产业园(FNXM012022020-1)
广东省农业农村厅科研委及技术推广示范类项目(2023L204)
广东省现代农业产业技术创新团队专项基金(2023KJ120)。
关键词
柑橘叶片
氮磷含量
高光谱
深度学习
无损检测
检测系统
Nitrogen and phosphorus contents
Citrus leaves
Hyperspectra
Deep learning
Non-destructive detection
Detection system
