食用菌规模化生产监控云服务方法研究

发布时间：2018-03-01 23:11

本文关键词： 食用菌云服务平台数据服务中心模糊推理神经网络网络新媒体　出处：《中国农业大学》2017年博士论文　论文类型：学位论文

【摘要】：我国是栽培食用菌最早的国家,食用菌产量现己居世界首位,但与国外发达国家相比,仍存在巨大差距,如产业化发展的时间较短,发展不均衡、生产规模偏小、技术水平低、产品质量差、竞争能力弱等问题。随着我国供给侧改革和食用菌产业整体提升的需要,急需一种低成本、专业化服务、推广方便的食用菌信息化解决方案,促进食用菌产业向组织化、规模化、标准化和专业化方向转变,提升我国食用菌产业信息化管理能力。近年来发展的"云计算"技术通过网络提供云端基础设施、平台和软件服务,这种面向服务的新型计算模式为解决食用菌生产和技术推广领域中需求和投入的矛盾,建设低成本、专业化的食用菌业务应用服务系统提供了新思路。本研究主要研究内容和结论如下:(1)设计了食用菌规模化生产云服务平台的架构结合对我国食用菌生产业务特点分析,归纳总结了食用菌规模化云服务平台建构的关键问题;最后针对这些关键问题,设计了食用菌规模化云服务平台的整体架构和核心服务。(2)食用菌物联网多源异构海量数据服务架构研究。在云服务平台中,采用感知数据的符号表示方法,实现了对传感器数据的一致化统一描述和表达,设计了食用菌物联网数据交互协议规范;提出了一种通用性较强的传感器数据注册适配接入机制;引入消息服务总线,采用分布式面向服务构建方法,设计了食用菌物联网数据服务管理平台的整体架构。(3)提出了云环境下基于前向模糊推理的菇房环境预警模型。采用分布图法、加权平均和最优方差等方法,实现了菇房环境监测数据的预处理和融合技术,构建了稳定可靠地感知数据预处理模型;研究基于菇房环境关键因子的模糊化表达,构建了基于多维环境因子的模糊推理模型,针对食用菌云服务平台提供的数据和服务,采用分布式计算模型,优化构建了菇房环境监测预警推理模型。(4)基于矩阵分解离散Hopfield的食用菌干燥控制模型的研究。围绕着基于云服务平台提供的服务,首先通过食用菌介电特性,设计了在线的水分监测框架,构建了食用菌水分测定模型;采用优化链接权重和采用矩阵分解的DHNN模型,构建基于水分在线测定的食用菌干燥控制模型,实现了基于云服务平台的食用菌水分在线监测与干燥控制模型。(5)基于网络新媒体的食用菌规模云服务模式研究。实现智能设备+微信公众号的服务模式,为解决食用菌种植现有推广难、成本高、服务内容少的问题,提供一种新的重要的解决方案。
[Abstract]:China is the earliest country to cultivate edible fungi, and the production of edible fungi is now the first in the world. However, compared with the developed countries, there is still a huge gap, such as the short time of industrialization development, uneven development, small scale of production and low level of technology. With the demand of supply-side reform and the overall promotion of edible fungus industry in China, a low-cost, specialized service and convenient edible fungus informatization solution is urgently needed. To promote the transformation of the edible fungus industry towards organization, scale, standardization and specialization, and to enhance the information management capability of the edible fungus industry in China. The "cloud computing" technology developed in recent years provides cloud infrastructure through the network. Platform and software services, a new service-oriented computing model to solve the problem of demand and investment in the field of edible fungus production and technology extension, to build low-cost, The main contents and conclusions of this study are as follows: (1) the structure of the cloud service platform for the large-scale production of edible fungi is designed to analyze the characteristics of edible fungus production business in China. This paper summarizes the key problems of constructing the large-scale cloud service platform of edible fungi, and finally, aiming at these key problems, This paper designs the whole architecture of the edible fungus scale cloud service platform and the core service. 2) the architecture of the edible fungus Internet of things multi-source heterogeneous mass data service architecture is designed. In the cloud service platform, the symbolic representation method of the perceptual data is adopted. The uniform description and expression of sensor data are realized, and the data interaction protocol specification of edible fungus Internet of things is designed. A universal access mechanism of sensor data registration and adaptation is proposed, and a message service bus is introduced. In this paper, a distributed service-oriented method is used to design the whole architecture of Edible Mushroom Internet of things data service management platform. (3) an environmental early warning model based on forward fuzzy reasoning in cloud environment is proposed. The distribution map method is used. Based on weighted average and optimal variance, the preprocessing and fusion technology of environmental monitoring data in mushroom room is realized, and a stable and reliable preprocessing model of perceived data is constructed, and the fuzzy expression of key factors in mushroom room environment is studied. A fuzzy inference model based on multi-dimensional environmental factors is constructed. According to the data and services provided by the edible fungus cloud service platform, the distributed computing model is adopted. Based on matrix decomposition discrete Hopfield, the study of mushroom drying control model is carried out. First of all, the dielectric properties of edible fungi are obtained by means of the service provided by cloud service platform. An on-line moisture monitoring framework was designed, and a moisture measurement model of edible fungi was constructed, and the drying control model of edible fungi based on on-line moisture measurement was constructed by using the DHNN model with optimized link weight and matrix decomposition. The online monitoring and drying control model of edible fungus moisture based on cloud service platform is realized. The research of edible fungus scale cloud service model based on new network media is carried out, and the service mode of intelligent device, WeChat Official account, is realized. In order to solve the problem of difficult popularization, high cost and little service content of edible fungus cultivation, a new and important solution is provided.
【学位授予单位】：中国农业大学
【学位级别】：博士
【学位授予年份】：2017
【分类号】：TP393.09;S646

【参考文献】