本文選題：蟲(chóng)害預(yù)測(cè)系統(tǒng) + PSO��； 參考：《浙江理工大學(xué)》2017年碩士論文

【摘要】：我國(guó)作為農(nóng)業(yè)大國(guó),農(nóng)作物的產(chǎn)量占據(jù)重要地位。蟲(chóng)害的發(fā)生對(duì)農(nóng)作物的生產(chǎn)造成了嚴(yán)重的危害。因此,及時(shí)、準(zhǔn)確的對(duì)蟲(chóng)害的發(fā)生進(jìn)行預(yù)測(cè)預(yù)報(bào),才能為蟲(chóng)害的防治工作提供基礎(chǔ),才能有利于農(nóng)業(yè)的良好發(fā)展,減少損失。隨著信息技術(shù)的發(fā)展,計(jì)算機(jī)網(wǎng)絡(luò),數(shù)據(jù)管理等技術(shù)早已被廣泛應(yīng)用到蟲(chóng)害的監(jiān)測(cè)和預(yù)測(cè)等領(lǐng)域。為了適應(yīng)農(nóng)作物蟲(chóng)害資料的規(guī)范化、信息化、網(wǎng)絡(luò)化的要求,以及相關(guān)人員日常工作的需求,本文構(gòu)建了一個(gè)基于Web技術(shù)的蟲(chóng)害預(yù)測(cè)系統(tǒng),該系統(tǒng)集蟲(chóng)害數(shù)據(jù)管理、查詢、預(yù)測(cè)于一體。蟲(chóng)害的發(fā)生不僅受天氣、農(nóng)作物的生長(zhǎng)情況等的影響,還具有地域上的差別,蟲(chóng)害數(shù)據(jù)自身又包含顯著的動(dòng)態(tài)時(shí)序特征,很難對(duì)其做到精準(zhǔn)的預(yù)測(cè)。為了能及時(shí)和準(zhǔn)確的對(duì)蟲(chóng)害的發(fā)生進(jìn)行預(yù)測(cè),本文主要研究?jī)?nèi)容為:(1)針對(duì)農(nóng)業(yè)中蟲(chóng)害發(fā)生數(shù)據(jù)的特點(diǎn),以及對(duì)相關(guān)基礎(chǔ)理論的研究,以偏最小二乘支持向量機(jī)(LSSVM)為核心,建立了針對(duì)農(nóng)業(yè)蟲(chóng)害發(fā)生的預(yù)測(cè)模型(PLS-PSO-LSSVM)。首先,針對(duì)LSSVM參數(shù)尋優(yōu)的問(wèn)題,提出用遺傳算法(GA)和粒子群算法(PSO)對(duì)其參數(shù)尋優(yōu)進(jìn)行改進(jìn)。其次,針對(duì)蟲(chóng)害發(fā)生影響因素之間的共線性問(wèn)題,提出用偏最小二乘法(PLS)對(duì)蟲(chóng)害發(fā)生影響因素進(jìn)行主成分提取。(2)基于區(qū)域的蟲(chóng)害發(fā)生量的預(yù)測(cè)。以稻飛虱為例,通過(guò)對(duì)其近30年發(fā)生情況的分析,稻飛虱的發(fā)生不僅受到溫度、濕度、降雨、日照的影響,發(fā)生的情況還有地域上的差別。因此,本文以具體地區(qū)的蟲(chóng)害影響因素作為預(yù)測(cè)因子,結(jié)合本文建立的預(yù)測(cè)模型進(jìn)行預(yù)測(cè),并與BP神經(jīng)網(wǎng)絡(luò)、偏最小二乘(PLS)模型進(jìn)行對(duì)比分析,得出本文建立的預(yù)測(cè)模型的預(yù)測(cè)精度更高。(3)根據(jù)基于Web技術(shù)的蟲(chóng)害預(yù)測(cè)系統(tǒng)的設(shè)計(jì)需求,對(duì)系統(tǒng)進(jìn)行了總體設(shè)計(jì)和詳細(xì)設(shè)計(jì)分析,并完成了系統(tǒng)的開(kāi)發(fā)。實(shí)現(xiàn)了實(shí)時(shí)蟲(chóng)害數(shù)據(jù)監(jiān)測(cè)、歷史蟲(chóng)害數(shù)據(jù)查詢、報(bào)表設(shè)計(jì)分析、蟲(chóng)害預(yù)測(cè)等功能模塊。實(shí)現(xiàn)了數(shù)據(jù)的集中管理,及時(shí)將蟲(chóng)情發(fā)送到相應(yīng)的用戶手中。
[Abstract]:As a large agricultural country, the output of crops occupies an important position in China. The occurrence of insect pests has caused serious harm to the production of crops. Therefore, timely and accurate prediction of the occurrence of insect pests can provide a basis for pest control, can be conducive to the good development of agriculture and reduce losses. With the development of information technology, computer network, data management and other technologies have been widely used in pest monitoring and forecasting. In order to meet the requirements of standardization, information and networking of crop pest data and the daily work of related personnel, a pest prediction system based on Web technology is constructed in this paper. Prediction is one thing. The occurrence of insect pests is not only affected by the weather and crop growth, but also has regional differences. The pest data itself contains significant dynamic temporal characteristics, it is difficult to accurately predict them. In order to predict the occurrence of insect pests in time and accurately, the main contents of this paper are as follows: (1) according to the characteristics of pest occurrence data in agriculture and the research of related basic theories, partial least squares support vector machine (LSSVM) is the core. A prediction model for agricultural pest occurrence (PLS-PSO-LSSVM) was established. Firstly, to solve the problem of LSSVM parameter optimization, genetic algorithm (GA) and particle swarm optimization (PSO) are proposed to improve the optimization of LSSVM parameters. Secondly, aiming at the problem of collinearity between the influencing factors of pest occurrence, the partial least square (PLS) method is proposed to extract the principal components of the influencing factors of pest occurrence. (2) the prediction of pest occurrence quantity based on region. Taking rice planthopper as an example, the occurrence of rice planthopper is not only affected by temperature, humidity, rainfall and sunshine, but also by regional difference through the analysis of the occurrence of rice planthopper in recent 30 years. Therefore, this paper takes the pest influence factors of specific area as the prediction factor, combining the prediction model established in this paper, and carries on the comparison analysis with the BP neural network, partial least squares (PLS) model. It is concluded that the prediction model established in this paper has higher prediction accuracy. (3) according to the design requirements of the pest prediction system based on Web technology, the overall design and detailed design analysis of the system are carried out, and the development of the system is completed. Real-time pest data monitoring, historical pest data query, report design and analysis, pest prediction and other functional modules are realized. The centralized management of the data is realized, and the bug situation is sent to the corresponding users in time.
【學(xué)位授予單位】：浙江理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類(lèi)號(hào)】：S431;TP393.09

【相似文獻(xiàn)】

相關(guān)期刊論文 前7條

1 趙國(guó)富;趙朋;;基于BP網(wǎng)絡(luò)的蟲(chóng)害預(yù)測(cè)預(yù)報(bào)系統(tǒng)的分析與實(shí)現(xiàn)[J];農(nóng)機(jī)化研究;2008年04期

2 韋艷玲;;ELM在蟲(chóng)害預(yù)測(cè)中的應(yīng)用研究[J];科學(xué)技術(shù)與工程;2012年22期

3 馮慧敏;閆巍;李雪非;;基于Choquet積分的非線性蟲(chóng)害預(yù)測(cè)[J];湖北農(nóng)業(yè)科學(xué);2013年22期

4 ;湖北省下半年蔬菜蟲(chóng)害預(yù)測(cè)[J];農(nóng)家顧問(wèn);2000年08期

5 汪璇;呂家恪;謝德體;魏朝富;;集成GASA混合學(xué)習(xí)策略的BP神經(jīng)網(wǎng)絡(luò)在水稻蟲(chóng)害預(yù)測(cè)中的應(yīng)用[J];中國(guó)農(nóng)學(xué)通報(bào);2007年04期

6 哈尼馬提·尼合買(mǎi)提;甘壽春;魏建華;馬冬梅;;2013年昌吉州棉花主要病蟲(chóng)害預(yù)測(cè)及綜合防治技術(shù)[J];新疆農(nóng)業(yè)科技;2013年01期

7 ;[J];;年期

相關(guān)會(huì)議論文 前1條

1 劉平;張鵬宇;馮興龍;劉孟軍;;昆蟲(chóng)的趨色性在蟲(chóng)害預(yù)測(cè)和防治中的應(yīng)用[A];第五屆全國(guó)干果生產(chǎn)、科研進(jìn)展學(xué)術(shù)研討會(huì)論文集[C];2007年

相關(guān)碩士學(xué)位論文 前2條

1 張芳群;基于Web技術(shù)的蟲(chóng)害預(yù)測(cè)系統(tǒng)的研究[D];浙江理工大學(xué);2017年

2 隆軻;BP神經(jīng)網(wǎng)絡(luò)在蟲(chóng)害預(yù)測(cè)上的應(yīng)用研究[D];湖南農(nóng)業(yè)大學(xué);2014年

，

本文編號(hào)：2063154