CN109215310A - 海湾扇贝养殖病害预警系统 - Google Patents
海湾扇贝养殖病害预警系统 Download PDFInfo
- Publication number
- CN109215310A CN109215310A CN201811322942.6A CN201811322942A CN109215310A CN 109215310 A CN109215310 A CN 109215310A CN 201811322942 A CN201811322942 A CN 201811322942A CN 109215310 A CN109215310 A CN 109215310A
- Authority
- CN
- China
- Prior art keywords
- cloud platform
- platform server
- bay scallop
- early warning
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
本发明公开一种海湾扇贝养殖病害预警系统,设有云平台服务器,与云平台服务器相接有数据记录单元及专家远程判断单元,所述云平台服务器设有帐户管理单元及预警模型,所述数据记录单元记录环境生态指标、贝类健康指标和病理学指标。采用养殖扇贝环境生态指标、养殖扇贝健康状况指标和病理学指标构建预警模型并最终优化得到输出变量(预测死亡率),用以评价海湾扇贝养殖生长状况。通过实时检测养殖扇贝相应的指标,由云平台服务器分析并通过专家远程判断、修正,实现海湾扇贝养殖病害预警。
Description
技术领域
本发明属于水产养殖领域,尤其涉及一种海湾扇贝养殖病害预警系统。
背景技术
海湾扇贝属于经济附加值较高的养殖品种,在我国北方黄渤海地区海水养殖产业中占据重要地位。但是,海湾扇贝容易受到病害尤其是细菌性病原侵染,进而出现大规模疫病爆发,导致贝类短时间内大面积死亡,造成巨大经济损失。由于贝类养殖多采用开放海域浮筏或底播的养殖模式,只能依靠养殖户的经验对养殖病害等进行判别,难以及时发现。
发明内容
本发明是为了解决现有技术所存在的上述技术问题,提供一种海湾扇贝养殖病害预警系统。
本发明的技术解决方案是:一种海湾扇贝养殖病害预警系统,设有云平台服务器,与云平台服务器相接有数据记录单元及专家远程判断单元,所述云平台服务器设有帐户管理单元及嵌入有预警模型,所述数据记录单元记录环境生态指标、贝类健康指标和病理学指标。
所述环境生态数据为日期、水温、叶绿素含量、浮游细菌丰度和灿烂弧菌比例;所述贝类健康指标为海湾扇贝总抗氧化能力及肌肉柱糖原含量;所述病理学指标为养殖贝类样品现场采集照片及组织病理学解剖和切片。
本发明首先采用养殖扇贝环境生态指标、养殖扇贝健康状况指标和病理学指标构建预警模型并最终优化得到输出变量(预测死亡率),用以评价海湾扇贝养殖生长状况。通过实时检测养殖扇贝相应的指标,由云平台服务器分析并通过专家远程判断、修正,实现海湾扇贝养殖病害预警。具有样品数据收集便捷、预测准确性高等特点。
附图说明
图1为本发明实施例预测死亡率与实际死亡率示意图。
具体实施方式
本发明的海湾扇贝养殖病害预警系统,设有云平台服务器,与云平台服务器相接有数据记录单元及专家远程判断单元,所述云平台服务器设有帐户管理单元及嵌入预警模型,所述数据记录单元记录环境生态指标、贝类健康指标和病理学指标。环境生态数据为日期、水温、叶绿素含量、浮游细菌丰度和灿烂弧菌比例;贝类健康指标为海湾扇贝总抗氧化能力及肌肉柱糖原含量;病理学指标为养殖贝类样品现场采集照片及组织病理学解剖和切片。
本发明的建模步骤如下:
1. 模型输入变量确定:需要预报建模的参数为水温(℃),叶绿素(μg/L),浮游细菌丰度(单位:107CFU/mL),灿烂弧菌所占比例(VS_ratio),总抗氧能力(protein mg)和肌肉柱糖原(mg/g),根据以上模型变量,得到其与输出变量(预测死亡率 %)的时序关系。
2. 检测模型建立
(1) 开始:所有变量初始化
(2) 读取模型训练所需数据集:选择BP神经网络模型训练,从数据库中读取或输入模型训练学习所需数据集。
(3) 数据预处理:针对养殖海区水文状况及监测点数据可能存在的跳变数据,采用噪声尖峰滤波算法用于剔除跳变数据;并进行归一化处理后,作为最终的预报模型的训练数据。
(4) 模型相关待定参数确定:确立以预测死亡率为输出变量并上传至云平台服务器(S8)进行检索分析和数据记录。
(5) 建模效果评估:利用已有历年渤海海区海湾扇贝养殖海区环境数据和海湾扇贝健康数据,验证模型。采用BP神经网络算法进行评估,若建模误差符合要求,则结束训练学习过程。
本发实施例建模及运算具体步骤如下:
SamNum=3;
输入样本数量
TestSamNum=3;
测试样本数量
ForcastSamNum=3;
预测样本数量
HiddenUnitNum=5;
中间层隐节点数量
InDim=1;
网络输入维度
OutDim=1;
网络输出维度
yuefen=[7 8 9];
%水温(单位:℃)
shuiwen=[18.3 22.5 21.5];
%叶绿素(单位:μg/L) chlorophyll
yelvsu=[2.56 1.12 1.86];
%浮游细菌丰度(单位:10^7CFU/mL) bacterioplankton abundance
fyxjfd=[9.5 25.7 57.6];
%灿烂弧菌所占比例VS_retio
clhjszbl=[0.039088796 0.057791527 0.554953963];
%总抗氧能力(单位/毫克蛋白)antioxidant_capacity
zkynl=[2.798113345 2.093014755 1.201754422];
%肌肉柱糖原(mg/g)Muscle column glycogen
jrzty=[1.153333333 1.854 1.201666667];
%死亡率(%)mortality
siwanglv=[19.1 33.1 23];
p=[yuefen;shuiwen;yelvsu;fyxjfd;clhjszbl;zkynl;jrzty];
输入数据矩阵
t=[siwanglv];
目标数据矩阵
[SamIn,minp,maxp,tn,mint,maxt]=premnmx(p,t);
原始样本初始化
rand('state',sum(100*clock))
依据系统时钟种子产生随机数
NoiseVar=0.01;
噪声强度为0.01
Noise=NoiseVar*randn(1,SamNum);
生成噪声
SamOut=tn + Noise;
将噪声添加到输出样本上
TestSamIn=SamIn;
TestSamOut=SamOut;
MaxEpochs=10000-100000;
lr=0.035;
E0=0.65*10-3;
W1=0.5*rand(HiddenUnitNum,InDim)-0.1;
B1=0.5*rand(HiddenUnitNum,1)-0.1;
W2=0.5*rand(OutDim,HiddenUnitNum)-0.1;
B2=0.5*rand(OutDim,1)-0.1;
ErrHistory=[ ];
fori=1:MaxEpochs
HiddenOut=logsig(W1*SamIn+repmat(B1,1,SamNum));
%NetworkOut=W2*HiddenOut+repmat(B2,1,SamNum);
Error=SamOut-NetworkOut;
SSE=sumsqr(Error);
ErrHistory=[ErrHistory SSE];
if SSE<E0,break, end
(6) 根据BP网络模型进行输出变量计算
Delta2=Error;
Delta1=W2'*Delta2.*HiddenOut.*(1-HiddenOut);
dW2=Delta2*HiddenOut';
dB2=Delta2*ones(SamNum,n);
dW1=Delta1*SamIn';
dB1=Delta1*ones(SamNum,n);
W2=W2+lr*dW2;
B2=B2+lr*dB2;
W1=W1+lr*dW1;
B1=B1+lr*dB1;
end
HiddenOut=logsig(W1*SamIn+repmat(B1,1,TestSamNum));NetworkOut=W2*HiddenOut+repmat(B2,1,TestSamNum);
a=postmnmx(NetworkOut,mint,maxt);
x=n:n;
newk=a(n,:);
figure ;
plot(x,newk,'r-o',x,siwanglv,'b--+')
得到输出变量值(预测死亡率)。
从图1可以看出,本发明预测数据(网络输出死亡率)与实际死亡率基本一致,误差较小,且变化趋势类似,说明本发明可为实现海湾扇贝的健康养殖提供保障。
Claims (2)
1.一种海湾扇贝养殖病害预警系统,其特征在于:设有云平台服务器,与云平台服务器相接有数据记录单元及专家远程判断单元,所述云平台服务器设有帐户管理单元及嵌入有预警模型,所述数据记录单元记录环境生态指标、贝类健康指标和病理学指标。
2.根据权利要求1所述的海湾扇贝养殖病害预警系统,其特征在于:所述环境生态数据为日期、水温、叶绿素含量、浮游细菌丰度和灿烂弧菌比例;所述贝类健康指标为海湾扇贝总抗氧化能力及肌肉柱糖原含量;所述病理学指标为养殖贝类样品现场采集照片及组织病理学解剖和切片。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811322942.6A CN109215310A (zh) | 2018-11-08 | 2018-11-08 | 海湾扇贝养殖病害预警系统 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811322942.6A CN109215310A (zh) | 2018-11-08 | 2018-11-08 | 海湾扇贝养殖病害预警系统 |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109215310A true CN109215310A (zh) | 2019-01-15 |
Family
ID=64994856
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811322942.6A Pending CN109215310A (zh) | 2018-11-08 | 2018-11-08 | 海湾扇贝养殖病害预警系统 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109215310A (zh) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102113468A (zh) * | 2010-11-29 | 2011-07-06 | 大连海洋大学 | 海水池塘养殖病害的预报方法 |
CN201907997U (zh) * | 2010-11-20 | 2011-07-27 | 大连海事大学 | 一种氧活性粒子治理赤潮的装置 |
CN102818642A (zh) * | 2012-07-18 | 2012-12-12 | 辽宁省海洋水产科学研究院 | 刺参病害预警系统 |
JP2015142522A (ja) * | 2014-01-31 | 2015-08-06 | ケー・デー・エル株式会社 | 魚介類の鮮度保持方法 |
-
2018
- 2018-11-08 CN CN201811322942.6A patent/CN109215310A/zh active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201907997U (zh) * | 2010-11-20 | 2011-07-27 | 大连海事大学 | 一种氧活性粒子治理赤潮的装置 |
CN102113468A (zh) * | 2010-11-29 | 2011-07-06 | 大连海洋大学 | 海水池塘养殖病害的预报方法 |
CN102818642A (zh) * | 2012-07-18 | 2012-12-12 | 辽宁省海洋水产科学研究院 | 刺参病害预警系统 |
JP2015142522A (ja) * | 2014-01-31 | 2015-08-06 | ケー・デー・エル株式会社 | 魚介類の鮮度保持方法 |
Non-Patent Citations (2)
Title |
---|
刘超: "温度对底播虾夷扇贝适合度性状影响的研究", 《中国博士学位论文全文数据库 农业科技辑》 * |
杜佗: "刺参大水面养殖系统中菌群、藻相结构的季节变化与益生菌的初步筛选", <中国优秀硕士学位论文全文数据库 农业科技辑> * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
AU2020103130A4 (en) | Habitat Identification Method Based on Fish Individual Dynamic Simulation Technology | |
Friedland et al. | Changes in higher trophic level productivity, diversity and niche space in a rapidly warming continental shelf ecosystem | |
Eriksen et al. | From single species surveys towards monitoring of the Barents Sea ecosystem | |
Williamson et al. | The box plot: a simple visual method to interpret data | |
Carter et al. | Social networks, long-term associations and age-related sociability of wild giraffes | |
Nobre et al. | Management of coastal eutrophication: integration of field data, ecosystem-scale simulations and screening models | |
Wang et al. | Food safety trends: From globalization of whole genome sequencing to application of new tools to prevent foodborne diseases | |
Ruiz‐Sanchez et al. | Phylogeography of L iquidambar styraciflua (A ltingiaceae) in M esoamerica: survivors of a N eogene widespread temperate forest (or cloud forest) in N orth A merica? | |
Sargent et al. | Phylogenetic evidence for a flower size and number trade‐off | |
CN108009404A (zh) | 一种基于环境微生物数据的环境安全检测评估方法及系统 | |
Kim et al. | Effects of climate-driven freshwater inflow variability on macrobenthic secondary production in Texas lagoonal estuaries: A modeling study | |
Duchoslav et al. | Intricate distribution patterns of six cytotypes of Allium oleraceum at a continental scale: niche expansion and innovation followed by niche contraction with increasing ploidy level | |
Chytrý et al. | Dispersal limitation is stronger in communities of microorganisms than macroorganisms across Central European cities | |
Cuttitta et al. | Different key roles of mesoscale oceanographic structures and ocean bathymetry in shaping larval fish distribution pattern: A case study in Sicilian waters in summer 2009 | |
Ndraha et al. | A climate-driven model for predicting the level of Vibrio parahaemolyticus in oysters harvested from Taiwanese farms using elastic net regularized regression | |
Tang et al. | Functional diversity of copepod assemblages along a basin-scale latitudinal gradient in the North Pacific Ocean | |
CN109215310A (zh) | 海湾扇贝养殖病害预警系统 | |
Valdés-Rodríguez et al. | Seedling characteristics of three oily species before and after root pruning and transplant | |
Enneson et al. | Stochastic and spatially explicit population viability analyses for an endangered freshwater turtle, Clemmys guttata | |
Mendes et al. | Seascape genetics in a polychaete worm: Disentangling the roles of a biogeographic barrier and environmental factors | |
Winship | Estimating the impact of bycatch and calculating bycatch limits to achieve conservation objectives as applied to harbour porpoise in the North Sea | |
Du et al. | Prediction of the dynamic distribution for Eucheuma denticulatum (Rhodophyta, Solieriaceae) under climate change in the Indo-Pacific Ocean | |
Hollowed et al. | Regional assessment of climate change impacts on Arctic marine ecosystems | |
Grillo et al. | Machine learning applied to species occurrence and interactions: the missing link in biodiversity assessment and modelling of Antarctic plankton distribution | |
Wagutu et al. | Genetic structure of wild rice Zizania latifolia in an expansive heterogeneous landscape along a latitudinal gradient |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190115 |
|
WD01 | Invention patent application deemed withdrawn after publication |