基于游程检测法重构集合经验模态的养殖水质溶解氧预测
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Dissolved oxygen prediction in aquaculture based on ensemble empirical mode decomposition and reconstruction using run test method
  • 作者:宦娟 ; 曹伟建 ; 秦益霖 ; 吴帆
  • 英文作者:Huan Juan;Cao Weijian;Qin Yilin;Wu Fan;School of Information Science & Engineering, Changzhou University;Changzhou Technical Institute of Tourism & Commerce;
  • 关键词:水质 ; 水产养殖 ; 模型 ; 溶解氧 ; 集合经验模态分解 ; 游程检测法 ; 组合预测
  • 英文关键词:water quality;;aquaculture;;models;;dissolved oxygen;;ensemble empirical mode decomposition;;runs test method;;combinatorial prediction model
  • 中文刊名:NYGU
  • 英文刊名:Transactions of the Chinese Society of Agricultural Engineering
  • 机构:常州大学信息科学与工程学院;常州旅游商贸高等职业技术学校;
  • 出版日期:2018-04-23
  • 出版单位:农业工程学报
  • 年:2018
  • 期:v.34;No.335
  • 基金:国家自然科学基金(61772090);; 溧阳市第一批重点研发计划(现代农业)项目(LB2016003)
  • 语种:中文;
  • 页:NYGU201808029
  • 页数:7
  • CN:08
  • ISSN:11-2047/S
  • 分类号:228-234
摘要
为了提高水产养殖中溶解氧的预测精度,该文提出了基于集合经验模态(ensemble empirical mode decomposition,EEMD)分解、游程检测法重构、适宜的单项预测算法建模和BP神经网络非线性叠加的组合预测模型。该模型首先将溶解氧原始序列用EEMD分解法进行分解,得到了多个分量;其次,用游程检测法将这些分量重构成高频分量、中频分量和低频分量等3个分量;接着,针对高频分量波动性大且复杂、中频分量呈现周期性、低频分量几乎呈线性的特点,采用粒子群(particle swarm optimization,PSO)优化的最小二乘支持向量机(least square support vector machine,LSSVM)对高频项进行预测,采用极限学习机(extreme learning machine,ELM)对中频项预测,采用非线性回归(nonlinear regression method,NRM)对低频项预测;最后,将3个分量预测的结果用BP神经网络进行重构得到最终的预测结果。将该模型应用于江苏省溧阳市埭头黄家荡特种水产养殖场的溶解氧预测中,试验表明,该种以游程检测法重构EEMD为基础的混合预测模型的预测精度高于PSO-LSSVM和单一的ELM预测模型。在预测未来48 h的溶解氧值时,该模型的预测值与实测值的均方根误差RMSE为0.099 2、平均相对误差均值MAPE为0.078、平均绝对误差MAE为0.015 5,R~2为0.995 5。表明该模型有较好的预测精度和泛化能力,能够满足现代化水产养殖业对溶解氧精细化管理的高要求。
        Dissolved oxygen(DO) is one of the key water quality parameters for water products, which reflects changes in water quality in aquaculture. To increase prediction accuracy of dissolved oxygen(DO) in aquaculture, a hybrid model based on ensemble empirical mode decomposition(EEMD), reconstruction using runs test method, the appropriate forecasting method and superposition by BPANN was proposed. Firstly, the dissolved oxygen sequence was decomposed into a series of components by EEMD. EEMD performs very well in noise reduction and detail features extraction. Original dissolved oxygen datasets were decomposed to 9 IMFs and a Res. Then these components were reconstructed into high frequency component,intermediate frequency and low frequency component by the runs test method, which centralized the characteristic information and reduced the difficulty of predicting. Thirdly, based on the changed characteristics of each sequence, the appropriate prediction method was selected. According to the characteristics of high frequency component, which fluctuated violently and varied complicatedly, the least squares support vector machine(LSSVM) optimized by particle swarm optimization(PSO) was used to predict this term because this method had high accuracy and adaptability to predict. Intermediate frequency component was forecasted by extreme learning machine(ELM) because this component presented a periodic characteristic. The fluctuation of low frequency term was gentle and periodic, so it could be modeled by nonlinear regression method. Finally, the predicted values of DO datasets were calculated by using BPANN to reconstruct the forecasting values of all components, which ensured good fitting effect and stability. The model adopted BPANN nonlinear superposition to replace simple adaptive superposition, which achieved better fitting effect. This model was tested in Daitou Huangjiadang Special Aquaculture Farm in Liyang City, Jiangsu Province. Based on the prediction model, the dissolved oxygen changing was predicted for aquaculture pond during June 23 to June 24, 2016. The experimental results demonstrated that the proposed combinatorial prediction model had better prediction effect than the ELM and LSSVM. When it predicted the next 12, 24, 36 h dissolved oxygen values by using the proposed combinatorial prediction model, the root mean square error(RMSE) of the proposed combination prediction model was 0.088 6, 0.093 1 and 0.095 7, respectively, mean absolute errors(MAE) were 0.066 6, 0.071 2 and 0.076 9, respectively; and mean absolute percentage errors(MAPE) were 0.008 9, 0.013 1 and 0.014 2. When dissolved oxygen values of next 48 h were predicted, the RMSE, MAPE, and MAE of the proposed combination prediction model were 0.099 2, 0.078 and 0.015 5, respectively. The RMSE, MAPE and MAE for dissolved oxygen value of the standard extreme learning machine(ELM) were 0.1581, 0.111 2 and 0.027 6, respectively. Three indexes of LSSVM were 0.134 4, 0.102 6 and 0.021 3, respectively, under the same experimental conditions. The proposed model performs well in terms of all the evaluation indexes, so the proposed model is highly competitive with the compared models. It is obvious that the proposed hybrid model has high forecast accuracy and is proven to be an effective way to predict DO.
引文
[1]胡金有,王靖杰,张小栓,等.水产养殖信息化关键技术研究现状与趋势[J].农业机械学报,2015,46(7):251-263.Hu Jinyou,Wang Jingjie,Zhang Xiaoshuan,et al.Research status and development trends of information Technologies in aquacultures[J].Transactions of the Chinese Society for Agricultural Machinery,2015,46(7):251-263.(in Chinese with English abstract)
    [2]Buentello J A,Gatlin D M,Neill W H.Effects of water temperature and dissolved oxygen on daily feed consumption,feed utilization and growth of channel catfish(Ictalurus punctatus)[J].Aquaculture,2000,182(4):339-352.
    [3]刘双印,徐龙琴,李道亮,等.基于蚁群优化最小二乘支持向量回归机的河蟹养殖溶解氧预测模型[J].农业工程学报,2012,28(23):167-175.Liu Shuangyin,Xu Longqin,Li Daoliang.Dissolved oxygen prediction model of eriocheir sinensis culture based on least squares support vector regression optimized by ant colony algorithm[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2012,28(23):167-175.(in Chinese with English abstract)
    [4]Liu S,Xu L,Jiang Y,et al.A hybrid WA-CPSO-LSSVRmodel for dissolved oxygen content prediction in crab culture[J].Engineering Applications of Artificial Intelligence,2014,29(3):114-124.
    [5]Ahmed A A M.Prediction of dissolved oxygen in Surma River by biochemical oxygen demand and chemical oxygen demand using the artificial neural networks(ANNs)[J].Journal of King Saud University-Engineering Sciences,2017,29(2):151-158.
    [6]Ahmed A A M,Shah S M A.Application of adaptive neuro-fuzzy inference system(ANFIS)to estimate the biochemical oxygen demand(BOD)of Surma River[J].Journal of King Saud University-Engineering Sciences,2015,29(3):237-243.
    [7]Yan J X,Yu L J,Mao W W,et al.Study on prediction model of dissolved oxygen about water quality monitoring system based on BP neural network[J].Advanced Materials Research,2014,912/913/914:1407-1411.
    [8]Kong Y,Meng Y,Li W,et al.Satellite image time series decomposition based on EEMD[J].Remote Sensing,2015,7(11):15583-15604.
    [9]Wu Zhaohua,Ne Huang.Ensemble empirical mode decomposition:A noise-assisted data analysis method[J].Advances in Adaptive Data Analysis,2009,1(1):0900004.
    [10]张瑜,汪小旵,孙国祥,等.基于集合经验模态分解与Elman神经网络的线椒株高预测[J].农业工程学报,2015,31(18):169-174.Zhang Yu,Wang Xiaochan,Sun Guxiang,et al.Prediction of cayenne pepper plant height based on ensemble empirical mode decomposition and Elman neural network[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2015,31(18):169-174.(in Chinese with English abstract)
    [11]徐龙琴,李乾川,刘双印,等.基于集合经验模态分解和人工蜂群算法的工厂化养殖p H值预测[J].农业工程学报,2016,32(3):202-209.Xu Longqin,Li Qianchuan,Liu Shuangyin,et al.Prediction of p H value in industrialized aquaculture based on ensemble empirical mode decomposition and improved artificial bee colony algorithm[J].Transactions of the Chinese Society of Agricultural Engineering(Transactions of the CSAE),2016,32(3):202-209.(in Chinese with English abstract)
    [12]王贺,胡志坚,张翌晖,等.基于聚类经验模态分解和最小二乘支持向量机的短期风速组合预测[J].电工技术学报,2014,29(4):237-245.Wang He,Hu Zhijian,Zhang Yihui,et al.A hybrid model for short-term wind speed forecasting based on ensemble empirical mode decomposition and least squares support vector machines[J].Transactions of China Electrotechnical Society,2014,29(4):237-245.(in Chinese with English abstract)
    [13]Wang Shouxiang,Wang Yamin,Liu Yan,et al.Hourly solar radiation forecasting based on EMD and ELM neural network[J].Electric Power Automation Equipment,2014,34(8):7-12.
    [14]Wang T,Zhang M,Yu Q,et al.Comparing the application of EMD and EEMD on time-frequency analysis of seimic signal[J].Journal of Applied Geophysics,2012,83(6):29-34.
    [15]Jiang H,Li C,Li H.An improved EEMD with multiwavelet packet for rotating machinery multi-fault diagnosis[J].Mechanical Systems&Signal Processing,2013,36(2):225-239.
    [16]Ding G,Wang L,Shen P,et al.Sensor fault diagnosis based on ensemble empirical mode decomposition and optimized least squares support vector machine[J].Journal of Computers,2013,8(11).DOI:10.4304/jcp.8.11.2916-2924
    [17]Wang X,Wang Y.A hybrid model of EMD and PSO-SVRfor short-term load forecasting in residential quarters[J].Mathematical Problems in Engineering,2016(5):1-10.
    [18]李乐,刘天琪,陈振寰,等.基于EEMD和ARCH的风电功率超短期预测[J].电测与仪表,2015,52(18):16-21.Li Le,Liu Tianqi,Chen Zhenhuan,et al.Ultra-short-term wind power forecasting based on EEMD and ARCH[J].Electrical Measurement&Instrumentation,2015,52(18):16-21.(in Chinese with English abstract)
    [19]于群,朴在林,胡博.基于EEMD和BP神经网络的短期光伏功率预测模型[J].电网与清洁能源,2016,32(7):132-137.Yu Qun,Piao Zailin,Hu Bo.A Hybrid model for short-term photovoltaic power forecasting based on EEMD-BPcombined method[J].Power System&Clean Energy,2016,32(7):132-137.(in Chinese with English abstract)
    [20]Huanga E,Shen Z,Long S R.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings Mathematical Physical&Engineering Sciences,1998,454:903-995.
    [21]Sun W,He Y,Chang H.Forecasting fossil fuel energy consumption for power generation using QHSA-based LSSVM Model[J].Energies,2015,8(2):939-959.
    [22]江田汉,束炯.基于LSSVM的混沌时间序列的多步预测[J].控制与决策,2006,21(1):77-80.Jiang Tianhan,Shu Jiong.Multi-step prediction of chaotic time series using the least squares support vector machines[J].Control&Decision,2006,21(1):77-80.(in Chinese with English abstract)
    [23]Huang G B,Chen L,Siew C K.Universal approximation using incremental constructive feedforward networks with random hidden nodes[J].IEEE Trans Neural Netw,2006,17(4):879-892.
    [24]Huang G B,Zhou H,Ding X,et al.Extreme learning machine for regression and multiclass classification[J].IEEETransactions on Systems Man&Cybernetics Part BCybernetics,2012,42(2):513.
    [25]Chen Y,Xu J,Yu H,et al.Three-dimensional short-term prediction model of dissolved oxygen content based on PSO-BPANN algorithm coupled with Kriging interpolation[J].Mathematical Problems in Engineering,2016(1):1-10.
    [26]朱成云,刘星桥,李慧,等.工厂化水产养殖溶解氧预测模型优化[J].农业机械学报,2016,47(1):273-278.Zhu Chengyun,Liu Xingqiao,Li Hui,et al.Optimization of prediction model of dissolved oxygen in industrial aquaculture[J].Transactions of the Chinese Society for Agricultural Machinery,2016,47(1):273-278.(in Chinese with English abstract)

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700