[1]唐毅,徐全,杜彬,等.基于SARIMA-VMD-LSSVM的水产养殖溶解氧质量浓度预测[J].江苏农业学报,2024,(08):1473-1482.[doi:doi:10.3969/j.issn.1000-4440.2024.08.012]
　TANG Yi,XU Quan,DU Bin,et al.Prediction of dissolved oxygen mass concentration in aquaculture based on SARIMA-VMD-LSSVM[J].,2024,(08):1473-1482.[doi:doi:10.3969/j.issn.1000-4440.2024.08.012]
点击复制

基于SARIMA-VMD-LSSVM的水产养殖溶解氧质量浓度预测()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2024年08期
页码:
1473-1482
栏目:
畜牧兽医·水产养殖·益虫饲养
出版日期:
2024-08-30

文章信息/Info

Title:
Prediction of dissolved oxygen mass concentration in aquaculture based on SARIMA-VMD-LSSVM
作者:
唐毅; 徐全 ; 杜彬; 王磊; 袁瑞豪; 袁禹
（西华大学机械工程学院,四川 成都 610039）
Author(s):
TANG Yi; XU Quan; DU Bin; WANG Lei; YUAN Ruihao; YUAN Yu
(School of Mechanical Engineering, Xihua University, Chengdu 610039， China)
关键词:
水产养殖; 溶解氧; 变分模态分解; 组合预测方法; 改进的灰狼算法
Keywords:
aquaculture; dissolved oxygen; variational mode decomposition; combinatorial forecasting methods; improved gray wolf algorithm
分类号:
TP391；S912
DOI:
doi:10.3969/j.issn.1000-4440.2024.08.012
文献标志码:
A
摘要:
为了充分利用溶解氧质量浓度的数据特征,进一步提高水产养殖中溶解氧质量浓度预测的准确性,提出“线性与非线性”与“分解-预测-集成”相结合的溶解氧质量浓度预测模型。该模型首先由季节性差分自回归滑动平均(SARIMA)模型对溶解氧质量浓度随着时间变化而组成的数据序列（简称溶解氧质量浓度的时间序列）进行线性拟合,使用变分模态分解(VMD)对残差序列进行分解,然后将各残差分量代入经改进的灰狼算法(IGWO)优化的最小二乘支持向量机模型(LSSVM)中,得到非线性分量的预测结果。最后集成线性与非线性预测结果,得到最终的溶解氧质量浓度预测值。结果表明,与SARIMA、LSSVM、VMD-LSSVM模型相比,基于SARIMA-VMD-LSSVM模型对溶解氧质量浓度进行预测的精度显著提高,预测的均方根误差(RMSE)为0.078 7,平均相对误差(MAPE)为0.022 6,说明该组合模型可有效提取溶解氧质量浓度的时间序列的多尺度特征,从而更精准地进行溶解氧质量浓度的预测。
Abstract:
In order to make full use of the data characteristics of dissolved oxygen mass concentration and further improve the accuracy of dissolved oxygen mass concentration prediction in aquaculture, a dissolved oxygen mass concentration prediction model combining "linear and nonlinear" and "decomposition-prediction-integration" was proposed. Firstly, the seasonal auto regressive integrated moving average (SARIMA) model was used to linearly fit the dissolved oxygen mass concentration time series, and the residual sequence was decomposed using variational mode decomposition (VMD). Then, each residual component was substituted into the least square support vector machine (LSSVM) model optimized by the improved gray wolf algorithm (IGWO) to obtain the prediction results of the nonlinear component. Finally, the linear and nonlinear prediction results were integrated to obtain the final dissolved oxygen mass concentration prediction value. Experimental results showed that compared with SARIMA, LSSVM, and VMD-LSSVM models, the prediction accuracy of SARIMA-VMD-LSSVM model was significantly improved. The root mean square error (RMSE) was 0.078 7, and the mean absolute percentage error (MAPE) was 0.022 6, indicating that the combined model could effectively extract the multi-scale features of the time series of dissolved oxygen mass concentration, and achieve more accurate prediction.

参考文献/References:

[1]谢雨茜, 李路, 朱明,等. 基于EMD与K-means的ILSTM模型在池塘溶解氧预测中的应用[J]. 华中农业大学学报(自然科学版),2022,41(3):200-210.
[2]PARK K D, KANG D H, SO Y, et al. Water quality prediction using the ARIMA time series analysis model in the Nakdong River estuary[C]. San Francisco: AGU Fall Meeting Abstracts,2019.
[3]张梦迪,徐庆,刘振鸿,等. 基于动态滑动窗口BP神经网络的水质时间序列预测[J]. 环境工程技术学报,2022,12(3):809-815.

[4]龚怀瑾,毛力,杨弘. 基于变尺度混沌QPSO-LSSVM的水质溶氧预测建模[J]. 计算机与应用化学, 2013,30(3):315-318.
[5]刘晨,李莎,丛孙丽,等. 基于EEMD和萤火虫算法优化SVM的溶解氧预测[J]. 计算机仿真, 2021,38(1):359-365.
[6]白雯睿,杨毅强,郭辉,等. 基于VMD-CNN-LSTM的珠江流域水质多步预测模型研究[J]. 四川轻化工大学学报(自然科学版),2022,35(4):66-74.
[7]DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing,2014,62(3):531-544.
[8]LUO H, PAAL S G. Metaheuristic least squares support vector machine-based lateral strength modelling of reinforced concrete columns subjected to earthquake loads[J]. Structures,2021,33:748-758.
[9]MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software,2014,69(3):46-61.
[10]高兵,郑雅,秦静, 等. 基于麻雀搜索算法和改进粒子群优化算法的网络入侵检测算法[J]. 计算机应用,2022,42(4):1201-1206.
[11]胡衍坤,王宁,刘枢,等. 时间序列模型和LSTM模型在水质预测中的应用研究[J]. 小型微型计算机系统,2021,42(8):1589-1573.
[12]LIU J T, YU C, HU Z H, et al. Accurate prediction scheme of water quality in smart mariculture with deep Bi-S-SRU learning network[J]. Ieee Access,2020,8(99):24784-24798.
[13]郑圆,胡建中,贾民平,等. 一种基于参数优化变分模态分解的滚动轴承故障特征提取方法[J]. 振动与冲击,2020,39(21):195-202.
[14]崔东文,袁树堂. 基于WPD-AHA-ELM模型的水质时间序列多步预测[J]. 三峡大学学报(自然科学版),2023,45(1):6-13.

相似文献/References:

[1]刘国锋,徐跑,吴霆,等.中国水产养殖环境氮磷污染现状及未来发展思路[J].江苏农业学报,2018,(01):225.[doi:doi:10.3969/j.issn.1000-4440.2018.01.033]
　LIU Guo-feng,XU Pao,WU Ting,et al.Present condition of aquaculture nitrogen and phosphorus environmental pollution and future development strategy[J].,2018,(08):225.[doi:doi:10.3969/j.issn.1000-4440.2018.01.033]
[2]冯国富,卢胜涛,陈明,等.基于自注意力机制和改进的K-BiLSTM的水产养殖水体溶解氧含量预测模型[J].江苏农业学报,2024,(03):490.[doi:doi:10.3969/j.issn.1000-4440.2024.03.011]
　FENG Guo-fu,LU Sheng-tao,CHEN Ming,et al.Prediction model of dissolved oxygen content in aquaculture water based on self-attention mechanism and improved K-BiLSTM[J].,2024,(08):490.[doi:doi:10.3969/j.issn.1000-4440.2024.03.011]

备注/Memo

备注/Memo:
收稿日期：2023-05-25基金项目：四川省科技成果转移转化示范项目（2020ZHCG0076）；工业控制技术国家重点实验室开放课题（ICT2022B45）作者简介：唐毅（1997-）,男,四川江油人,硕士,主要研究方向为机器学习、智能水产养殖。（Tel）13320889755；(E-mail)tangyi970516@163.com通讯作者：徐全,(E-mail)quanxnjd@sina.com
更新日期/Last Update: 2024-09-18