基于ISSA-LSTM的黄鳝池溶氧量多参数预测

doi:10.16180/j.cnki.issn1007-7820.2024.04.012

摘要/Abstract

摘要：

为提高溶氧量的多参数预测精度,文中基于改进的麻雀搜索算法(Improved Sparrow Search Algorithm, ISSA)与长短期记忆神经网络(Long and Short-Term Memory Neural Networks, LSTM)建立ISSA-LSTM溶氧量预测模型,并将该模型用于上海市农业科学院黄鳝养殖池溶氧量预测。利用混沌映射、透镜成像反向学习、自适应调节和柯西变异对麻雀搜索算法进行优化,通过小波变换进行数据预处理,并利用主成分分析法确定模型训练的输入参数。训练结果表明,相关系数、均方根误差、均方误差和平均绝对误差分别为0.911、1.392 mg·L^-1、1.938 mg·L^-1和0.992 mg·L^-1,均优于对照模型。选择模型输入参数对模型预测结果也会产生影响,使用与溶氧量中等相关和强相关的参数同时作为输入参数的模型预测效果最优。训练结果为溶氧量多参数预测模型的发展提供了新视角。

关键词: 溶氧量预测, 长短期记忆神经网络, 麻雀搜索算法, 主成分分析法, 小波变换, 柯西变异, 混沌映射, 黄鳝养殖

Abstract:

In order to improve the multi-parameter prediction accuracy of dissolved oxygen, an ISSA-LSTM (Improved Sparrow Search Algorithm-Long and Short-Term Memory Neural Networks) dissolved oxygen prediction model is developed based on the ISSA and LSTM. The model is applied to the prediction of dissolved oxygen in eel breeding ponds at Shanghai academy of agricultural sciences. The sparrow search algorithm is optimized using chaos mapping, lensing imaging backward learning, adaptive adjustment and Cauchy variation. The data are pre-processed by wavelet transform, the input parameters for model training are determined using principal component analysis. The training results show that the correlation coefficient, root mean square error, mean square error and mean absolute error are 0.911, 1.392 mg·L^-1, 1.938 mg·L^-1 and 0.992 mg·L^-1, which are all better than those in the control model. The choice of model input parameters also have an impact on the model prediction results, with the best model predictions using both moderately and strongly correlated parameters with dissolved oxygen as input parameters. The training results provide a new perspective for the development of the dissolved oxygen multi-parameter prediction model.

Key words: dissolved oxygen prediction, long and short-term memory neural networks, sparrow search algorithm, principal component analysis, wavelet transform, Cauchy variation, chaos mapping, eel farming

中图分类号:

TP391.7

林彬彬, 徐震, 袁泉, 田志新. 基于ISSA-LSTM的黄鳝池溶氧量多参数预测[J]. 电子科技, 2024, 37(4): 87-96.

LIN Binbin, XU Zhen, YUAN Quan, TIAN Zhixin. Multi-Parameter Prediction of Dissolved Oxygen in Eel Ponds Based on ISSA-LSTM[J]. Electronic Science and Technology, 2024, 37(4): 87-96.

图/表 9

图1

图2

表1

图3

图4

表2

图5

表3

表4

参考文献 27

[1]	周文宗, 李洪涛, 张硌, 等. pH值对黄鳝最大摄食率的影响[J]. 江苏农业科学, 2007, 35(1):141-143.
	Zhou Wenzong, Li Hongtao, Zhang Ge, et al. Effect of pH value on the maximum feeding absorption of monopterus albus[J]. Jiangsu Agricultural Sciences, 2007, 35(1):141-143.
[2]	王李想. 基于多指标时序数据的城市河道水质异常检测方法研究[D]. 杭州: 浙江大学, 2021:32-36.
	Wang Lixiang. Research on water quality anomaly detection of urban river using multi-indicator time series data[D]. Hangzhou: Zhejiang University, 2021:32-36.
[3]	Ji X H, Pan Y, Jia G Q, et al. A neural network-based prediction model in water monitoring networks[J]. Water Supply, 2021, 21(5):2347-2356. doi: 10.2166/ws.2021.046
[4]	冯先丁, 魏镜弢, 吴张永, 等. 基于PCA-PSO-SVM的球磨机负荷预测研究[J]. 电子科技, 2022, 35(1):29-34.
	Feng Xianding, Wei Jingtao, Wu Zhangyong, et al. Research on load forecast of ball mill based on PCA-PSO-SVM[J]. Electronic Science and Technology, 2022, 35(1):29-34.
[5]	马创, 王尧, 李林峰. 基于遗传算法与支持向量机的水质预测模型[J]. 重庆大学学报, 2021, 44(7):108-114.
	Ma Chuang, Wang Yao, Li Linfeng, et al. A water quality prediction model based on genetic algorithm and SVM[J]. Journal of Chongqing University, 2021, 44(7):108-114.
[6]	Peng X H, Xie S Y, Yu Y H, et al. Fuzzy neural network based prediction model applied in primary component analysis[J]. Cluster Comput, 2017, 20(1):131-140. doi: 10.1007/s10586-017-0738-2
[7]	Moghadam S V, Sharafati A, Feizi H, et al. An efficient strategy for predicting river dissolved oxygen concentration:Application of deep recurrent neural network model[J]. Environmental Monitoring and Assessment, 2021, 193(11):1-18. doi: 10.1007/s10661-020-08746-9
[8]	任永琴, 金柱成, 俞真元, 等. 基于双向门控循环单元的地表水氨氮预测[J]. 中国环境科学, 2022, 42(2):672-679.
	Ren Yongqin, Jin Zhucheng, Yu Zhenyuan, et al. Ammonia nitrogen prediction in surface water based on bi-directional gating cycle unit[J]. China Environmental Science, 2022, 42(2):672-679.
[9]	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.
	Xie Yuxi, Li Lu, Zhu Ming, et al. Application of ILSTM model based on EMD and K-means in prediction of dissolved oxygen in pond[J]. Journal of Huazhong Agricultural University(Natural Science Edition), 2022, 41(3):200-210.
[10]	梁冰, 田斌, 洪汉玉. 基于LSTM-Attention的水质参数预测研究[J]. 自动化与仪表, 2022, 37(3):80-84.
	Liang Bing, Tian Bin, Hong Hanyu. Research on water quality parameter prediction based on LSTM-attention[J]. Automation and Instrumentation, 2022, 37(3):80-84.
[1]	Bjer D, Martinovic G, Brest J. A population initialization method for evolutionary algorithms based on clustering and Cauchy deviates[J]. Expert Systems with Applications, 2016, 60(10):294-310. doi: 10.1016/j.eswa.2016.05.009
[2]	Xue J, Shen B. A novel swarm intelligence optimization approach:Sparrow search algorithm[J]. Systems Science & Control Engineering, 2020, 8(1):22-34.
[11]	Song C, Yao L, Hua C, et al. A water quality prediction model based on variational mode decomposition and the least squares support vector machine optimized by the sparrow search algorithm of the Yangtze River[J]. Environmental Monitoring and Assessment, 2021, 193(6):363-379. doi: 10.1007/s10661-021-09127-6
[12]	Zhang H, Peng Z, Tang J, et al. A multi-layer extreme learning machine refined by sparrow search algorithm and weighted mean filter for short-term multi-step wind speed forecasting[J]. Sustainable Energy Technologies and Assessments, 2022, 50(3):1-14.
[13]	Li D, Yu X, Liu S, et al. Wind power prediction based on PSO-Kalman[J]. Energy Reports, 2022, 8(7):958-968.
[14]	贺振霞, 鲍学英. 基于改进PSO优化SVR的地下水水质综合评价研究[J]. 水文, 2021, 41(6):26-32.
	He Zhenxia, Bao Xueying. Comprehensive evaluation of groundwater quality based on SVR optimized by improved[J]. Hydrology, 2021, 41(6):26-32.
[15]	刘耀东, 姜文超, 廖宇航. 基于蜂群优化极限学习算法的用电功率预测[J]. 电气应用, 2022, 41(1):21-25,9.
	Liu Yaodong, Jiang Wenchao, Liao Yuhang. Eletric power forecasting based on bee colony optimized extreme learning machine algorithm[J]. Electrical Application, 2022, 41(1):21-25,9.
[16]	王立辉, 杨辉斌, 王银堂, 等. 基于GWO-LSTM的丹江口水库入库径流预测[J]. 水利水运工程学报, 2021(6):51-59.
	Wang Lihui, Yang Huibin, Wang Yintang, et al. Prediction of inflow to the Danjiangkou reservoir based on GWO-LSTM[J]. Hydro-Science and Engineering, 2021(6):51-59.
[17]	袁红春, 高子玥, 张天蛟. 基于改进的XGBoost模型预测南太平洋长鳍金枪鱼资源丰度[J]. 海洋湖沼通报, 2022, 44(2):112-120. doi: 10.13984/j.cnki.cn37-1141.2022.02.015
	Yuan Hongchun, Gao Ziyue, Zhang Tianjiao. Predicting of albacore tuna abundance in South Pacific based on improved XG Boost model[J]. Transactions of Oceanology and Limnology, 2022, 44(2):112-120. doi: 10.13984/j.cnki.cn37-1141.2022.02.015
[18]	杨帆, 申亚, 李东东, 等. 基于GA-GNNM的极地光伏发电功率预测方法[J]. 太阳能学报, 2022, 43(4):167-174. doi: 10.19912/j.0254-0096.tynxb.2020-0768
	Yang Fan, Shen Ya, Li Dongdong, et al. Polar photovoltaic power forecasting method based on GA-GNNM[J]. Acta Energiae Solaris Sinica, 2022, 43(4):167-174. doi: 10.19912/j.0254-0096.tynxb.2020-0768
[19]	孟志军, 刘淮玉, 安晓飞, 等. 基于SPA-SSA-BP的小麦秸秆含水率检测模型[J]. 农业机械学报, 2022, 53(2):231-238,245.
	Meng Zhijun, Liu Huaiyu, An Xiaofei, et al. Prediction model of wheat straw moisture content based on SPA-SSA-BP[J]. Transaction of the Chinese Society for Agricultural Machinery, 2022, 53(2):231-238,245.
[20]	Wu C, Fu X, Pei J, et al. A novel sparrow search algorithm for the traveling salesman problem[J]. IEEE Access, 2021, 9(11):153456-153471. doi: 10.1109/ACCESS.2021.3128433
[21]	Qiao W, Liu W, Liu E. A combination model based on wavelet transform for predicting the difference between monthly natural gas production and consumption of US[J]. Energy, 2021, 235(11):121216-121243. doi: 10.1016/j.energy.2021.121216
[22]	Zhang W, Lin Z, Liu X. Short-term off shore wind power forecasting:A hybrid model based on discrete wavelet transform,seasonal autoregressive integrated moving average,and deep-learning-based long short-term memory[J]. Renewable Energy, 2022, 185(2):611-628. doi: 10.1016/j.renene.2021.12.100
[23]	Kumar A, Tomar H, Mehla V K, et al. Stationary wavelet transform based ECG signal denoising method[J]. ISA Transactions, 2021, 114(8):251-262. doi: 10.1016/j.isatra.2020.12.029
[24]	夏峰, 卢才武, 顾清华. 无人机采场图像二维经验小波变换降噪研究[J]. 测绘科学, 2021, 46(1):108-113.
	Xia Feng, Lu Caiwu, Gu Qinghua. Research on 2D empirical wavelet transform noise reduction of UAV stope images[J]. Science of Surveying and Mapping, 2021, 46(1):108-113.
[25]	Feng J, Zhang J, Zhu X, et al. A novel chaos optimization algorithm[J]. Multimedia Tools and Applications, 2017, 76(16):17405-17436. doi: 10.1007/s11042-016-3907-z
[26]	龙文, 伍铁斌, 唐明珠, 等. 基于透镜成像学习策略的灰狼优化算法[J]. 自动化学报, 2020, 46(10):2148-2164.
	Long Wen, Wu Tiebin, Tang Mingzhu, et al. Grey wolf optimizer algorithm based on lens imaging learning strategy[J]. Acta Automatic Sinica, 2020, 46(10):2148-2164.
[27]	刘航, 张晓明, 汪长剑. 基于柯西分布和父种轮换机制的种子优化算法[J]. 模式识别与人工智能, 2021, 34(7): 581-591. doi: 10.16451/j.cnki.issn1003-6059.202107001
	Liu Hang, Zhang Xiaoming, Wang Changjian. Bean optimization algorithm based on Cauchy distribution and parent rotation mechanism[J]. Pattern Recognition and Artificial Intelligence, 2021, 34(7):581-591. doi: 10.16451/j.cnki.issn1003-6059.202107001

参数	小波变换降噪信噪比/dB	傅里叶降噪信噪比/dB
溶氧量	113.50	86.4
pH	115.00	95.9
温度	111.00	92.3
氧化还原电位	123.63	102.5
电导率	129.90	115.6
浊度	111.10	89.0
叶绿素浓度	93.20	70.8
蓝藻素浓度	64.60	73.7
铵根离子浓度	113.00	93.3
硝酸根离子浓度	105.70	96.5
氯离子浓度	99.40	96.8
pH电位	102.70	98.5

	ISSA-LSTM	SSA-LSTM	PSO-LSTM	LSTM	GRU	SVR	BP	随机森林
R²	0.911	0.898	0.892	0.831	0.848	0.795	0.768	0.760
MAE/mg·L^-1	0.992	1.107	1.185	1.511	1.410	1.803	1.906	1.880
MSE/mg·L^-1	1.938	2.224	2.348	3.682	3.314	4.473	6.020	5.247
RMSE/mg·L^-1	1.392	1.491	1.532	1.919	1.821	2.115	2.254	2.291

模型1	模型2	模型3
温度	温度	温度
pH	pH	pH
浊度	时间	pH电位
时间	pH电位	-
pH电位	氧化还原电位	-
铵根离子浓度	-	-
氧化还原电位	-	-
硝酸根离子浓度	-	-

指标	模型1	模型2	模型3
R²	0.911	0.913	0.898
MAE/mg·L^-1	0.992	1.037	1.107
MSE/mg·L^-1	1.938	1.908	2.224
RMSE/mg·L^-1	1.392	1.381	1.491