Fuzzy neural network for studying the prediction of dissolved oxygen in aquaculture ponds based on particle swarm#br#

doi:10.3969/j.issn.1007-9580.2018.04.002

Fuzzy neural network for studying the prediction of dissolved oxygen in aquaculture ponds based on particle swarm#br#

ZHAO Jingbo, XUE Bingxin( School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, Shandong, China)

( School of Information and Control Engineering, Qingdao University of Technology, Qingdao 266520, Shandong, China)

Online:2018-08-20 Published:2018-10-16

基于粒子群的模糊神经网络池塘溶解氧预测研究

赵景波，薛秉鑫（青岛理工大学信息与控制工程学院，山东青岛 266520）

（青岛理工大学信息与控制工程学院，山东青岛 266520）

作者简介:赵景波（1971—），男，博士，副教授，研究方向：控制理论及应用，E-mail：zhaojingbo6666@163.com
基金资助:
国家自然科学基金项目（51475251）；山东省自然科学基金（ZR2013FM014）；山东省高等学校科技计划项目（J12LN37）；青岛市科技计划项目（15-9-2-109-nsh）

Abstract

Abstract: As an important indicator in aquaculture, dissolved oxygen has a very close relationship with the growth of aquatic products. In order to accurately predict dissolved oxygen content in aquaculture ponds and reduce aquaculture risk, a combined fuzzy neural network model for prediction based on wavelet packet analysis and particle swarm optimization is proposed. First, wavelet packet transform is used to denoise the collected original signals. Then the processed approximation signal is divided into training data and test data. Training data is used to train fuzzy neural network, and particle swarm is used to optimize network parameters. Finally, test data is used to predict the dissolved oxygen and test the performance of the prediction model. Through comparison, the effectiveness of particle swarm optimization and wavelet packet transform is proved respectively. When predicting dissolved oxygen, based on wavelet packet transform, compared with BP algorithm, such error indexes as RMSE, MAPE and MAE of particle swarm optimization are decreased by 22.75%, 3.97% and 22.86% respectively; based on particle swarm optimization, compared with absence of wavelet packet transform, the three indexes are decreased by 16.82%, 3.36% and 16.65% respectively for existence of wavelet packet transform. The study shows that wavelet packet analysis and particle swarm optimization can improve the prediction accuracy, and the combined model can effectively predict dissolved oxygen.

Key words: Dissolved oxygen prediction, fuzzy neural network, particle swarm optimization, wavelet packet analysis

摘要： 溶氧是水产养殖中的一项重要指标，与水产品生长有着十分密切的关系。为准确预测养殖池塘的溶氧量，降低水产养殖风险，提出基于小波包分析和粒子群算法优化模糊神经网络的组合预测模型。首先使用小波包变换对采集的原始信号进行消噪处理，然后将处理后的逼近信号分为训练数据和测试数据，利用训练数据对模糊神经网络进行训练，并使用粒子群算法对网络参数进行优化，最后利用测试数据进行溶氧预测并检验预测模型的性能。通过对比试验，分别证明了粒子群算法和小波包变换的有效性：预测溶氧值时，基于小波包变换，粒子群算法与BP算法相比，误差指标均方根误差（RMSE）、平均相对误差均值（MAPE）和平均绝对误差（MAE）分别降低了22.75%、3.97%和22.86%；基于粒子群算法，有小波包变换和无小波包变换相比，三项指标分别降低了16.82%、3.36%和16.65%。研究表明：小波包分析和粒子群算法可提高预测精度，该组合模型可对溶氧进行有效预测。

关键词: 溶氧预测, 模糊神经网络, 粒子群算法, 小波包分析

ZHAO Jingbo, XUE Bingxin. Fuzzy neural network for studying the prediction of dissolved oxygen in aquaculture ponds based on particle swarm#br#[J]. Fishery Modernization, doi: 10.3969/j.issn.1007-9580.2018.04.002.

赵景波, 薛秉鑫. 基于粒子群的模糊神经网络池塘溶解氧预测研究[J]. 渔业现代化, doi: 10.3969/j.issn.1007-9580.2018.04.002.

/ / Recommend / Download Citations

URL: https://fm.fmiri.ac.cn/EN/10.3969/j.issn.1007-9580.2018.04.002

https://fm.fmiri.ac.cn/EN/Y2018/V45/I4/8

[1]	ZHANG Mingchen, ZHAO Lun, SHI Jie, LIN Sen, WANG Haibo, Md Shafiqul Islam. PSO-ShuffleNet fish recognition method based on transfer learning#br# #br# [J]. Fishery Modernization, 2023, 50(2): 67-73.
[2]	LIN Binbin, YUAN Quan, TIAN Zhixin, PAN Xianbin, ZHOU Wenzong, XU Zhen. Dissolved oxygen prediction in eel ponds based on SSA-LSTM model [J]. Fishery Modernization, 2023, 50(1): 71-.
[3]	WENG Zheng1,2，CHEN Ming1,2，CHI Tao1,2，LIU Yarui1,2. Design and research of aquaculture monitoring platform with dissolved oxygen prediction [J]. , 2021, 48(4): 43-.
[4]	SHEN Shiyu, CHEN Ming. Application of Prophet time series model in short-term prediction of dissolved oxygen in water#br# [J]. , 2020, 47(3): 29-.
[5]	LIU Ximing , WANG Yi , NIE Simin. Design of water quality monitoring system based on distributed wireless network [J]. Fishery Modernization, 2017, 44(4): 50-56.
[6]	HUAN Juan, CAO Weijian, QIN Yilin, et al. Prediction of dissolved oxygen based on empirical mode decomposition and least squares support vector machine [J]. Fishery Modernization, 2017, 44(4): 37-43.
[7]	XU Daming, ZHOU Chao, SUN Chuanheng, et al. Prediction model of aquaculture water temperature and pH based on BP neural network optimized by particle swarm algorithm [J]. Fishery Modernization, 2016, 43(1): 24-29.