| 基于经验模态分解和最小二乘支持向量机的溶氧预测 |
| |
| 引用本文： | 宦娟,曹伟建,秦益霖,顾玉宛.基于经验模态分解和最小二乘支持向量机的溶氧预测[J].渔业现代化,2017(4):37-43. |
| |
| 作者姓名： | 宦娟 曹伟建 秦益霖 顾玉宛 |
| |
| 作者单位： | 1. 常州大学信息科学与工程学院,江苏 常州,213164;2. 常州大学信息科学与工程学院,江苏 常州213164;常州旅游商贸高等职业技术学校,江苏 常州213032 |
| |
| 基金项目： | 国家自然科学基金项目(61640211)，2016年度溧阳市第一批重点研发计划(现代农业)项目(LB2016003) |
| |
| 摘 要： | 养殖池塘中溶氧(DO)与鱼、蟹等水产品的生长有着十分密切的关系。为了提高DO的预测精度和有效性,提出了一种基于经验模态分解(EMD)和自适应扰动粒子群优化最小二乘支持向量机(LSSVM)的组合预测模型。首先将DO时间序列通过EMD分解成若干分量,接着对各个分量进行相空间重构,在相空间中用LSSVM对各分量进行建模预测,并使用自适应扰动粒子群算法对LSSVM的超参数进行优化,采用单点迭代法进行多步预测。结果显示:该模型与单一LSSVM预测模型相比,具有良好的预测效果。预测未来4 h DO值时,各项性能指标误差均方根(RMSE)、平均相对误差均值(MAPE)和平均绝对误差(MAE)三项指标分别降低了13.4%、11.3%和1.8%;预测未来24 h DO值时,三项指标分别降低了12.9%、12.1%和2.7%。研究表明:该组合模型可有效提取DO序列特性,具有较高的预测精度和泛化性能。
|
| 关 键 词： | 溶氧预测 经验模态分解 最小二乘支持向量机 自适应粒子群算法 单次迭代法 |
Prediction of dissolved oxygen based on empirical mode decomposition and least squares support vector machine |
| |
| HUAN Juan,CAO Weijian,QIN Yilin,GU Yuwan.Prediction of dissolved oxygen based on empirical mode decomposition and least squares support vector machine[J].Fishery Modernization,2017(4):37-43. |
| |
| Authors: | HUAN Juan CAO Weijian QIN Yilin GU Yuwan |
| |
| Abstract: | The dissolved oxygen (DO) in the pond has a very close relationship with the growth of aquatic products such as fish and shrimp.In order to improve the prediction accuracy and effectiveness of DO, a combined prediction model based on empirical mode decomposition (EMD) and least squares support vector machine (LSSVM) of adaptive disturbance particle swarm optimization is proposed.First DO time series are decomposed into several components by EMD, then each component is subject to phase space reconstruction and modeling prediction by LSSVM in the phase space, and finally adaptive disturbance particle swarm optimization is applied for optimization of hyper-parameters of LSSVM and single point iterative method for multi-step prediction.The results show that the model has good prediction effect compared with single LSSVM prediction model.When DO value of next 4 h is predicted RMSE, MAPE and MAE are decreased by 13.4%, 11.3% and 1.8% respectively;when DO value of next 24 h is predicted, the three indexes are decreased by 12.9%, 12.1% and 2.7% respectively.The study shows that the combined model can extract DO series features effectively and has relatively high prediction accuracy and generalization performance. |
| |
| Keywords: | prediction of dissolved oxygen empirical mode decomposition least squares support vector machine adaptive particle swarm optimization single point iterative method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
