| 基于改进SSA-LSSVM模型的超声波氧气浓度在线估计方法 |
投稿时间：2024-03-25 修订日期：2024-05-24  点此下载全文 |
| 引用本文： |
| 摘要点击次数: 67 |
| 全文下载次数: 0 |
|
| 基金项目:浙江省自然科学基金 |
|
| 中文摘要:针对氧气浓度预测在样本数量较少时难以建立准确测量模型以及预测精度不高的问题，提出一种基于改进麻雀搜索算法(ISSA)优化的最小二乘支持向量机模型(LSSVM)的超声波氧气浓度在线估计方法。首先针对麻雀搜索算法(SSA)易陷入局部最优的问题,引入改进Sine混沌映射优化种群初始参数，引入Lévy飞行策略对SSA跟随者位置更新方式进行改进。应用4种基准测试函数检验ISSA的性能，结果显示ISSA有效提升了收敛速度和寻优能力。然后构建ISSA-LSSVM超声波氧气浓度预测模型，基于实际数据的实验结果表明，ISSA-LSSVM模型在氧气浓度预测中准确率达到99.87%，验证了所提出方法的有效性。 |
| 中文关键词:氧浓度预测 改进麻雀搜索算法 最小二乘支持向量机 改进Sine混沌映射 Lévy飞行策略 |
| |
| Online Estimation Method of Ultrasonic Oxygen Concentration Based on Improved SSA-LSSVM Model |
|
|
| Abstract:To Address the issues of difficulty in establishing accurate measurement models and low prediction accuracy in oxygen concentration prediction when dealing with limited sample sizes, an online estimation method for ultrasonic oxygen concentration is proposed, which is based on the optimized Least Squares Support Vector Machine (LSSVM) model using an Improved Sparrow Search Algorithm (ISSA). Firstly, to address the problem of Sparrow Search Algorithm (SSA) easily falling into local optima, an improved Sine chaotic mapping is introduced to optimize the initial parameters of the population, and the Lévy flight strategy is applied to improve the position update method of SSA followers. The performance of ISSA is tested using four benchmark test functions, and the result shows that ISSA effectively improves the convergence speed and optimization ability. Then, an ISSA-LSSVM ultrasonic oxygen concentration prediction model is constructed. Experimental results based on actual data indicate that the accuracy of the ISSA-LSSVM model in oxygen concentration prediction reaches 99.87%, verifying the effectiveness of the proposed method. |
| keywords:Oxygen concentration prediction Improving Sparrow Search Algorithm Least Squares Support Vector Machine Improving Sine Chaotic Mapping Lévy Flight Strate |
| 查看全文 查看/发表评论 下载pdf阅读器 |
位访问者,今日访问
