期刊文献+

粒子群算法优化支持向量回归的民机客舱座椅舒适度评价预测

Particle Swarm Algorithm Optimized Support Vector Regression for the Prediction of Passenger Cabin Seat Comfort Evaluation in Civil Aircraft
下载PDF
导出
摘要 为建立民机客舱座椅舒适度主客观评价之间复杂非线性的评价预测模型,同时提高模型的预测精度,本文将支持向量回归(Support vector regression,SVR)中的惩罚参数C、通道控制参数ε以及核函数参数σ作为优化目标,利用粒子群算法(Particle swarm optimization,PSO)寻找全局最优参数,建立PSO-SVR人-民机客舱座椅舒适度评价预测模型,并对预测结果进行对比分析。分析结果表明:与BP神经网络(Back propagation,BP)模型相比,支持向量回归模型具有良好的鲁棒性;与SVR模型相比,PSO-SVR模型预测精度更高,误差波动小,预测结果均方误差(MSE)降低了85.95%,决定系数(R2)提高了15.42%。因此粒子群算法可以有效提高支持向量回归模型的预测精度和泛化能力。 To build a complex nonlinear prediction model among subjective and objective evaluation of passenger cabin seat comfort and improve the prediction accuracy of the model.In this paper,penalty parameter C,the channel control parameterεand the kernel function parameterσin support vector regression(SVR)are taken as the optimization objectives,the particle swarm optimization(PSO)algorithm is used to find the global optimal parameters,and PSO-SVR human-civil aircraft seat comfort evaluation and prediction model is built,and the prediction results are compared and analyzed.The analysis results show that:compared with the back propagation neural network model,the support vector regression model has good robustness;compared with the SVR model,the PSO-SVR model has higher prediction accuracy and smaller error fluctuation,the mean square error of the prediction results is reduced by 85.95%,and the determination coefficient is increased by 15.42%.So,the particle swarm optimization can effectively improve the prediction accuracy and generalization ability of the support vector regression model.
作者 逄欣 苟秉宸 PANG Xin;GOU Bingchen(College of Mechanical and Electrical Engineering,Northwest University of Technology,Xi′an 710072,China)
出处 《机械科学与技术》 CSCD 北大核心 2024年第9期1624-1630,共7页 Mechanical Science and Technology for Aerospace Engineering
基金 陕西省高层次人才特殊支持计划(TZ0408) 工信部民机专项((2018)105号)。
关键词 民机客舱座椅 支持向量机回归 粒子群算法 舒适度评价预测 civil aircraft cabin seats SVR PSO comfort rating prediction
  • 相关文献

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部