为提升chirplet变换(chirplet transform,CT)估算瞬时频率的精度,在CT基础上结合花斑翠鸟优化(pied kingfisher optimizer,PKO)和径向基移动最小二乘(radial basis function moving least squares,RBFMLS)算法提出了一种识别结构瞬时频...为提升chirplet变换(chirplet transform,CT)估算瞬时频率的精度,在CT基础上结合花斑翠鸟优化(pied kingfisher optimizer,PKO)和径向基移动最小二乘(radial basis function moving least squares,RBFMLS)算法提出了一种识别结构瞬时频率的新方法。该方法采用正定紧支径向基函数作为移动最小二乘近似的权函数,对CT的能量脊线进行估算,同时应用PKO对RBFMLS节点支撑半径和CT窗函数宽度进行优化。通过一组解析信号数值算例和一个时变拉索试验验证了所提方法的有效性。研究结果表明,该方法能有效改善信号分析的能量聚集性,提高瞬时频率的识别精度。展开更多
在对海平面变化规律进行深入分析的基础上,应用最小二乘神经网络组合模型对海平面变化趋势进行预测;对卫星测高海平面异常序列中的周期项及线性趋势项利用最小二乘模型进行拟合,残差部分则采用径向基函数神经网络模型进行预测。对中国...在对海平面变化规律进行深入分析的基础上,应用最小二乘神经网络组合模型对海平面变化趋势进行预测;对卫星测高海平面异常序列中的周期项及线性趋势项利用最小二乘模型进行拟合,残差部分则采用径向基函数神经网络模型进行预测。对中国近海海域卫星测高海平面异常序列的预测表明,连续1个月的预测精度为0.52 cm, 3个月的预测精度为0.65 cm,证明了该组合模型在海平面变化短期预测方面的可靠性,其在海平面变化预测领域具有较高的应用价值。展开更多
Methods of PCA (principal component analysis) and PLS (partial least squares) based on RBF (radial basis function)neural network are proposed for the reason that the generalization ability of common neural networks de...Methods of PCA (principal component analysis) and PLS (partial least squares) based on RBF (radial basis function)neural network are proposed for the reason that the generalization ability of common neural networks debases when the input data is high dimension or correlations exist These two methods can reduce the dimension and extract the correlations of the input data They are used in the prediction of polypropylene melt index, and the simulation results show that the statistical methods improve the predictive precision展开更多
文摘为提升chirplet变换(chirplet transform,CT)估算瞬时频率的精度,在CT基础上结合花斑翠鸟优化(pied kingfisher optimizer,PKO)和径向基移动最小二乘(radial basis function moving least squares,RBFMLS)算法提出了一种识别结构瞬时频率的新方法。该方法采用正定紧支径向基函数作为移动最小二乘近似的权函数,对CT的能量脊线进行估算,同时应用PKO对RBFMLS节点支撑半径和CT窗函数宽度进行优化。通过一组解析信号数值算例和一个时变拉索试验验证了所提方法的有效性。研究结果表明,该方法能有效改善信号分析的能量聚集性,提高瞬时频率的识别精度。
文摘在对海平面变化规律进行深入分析的基础上,应用最小二乘神经网络组合模型对海平面变化趋势进行预测;对卫星测高海平面异常序列中的周期项及线性趋势项利用最小二乘模型进行拟合,残差部分则采用径向基函数神经网络模型进行预测。对中国近海海域卫星测高海平面异常序列的预测表明,连续1个月的预测精度为0.52 cm, 3个月的预测精度为0.65 cm,证明了该组合模型在海平面变化短期预测方面的可靠性,其在海平面变化预测领域具有较高的应用价值。
文摘Methods of PCA (principal component analysis) and PLS (partial least squares) based on RBF (radial basis function)neural network are proposed for the reason that the generalization ability of common neural networks debases when the input data is high dimension or correlations exist These two methods can reduce the dimension and extract the correlations of the input data They are used in the prediction of polypropylene melt index, and the simulation results show that the statistical methods improve the predictive precision
