期刊文献+
共找到5篇文章
< 1 >
每页显示 20 50 100
双曲线函数拟合工程沉降规律的方法研究 被引量:1
1
作者 张子贤 《水利水电快报》 2018年第3期30-33,共4页
为了提高双曲线函数回归的拟合精度,结合双曲线函数拟合工程沉降规律的实例,从理论上分析了采用线性化回归方法导致其回归失真的原因。指出对双曲线函数应采用非线性回归方法求解。给出了采用高斯-牛顿法和借助MATLAB软件中nlinfit函数... 为了提高双曲线函数回归的拟合精度,结合双曲线函数拟合工程沉降规律的实例,从理论上分析了采用线性化回归方法导致其回归失真的原因。指出对双曲线函数应采用非线性回归方法求解。给出了采用高斯-牛顿法和借助MATLAB软件中nlinfit函数进行双曲线函数非线性回归的方法。实例计算表明,采用非线性回归方法拟合效果显著优于线性化的回归方法,且借助MATLAB软件易于实现。 展开更多
关键词 双曲线函数 线性化回归方法 线性回归方法 沉降规律 拟合精度
下载PDF
指数函数拟合公路隧道工程沉降规律的方法研究
2
作者 张子贤 《城市道桥与防洪》 2017年第12期157-160,共4页
对于指数函数回归,只当采用乘积随机误差时才能够线性化。导出了采用乘积随机误差及采用线性化回归方法时,指数函数因变量的数学期望的表达式,该式表明,该因变量的估计值并非是其数学期望的估值。分析表明,采用线性化回归方法所求指数... 对于指数函数回归,只当采用乘积随机误差时才能够线性化。导出了采用乘积随机误差及采用线性化回归方法时,指数函数因变量的数学期望的表达式,该式表明,该因变量的估计值并非是其数学期望的估值。分析表明,采用线性化回归方法所求指数函数的回归系数不满足该因变量的残差平方和为最小。基于上述不合理现象,对指数函数的回归计算应采用非线性回归方法求解。文中给出了采用高斯-牛顿法或借助MATLAB软件中nlinfit函数求解指数函数非线性回归的方法。实例进一步表明,采用非线性回归方法拟合效果显著优于线性化的回归方法,且借助MATLAB软件易于实现。 展开更多
关键词 指数函数 线性化回归方法 线性回归方法 沉降规律拟合 拟合精度
下载PDF
指数函数与幂函数回归计算的极大似然法及其应用 被引量:4
3
作者 张子贤 刘玉伟 刘家春 《数学的实践与认识》 北大核心 2018年第24期217-222,共6页
为提高拟合精度,研究了指数函数与幂函数非线性回归计算的极大似然法.分析表明,在指数函数与幂函数回归计算的因变量为正态随机变量的情况下,极大似然估计与非线性回归的最小二乘估计具有相同的结果;导出了极大似然法求解指数函数与幂... 为提高拟合精度,研究了指数函数与幂函数非线性回归计算的极大似然法.分析表明,在指数函数与幂函数回归计算的因变量为正态随机变量的情况下,极大似然估计与非线性回归的最小二乘估计具有相同的结果;导出了极大似然法求解指数函数与幂函数回归参数的方程式,并给出了计算方法.此方法拟合因变量的残差平方和为最小.实例表明,本文方法拟合精度与高斯-牛顿法相当、显著优于线性化的回归方法,而计算方法要比高斯-牛顿法简单方便,易于实现. 展开更多
关键词 指数函数 幂函数 线性化回归方法 线性回归方法 极大似然法 残差平方和 拟合精度
原文传递
Flow reconstructions and aerodynamic shape optimization of turbomachinery blades by POD-based hybrid models 被引量:2
4
作者 LUO JiaQi ZHU YaLu +1 位作者 TANG Xiao LIU Feng 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2017年第11期1658-1673,共16页
This study presented a hybrid model method based on proper orthogonal decomposition(POD) for flow field reconstructions and aerodynamic design optimization. The POD basis modes have better description performance in a... This study presented a hybrid model method based on proper orthogonal decomposition(POD) for flow field reconstructions and aerodynamic design optimization. The POD basis modes have better description performance in a system space compared to the widely used semi-empirical basis functions because they are obtained through singular value decomposition of the system.Instead of the widely used linear regression, nonlinear regression methods are used in the function response of the coefficients of POD basis modes. Moreover, an adaptive Latin hypercube design method with improved space filling and correlation based on a multi-objective optimization approach was employed to supply the necessary samples. Prior to design optimization, the response performance of POD-based hybrid models was first investigated and validated through flow reconstructions of both single-and multiple blade rows. Then, an inverse design was performed to approach a given spanwise flow turning distribution at the outlet of a turbine blade by changing the spanwise stagger angle, based on the hybrid model method. Finally, the span wise blade sweep of a transonic compressor rotor and the spanwise stagger angle of the stator blade of a single low-speed compressor stage were modified to reduce the flow losses with the constraints of mass flow rate, total pressure ratio, and outlet flow turning.The results are presented in detail, demonstrating the good response performance of POD-based hybrid models on missing data reconstructions and the effectiveness of POD-based hybrid model method in aerodynamic design optimization. 展开更多
关键词 flow reconstruction aerodynamic design optimization proper orthogonal decomposition TURBOMACHINERY hybrid model computational fluid dynamics TRANSONIC
原文传递
Increasing trend of lightning activity in the South Asia region 被引量:3
5
作者 Kai Qie Xiushu Qie Wenshou Tian 《Science Bulletin》 SCIE EI CSCD 2021年第1期78-84,M0004,共8页
Lightning is an important natural source of wildfires and oxynitride,and hence significantly influences ecological systems and atmospheric chemistry.Here,we choose South Asia,an important region for global water reall... Lightning is an important natural source of wildfires and oxynitride,and hence significantly influences ecological systems and atmospheric chemistry.Here,we choose South Asia,an important region for global water reallocation and global climate changes,to examine lightning variations based on the longest existing lightning dataset from the OTD/LIS observations.We identify a clear increase in lightning density in the research region,increasing at a rate of 0.096 fl km^(-2)a^(-1)over the last two decades.Multiple linear regression analysis is adopted to identify the main influencing factors among ten potential thermodynamic or microphysical factors and the crucial areas contributing to the increases in lightning.The surface latent heat flux along the west coast of the Indian subcontinent is the largest contributor,explaining52%of the lightning variance and contributing to a 0.025 fl km^(-2)a^(-1)increase.The sea surface temperature in the Arabian Sea,the convective available potential energy(CAPE)over the northwestern Indian subcontinent,and the wind shear along the northwestern coast also make important contributions to the lightning increase,indicating that the thermodynamic effects overwhelm the microphysical effects on lightning activity over the South Asia region. 展开更多
关键词 Lightning activity TREND South Asian monsoon region Thermodynamic and microphysical factors Multiple linear regression analysis
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部