SVD样本学习的嵌入式智能吹风系统设计
|
摘要
针对传统吹风系统不能根据环境温度和光照强度实现智能化多档位调整的缺点,设计一款基于奇异值分解的样本学习的新型多档位自动调节智能吹风系统。该系统以STM32F407ZGT6最小系统为控制核心,采用温度传感器和光敏二极管实时采集环境温度和光照强度。利用奇异值分解的最小二乘算法,根据周围的温度与亮度参数,利用最小二乘方法做线性拟合,预测出当前所需要的电机转速。实验结果表明,该系统能够根据用户习惯,随着环境温度和光照强度,实现多档位智能调速,以满足不同用户的需求。
In allusion to the disadvantage that the traditional blowing system cannot realize intelligent multi-switching adjustment according to the environmental temperature and illumination intensity,a new multi-switching automatically-adjusted intelligent blowing system based on sample learning of singular value decomposition(SVD) is designed. In the system with the STM32F407ZGT6 minimum system as the control core,the ambient temperature and illumination intensity are collected in real time by using the temperature sensor and photosensitive diode. In accordance to the ambient temperature and luminance parameters,linear fitting is conducted by using the least squares algorithm based on SVD,so as to predict the currently-needed rotation speed of the motor. The experimental results show that the system can realize multi-switching intelligent speed adjustment with variation of ambient temperature and illumination intensity according to user habits,so as to meet the needs of different users.
In allusion to the disadvantage that the traditional blowing system cannot realize intelligent multi-switching adjustment according to the environmental temperature and illumination intensity,a new multi-switching automatically-adjusted intelligent blowing system based on sample learning of singular value decomposition(SVD) is designed. In the system with the STM32F407ZGT6 minimum system as the control core,the ambient temperature and illumination intensity are collected in real time by using the temperature sensor and photosensitive diode. In accordance to the ambient temperature and luminance parameters,linear fitting is conducted by using the least squares algorithm based on SVD,so as to predict the currently-needed rotation speed of the motor. The experimental results show that the system can realize multi-switching intelligent speed adjustment with variation of ambient temperature and illumination intensity according to user habits,so as to meet the needs of different users.
引文
[1]Anon.UFLDL tutorial.[2013-04-07].http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial.
[2]GOLUB G H,KAHAN W.Calculating the singular values and pseudo-inverse of a matrix[J].SIAM journal on numerical analysis,1965,2(2):205-224.
[3]KALMAN D.A singularly valuable decomposition:the SVD of a matrix[J].The college mathematics journal,1996,27(1):2-23.
[4]GOLUB G H,LOAN C F V.Matrix computations[M].3rd ed.Baltimore:John Hopkins University Press,1996.
[5]PRESS W H,FLANNERY B P,TEUKOLSKY S A,et al.Numerical recipes in C[M].Beijing:Publishing House of Electronic Industry,1992.
[6]PRATA S.C primer plus[M].6th ed.London:Pearson,2014.
[7]ARBENZ P.252-0504-00 G:numerical methods for solving large scale eigenvalue problems[EB/OL].[2018-02-21].http://people.inf.ethz.ch/arbenz/ewp/.
[8]DAHLQUIST G,BJ?RCK A.Numerical methods in scientific computing:volume II[M].Berlin:Springer,2014.
[9]WATKINS D S.Fundamentals of matrix computations[M].3rd ed.Hoboken:Wiley,2010.
[10]ANDERSON E,BAI Z,BISCHOF C,et al.LAPACK users′guide[M].3rd ed.Philadelphia:Society for Industrial and Applied Mathematics,1999.
[11]FRANCIS J G F.The QR transformation:a unitary analogue to the LR transformation-part 1[J].The computer journal,1961,4(3):265-271.
[12]MAREK A,BLUM V,JOHANNI R,et al.The ELPA library:scalable parallel eigenvalue solutions for electronic structure theory and computational science[J].Journal of physics:condensed matter,2014,26(21):213201.
[13]AUCKENTHALER T,BUNGARTZ H J,HUCKLE T,et al.Developing algorithms and software for the parallel solution of the symmetric eigenvalue problem[J].Journal of computational science,2011,2(3):272-278.
[14]GOLUB G H,VAN LOAN C F.Matrix computations[M].4th ed.Baltimore:The Johns Hopkins University Press,2012.
[15]佚名.STM32f4xx标准外设固件库[EB/OL].[2015-04-10].https://www.cnblogs.com/King-Gentleman/p/4369381.html.Anon.Standard peripheral hardware library of STM32f4xx[EB/OL].[2015-04-10].https://www.cnblogs.com/King-Gentleman/p/4369381.html.
[2]GOLUB G H,KAHAN W.Calculating the singular values and pseudo-inverse of a matrix[J].SIAM journal on numerical analysis,1965,2(2):205-224.
[3]KALMAN D.A singularly valuable decomposition:the SVD of a matrix[J].The college mathematics journal,1996,27(1):2-23.
[4]GOLUB G H,LOAN C F V.Matrix computations[M].3rd ed.Baltimore:John Hopkins University Press,1996.
[5]PRESS W H,FLANNERY B P,TEUKOLSKY S A,et al.Numerical recipes in C[M].Beijing:Publishing House of Electronic Industry,1992.
[6]PRATA S.C primer plus[M].6th ed.London:Pearson,2014.
[7]ARBENZ P.252-0504-00 G:numerical methods for solving large scale eigenvalue problems[EB/OL].[2018-02-21].http://people.inf.ethz.ch/arbenz/ewp/.
[8]DAHLQUIST G,BJ?RCK A.Numerical methods in scientific computing:volume II[M].Berlin:Springer,2014.
[9]WATKINS D S.Fundamentals of matrix computations[M].3rd ed.Hoboken:Wiley,2010.
[10]ANDERSON E,BAI Z,BISCHOF C,et al.LAPACK users′guide[M].3rd ed.Philadelphia:Society for Industrial and Applied Mathematics,1999.
[11]FRANCIS J G F.The QR transformation:a unitary analogue to the LR transformation-part 1[J].The computer journal,1961,4(3):265-271.
[12]MAREK A,BLUM V,JOHANNI R,et al.The ELPA library:scalable parallel eigenvalue solutions for electronic structure theory and computational science[J].Journal of physics:condensed matter,2014,26(21):213201.
[13]AUCKENTHALER T,BUNGARTZ H J,HUCKLE T,et al.Developing algorithms and software for the parallel solution of the symmetric eigenvalue problem[J].Journal of computational science,2011,2(3):272-278.
[14]GOLUB G H,VAN LOAN C F.Matrix computations[M].4th ed.Baltimore:The Johns Hopkins University Press,2012.
[15]佚名.STM32f4xx标准外设固件库[EB/OL].[2015-04-10].https://www.cnblogs.com/King-Gentleman/p/4369381.html.Anon.Standard peripheral hardware library of STM32f4xx[EB/OL].[2015-04-10].https://www.cnblogs.com/King-Gentleman/p/4369381.html.