基于遗传神经网络的多光谱辐射测温法
|
摘要
针对BP神经网络易陷入局部极小等缺陷,将遗传算法(GA)与神经网络相结合,提出了一种将GA-BP算法应用于多光谱辐射测温的数据处理方法,并对基于亮度温度模型的多光谱辐射测温数据进行了仿真实验。结果表明已训练样本的真实温度识别精度,GA-BP算法为±5K,BP神经网络为±10K;未训练样本的真实温度识别精度,GA-BP算法为±10K,BP神经网络为±20K;无论是GA-BP算法还是BP神经网络,已训练样本的真实温度识别精度比未训练样本的真实温度识别精度都更精确些,靠近训练样本集边缘的样本真实温度的识别精度偏低。说明GA-BP算法比BP神经网络可以更好地解决了目标真实温度的测量问题。
Considering some defects of back-propagation neural network (BP), a new algorithm combining genetic algorithm (GA) with BP was described. The application of GA-BP to the data processing of multi-spectral thermometry was proposed. The simulation experiments, based on GA-BP algorithm and BP neural network respectively, show that the recognition precision of trained emissivity samples is ±5 K and ±10 K respectively, and that of untrained emissivity samples is ±10 K and ±20 K respectively. No matter GA-BP algorithm or BP neural network is used, in general, the recognition precision of trained emissivity samples is higher than that of untrained emissivity samples. The recognition precision of true temperature is lower near the edge of sample sets. The GA-BP algorithm was more efficient than the BP neural network in the true temperature measurement.
Considering some defects of back-propagation neural network (BP), a new algorithm combining genetic algorithm (GA) with BP was described. The application of GA-BP to the data processing of multi-spectral thermometry was proposed. The simulation experiments, based on GA-BP algorithm and BP neural network respectively, show that the recognition precision of trained emissivity samples is ±5 K and ±10 K respectively, and that of untrained emissivity samples is ±10 K and ±20 K respectively. No matter GA-BP algorithm or BP neural network is used, in general, the recognition precision of trained emissivity samples is higher than that of untrained emissivity samples. The recognition precision of true temperature is lower near the edge of sample sets. The GA-BP algorithm was more efficient than the BP neural network in the true temperature measurement.
引文
[1]DAI Jing-min,SUN Xiao-gang(戴景民,孙晓刚).Theory and Application of Muti-Spetral Radiation Pyrometry(多光谱辐射测温理论与应用).Beijing:Higher Education Press(北京:高等教育出版社),2002.
[2]SUN Xiao-gang(孙晓刚).Journal of Infrared and Milli meter Waves(红外与毫米波学报),2001,20(2):151.
[3]CONG Da-cheng(丛大成).Journal of Infrared and Milli meter Waves(红外与毫米波学报),2001,20(2):97.
[4]REN Wen-jie,SUJing-yu,DOU Yuan-ming(任文杰,苏经宇,窦远明).Earthquake Engineering and Engineering Vibration(地震工程与工程振动),2003,23(3):145.
[5]GAOJing-wei,ZHANG Pei-lin,LI Feng(高经纬,张培林,李锋).Lubrication Engineering(润滑与密封),2004,1:16.
[6]WANG Xiao-ping,CAO Li-ming(王小平,曹立明).Genetic Algorithm-Theory,Application and Realizing Software(遗传算法—理论·应用与软件实现).Xi’an:Xi’an Jiaotong University Press(西安:西安交通大学出版社),2002.
[7]XU Dong,WUZheng(许东,吴铮).Neural Networks-Systems Analysis and Design Based on MATLAB6.X(基于MATLAB6.X的系统分析与设计—神经网络).Xi’an:Xidian University Press(西安:西安电子科技大学出版社),2002.
[8]BAI Ying-kui,MENG Xian-jiang,DI NG Dong,et al(白英奎,孟宪江,丁东,等).Spectroscopy and Spectral Analysis(光谱学与光谱分析),2005,25(3):381.
[2]SUN Xiao-gang(孙晓刚).Journal of Infrared and Milli meter Waves(红外与毫米波学报),2001,20(2):151.
[3]CONG Da-cheng(丛大成).Journal of Infrared and Milli meter Waves(红外与毫米波学报),2001,20(2):97.
[4]REN Wen-jie,SUJing-yu,DOU Yuan-ming(任文杰,苏经宇,窦远明).Earthquake Engineering and Engineering Vibration(地震工程与工程振动),2003,23(3):145.
[5]GAOJing-wei,ZHANG Pei-lin,LI Feng(高经纬,张培林,李锋).Lubrication Engineering(润滑与密封),2004,1:16.
[6]WANG Xiao-ping,CAO Li-ming(王小平,曹立明).Genetic Algorithm-Theory,Application and Realizing Software(遗传算法—理论·应用与软件实现).Xi’an:Xi’an Jiaotong University Press(西安:西安交通大学出版社),2002.
[7]XU Dong,WUZheng(许东,吴铮).Neural Networks-Systems Analysis and Design Based on MATLAB6.X(基于MATLAB6.X的系统分析与设计—神经网络).Xi’an:Xidian University Press(西安:西安电子科技大学出版社),2002.
[8]BAI Ying-kui,MENG Xian-jiang,DI NG Dong,et al(白英奎,孟宪江,丁东,等).Spectroscopy and Spectral Analysis(光谱学与光谱分析),2005,25(3):381.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心