激光与红外
激光與紅外
격광여홍외
LASER & INFRARED
2010年
1期
57-61
,共5页
神经网络%多光谱%辐射测温
神經網絡%多光譜%輻射測溫
신경망락%다광보%복사측온
ANN%spectral measurement%the radiation measurement temperature
采用BP神经网络处理多光谱测温数据,利用MATLAB神经网络工具箱进行计算机仿真试验,并分析了随机噪声对测量结果的影响.实验结果表明,该方法可以取消大多数工程材料发射率与波长之间的假设模型,克服最小二乘法解决上述问题的局限,是一种获得目标真温及光谱发射率行之有效的方法.
採用BP神經網絡處理多光譜測溫數據,利用MATLAB神經網絡工具箱進行計算機倣真試驗,併分析瞭隨機譟聲對測量結果的影響.實驗結果錶明,該方法可以取消大多數工程材料髮射率與波長之間的假設模型,剋服最小二乘法解決上述問題的跼限,是一種穫得目標真溫及光譜髮射率行之有效的方法.
채용BP신경망락처리다광보측온수거,이용MATLAB신경망락공구상진행계산궤방진시험,병분석료수궤조성대측량결과적영향.실험결과표명,해방법가이취소대다수공정재료발사솔여파장지간적가설모형,극복최소이승법해결상술문제적국한,시일충획득목표진온급광보발사솔행지유효적방법.
The paper applied the BP nerve network processing many the spectral measurement data,and made use of the MATLAB nerve network tool box to carry on calculator's imitate true experiment,and analyzed the influence of random voice to measurement result.Experimental result proved that the method could cancel the assumption model of emissivity and wave-lengths,overcoming limit of minimum two multiplications which resolve the above-mentioned problem.It is a kind of valid method to acquire the true temperature and spectral emissivity.
