应用BP神经网络的光谱测温与仿真  

Spectral temperature measurement and simulation based on BP ANN

作　　者：季中敏[1] 刘晓东[1] 

机构地区：[1]哈尔滨工业大学低温超导研究所,黑龙江哈尔滨150080

出　　处：《激光与红外》2010年第1期57-61,共5页Laser & Infrared

摘　　要：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。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.

关 键 词：神经网络 多光谱 辐射测温 

分 类 号：TN216[电子电信—物理电子学]