基于臀部红外测量的神经网络体温算法研究

发布时间：2018-06-19 22:08

  本文选题：偏最小二乘法 + 人工神经网络　； 参考：《电子测量与仪器学报》2017年09期

【摘要】：红外测体温的精度受到多种因素的影响,具有非线性和高度复杂性的特点。为了提高红外测体温的精度,分析了环境温度、测量距离、发射率等对红外测体温精度的影响。研究了基于臀部的红外体温测量方法,建立了由臀部体表温度转化为人体实际体温的温度场扩散模型,利用偏最小二乘法和人工神经网络对温度场模型进行优化补偿,有效的解决了各影响因素之间多重相关性的问题和补偿模型的非线性问题,提高了系统的可靠性。实验结果表明,所提出的红外测体温补偿模型测温误差范围在-0.12~0.11℃,具有更高的测量精度且适应性更强。
[Abstract]:The accuracy of infrared temperature measurement is influenced by many factors and has the characteristics of nonlinearity and high complexity. In order to improve the accuracy of infrared temperature measurement, the effects of ambient temperature, measuring distance and emissivity on the accuracy of infrared temperature measurement are analyzed. The infrared temperature measurement method based on buttocks is studied, and the diffusion model of temperature field is established, which is transformed from hip surface temperature to actual body temperature. The partial least square method and artificial neural network are used to optimize and compensate the temperature field model. It effectively solves the problem of multiple correlation among various factors and the nonlinear problem of compensation model, and improves the reliability of the system. The experimental results show that the temperature measurement error range of the proposed infrared temperature compensation model is -0.12 ~ 0.11 鈩，

本文编号：2041502