基于机器学习的NTC温度校准方法研究  

Research on NTC temperature Calibration Method Based on Machine Mearning

作　　者：张译 张进成 孙志平 ZHANG Yi;ZHANG Jincheng;SUN Zhiping

机构地区：[1]云南省普洱市质量技术监督综合检测中心 [2]云南省大理州质量技术监督综合检测中心

出　　处：《计量与测试技术》2024年第8期83-85,共3页Metrology & Measurement Technique

摘　　要：基于机器学习的NTC热敏电阻温度校准方法由于制造过程和存储环境因素的差异,会导致传统校准方法可能存在一定的测量误差。本文采用机器学习技术中的支持向量机回归模型,对4组NTC热敏电阻样本进行温度校准。结果表明:该模型相对于传统方法,预测热敏电阻温度值与标准温度值的偏差为(-0.02~0.02)℃,具有更高的精确度和准确性。The NTC thermistor temperature calibration method based on machine learning may have some measurement errors due to the differences in manufacturing process and storage environment.In this paper,the support vector machine regression model in machine learning technology is used to calibrate 4 groups of NTC thermistor samples.The results show that compared with the traditional method,the deviation between the temperature of thermistor and the standard temperature is(-0.02~0.02)℃,and the model has higher precision and accuracy.

关 键 词：NTC热敏电阻 温度校准 机器学习 多项式拟合 

分 类 号：TN37[电子电信—物理电子学] TP181[自动化与计算机技术—控制理论与控制工程]