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

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.