基于RBF神经网络提高压力传感器精度的新方法

A New Method to Improve Pressure Sensor Precision Based on RBF Neural Network

传感器的温度漂移普遍存在 ,提出了一种新的补偿方法。用智能温度传感器DS18B2 0作为辅助传感器 ,结合主传感器测量变量 ,利用径向基函数 (RBF)神经网络构建双输入单输出网络模型 ,采用带遗忘因子的梯度下降算法实现了压力传感器高精度温度补偿 ,比普通补偿方法精度提高了 2～ 5倍。

As temperature drift exist in many sensors, a new method of sensor compensation is put forward. Intelligent temperature sensor DS18B20 is adopted as auxiliary sensor. A network model with two inputs and single output is constructed by radial basis function neural network. The two inputs include DS18B20 sensor and a main sensor. High precision temperature compensation of pressure sensor is achieved by gradient descend algorithm with a momentum factor in this network model. Measurement precision is improved 2～5 times comparing with general compensation method.