一种基于神经网络算法的高精度拟合传感器温度特性曲线的方法

Approach Fitting the Temperature Characteristic Curve of Sensor with a High Accuracy Based on Neural Network Algorithm

为了有效改善传感器温度补偿特性,提出了基于傅立叶基函数神经网络算法的温度特性曲线拟合模型.分析了算法的收敛性,为学习率的选择提供了理论依据.给出了对掺杂苯的SnO2纳米传感器的灵敏度-温度特性曲线进行拟合的实例.结果表明基于傅立叶基函数神经网络算法的传感器温度特性拟合曲线具有高的光滑性和高的拟合精度(10-6),因而是一种有效的温度特性曲线拟合方法.

In order to improve effectively temperature compensation characteristic of sensor, the model fitting the temperature characteristic curve based on the neural network algorithm with Fourier basis functions was presented. The convergence performance of the algorithm was proposed. The theory gist to select learning rate is provided by the convergence theorem. The simulating example of the sensitivity-temperature characteristic curve of the SnO2 nanosensor mixed with benzene was given. The result shows that the temperature characteristic curve fitting of sensor using the neural network algorithm with Fourier basis function is both smooth and accurate. The fitting precision is up to 10.6. Therefore, the method of curve fitting based on the neural network algorithm is effective.