论文部分内容阅读
压力传感器的输出随温度呈非线性变化,同时含有较大的随机噪声。针对BP神经网络对压力传感器温度补偿建模时误差较大的问题,提出了基于灰色模型和BP神经网络的压力传感器温度补偿模型。首先,用灰色模型对数据进行预处理,以减小原始数据的噪声;然后,用降噪后的样本数据作为BP神经网络的输入进行训练。在相同的训练次数下训练误差可减小一个数量级。结果表明,采用该模型补偿后的压力传感器补偿精度明显优于BP网络模型。
The output of the pressure sensor varies nonlinearly with temperature, and contains large random noise. Aiming at the large error in BP neural network modeling of pressure sensor temperature compensation, a temperature compensation model of pressure sensor based on gray model and BP neural network is proposed. First, the gray model is used to preprocess the data to reduce the noise of the original data. Then, the noise-reduced sample data is used as the input of BP neural network to train. The training error can be reduced by an order of magnitude at the same training times. The results show that the compensation accuracy of the pressure sensor compensated by this model is obviously better than that of the BP network model.