基于RBF神经网络分析的微弱电信号预报

Forecast on weak electrical signals by analysis of RBF neural networks

采用自制双重屏蔽系统(屏蔽室和屏蔽箱结合)和自制的铂金传感器刺入植物茎部接触式微弱电信号的测试方法,对绿萝(Scindpsus aureus)植物的自身电信号进行了测试.利用小波软阈值消噪法对测试数据进行消噪,并进行了时间序列的高斯径向基函数神经网络预测.结果表明,利用径向基函数(RBF)人工神经网络对植物微弱电信号进行短期预测是可行的.预测数据可用作温室和/或塑料大棚生产中建立植物自适应电信号智能自动化控制系统的重要参数.

The original weak electrical signals in Scindpsus aureus were tested by a touching testing used platinum sensors in a system of self-made double shields. The tested data of the electrical signals were denoised by the wavelet soft-threshold and using Gaussian radial base function （RBF） as the time series at a delayed input window chosen at 50. An intelligent RBF forecasting system was set up to forecast the signals in plants. The result shows that it is feasible to forecast the plant electrical signal for a short period. The forecast data can be used as the important preferences for the intelligent automatic control system based on the adaptive characteristic of plants to achieve the energy saving on agricultural production in the greenhouse and/or the plastic lookum.