长春花微弱电信号的ARIMA模型

Processing of forecast by ARIMA model on the weak electrical signals in Catharanthus roseus

依据长春花(Catharanthus roseus)植物电信号小波软阈值消噪后的数据进行其电信号时间序列的求和自回归移动平均(ARIMA)模型分析.长春花植物微弱低频电信号的模型是Xt=2Xt-1+Xt-2+tε-0.119 04tε-1-0.361 83tε-2-0.155 47tε-3-0.363 66tε-4.长春花电信号幅值后向10个点的真实值与预测值的相对误差小于15%,表明利用自回归移动平均(ARIMA)模型对植物微弱电信号特性进行预测是可行的.预测数据可作为以节能为目标依据植物自适应电信号特性建立温室和/或塑料大棚智能自动化控制系统的重要参数.

By taking an electrical signal in Catharanthus roseus as the time series and by using the model analysis of the autoregressive integrated moving average （ARIMA）, an intelligent ARIMA forecasting system was constructed to forecast plant characters of signals de-noised by the wavelet soft-threshold backward. The weak electrical signal of C. roseus is Xt=2Xt-1＋Xt-2＋εt-0.11904εt-1-0.36183εt-2-0.15547εt-3-0.36366εt-4. It is 〈15 % at relative errors between the real and forecast values at backward 10 points of the electrical signal test in C. roseus, which shows it is feasible to forecast the plant electrical signal for a short period by the analysis of ARIMA. The forecast data can be used as important preferences for the intelligent automatic control system based on the adaptive characters of plants to achieve energy saving on agricultural production in the greenhouse and/or the plastic lookum.