基于SAGA-SVR的马铃薯贮藏库温度预测方法

马铃薯贮藏库温度受室外温度、室内马铃薯呼吸释放温度、通风降温等因素的影响难以准确预测,提出了一种改进遗传算法(Genetic Algorithm,GA)优化支持向量回归机(Support Vector Regression,SVR)的马铃薯贮藏库温度预测方法。该方法针对支持向量回归机参数难以选择、容易陷入局部极小的缺点,引入了具有并行性、全局搜索能力强的GA算法,结合局部搜索能力强的模拟退火算法(Simulated Annealing,SA),实现支持向量回归机的自动寻优。以新疆某农产品加工公司马铃薯贮藏库实测温度数据为样本,建立SAGA-SVR马铃薯贮藏库温度预测模型,进行贮藏库温度准确的预测。仿真结果表明,与GA-SVR、反向传播(Back Propagation,BP)温度预测模型的预测结果相比较,SAGASVR预测结果优于GA-SVR、BP预测结果,具有良好的预测效果。该预测方法较好地解决了系统非线性、小样本等问题,为类似应用场合地温度预测提供参考。

Prediction of Potato Storage Warehouse Temperature Based on SAGA-SVR

It was difficult to accurately predict the temperature of potato storage warehouse which were influenced by factors such as the outdoor temperature, indoor breathing release temperature, and ventilation and cooling. A potato storage temperature prediction method was proposed based on Support Vector Regression (SVR) machine optimized by improved Genetic Algorithm (GA). Considering that the parameters of support vector regression machines were difficult to select and easy to fall into local minimum, GA algorithm with a good parallel and strong global search ability was introduced, combined with Simulated Annealing(SA) which had the strong local search capacity, to realize the automatic optimum of support vector regression machines. Taking the measured temperature data of potato storage reservoir in a Xinjiang agricultural products processing company as samples, a SAGA-SVR potato storage temperature prediction model was established. To verify the accuracy of the model, SAGA-SVR prediction results were compared with GA-SVR and Back Propagation (BP), simulation results showed that SAGA-SVR prediction results were better than GA-SVR and BP, and had good prediction effect. The prediction method could solve the problems of system nonlinearity and small sample, and provide a reference for temperature prediction in similar applications.