论文部分内容阅读
研究了人参真空冷冻干燥工艺参数对干燥速率的影响规律。运用正交试验方法研究了干燥室压力、物料厚度、加热温度对干燥速率的影响,得到了优化的工艺组合。在此基础上运用BP神经网络对试验数据进行分析处理,建立BP神经网络模型,并通过该模型进行预测和优选,得到最佳的方案,即加热温度为60℃、干燥室压力为80 Pa、物料厚度为5 mm,此时干燥速率为1.46 h-1,与网络预测值1.44 h-1相差1.38%。结果表明,经正交试验数据训练过的BP神经网络,能较好的反应工艺参数与优化指标之间的复杂非线性关系,对指导生产试验与降低经济成本具有一定的意义。
The effects of ginseng vacuum freeze-drying process parameters on drying rate were studied. The influence of drying chamber pressure, material thickness and heating temperature on the drying rate was studied by orthogonal test. The optimized process combination was obtained. On this basis, the BP neural network is used to analyze and process the experimental data to establish the BP neural network model. Through the prediction and optimization of the model, the best scheme is obtained, namely the heating temperature is 60 ℃, the drying chamber pressure is 80 Pa, The material thickness is 5 mm, the drying rate is 1.46 h-1, which is 1.38% different from the network prediction value of 1.44 h-1. The results show that the BP neural network trained by orthogonal test data can well reflect the complex nonlinear relationship between process parameters and optimization indexes, which is of great significance to guide the production test and reduce the economic cost.