刺梨微波真空干燥特性及水分比预测模型研究

Microwave vacuum drying characteristics and moisture ratio prediction modeling of Rosa roxburghii Tratt

关键词:  刺梨，微波真空干燥，干燥特性，干燥动力学模型，神经网络模型，水分比预测

Key words:  Rosa roxburghii Tratt  microwave vacuum drying  drying characteristics  drying kinetics model  neural network model  water ratio prediction.

摘要:

目的 探索刺梨微波真空干燥特性和实现干燥过程中水分比预测。方法 以微波功率、真空度和装载量为考察因素，探究刺梨微波真空干燥过程中水分比和干燥速率变化情况，采用4种干燥动力学模型和反向传播人工神经网络（back propagation artificial neural network，BP-ANN）建立其水分比与干燥时间关系的预测模型，并对模型进行验证和预测精度对比。结果 在试验参数范围内，与真空度相比，提高微波功率、减少装载量可以更有效缩短刺梨干燥时间。4种数学模型中，Page模型拟合度最好，R2在0.99599～0.99976之间，χ2和SSE分别在0.00003～0.00024和0.00046～0.00409之间。经筛选确定BP-ANN模型的最佳隐含层个数为8，网络拓扑结构为4-8-1，R2=0.99756，MSE=0.00018。经试验验证发现，Page模型和BP-ANN模型水分比预测误差分别为3.63%和1.15%。结论 干燥特性研究为刺梨微波真空干燥工艺优化提供了数据支撑，BP-ANN模型能够为刺梨干燥过程中的水分比在线预测提供科学依据。

Abstract:

OBJECTIVE To explore the microwave vacuum drying characteristics of Rosa roxburghii Tratt and to predict the moisture ratio during the drying process. METHODS The microwave power, vacuum degree, and loading capacity were investigated as factors affecting the moisture ratio and drying rate during the microwave vacuum drying process of Rosa roxburghii Tratt. Four drying kinetic models and a back propagation artificial neural network (BP-ANN) were employed to develop a predictive model for the relationship between moisture ratio and drying time, which was subsequently validated and compared for prediction accuracy. RESULTS Within the range of experimental parameters, increasing microwave power and decreasing loading volume were more effective in shortening the drying time of Rosa roxburghii Tratt than adjustments to the vacuum degree. Among the four mathematical models, the Page model exhibited the best fit, with R2 values ranging from 0.99599 to 0.99976, and χ2 and SSE values ranging from 0.00003 to 0.00024 and 0.00046 to 0.00409, respectively. The optimal number of hidden layers for the BP-ANN model was determined to be 8, with a network topology of 4-8-1, with R2=0.99756 and MSE=0.00018. Experimental validation revealed that the prediction errors for the moisture ratio were 3.63% for the Page model and 1.15% for the BP-ANN model. CONCLUSION The investigation of drying characteristics offers valuable data to optimize the microwave vacuum drying process of Rosa roxburghii Tratt. Furthermore, the BP-ANN model serves as a scientific foundation for the online prediction of moisture ratio during the drying process of Rosa roxburghii Tratt.