基于人工神经网络的二元液体闪点预测

Prediction of Flash Points of Binary Liquid Based on Artificial Neural Networks

建立了一个基于人工神经网络的理论模型,用于预测二元混合液体的闪点。根据所研究混合液体的物理性质,选择了相关黏度、表面张力等物理参数来表征闪点,以这些参数作为输入参数,二元混合液体的闪点作为输出值,应用反向传播(BP)人工神经网络方法对两者之间的内在定量关系进行模拟。结果表明,闪点预测值与实验值符合良好,优于传统的计算方法。

A model based on artificial neural networks is established to predict the flash points of binary liquid.Based on the physical properties such as viscosity and surface tension which are chosen to represent flash point.Also,these physical parameters are used as input arguments and flash points of binary liquid used as output one.Back-propagation artificial neural networks are used to simulate the quality relationship between input arguments and output one.The result shows that the predicted flash points are in good agreement with the experimental value,superior to those conventional calculated methods.