In this study, an artificial neural network (ANN) is used to develop predictive models for estimating molecular diffusion coefficients of various gases at multiple pressures over a large field of temperatures. Two feed-forward neural networks NN1 and NN2 are trained using six physicochemical properties: molecular weight, critical volume, critical temperature, dipole moment, temperature, and pressure for NN1 and molecular weight, critical pressure, critical temperature, dipole moment, temperature, and pressure for NN2. The diffusion coefficients are regarded as the output. A set of 1252 gases (941 non-polar gases and 311 polar gases) is used for training and testing the ANN performance, and good correlations are found ( R = 0.986 for NN1 and R = 0.988 for NN2). The result of the sensitivity analysis shows the importance of the six input parameters selected for modeling the diffusion coefficient. Moreover, the present ANN model provides more accurate predictions than other models.

中文翻译：

---

预测极性和非极性二元气体分子扩散系数的人工神经网络模型的优化方法

在这项研究中，人工神经网络 (ANN) 被用于开发预测模型，用于估计各种气体在大温度范围内多种压力下的分子扩散系数。两个前馈神经网络 NN1 和 NN2 使用六种物理化学特性进行训练：NN1 的分子量、临界体积、临界温度、偶极矩、温度和压力以及分子量、临界压力、临界温度、偶极矩、温度和NN2 的压力。扩散系数被视为输出。一组 1252 种气体（941 种非极性气体和 311 种极性气体）用于训练和测试 ANN 性能，并发现了良好的相关性（NN1 的 R = 0.986 和 NN2 的 R = 0.988）。敏感性分析的结果显示了为扩散系数建模而选择的六个输入参数的重要性。此外，目前的 ANN 模型比其他模型提供更准确的预测。