Mujiburohman Muhammad, Elkamel Marwen, Hourfar Farzad, Elkamel Ali
Chemical Engineering Department, Universitas Muhammadiyah Surakarta (UMS), 57102, Indonesia.
Industrial Engineering & Management Systems Department, University of Central Florida, Orlando, FL, 32816, USA.
Heliyon. 2025 Feb 13;11(4):e42714. doi: 10.1016/j.heliyon.2025.e42714. eCollection 2025 Feb 28.
It is well accepted that the pervaporation (PV) permeation was affected by the physicochemical properties of permeant-membrane materials and process conditions. Given many experimental data of PV, a predictive model on PV permeation based on their physicochemical properties and process conditions can be constructed. This study proposes a machine learning approach in terms of artificial neural network (ANN) to predict the permeation flux of PV, as a function of physicochemical properties of permeant-membrane material and process conditions. A large dataset was assembled from the literature and was divided into a training subset and a testing subset. The output variable was the PV flux, while the input variables were the physicochemical properties of permeant-membrane and the process conditions which were considered to affect the PV flux. Two types of inputs were evaluated: regular variables (Type I) and dimensionless groups derived from these regular variables (Type II). Several neural network architectures were evaluated. The best predictive performance for Type I inputs was achieved with a deep neural network consisting of two layers, each with 7 neurons. For Type II inputs, the optimal architecture was a shallow neural network with a single layer containing 6 neurons. The correlation coefficients () during model training for Type I and Type II were 0.93674 and 0.88332, respectively, while the root mean square errors (RMSE) were 42.2558 and 38.0766, respectively. The extent of dependency of output on input variables was determined using Garson's equation. It was found that the most affecting physicochemical properties on the PV permeation flux were glass transition temperature ( ), solubility difference of two different permeants , and molar volume of permeant ( ), consecutively. Whereas the operating condition that dominantly affects the PV permeation flux was permeate pressure ( ).
普遍认为，渗透蒸发（PV）渗透受到渗透物 - 膜材料的物理化学性质和工艺条件的影响。鉴于大量的PV实验数据，可以构建一个基于其物理化学性质和工艺条件的PV渗透预测模型。本研究提出了一种基于人工神经网络（ANN）的机器学习方法来预测PV的渗透通量，该通量是渗透物 - 膜材料的物理化学性质和工艺条件的函数。从文献中收集了一个大型数据集，并将其分为训练子集和测试子集。输出变量是PV通量，而输入变量是渗透物 - 膜的物理化学性质以及被认为会影响PV通量的工艺条件。评估了两种类型的输入：常规变量（I型）和从这些常规变量导出的无量纲组（II型）。评估了几种神经网络架构。对于I型输入，由两层组成、每层有7个神经元的深度神经网络实现了最佳预测性能。对于II型输入，最优架构是具有单个包含6个神经元的层的浅神经网络。I型和II型在模型训练期间的相关系数分别为0.93674和0.88332，而均方根误差（RMSE）分别为42.2558和38.0766。使用加森方程确定输出对输入变量的依赖程度。结果发现，对PV渗透通量影响最大的物理化学性质依次是玻璃化转变温度（ ）、两种不同渗透物的溶解度差（ ）和渗透物的摩尔体积（ ）。而对PV渗透通量起主要影响的操作条件是渗透压力（ ）。
