The Application of Principal Component Analysis (PCA) for the Optimization of the Conditions of Fabrication of Electrospun Nanofibrous Membrane for Desalination and Ion Removal

Abstract

Nowadays, acquiring a water supply for urban and industrial uses is one of the greatest challenges facing humanity for ensuring sustainability. Membrane technology has been considered cost-effective, encompasses lower energy requirements, and at the same time, offers acceptable performance. Electrospun nanofibrous membranes (ENMs) are considered a novel and promising strategy for the production of membranes that could be applied in several treatment processes, especially desalination and ion removal. In this study, we apply an unsupervised machine-learning strategy, the so-called principal component analysis (PCA), for the purpose of seeking discrepancies and similarities between different ENMs. The main purpose was to investigate the influence of membrane fabrication conditions, characteristics, and process conditions in order to seek the relevance of the application of different electrospun nanofibrous membranes (ENMs). Membranes were majorly classified into single polymers/layers, from one side, and dual multiple layer ENMs, from another side. For both classes, variables related to membrane fabrication conditions were not separated from membrane characterization variables. This reveals that membranes’ characteristics not only depend on the chemical composition, but also on the fabrication conditions. On the other hand, the process conditions of ENM fabrication showed an extensive effect on membranes’ performance.

Application of Unsupervised Learning for the Evaluation of Aerogels’ Efficiency towards Dye Removal—A Principal Component Analysis (PCA) Approach

“…We have used similar methodology that we used in our previously published work [ 60 , 61 , 62 ]. After normalization, PCA findings were yielded by using XLSTAT 2014 software, following the similar approach adopted by Younes et al [ 60 , 61 , 62 ].…”

“…We have used similar methodology that we used in our previously published work [ 60 , 61 , 62 ]. After normalization, PCA findings were yielded by using XLSTAT 2014 software, following the similar approach adopted by Younes et al [ 60 , 61 , 62 ]. In this study, the missing data were estimated using a built-in feature that replaces a missing value with the “Mode”, following the respective variables.…”

Assessment of the Efficiency of Chemical and Thermochemical Depolymerization Methods for Lignin Valorization: Principal Component Analysis (PCA) Approach

“…PCA was first introduced in 1901 by Karl Pearson [ 34 , 35 ], where it is also referred to and known as discrete Karhunen–Loève transform (KLT). PCA technique is employed to reduce the dimensionality of the problem by transforming a large set of input variables into smaller features referred to as principal components (PCs) [ 36 ]. However, reducing the number of variables might affect the accuracy, and, hence, there is a trade-off between accuracy and simplicity of the problem.…”

Investigating the Physical and Operational Characteristics of Manufacturing Processes for MFI-Type Zeolite Membranes for Ethanol/Water Separation via Principal Component Analysis

“…Principal Component Analysis (PCA) is a powerful statistical tool widely used in membrane sciences for various critical applications [19][20][21]. One major application of PCA in this field resides in the analysis and interpretation of complex datasets, such as those obtained from spectroscopic measurements, and operational conditions [22,23].…”