The Editor’s Choice article from the March issue of CJCE is the preface to the Artificial Intelligence and Machine Learning Applications in Chemical Engineering Special Issue Section by guest editor Simant Upreti of Toronto Metropolitan University. Within the preface, Dr. Upreti summarizes the 16 invited articles that make up this special issue section and notes the role of artificial intelligence and machine learning in the chemical engineering field: “Artificial intelligence (AI) and machine learning (ML), as they penetrate human endeavours from all walks of life, hold significant prospects in not only replacing complex tasks requiring supervision but also solving difficult problems and enhancing performance in a variety of scenarios. Chemical engineering, which is intimately involved with the transformation of materials and energy, is a fertile ground for AI and ML applications.” Be sure to explore this special issue section for insight into these exciting topics.
The first issue highlight from the issue is an open access article from the special issue section, titled “Assuring optimality in surrogate-based optimization: A novel theorem and its practical implementation in pressure swing adsorption optimization” by Carine Menezes Rebello, Erbet Almeida Costa, Antonio Santos Sánchez, Fredy Vides, and Idelfonso B. R. Nogueira of the Norwegian University of Science and Technology, Federal University of Ouro Preto (Brazil), and National Autonomous University of Honduras. The authors note that “The main contribution of this work is the derivation of a robustness test that guarantees the optimality of surrogate-based optimization. The derivation of this metric is based on the universal approximation theorem. The full framework proposed in this work is also composed by a sampling sizing methodology to randomly select samples within a feasible operating region (FOR) resulting from the optimization population, reducing the computational cost of the analysis and avoiding biases in the robustness calculation.” They continue that “The applicability and importance of this methodology are demonstrated through a case study of a complex chemical process—a pressure swing adsorption (PSA) unit—which presents a high computational cost to solve optimization problems. The results highlight the need and importance of evaluating the optimality of surrogate-based optimization schemes.”
The next issue highlight from the March issue is another open access article from the special issue section: “A new intelligent prediction model using machine learning linked to grey wolf optimizer algorithm for O2/N2 adsorption” by Hossein Mashhadimoslem, Vahid Kermani, Kourosh Zanganeh, Ahmed Shafeen, and Ali Elkamel of University of Waterloo and Natural Resources Canada. Within this article, the authors “address the deficiency and predict the adsorption performance in different adsorbents” by proposing “a new optimizer linked to the machine learning (ML) model considering the performance of the adsorption process.” They continue that “The main goal is to predict adsorption under different process conditions with different adsorbents and provide a unified framework, leading to the prediction of adsorption phenomena instead of traditional isotherm models. This research focuses on predicting the adsorbed amount of O2 and N2 on several carbon-based adsorbents using the ML approach linked to the grey wolf optimizer algorithm (GWO).” Ultimately, “The new ML-generated model can accurately predict the adsorption process behaviour of different carbon-based adsorbents under various process conditions. The results of this research have the potential to assist a wide range of gas separation industries.”
The final issue highlight is an open access article from authors Shazia Tanvir, Amandeep Kaur, and William A. Anderson of University of Waterloo: “Rapid determination of the antimicrobial properties of surfaces using an enzymatic activity surrogate”. Within this article, the authors explore a different methodology for examining the antimicrobial activity of metals-based surfaces: “Typical approaches for assessing the antimicrobial activity of metals-based surfaces involve the contact of a bacterial culture with the surface for a period of time, followed by culturing on agar plates to assess the decrease in microbial viability versus controls. This is a time-consuming methodology requiring at least 24 h to produce a set of results, which can be a bottleneck for productivity in novel materials development. An enzyme-based method was shown to be a satisfactory and much more rapid surrogate test for this application.”