Adsorption systems are characterized by challenging behavior to simulate any numerical method. A novel field of study emerged within the numerical method in the last two years: the physics-informed neural network (PINNs), the application of artificial intelligence to solve partial differential equations. This is a complete new standpoint for solving engineering first-principle models, which up to that date was not explored in the field of adsorption systems. Therefore, this work proposed the evaluation of PINN to address the numerical solutions of a fixed-bed column where a monoclonal antibody is purified. The PINNs solution is compared with a traditional numerical method. The results show the accuracy of the proposed PINNs when compared with the numerical method. This points towards the potential of this technique to address complex numerical problems found in chemical engineering.

Flavor is an essential component in the development of numerous products in the market. The increasing consumption of processed and fast food and healthy packaged food has upraised the investment in new flavoring agents and consequently in molecules with flavoring properties. In this context, this work brings up a scientific machine learning (SciML) approach to address this product engineering need. SciML in computational chemistry has opened paths in the compound's property prediction without requiring synthesis. This work proposes a novel framework of deep generative models within this context to design new flavor molecules. Through the analysis and study of the molecules obtained from the generative model training, it was possible to conclude that even though the generative model designs the molecules through random sampling of actions, it can find molecules that are already used in the food industry, not necessarily as a flavoring agent, or in other industrial sectors. Hence, this corroborates the potential of the proposed methodology for the prospecting of molecules to be applied in the flavor industry.

A misusage of machine learning (ML) strategies is usually observed in the process systems engineering literature. This issue is even more evident when dynamic identification is performed. The root of this problem is the gradient explode and vanishing issue related to the recurrent neural networks training. However, after the advent of deep learning, these issues were mitigated. Furthermore, the problem of data structuration is often overlooked during the machine learning model identification in this field. In this scenario, this work proposes a guideline for identifying ML models for the different applications in process systems engineering, which are usually for simulation or prediction purposes. While using the proposed guideline, the work also identifies a virtual analyzer for a pressure swing adsorption unit. In these types of adsorption separations, it is usual that the measurement of the main properties is not done online. Therefore, the virtual analyzer is another contribution of this manuscript. The overall results demonstrate that even though the test provides good performance during the ML model identification, its quality might degenerate over the application domain if the model application is overlooked.