Drying processes are among the most energy-intensive industrial processes. There is a need for development of the efficient methods needed for estimating, measuring, and reducing energy use. Different machine learning algorithms might provide some of the answers to these issues in a faster and less costly way, without the need for time-consuming and expensive experiments done at different scales of the dryers. The aim of this paper was to provide a comprehensive overview of machine learning applications for addressing energy-related challenges by exploration of different energy types and energy reduction opportunities. Also, the analysis of the applied algorithms, their specific applications and a critical evaluation of the obtained results are provided. The paper is based on the necessity of the improvements in energy use needed for drying related on the existing data. The overview of the ways for such achievements, and a general classification of machine learning algorithm are the background of the paper. The methods used are the machine learning techniques employed in different energy-related issues for drying processes. The paper focuses on the applications of artificial neural networks and other machine learning algorithms and models for different energy-related issues, including different energy types applications, challenges associated with energy consumption, and opportunities for energy reduction. Not only the applied algorithms, but also their specific applications, and the statistical analysis of the obtained results are also overviewed. Finally, a critical evaluation of the findings highlighting the potentials of machine learning algorithms in addressing energy-related challenges (such as estimation of energy consumption, opportunities for energy reduction, and use of different energy sources) is provided. The presented analysis underscored the effectiveness of machine learning applications for these purposes.

This work presents a procedure for direct numerical minimization of entropy production in a diabatic tray column with heat exchanged on the trays as control variables, as opposed to previously used procedures with temperature on the trays as control variables. The procedure, which had previously been demonstrated on a binary mixture, was in this work applied to a multicomponent mixture, with minor modifications. The procedure comprised the complex optimization method and the Ishii-Otto method for solving the equations of a column model based on the iterative Newton-Raphson technique with partial linearization of the equations. The desired separation of the components was realized by the addition of a penalty function to the goal function, i.e. entropy production in the column. The required thermodynamic characteristics were calculated by the Soave equation of state. As an illustration, an industrial debutanizer with five components was used whose data, obtained by simulation, were compared with the optimization results of a diabatic column with the same desired separation and number of trays. After the diabatic column optimization procedure, the value of 91.91 J/Ks was obtained as the best result for entropy production. According to the best solution, entropy production in the diabatic column was 23.2% lower than in the adiabatic column. The heat to be removed from the column increased by 24.7%, while the heat to be added to the column increased by 28.8%.

Prilikom donošenja odluka uobičajeno je da se uradi analiza koja će u obzir uzeti različite kriterijume. Pošto postoji nekoliko poznatih načina za sušenje oraha, postavlјa se pitanje koji od njih odabrati. U radu je obavljena analiza na osnovu kriterijuma različite vrste koji bi donosiocu odluke mogli da pomognu u donošenju odgovarajuće odluke. Analizirani su aspekti koji mogu da utiču na formiranje i odabir odgovarajućih kriterijuma, a analiza je sprovedena i na konkretnom primeru.

In this paper, a simple approach for the prediction of final state during solid-liquid phase transition of a phase change material (PCM) is proposed based on a mathematical model of heat conduction with phase transition in a cylindrical coordinate system. Generally speaking, models like this one assume a moving boundary between the liquid and solid phases. Myristic acid is used as a PCM, and the analysis is carried out on a 60-minute basis. The aim of the presented piece of research is an experimental validation of the usage of the mentioned models. The approach proposed has resulted in a good prediction in terms of the final melting interface position. On the other side, in the initial period, the model overestimates the melting front motion, and thus it cannot be used to precisely predict the motion and shape of the melting front.