“…The problem with using invasive sensors is the inability to directly examine any part of the reactor's interior, the accuracy of the measurements taken, the requirement to use multiple monitoring systems at the same time, and the high uncertainty in determining the dynamic state of the process based on incomplete data (indirect method). Electrical capacitance tomography (ECT) [4][5][6][7][8][9][10][11][12][13][14][15][16], electrical impedance tomography (EIT) [17][18][19][20][21][22][23][24], magnetoacoustic tomography [25], ultrasound and radio [26,27], X-ray tomography [28], optical tomography [29,30], and other non-invasive technologies are used to monitor industrial operations. Recently, an increasing number of research papers in the field of industrial system operation have included the use of various computational methods, such as intelligent predictive methods [31], fuzzy logic [32,33], machine learning [34], numerical modelling [35], deep learning [18,36], and binary programming [37].…”