Artificial Intelligence Modeling-Based Optimization of an Industrial-Scale Steam Turbine for Moving toward Net-Zero in the Energy Sector.

Augmentation of energy efficiency in the power generation systems can aid in decarbonizing the energy sector, which is also recognized by the International Energy Agency (IEA) as a solution to attain net-zero from the energy sector. With this reference, this article presents a framework incorporating artificial intelligence (AI) for improving the isentropic efficiency of a high-pressure (HP) steam turbine installed at a supercritical power plant. The data of the operating parameters taken from a supercritical 660 MW coal-fired power plant is well-distributed in the input and output spaces of the operating parameters. Based on hyperparameter tuning, two advanced AI modeling algorithms, i.e., artificial neural network (ANN) and support vector machine (SVM), are trained and, subsequently, validated. ANN, as turned out to be a better-performing model, is utilized to conduct the Monte Carlo technique-based sensitivity analysis toward the high-pressure (HP) turbine efficiency. Subsequently, the ANN model is deployed for evaluating the impact of individual or combination of operating parameters on the HP turbine efficiency under three real-power generation capacities of the power plant. The parametric study and nonlinear programming-based optimization techniques are applied to optimize the HP turbine efficiency. It is estimated that the HP turbine efficiency can be improved by 1.43, 5.09, and 3.40% as compared to that of the average values of input parameters for half-load, mid-load, and full-load power generation modes, respectively. The annual reduction in CO2 measuring 58.3, 123.5, and 70.8 kilo ton/year (kt/y) corresponds to half-load, mid-load, and full load, respectively, and noticeable mitigation of SO2, CH4, N2O, and Hg emissions is estimated for the three power generation modes of the power plant. The AI-based modeling and optimization analysis is conducted to enhance the operation excellence of the industrial-scale steam turbine that promotes higher-energy efficiency and contributes to the net-zero target from the energy sector.

Artificial Intelligence and Computational Issues in Engineering Applications.

High-performance supercomputers and emerging computing clusters created in research and development centres are rapidly increasing available computing power, which scientists are eager to use to implement increasingly advanced computing methods [...].

Experimental Investigation of an Intensified Heat Transfer Adsorption Bed (IHTAB) Reactor Prototype.

The first experience in the operation of intensified heat transfer adsorption bed reactor designed for low-pressure adsorption processes is presented in this paper. This work aims to assess the possibility of fluidizing the porous media bed induced by the pressure difference between the evaporator and the adsorption reactor. The conducted experimental research allowed indicating the type of silica gel recommended to use in fluidized beds of adsorption chiller. The fixed bed of silica gel was observed for the lower pressure differences, while fluidization appeared in the case of the pressure difference between the evaporator and the adsorption chamber higher than 1000 Pa. The most significant differences in the adsorption process between the fixed bed and the fluidized bed are revealed in the changes of sorbent temperatures. The silica gel bed was fluidized with water vapor generated in the evaporator.

Artificial Intelligence and Computational Methods in the Modeling of Complex Systems.

Based on the increased attention, the Special Issue aims to investigate the modeling of complex systems using artificial intelligence and computational methods [...].

Comprehensive Knowledge-Driven AI System for Air Classification Process.

Air classifier devices have a distinct advantage over other systems used to separate materials. They maximize the mill's capacity and therefore constitute efficient methods of reducing the energy consumption of crushing and grinding operations. Since improvement in their performance is challenging, the development of an efficient modeling system is of great practical significance. The paper introduces a novel, knowledge-based classification (FLClass) system of bulk materials. A wide range of operating parameters are considered in the study: the mean mass and the Sauter mean diameter of the fed material, classifier rotor speed, working air pressure, and test conducting time. The output variables are the Sauter mean diameter and the cut size of the classification product, as well as the performance of the process. The model was successfully validated against experimental data. The maximum relative error between the measured and predicted data is lower than 9%. The presented fuzzy-logic-based approach allows an optimization study of the process to be conducted. For the considered range of input parameters, the highest performance of the classification process is equal to almost 362 g/min. To the best of our knowledge, this paper is the first one available in open literature dealing with the fuzzy logic approach in modeling the air classification process of bulk materials.

The Effect of Adhesive Additives on Silica Gel Water Sorption Properties.

Adsorption chillers are characterized by low electricity consumption, lack of moving parts, and high reliability. The disadvantage of these chillers is their large weight due to low adsorbent sorption capacity. Therefore, the attention is turned to finding a sorbent with a high water sorption capacity and enhanced thermal conductivity to increase chiller efficiency. The article discusses the impact of selected adhesives used for the production of an adsorption bed in order to improve heat exchange on its surface. Experiments with silica gel with three commercial types of glue on metal plates representing heat exchanger were performed. The structure of samples was observed under a microscope to determine the coverage of adsorbent by glue. To determine the kinetics of the free adsorption, the amounts of moisture adsorbed and the desorption dynamics the prepared samples of coated bed on metal plates were moisturized and dried in a moisture analyzer. Samples made of silica gel mixed with the adhesive 2-hydroxyethyl cellulose, show high adsorption capacity, low dynamic adsorption, and medium dynamic desorption. Samples containing adhesive poly(vinyl alcohol) adsorb less moisture, but free adsorption and desorption were more dynamic. Samples containing the adhesive hydroxyethyl cellulose show lower moisture capacity, relatively dynamic adsorption, and lower dynamic desorption.

Fluidized Bed Jet Milling Process Optimized for Mass and Particle Size with a Fuzzy Logic Approach.

The milling process is a complex phenomenon dependent on various technological and material parameters. The development of a fluidized bed jet milling model is of high practical significance, since milling is utilized in many industries, and its complexity is still not sufficiently recognized. Therefore, this research aims to optimize fluidized bed jet milling with the use of fuzzy logic (FL) based approach as one of the primary artificial intelligence (AI) methods. The developed fuzzy logic model (FLMill) of the investigated process allows it to be described as a non-iterative procedure, over a wide range of operating conditions. Working air pressure, rotational speed of the classifier rotor, and time of conducting the test are considered as inputs, while mass and mean Sauter diameter of the product are defined as outputs. Several triangular and constant linguistic terms are used in the developed FLMill model, which was validated against the experimental data. The optimum working air pressure and the test's conducting time are 500 kPa and 3000 s, respectively. The optimum rotational speed of the classifier is equal to 50 s-1, considering the mass of the grinding product, and 250 s-1 for the mean Sauter diameter of the product. Such operating parameters allow obtaining 243.3 g of grinding product with the mean Sauter diameter of 11 µm. The research proved that the use of fuzzy logic modeling as a computer-based technique of solving mechanical engineering problems allows effective optimization of the fluidized bed jet milling process.

Review article: lack of effect of opiates in the treatment of acute cardiogenic pulmonary oedema.

Opiates have traditionally been used as one of the main treatments of acute heart failure and are still recognized as such. Most current textbooks and official guidelines advise the use of morphine as one of the first-line treatments for patients in acute cardiogenic pulmonary oedema and a majority of physicians accept it to be the case. The author performed an extensive literature search in order to validate the evidence for the use of opiates in this condition. A total of seven papers, six in English and one in Polish, were found that directly investigated or reported the clinically important outcomes of treatment of acute pulmonary oedema. Only five of these dealt specifically with the effects of administration of opiates in acute cardiogenic pulmonary oedema. None of the above publications suggested a clinically significant improvement in outcomes of patients treated with morphine, although early research did suggest reduced anxiety, blood pressure and pulse rate as well as a reduction in arterial oxygen contents. The more recent studies suggest a strong association between increased mortality and morbidity (e.g. intensive care unit admissions or intubation rates), although causality is difficult to establish because of research methodologies. The current evidence does not support the routine use of opiates in the treatment of acute pulmonary oedema.

Modular extracorporeal life support for multiorgan failure patients.

Adults receiving respiratory Extracorporeal Membrane Oxygenation (ECMO) have 66% survival. Nonsurvivors develop multisystem organ failure (MSOF). Once hepatic failure develops, death usually follows shortly. Serum bilirubin > 300 micromol/l predicted death with 87.8% sensitivity and 90.3% specificity in 41 adults who received ECMO in our institution during 1998 and 1999. No patients survive with a peak bilirubin > 400 micromol/l. The Molecular Adsorbent Recirculating System (MARS) is a cell-free extracorporeal liver support device; we hypothesized that using MARS in adult respiratory ECMO patients with a bilirubin >300 micromol/l could improve survival in MSOF. The MARS was used in five such patients aged 19-56 who developed liver failure secondary to a respiratory illness. Mean peak bilirubin was 529 micromol/l and the lowest peak bilirubin was 436 micromol/l. Patients received between 1 and 8 MARS treatments, mean reduction in serum bilirubin for each patient ranging between 30 and 162 micromol/l. Two of five patients survived (40%), survivors showing the greatest reduction in serum bilirubin in response to MARS. All patients would have been expected to die according to our previous experience. We believe that MARS may prove a useful therapy for patients with MSOF.