امیراحسان فیلی منفرد

Submerged combustion vaporizers are one of the industrial equipments that produce a large amount of nitrogen oxides (NOx). These equipments are actually heat exchangers that are used in liquefied natural gas (LNG) terminals to evaporate liquefied natural gas and convert it into gas. Since previous studies have shown that the operating conditions of this equipment are effective on the amount of NOx production in it, artificial intelligence tools were used in this research to model and then optimize NOx emission in this equipment. For this purpose, 63 laboratory data were extracted from the researchers' previous researches, and then a combination of adaptive neural fuzzy inference system and genetic algorithm was used to model the data. In the developed system, oxygen concentration, temperature, water-oxygen concentration and solution pH were considered as input parameters to the model and NOx reduction percentage as output. The statistical analysis of the built model showed that this model with correlation coefficient of 0.9714, mean square error of 1.0938, average absolute error percentage of 4.9713 and maximum absolute error percentage of 13.2144 has a good accuracy in estimating the amount of NOx reduction. In the next step after the development of the model, the genetic algorithm and the built model were used to optimize the operating conditions with the lowest NOx emission rate. The results of this part of the research also showed that if the operating conditions are optimized, it is possible to reduce the amount of NOx released up to 37.24%

In recent years, the high efficiency of dust removal from gases by Rotating Packed Beds has attracted the attention of various industries. However the design process of this equipment using experimental methods and their computational fluid dynamics simulations, Due to the complexity of these beds and the number of parameters affecting their efficiency, using experimental methods for design will be very costly and time-consuming. This research evaluated the performance of Genetic Programming method in modelling these beds. Based on this, with 561 experimental data and using genetic programming, various equations were developed to estimate the system's efficiency. Among the created models, an equation with the least complexity and the most accuracy was selected. Results showed that the obtained equation, with a correlation coefficient of 0.9714, a mean square error of 3.79 and a maximum percentage of error of 1.51, had high accuracy for the design of these Rotating packed beds. Sensitivity analysis of the selected equation was also conducted and the results showed that particle size, rotational speed and liquid flow rate would have the most positive effect on efficiency of these beds.

In recent years, the capabilities of rotating packed beds in dust removal from gases has attracted the attention in different industries. On the other hand, due to intricate complexities of such beds, employment of computational fluid dynamic techniques for design and modeling purposes would be difficult. Therefore, in this research the performance of artificial intelligence techniques in design of theses equipment was investigated. Accordingly, in the first step and by using 561 experimental data points, an artificial neural network system was developed. In the constructed model, dust removal efficiency was considered as the output and the working and design conditions of the bed were fed as the inputs. Performance of the developed system was analyzed both quantitatively and qualitatively and achieving value of 0.99 for correlation coefficient demonstrates its suitable accuracy in efficiency determination. Finally, employing the developed neural network system combined with genetic algorithms, a novel method for optimum design of beds with arbitrary characteristics was proposed. Performed analyses showed that the constructed system while being simple, offers flexibility and precision in design of rotating packed beds. Also, its low coast of development makes it an attractive idea to be employed in industry scale.