genetic algorithm

The global warming and climate change due to the increase in greenhouse gas emissions are the vital and challenging issues in this period of human life. Human’s effort to address this problem has led to provide several solutions including net-zero carbon, i.e., carbon capture and storage and energy transition i.e., reducing or even replacing fossil fuels with renewable energy sources such as solar, wind, hydro etc. However, climate dependence and the highly fluctuating nature of clean energy production from these sources require a large-scale storage system to continuously meet energy demand. Hydrogen as an energy carrier, and underground hydrogen storage (UHS) hold potential for sustainable supply of a large amount of energy in the peak of energy consumption. Hydrogen has different characteristics and dynamical behaviors in the porous media compared to other gases. Thus it is required to create complex compositional models and perform time-consuming simulations to seek for the best gas storage scenario based on operational parameters including and cushion gas and working gas injection/production flowrates, perforations and cushion gas composition. In this study, the process of UHS in a depleted gas reservoir was simulated. Due to the reservoir remaining gas saturation and phase behavior of fluids in porous media, both hydrogen recovery factor and purity are considered as target variables. Next, the design of experiment methods (e.g., Latin hypercube) was utilized to generate the required train and test subsets for artificial neural network model. The feed-forward model with 10 neurons and sigmoid activation function as a smart proxy model with accuracy equal to 0.97 and 0.94, respectively, for training and testing subsets provided the best performance for predicting the hydrogen purity and recovery factor or the target parameters in the multi-objective optimization process of decision variables by genetic algorithm. The optimum solutions, i.e., Pareto front for the decision variables showed the dominant percentage of nitrogen gas with the base gas composition of 75, 20 and 5% respectively for nitrogen, carbon dioxide and methane. Moreover, production from top perforations and hydrogen injection in the lower part of the preformation were determined as optimal conditions. The implemented procedure in this paper can be used for UHS field studies and fast decision making in the large-scale energy storage operations.

This research presents a simple hybrid approach to tackle heat exchanger network (HEN) synthesis problems. The formulations governing these issues are inherently non-convex non-linear models, which are challenging to solve. In this new method, structural variables were managed by genetic algorithm (GA) to reach optimal networks. While the optimization of continuous variables was done in the first section by a linear programming (LP) model and in the second part by a correction procedure (COP). In production structures by the GA, to increase the search space, the possibility of utilizing internal utility exchangers was also provided. In this way, the complex models governing the HEN synthesis problems were transformed into a straightforward and relatively linear hybrid strategy, which increased the likelihood of reaching optimal solutions. Despite the simplicity of the proposed approach, implementing this method in a case study demonstrated its high efficiency in generating new solutions and reducing the total annual cost of the network by 1.21%.

In the customer's interaction with the company, environmental information is received by the five senses. The compatibility or lack of compatibility of the environment's characteristics with the customer's sensory tastes can cause the customer's satisfaction or dissatisfaction. This research has two goals. The effect of mixed sensitive marketing on customer loyalty of Iranian clothing brands and optimization of the effect of mixed sensitive marketing on customer loyalty. The research method is descriptive-survey and practical in terms of purpose. The statistical population is unlimited and includes the buyers and consumers of clothes of 18 Iranian brands in the age group of children, teenagers and adults. The sample size of 384 was determined and selected using non-probability sampling method. In order to collect the data, the mixed sensitive marketing questionnaires of Kian and Loui 2009 and the customer loyalty questionnaire of vaida,kanopaite 2015 were used. In order to analyze the data, structural equations and LISREL software were used. The meta-heuristic algorithm part of the genetic algorithm was used for its optimal modeling. In this way, the rules related to the effect of the mixed dimensions of sensory marketing on customer loyalty were first identified by the decision tree and then these rules were optimized with the help of genetic algorithm with MATLAB software. The results of the research in the first part showed the approval of all sensory marketing components except the interaction component. In the second part, using the decision tree with the help of the genetic optimization algorithm, customer loyalty can be predicted with 97% accuracy and accuracy using 27 rules.

Assessment of petroleum generation potential of the source rock as a function of total organic carbon content and kerogen type is of great importance in oil and gas exploration studies. The main aim of this research is to compare the performance of artificial neural networks trained by back propagation algorithm (ANN-BP) and metaheuristic methods including genetic algorithm (ANN-GA) and particle swarm optimization (ANN-PSO) for prediction of total organic carbon (TOC) content and remaining petroleum potential (S2) from the wireline data. For this purpose, Pabdeh Formation (Paleocene-Oligocene) in Mansuri oilfield is studied. Based on the results of linear regression on the test data, ANN-PSO method provides more accurate predictions of Rock-Eval derived TOC and S2 parameters with correlation coefficient (R2) values of 0.8548 and 0.9089, respectively. In addition, hydrogen index (HI) is appropriately predicted based on the relationship between TOC and S2 values obtained from the ANN-PSO method with R2 value of 0.6882, from which different types of kerogen can be distinguished with classification accuracy of 74 percent. Geochemical zonation of Pabdeh Formation based on organic richness and kerogen type reveals three distinctive parts, among which the middle part (Brown Shale Unit, BSU) demonstrates the greater petroleum generation potential with having the significant values of total organic carbon and hydrogen index. Therefore, the BSU can play an important role in hydrocarbon charging of the oilfield traps if it attains proper level of thermal maturity. Accordingly, precise determination of petroleum generation characteristics of Pabdeh Formation using the ANN-PSO model proposed in this study will lead to a reduction in uncertainty associated with petroleum system modeling, and therefore will considerably increase the exploration efficiency in the Mansuri oilfield.

After recognizing the toxic and carcinogenic effects of Lead organic compounds, production of compounds such as Methyl tertiary butyl ether as an additive to ordinary hydro carbonate gases was proposed. These materials are able to enter into water, soil and air due to relative steam pressure and partial dissolution in water and cause the pollution. As a result, development of a new process for producing gas with high octane from complex compounds of light petroleum distillates was initiated. This method is based on separating C5-C8 linear and branched alkanes according to their absorption properties, chain length and the number of branches. In this study, the hybrid neural network model based on experimental data in the database has been used as an alternative model for predicting the separation rate of linear and branched paraffin through absorption process. Absorption temperature, absorption time, hydrocarbons' octane number, and hydrocarbon density are considered as four input parameters, and the ratio of linear paraffin concentration to total (C/C0) as the output parameter of neural network. The neural network model was successfully generalized by experimental database and then was investigated with the help of test data. The results of modeling for the test data indicated the success of neural network model in predicting the rate of linear paraffin separation from non-linear ones. Therefore, the developed neural network model can be used for determining the C/C0 with confidence in absorption process. According the obtained results for test data, the minimum mean squared error is 0/0518, which is a satisfactory measure. The model and experimental data were compared and regression coefficient 0.990 shows good matching between modeling results and experimental results.

In this study, the process of single stage mixed natural gas liquefaction is reviewed, then process energy optimization and economic analysis are followed. The effect of specific energy consumption optimization on the costs of cooling equipment was investigated. The basis of this study is PRICO process and due to some limitations and concerns for Iran, it is tried to develop a new modified process so that the available process restrictions would expel and finally the recommended process optimized by genetic algorithm. Mole flow of refrigerant, low pressure and high pressure of refrigerant in the cycle, are the most important operational parameters that were selected by sensitivity analysis. The total energy consumption of compressors reached 1413.8 kW and decreased by 11 percent. Results showed optimization of the specific energy consumption increases the cost of the heat exchanger, due to the reduction of heat exchanger temperature driving force and need to higher heat transfer area. However, the operating cost of compressors can be reduced.

Addition of nanoparticles to a polymeric matrix leads to enhance the performance of membrane gas separation. In this study, the aim is to find the optimum operative point of polymeric membrane modified by adding nanoparticles in gas separation. The assessed factors are type of nanoparticle, percentage of added nanoparticle, and cross membrane pressure.  Nanoparticles of AL2O3, ZnO, and TiO2 were used. Further, the ranges of nanoparticle concentration and operative cross membrane pressure were 2.5 to 15% and 2 to 25 bar respectively. To optimize a process, developing a robust model is necessary. Therefore, first, a powerful model based on artificial neural network was developed, which it was able to predict the values of permeability of oxygen, nitrogen, methane, and carbon dioxide. Neural network models were developed that had R2 greater than 0.9. Next, the optimum operative conditions for assessed gases were found using methodology based on genetic algorithm and considering four strategies. The results of optimization show that the maximum values of permeability for oxygen, nitrogen, methane, and carbon dioxide are 334.7, 779.9, 902.7, and 270.4 respectively.

Initially a model of neural network analysis achieved and was using by genetic algorithm optimization. Comparing the results of Petro-SIM’s optimization software, and genetic algorithm showed that the temperature in both are equal and pressure from genetic algorithms and Petro-SIM’s software, respectively 75.6 psig and 79.5 psig that are slightly lower than the amount of operational. In contrast the help of genetic algorithm to optimize air flow rate is 181 kg/hr and the optimum value obtained from the Software is 169.8 kg/hr. In addition, optimum weight fraction of soda in both techniques is almost equal to the values in the unit. Using the results of genetic algorithm and Entering this condition to Petro-SIM software and simulation it became clear that optimize the optimum conditions, the value of mercaptan concentration in the product will be less than 1ppm.

Recently, optimization methods have been extensively applied in phase equilibrium calculations. Among these methods, Genetic Algorithm (GA) can be used to calculate the interaction parameters of activity coefficient models in equilibrium systems. In this study, based on the genetic algorithm, the interaction parameters of 5 activity coefficient models (2-suffix Margules, 3-suffix Margules, Wilson, NRTL and UNIQUAC) have been calculated for 20 ternary extraction systems (water + carboxylic acids + organic solvents) including 126tie-lines. The values of binary interaction parameters of these models along with the root mean square deviations (RMSD) are reported. The mean values of RMSD of the systems in the order of the mentioned models have been calculated 0.0298, 0.0067, 0.0114, 0.0025 and 0.0052, respectively. The results show that all models except 2-suffix Margules model have relatively good accuracy. By comparing the RMSD values in literature and the values determined by GA for NRTL and UNIQUAC models, the RMSD values of the models improved from 0.0124 and 0.0181 to 0.0025 and 0.0052, respectively

One of the non-destructive tests developed for determining fruit maturity stage is the analysis of imapact fruit response of fruit . Therefore, in this study, in order to evaluate the quality and maturity stages of pomegranate fruit, a system for recording acoustic responses was developted. For this purpose, the acoustic response of 150 pomegranates in three maturity stages (immature, ripe, and over-ripe) was recorded. To evaluate the destructive properties, the total soluble solids, acidity, ascoric acid , anthocyanin, total phenol and pH were measured; Also, in order to record and extract the acoustic features (non-destructive test), positions of microphone (behind, next to and under the fruit), as well as the hitting angle (5, 10 and 15 degrees) were evaluated as variables. In order to classify the data, a decision tree classifier combined with the genetic algorithm was utilized. Based on the statistical analysis, it was determined that the best orientation of the microphone and the hitting angle were the placement of the microphone next to hitting ball and 15 degrees, respectivily. Based on the results of the classification, the highest, lowest and overall classification accuricy were 96.7% (in the ripe group), 73% (in the over-ripe group) and 89.2%, respectively.

Mixed refrigerant is widely used in the natural gas liquefaction process, and this makes it important to optimize the parameters affecting this process. In this research, a PRICO process with mixed refrigerant was optimized by using Non-dominated Sorting Genetic Algorithm (NSGAII). In this optimization, energy consumption and the surface of heat exchanger were optimized simultaneously to eliminate the adverse effect of the surface of heat exchanger increase due to the single-objective optimization of the energy consumption observed in the previous papers. Molar flow rates of mixed refrigerant compounds including methane, ethylene, propane, isopentane and nitrogen, outlet pressures of the first and second compressors and outlet pressure of the cooling cycle valve were considered as optimization variables. Also, the considered objective functions were performed on sensitive analysis towards optimization variables Moreover, the optimization solutions were presented as a set of optimal solutions called Pareto optimal fronts whose results showed the contradiction of the two objective functions well. Afterwards, multi-objective optimization results were compared with single-objective minimization results. Ultimately, comparison results showed that the surface of heat exchanger in multi-objective optimization was reduced by 54% in comparison with  single-objective optimization (energy optimization).