genetic algorithm

Analyzing financial ratios over consecutive years is beneficial for evaluating the financial performance of construction companies. However, such an analysis can be tedious due to the vast number of the ratios. Therefore, developing an expert system based on artificial intelligence algorithms to identify and predict factors influencing the construction companies' financial performance is essential. To this end, a hybrid model based on Genetic Algorithm (GA) and Adaptive Neuro-Fuzzy Inference System (ANFIS) was introduced in this research to predict the financial performance of construction companies in Iran. This research is applied as descriptive and in terms of methodology well developed; also conducted cross-sectionally. The statistical population included all active construction companies in the construction sector in Tehran. Due to time and resource constraints, a random sampling technique was used. A questionnaire was utilized for data collection and data analysis, factor analysis methods and neuro-fuzzy system combined with GA were employed. The ANFIS combined with GA can evaluate the construction companies' financial performance with the minimum error. The findings ultimately resulted development of a model that forecasts the financial performance of Iranian construction companies, allowing them to concentrate on factors that improve financial performance.

The present study aims to optimize a green closed-loop supply chain (GCLSC) network while minimizing carbon emissions and maximizing product shipments. The proposed model incorporates unbalanced factors such as capacity level, input current limit to each distribution center, and facility environmental level. We considered emission control levels for locating distribution centers as well as the reduction in CO2 emissions at all levels of the supply chain. Moreover, all types of expenditures in a closed-loop supply chain including manufacturing, distribution, recovery, assembly, and disassembly in the model are considered. Consideration of these assumptions closes this study to reality and makes this study an innovative one. Moreover, to account for demand uncertainty, a robust optimization method, the Bertsimas and Sim optimization approach, is used. The Epsilon Constraint Method and non-dominated sorting genetic algorithm II (NSGA-II) were employed to solve multi-objective functions with unknown demand, and the genetic algorithm is used to solve large-scale problems. The results indicate that the proposed approach achieves the objectives of reducing costs, minimizing environmental impact. Moreover, the NSGA-II algorithm outperforms other solution methods in terms of the number and diversity of solutions on the Pareto front. Specifically, the Pareto boundary obtained by NSGA-II contains a larger number of solutions compared to the different types of epsilon constraint methods. Additionally, the diversity of solutions on the Pareto front is higher in the NSGA-II algorithm, indicating a more well-spread and diverse set of solutions. These findings highlight the superiority of NSGA-II as a powerful and effective algorithm for multi-objective optimization problems in green closed-loop supply chain networks.

Mill optimization has many economic benefits. Semi autogenous grinding mills are complex multi-input and multi-output systems that are difficult to optimize. The purpose of this study is to examine the functions of the wear of lifters, power draw and product size distribution. The design variables are mill speed, ball filling, slurry concentration and slurry filling. To achieve this aim, a pilot mill was carried out. The experimental results used to create training cases for the artificial neural network and then the optimization of the design variables is conducted by multi-objective genetic algorithm. Level diagrams are then used to select the best solution from the Pareto front. Finally, the response surface methodology has been used to study the interaction between the design parameters. The results showed that the best grinding occurs at 70-80% of the critical speed and ball filling of 15-20%. Optimized grinding was observed when the slurry volume was 1-1.5 times of the ball bed voidage volume and the slurry concentration was 60-70%. Additionally, variables with the largest effect on the process are mill speed and ball filling.

Magnetic Resonance (MR) images have many applications in medical science and play an essential role in the diagnosis and treatment of diseases. However, unavoidable artifacts and noise reduce the resolution of these images. In this paper,  we propose a hybrid noise reduction framework using the wavelet transform, the exponential function thresholding, and the Wiener filter. In particular, we first employ the Genetic algorithm to optimize the exponential function coefficient. Furthermore, we adopt the Winner filter to increase the robustness of the proposed scheme against different types of noise, such as Gaussion and Rician noise. Some common performance measures, such as Mean Square Error (MSE) and Peak Signal-to-Noise-Ratio (PSNR), have been used to evaluate the performance of the proposed method compared to existing counterparts. The results show that the performance of the proposed hybrid method is better than the existing methods, such as universal thresholding and plain exponential function thresholding. For example, for human brain images with Gaussian noise, the obtained PSNR using the proposed method is 53.3947, while the PSNR value is 51.7532 using the universal threshold. Moreover, the results indicate that by using the Winner filter, we can effectively control the robustness against noise and image blurring.

To enhance the performance of meta-heuristic algorithms, the development of new operators and the efficient combination of various optimization techniques are valuable strategies for discovering global optimal solutions. In this research endeavor, we introduce a novel optimization algorithm called PGS (Particle Swarm Optimization-GA-Sliding Surface). PGS combines the strengths of particle swarm optimization (PSO), genetic algorithm (GA), and sliding surface (SS) to tackle both mathematical test functions and real-world optimization problems. To achieve this, we adaptively tune the weighting function and learning coefficients of the PSO algorithm using the sliding mode control's SS relation. The global best particle discovered through the PSO method serves as one of the parents in the GA's crossover operation. This new crossover operator is then probabilistically integrated with an improved particle swarm optimization algorithm, enhancing convergence speed and facilitating escape from local optima. We evaluate the proposed algorithm's performance on both uni-modal and multi-modal mathematical test functions, considering un-rotated and rotated cases, thereby testing its effectiveness and efficiency against other prominent optimization techniques. Furthermore, we successfully implement the PGS algorithm in optimizing the state feedback controller for a nonlinear quadcopter system and determining the cross-section for an inelastic compression member.

Wireless sensor networks contain of many sensors that can serve as powerful tools for data collection in environments. A key challenge in these networks is the limited lifetime of sensor batteries. Ideally, all nodes would exhaust their energy simultaneously or through regular scheduling, maximizing the lifetime. Consequently, the primary concern is achieving optimal energy utilization to extend the network's lifetime over a logical duration. Depleting the batteries of the sensors means stopping the operation of the network, because it is practically impossible to replace the batteries of thousands of nodes. To address this issue, the low energy adaptive clustering hierarchical (LEACH) protocol has been widely recognized as one of the prominent solutions for clustering WSNs. However, the random selection of cluster heads in each round under the LEACH protocol fails to guarantee proper convergence. To overcome this limitation, this paper proposes a refined approach by utilizing a genetic algorithm and a novel objective function that incorporates various factors, including energy level and distance. The algorithm employs chromosomes to represent CHs and facilitates the selection of cluster nodes. Notably, the proposed algorithm dynamically performs clustering, meaning that clustering is conducted iteratively, considering identifying dead nodes. By leveraging this approach, the algorithm significantly enhances the clustering quality, ultimately leading to an increased network lifetime. To validate its effectiveness, it is compared with LEACH, LEACH_E and LEACH_EX algorithms, demonstrating its superior capabilities. On average, the proposed algorithm has more alive nodes in the network, and the remaining energy is at least 11% higher than the best other algorithms.

Today, with the growth of the population and increasing trend in the use of electrical energy, the importance of the reliability and stability of the power grid has increased. The ever-increasing development of the power grid and subsequent blackouts of the power grid can lead to serious problems in the daily life and economy of a country. In addition to economic damages, power losses in the power network can lead to dissatisfaction and decreased consumer confidence in the power grid. This research has been carried out to check the application of the genetic algorithm to calculate reliability indices including SAIFI, SAIDI, etc., and its impact on enhancing the reliability of the standard IEEE 33 and 69 bus distribution networks. Additionally, this study explores the GA effectiveness in minimizing both active and reactive power losses. The simulation results in MATLAB, show the constructive effect of applying the GA, shedding light on its potential to optimize the distribution network reliability and minimize power losses, offering valuable insights for power system optimization and reliability improvement.

The wide area measurement system (WAMS) consists of two different measuring and communication infrastructures, which is respectively responsible for measuring power girds’ data in the wide area and sending and processing them in the control centers. The design of WAMS can include the design of each of its infrastructures or target both infrastructures at the same time, the latter has been known as the WAMS comprehensive design. The WAMS comprehensive design means the simultaneous placement of measurement components and its required communication, which is known as minimum connected dominating set (MCDS) problem in graph theory and is formulated in the form of an optimization problem. Solving such a complex optimization problem is often done with evolutionary algorithms (e.g. genetic algorithm and ant colony), and the speed and efficiency of finding the solution has always been a challenge. This research proposes an adaptive genetic algorithm known as the Adam and Eve algorithm, which has the ability to solve the MCDS problem that arises from the WAMS comprehensive design. Through simulation results for IEEE 1354 bus network, we demonstrate that proposed algorithm is well-tuned to solved MCDS related to the power graphs. It is 30% faster than simple genetic algorithm, handles large-scale problems effectively, and outperforms both simple genetic algorithm and ant colony algorithm within a given timeframe.

The importance of employing appropriate pricing strategies for perishable products within the supply chain cannot be overstated. Pricing is a cross-functional driver of each supply chain, playing an irrefutable role in the success and profitability of the supply chain alongside other factors such as inventory and production policies which has been investigated in this research. The research emphasizes the significant role of pricing in profitability, along with the interplay of production policies and inventory control, highlighting their collective influence on financial outcomes, the subject of dynamic pricing within a multi-product, multi-period problem in a three-level supply chain with perishable products has garnered relatively limited attention. The study focuses on optimizing an integrated production-distribution system with multiple producers and distribution centers serving specific customer groups. Direct shipments between production centers, distribution centers, and retailers are optimized using a vehicle routing problem approach. A mixed-integer programming model is formulated, and a genetic algorithm-based metaheuristic approach is proposed. The BARON solver was initially used to solve two simplified test problems, with results compared to a self-designed genetic algorithm implemented in C#. After confirming the efficiency and effectiveness of our genetic algorithm (GA), the investigation is further extended to encompass five distinct problems, each comprising nine sub-problems. The GA demonstrates its power and adaptability by providing high-quality solutions efficiently within a reasonable computational time.

In this article, equipment overhaul is considered in a multi-stage flow shop scheduling problem. In this problem, the equipments are disassembled in the first stage, overhaul and repairs are done on the equipment in parallel workshops in the second stage, and the assembly operation is done in parallel workshops in the third stage. Considering a three-stage overhaul with parallel machines in the second and third stages is new in the overhaul industry. The sequence of equipment processing is determined in the first stage, as well as the allocation and sequence of equipment in the second and third stages should be done in such a way that the total completion time of jobs is minimized. Unlike most articles, the sequence of processing jobs is not the same in all stages and changes with the use of decoding. For the next innovation: in order to solve the problem, a new mathematical model is presented. Two new improved algorithms, Genetic Algorithms (GA) and Particle Swarm Optimization (PSO) are presented to solve the problem in large dimensions. By using the shortest processing time (SPT) heuristic, these two algorithm have been improved and Hybrid GA (HGA) and Hybrid PSO (HPSO) algorithms have been presented. In order to achieve better results with the current conditions, the parameters setting is done by one-way analysis of variance (ANOVA). Finally, it is possible to improve the performance of the equipment by applying the discussed issues.

In image processing, compression plays an important role in monitoring, controlling, and securing the process. The spatial resolution is one of the most effective factors in improving the quality of an image; but, it increases the amount of storage memory required. Based on meta-heuristic algorithms, this article presents a compression model for face images with block division and variable bit allocation. Wavelet transform is used to reduce the dimensions of high spatial resolution face images. In order to identify important and similar areas of identical macroblocks, genetic algorithms and gray wolves are used. A bit rate allocation is calculated for each block to achieve the best recognition accuracy, average PSNR, and SSIM. The CIE and FEI databases have been used as case studies. The proposed method has been tested and compared with the accuracy of image recognition under uncompressed conditions and using the common SPIHT and JPEG coding methods. Recognition accuracy increased from 0.18% for 16×16 blocks to 1.97% for 32×32 blocks. Additionally, the gray wolf algorithm is much faster than the genetic algorithm in reaching the optimal answer. Depending on the application type of the problem, the genetic algorithm or the gray wolf may be preferred to achieve the maximum average PSNR or SSIM. At the bit rate of 0.9, the maximum average PSNR for the gray wolf algorithm is 34.92 and the maximum average SSIM for the genetic algorithm is 0.936. Simulation results indicate that the mentioned algorithms increase PSNR and SSIM by stabilizing or increasing recognition accuracy.

Cash transfer from the central treasury to the bank branches and automated teller machines (ATMs) all over the city is one of the vital processes in a banking system. There are multiple factors (e.g., location of the treasury, transportation fleet, geographic distribution of the branches and ATMs, the demand for cash, customer satisfaction, and traffic that influence the efficiency of the cash transfer). Moreover, environmental issues, and in particular the issue of greenhouse gas (GHG) emissions are given weight. In this paper, a new mathematical model for a location-routing problem with transport vehicles in the banking system is developed based on urban traffic in such a way that three objectives of decreasing greenhouse emissions, reducing location and routing costs, and increasing customer satisfaction are taken into consideration simultaneously. Furthermore, a new multi-objective genetic algorithm hybridized with a PROMETHEE method, namely the multi-objective genetic-PROMETHEE algorithm (MOGPA), is developed to tackle the proposed model. The efficiency of the proposed algorithm is examined by comparing it with the non-dominated sorting genetic algorithm (NSGA-II) and multi-objective imperialist competitive algorithm (MOICA) for the real-case issue of Saman Bank. Because management assumptions are considered in the preference functions of the proposed algorithm, the results show that the solutions of the proposed algorithm are more efficient and closer to reality.

Nowadays, the Permanent Magnet (PM) generator has become an instrumental tool for wind power generation due to its high performance. In this study, an optimal design is established to provide a cost-effective multiphase outer-rotor PM wind generator (OR-PMWG). The cost of the generation system (generator and power converter) as well as the annual energy output must be optimized to ensure cost-effective PM wind generation. In fact, the main novelty of this paper lies in the presentation of an accurate model of OR-PMWG and the investigation of the design variables affecting annual energy output and the generation system cost (GSC). In this respect, a multi-objective framework is presented to make satisfactory agreement among all objectives. At first, the main optimal design objectives namely generation system cost and annual energy output are optimized separately and then, a multi-objective optimization is established, in which all the objectives are considered simultaneously. In order to tackle these optimization problems, Genetic Algorithm (GA) is adopted herein to determine the design variables. It is also shown that simultaneous optimization with 71.39 (MWh) AEO and 2651.51 (US$) GSC leads to a more optimal design for a PM wind generation system. In addition, the effectiveness of the presented optimal design is demonstrated by making a comparison between a prototype outer-rotor PM wind generator and the theoretical counterpart. Finally, a finite element analysis (FEA) is carried out for the validation of the outcomes obtained from the proposed optimal design.

The surface quality of the industrial samples is one of the important factors in manufacturing industry, especially in drilling processes. It is well-known that ultrasonic vibrations can help to improve surface roughness and elimi-nate the pleat in drilled holes. The use of ultrasonic waves in the machining process also increases the dimensional accuracy of the produced pieces. In this study, the effect of few parameters including rotational speed, feed speed and amplitude of the vibration on the roughness of the drilled walls in the process of drilling with the aid of ultra-sonic vibration was performed on Al/SiC composite material. Based on the experimental data, the fitness function was designed and modeled and using the genetic algorithm technique, optimal machining variables were obtained to improve the surface finish of the machined work piece. The results showed that by increasing the amplitude of the vibration and the rotational speed of the tool, a smoother surface can be achieved. The results obtained from the genetic algorithm as well as the experiments showed the ability of the genetic algorithm technique to optimize the machining process of the aluminum silicon carbide composite.

In this study, the design of a nanofluid driven shell and tube heat exchanger is optimized, for the first time, by use of three multi objective algorithms. Two different operating conditions are investigated to compare the performance of the algorithms based on an economic model (cost function). Based on the obtained results, the Genetic, Particle Swarm and Jaya optimization algorithms can all improve the design. The amount of design improvement by each method is 9.66%, 10.63% and 10.9% respectively. Also from the view point of optimization time, Jaya optimization algorithm has relatively less CPU time than the other two algorithms, which in fact, reduces computational costs in complicated computations. Finally, due to the good performance of Jaya optimization algorithm in comparison with other considered algorithms, the performance of the heat exchangers is evaluated for using Ag, TiO2 and Al2O3 nanofluids of 0.5% to 5 vol.% by this algorithm. A performance evaluation factor (PE) is introduced as the criterion for simultaneous investigation of thermal and hydraulic performance of nanofluids. The results show that silver nanofluid, among other ones has better performance.

Optimum design of sound absorbers with optimum thickness and maximum sound absorption has always been an important issue to noise control. The purpose of this paper is an achievement of optimum design for micro-perforated panel (MPP) and its combination with a porous material and air gap to obtain maximum sound absorption with maximum overall thickness up to about 10 cm in the frequency range of (20-500 Hz), (500-2000 Hz) and (2000-10000 Hz). For this purpose, the genetic algorithm is proposed as an effective technique to solve the optimization problem. By using the precise theoretical models (i.e. simplified Allard's model and Atalla et al.’s model) to calculate the acoustic characteristics of each layer consisting of MPP, porous material, and airgap, we obtained more precise optimized structures. The transfer matrix method has been used to investigate the sound absorption of structures. To verify the operation of the programmed genetic algorithm, the results obtained from the optimization of the MPP absorber are compared with others that show the accuracy and efficiency of this method. After ensuring the accuracy of the proposed programmed genetic algorithm with more precise theoretical models to achieve the characteristics of each layer, new structures were obtained that have a much better sound absorption coefficient in the desired frequency range than the previous structures. The results show that the sound absorption coefficient can be reached to 0.67, 0.96, and 0.96 in the mentioned first, second, and third frequency range, respectively by optimum design parameter choosing of a composite structure.

This research looks at how photovoltaic (PV) cells generate energy in different weather conditions. Photovoltaic power today plays a key role in the production of energy and satisfying the needs of consumers all over the world. The PV cell's ability to generate electricity was entirely dependent on sunshine and temperature fluctuations in the environment. Several researchers are working on a variety of MPPT methods for a photovoltaic system. Outdated MPPT techniques are unable to withstand a dramatic change in weather conditions. The fundamental purpose of this study is to associate the numerous unadventurous and clever controllers for MPPT of the PV system, such as the PSO, GA, and CNFF. The MATLAB environment was used to create and simulate the recommended intelligent controller for MPPT in the PV system. Furthermore, the aforementioned findings like Voltage, Current and Power with respect to different irradiance and temperature are compared and evaluated. The performance of the above-mentioned topologies has been related to the optimum intelligent controller for the PV system and concluded that the CFFNN gives better efficiency with minimum time required to extract.

Deciphering the crucial interactions among genes is one of the key issues in understanding the fundamental molecular and intracellular mechanisms of cell. Computational modeling of gene regulatory networks can be used as a powerful tool in various fields of molecular biomedicine such as identification of metabolic, regulator, and signal transduction pathways, analysis of complex genetic diseases, and drug discovery. In this paper, an optimal Boolean approach is proposed for computational modeling of gene regulatory networks from temporal gene expression profile. In this method, the optimal values of the Boolean thresholds of gene expression signals and the parameters of the interaction patterns between target and regulator genes are all designed as a mixed-integer nonlinear programming solved by Genetic Algorithm. To evaluate the performance of the proposed scheme, it has been applied to a well-known time course microarray data and gene regulatory network of Saccharomyces Cerevisiae from the literature. The reference network has 11 genes, 9 targets, and 61 regulatory interactions, and the original transcriptional dataset includes 18 timepoints for each gene expression signal. In this case study, the proposed computational model contains 142 unknown parameters that are optimally determined through optimization. The results demonstrate the efficiency of the proposed approach.

A novel Halbach permanent magnet array with rectangle section and trapezoid section is proposed and optimized in this paper. The analytical model of the premanent magnet segment is established based on the surface current method, which is numerically efficient and can be utilized to evaluate the magnetic field closely with the premanent magnet segment’s configurations. The analytical model of the Halbach array is acquired based on the superposition principle and coordinate transformation. The fundamental component of the magnetic flux density and the sinusoidal distortion rate are chosen as the optimization object. And the optimization is executed on the Halbach array with one specific set of dimensions by the genetic algorithm in global scale. The effectiveness of the optimization is validated by the finite element analysis. Compared to the traditional Halbach array with rectangle section, the magnetic field created by the optimized proposed Halbach array in this paper owns better performance.