FIGURE 1 - uploaded by Ali M. El-Rifaie
Content may be subject to copyright.
Source publication
Proton Exchange Membrane Fuel Cells (PEMFC) is considered a propitious solution for an environmentally friendly energy source. A precise model of PEMFC for accurate identification of its polarization curve and an in-depth understanding of all its operating characteristics attracted the interest of many researchers. In this paper, recent meta-heuris...
Contexts in source publication
Context 1
... cells are considered a direct method of converting chemical energy into electrical energy. The construction of a typical proton exchange membrane (PEM) fuel cell is described in Fig. 1. As seen from the figure, the PEM fuel cell model comprises two electrodes (anode and cathode), between which a catalyst and membrane layers are stacked. In addition, at the anode and cathode sides, two channels are used for supplying hydrogen and air, which will be diffused through the ...
Context 2
... simulation tests have been done to test and evaluate the robustness of the MPA and PO optimization techniques with this case of study. The MPA and PO have been applied for 30 runs. The convergence curves of the 30 runs have been shown in Fig. 10 for both algorithms. The figure shows that the MPA has the ability to reach the same best solution over 30 runs while figure10.b) shows the PO algorithm reaches to different values of the best solution in the number of runs. This concludes that the MPA is the best choice for estimating the parameters of the PEMFC ...
Context 3
... results of the characteristics of SR-12PEM 500 W based on the estimated parameters using MPA and PO and the experimental data have been shown in Fig. 11.a). The figure shows that the obtained characteristics from the proposed MPA optimization algorithm introduce a high matching degree with the experimental data. Furthermore, the squared error between the measured voltages and the estimated based on MPA and Po algorithms have been illustrated in figure 11.b) and table 7. Moreover, due to ...
Context 4
... figure shows that the obtained characteristics from the proposed MPA optimization algorithm introduce a high matching degree with the experimental data. Furthermore, the squared error between the measured voltages and the estimated based on MPA and Po algorithms have been illustrated in figure 11.b) and table 7. ...
Context 5
... more validating, the estimated model based on the MPA is used for plotting the characteristics at different operating conditions such as the variation of temperature and pressure, as shown in Fig. ...
Context 6
... order to analyze the convergence characteristics of the two algorithms, the convergence curves of the PO and MPA algorithms via iterations have been shown in Fig. 13. The figure shows that the MPA has a better convergence speed of solving the optimization problem compared with the PO ...
Context 7
... time, the robustness and probability of finding the optimal answer by the MPA and PO algorithms have been tested by finding the best solution of 30 independent runs. The results of these runs have been shown in Fig. 14. Figure 14.a) proves the robustness of the MPA optimization algorithm for finding the best parameters of the PEMFC model. While figure 14.b) shows the results of PO algorithm which confirms the results have been varied each run around the best ...
Context 8
... time, the robustness and probability of finding the optimal answer by the MPA and PO algorithms have been tested by finding the best solution of 30 independent runs. The results of these runs have been shown in Fig. 14. Figure 14.a) proves the robustness of the MPA optimization algorithm for finding the best parameters of the PEMFC model. ...
Context 9
... results of these runs have been shown in Fig. 14. Figure 14.a) proves the robustness of the MPA optimization algorithm for finding the best parameters of the PEMFC model. While figure 14.b) shows the results of PO algorithm which confirms the results have been varied each run around the best one. ...
Context 10
... validation of the results has been proved by plotting the voltage and power characteristics versus the current for both models of MPA and PO, as shown in Fig. 15. From the figure, the precise matching between the estimated characteristics and the experimental data of the fuel cell can be easily investigated. Table 10 shows the squared error between the estimated and measured performance of 250 W stack based on PO and MPA. Furthermore, Table 11 shows the statistical measurement of the planned ...
Context 11
... the planned MPA and PO methods for 250 W stack based on 30 individual runs. The statistical results prove that the both algorithms of MPA and PO have robust performance with consideration of superiority of the MPA algorithm. Furthermore, the characteristics of the module with the variation of the temperature and pressure have been shown through Fig. ...
Similar publications
Estimating the parameters of solar photovoltaic (PV) panels is crucial for effectively managing operations in solar-based microgrids. Various techniques have been developed for this purpose, and one accurate approach is solar cell modeling using metaheuristic algorithms from current-voltage (I-V) data of the PV panel. However, this method relies on...
Citations
... Researchers have continuously explored novel approaches to enhance the performance and reliability of PEMFCs. For instance, the hybrid marine predator optimizer (MPO) and political optimizer (PO) [33], cooperative barebone PSO [34], improved chaotic gray wolf optimization (GWO) [35], TLBO-DE based on Elman Neural Network [36], shuffled multisimplexes search algorithm [37], bonobo optimizer [38], hybridized bee colony-DE algorithm [39], gorilla troops algorithm [4], and crow search optimizer [40] are among the recent optimization algorithms that have been proposed. ...
Fuel cells (FCs) have garnered significant attention due to their versatile applications, but their nonlinear characteristics pose challenges in the modeling process. This research presents a unique enhanced artificial hummingbird algorithm (EAHA) aimed at identifying the seven unknown parameters of the proton exchange membrane fuel cells (PEMFCs) stack by utilizing their experimental datasets. To accomplish this, the objective is to achieve accurate current/voltage (I/V) curves where a cost function is defined using the aggregation of quadratic deviations (AQD) between the measured dataset points and the appropriate model-based estimations. The presented EAHA combines several territorial foraging techniques with a linear regulating mechanism. The performance of the conventional AHA is compared with the suggested EAHA using three commonly employed PEMFC modules. Furthermore, a comparative analysis is conducted against previously published methodologies and newly developed optimizers such as the equilibrium optimizer (EO), social networking search (SNS) technique, slim mold algorithm (SMA), heap-based optimizer (HBO), and African vultures optimization (AVO) technique. The findings are compared to existing methodologies and other state-of-the-art optimizers, providing valuable insights into the efficacy of the proposed approach. For the 250 W PEMFC stack, the proposed EAHA shows improvements of 2.966%, 6.493%, 1.491%, 7.080%, 1.131%, and 2.875% over AHA, AVO, EO, HBO, SMA, and SNS, respectively, depending on the mean AQD values. Similar findings are attained for the other two stacks. For example, for the test case of the BCS 500 W PEMFCs stack, the proposed EAHA demonstrates improvements of 64.228%, 82.859%, 66.140%, 81.156%, 46.302%, and 71.635% over AHA, AVO, EO, HBO, SMA, and SNS, respectively.
... It performs favorably compared to various competitive algorithms and provides high-quality solutions for many optimization problems. Therefore, with the help of MPA's innovative and unique mechanism, many scholars have successfully addressed specific real-world optimization issues, mainly including feature selection [29], image segmentation [30], parameter estimation [31], and practical engineering problems [32][33][34]. Compared with existing advanced metaheuristic algorithms, MPA has a strong core competitiveness in addressing real-world problems. ...
... It performs favorably compared to various competitive algorithms and provides high-quality solutions for many optimization problems. Therefore, with the help of MPA's innovative and unique mechanism, many scholars have successfully addressed specific real-world optimization issues, mainly including feature selection [29], image segmentation [30], parameter estimation [31], and practical engineering problems [32][33][34]. Compared with existing advanced metaheuristic algorithms, MPA has a strong core competitiveness in addressing real-world problems. ...
Given the weak convergence, limited balance capacity, and optimization limitations observed in the Marine Predators Algorithm (MPA), which draws inspiration from the predatory behavior of marine organisms during evolutionary processes, this study introduces a Reinforcement Learning Marine Predators Algorithm (RLMPA). Firstly, based on the predatory characteristics at different stages, we have designed three location update strategies for search agents aimed at creating high-quality candidate solutions from three perspectives. In particular, ranking paired mutually beneficial learning is specifically designed to expand the scope of exploration to generate as many high-quality candidate solutions as possible for future generations. The Gaussian random walk learning is specifically designed to achieve better optimization in the transitional phase by adjusting the step-size control parameters, successfully completing the transition from exploration to local exploitation phase. Additionally, modified somersault foraging strategy is introduced to accelerate local convergence and perform more extensive local exploitation. Secondly, we integrate reinforcement learning into MPA and use Q-learning mechanism to adaptively select location update strategies. Agents fully utilize the collected information to evaluate the next action of the agents, coordinate the exploration phase and exploitation phase, and enhance the global optimization ability. Finally, compared with 10 competitive algorithms, RLMPA achieves better comprehensive performance in global optimization ability, search efficiency and convergence speed on 41 test functions and 5 practical engineering problems. In the Friedman rank sum tests, RLMPA achieves a preferable overall ranking, and has certain ascendant preponderances in solving practical problems with stability, effectiveness and robustness.
... PO process encompasses five unique phases: establishing the party and distributing constituencies, campaigning for elections, making changes to party policies, conducting legislative proceedings, and holding inter-party elections. By examining each of these stages in a multi-partypolitical system, the optimization algorithm and mathematical model develop new algorithms, allowing the framework to be scientifically demonstrated (Diab et al. 2020;Abdelhamid et al. 2020). ...
High-performance concrete (HPC) is extensively employed in the construction sector owing to its exceptional strength and durability. The mechanical characteristics of HPC, particularly its compressive and tensile strength, are vital indicators. Precise forecasts of concrete strength are essential for enhancing the design and performance of concrete structures. This study proposes a novel technique for predicting the strength of HPC. It involves utilizing the least square support vector regression (LSSVR) algorithm in combination with three optimizers: Gold Rush Optimizer, Political Optimizer, and Golden Sine Algorithm. LSSVR algorithm is a robust machine-learning method that has demonstrated favorable outcomes in numerous forecasting tasks. The use of LSSVR enables the accurate modeling and prediction of the intricate connection between the strongest attributes of HPC and the variables that impact it. To achieve this goal, a dataset containing 344 samples of high-performance concrete was gathered and utilized to train and assess the LSSVR algorithm. However, selecting appropriate optimization algorithms is critical for improving prediction accuracy and accelerating convergence speed. The proposed framework's performance is evaluated using actual strength data from HPC by conducting thorough experimentation and comparative analysis. The findings reveal that integrating LSSVR with the mentioned optimizers surpasses conventional optimization methods in prediction convergence speed and accuracy. The proposed framework offers a dependable and efficient solution for precisely predicting HPC strength, allowing engineers and researchers to optimize the design and construction of high-performance concrete structures.
... In [42], a new HGWO approach for identifying the UMPs was presented by combining GWO with crossover and mutation operators to enhance searchability and avoid local optima. Recently, the Political Optimizer (PO) and the Marine Predators Algorithm (MPA) were applied to the unknown parameters of PEMFCs [43]. These two algorithms were empirically evaluated using three commercial PEMFCs and compared with some rival optimizers. ...
... This section is presented to assess the performance of the proposed RGTO for estimating the parameters of PEMFCs as an additional application in engineering. Seven well-known metaheuristic algorithms in addition to the classical GTO are herein employed to be compared with the proposed RGTO to show its effectiveness for tackling this problem, including SMA [39], ISA, artificial ecosystem-based optimization (AEO) [44], moth-flame optimizer (MFO) [44], differential evolution (DE) [23], MPA [43], salp swarm algorithm (SSA) [44], and GTO. All of the aforementioned methods have been tested on the performance of six widely used PEMFCs stuck modules: 500 W Stack [83], 250 W Stack [83], NedStack PS6 [83], Ballard Mark V5 [83], H-12 Stack [83], and Avista SR-12 [83]. ...
... The mathematical model of this cell, described in detail in [136], involves seven unknown parameters (ξ 1 , ξ 2 , ξ 3 , ξ 4 , λ, R c , and β) that need to be accurately estimated to maximize its performance. The compared algorithms involve interior search algorithm (ISA) [137], artificial ecosystem-based optimization (AEO) [136], moth-flame optimizer (MFO) [136], SMA [138], differential evolution (DE) [139], salp swarm algorithm (SSA) [136], WOA [69], cnEpSin, and MPA [140]. All those algorithms are validated using four well-known commercial PEMFC stacks, including 500 W stack [141], Ballard Mark V5 [141], 250 W stack [141], and Avista SR-12 [141], under the same parameters recommended in the published papers, with the exception of the population size and the maximum number of function evaluations, which are set to 15 and 3000 to ensure a fair comparison. ...
This study presents a new nature-inspired optimization algorithm, namely the Mantis Search Algorithm (MSA), inspired by the unique hunting behavior and sexual cannibalism of praying mantises. In brief, MSA consists of three optimization stages, including the search for prey (exploration), attack prey (exploitation), and sexual cannibalism. Those operators are simulated using various mathematical models to effectively tackle optimization challenges across diverse search spaces. The performance of MSA is rigorously tested on fifty-two optimization problems and three real-world applications (five engineering design problems, and the parameter estimation problem of photovoltaic modules and fuel cells) to show its versatility and adaptability to different scenarios. To disclose the MSA’s superiority, it is compared to two categories from the rival optimizers: the first category involves well-established and highly-cited optimizers, like Differential evolution; and the second category contains recently-published algorithms, like African Vultures Optimization Algorithm. This comparison is conducted using several performance metrics, the Wilcoxon rank-sum test and the Friedman mean rank to disclose the MSA’s effectiveness and efficiency. The results of this comparison highlight the effectiveness of this new approach and its potential for future optimization applications. The source codes of the MSA algorithm are publicly available at https://www.mathworks.com/matlabcentral/fileexchange/131833-mantis-search-algorithm-msa.
... The mathematical model of this cell, described in detail in [136], involves seven unknown parameters (ξ 1 , ξ 2 , ξ 3 , ξ 4 , λ, R c , and β) that need to be accurately estimated to maximize its performance. The compared algorithms involve interior search algorithm (ISA) [137], artificial ecosystem-based optimization (AEO) [136], moth-flame optimizer (MFO) [136], SMA [138], differential evolution (DE) [139], salp swarm algorithm (SSA) [136], WOA [69], cnEpSin, and MPA [140]. All those algorithms are validated using four well-known commercial PEMFC stacks, including 500 W stack [141], Ballard Mark V5 [141], 250 W stack [141], and Avista SR-12 [141], under the same parameters recommended in the published papers, with the exception of the population size and the maximum number of function evaluations, which are set to 15 and 3000 to ensure a fair comparison. ...
This study presents a new nature-inspired optimization algorithm, namely the Mantis Search Algorithm (MSA), inspired by the unique hunting behavior and sexual cannibalism of praying mantises. In brief, MSA consists of three optimization stages, including the search for prey (exploration), attack prey (exploitation), and sexual cannibalism. Those operators are simulated using various mathematical models to effectively tackle optimization challenges across diverse search spaces. The performance of MSA is rigorously tested on fifty-two optimization problems and three real-world applications (five engineering design problems, and the parameter estimation problem of photovoltaic modules and fuel cells) to show its versatility and adaptability to different scenarios. To disclose the MSA’s superiority, it is compared to two categories from the rival optimizers: the first category involves well-established and highly-cited optimizers, like Differential evolution; and the second category contains recently-published algorithms, like African Vultures Optimization Algorithm. This comparison is conducted using several performance metrics, the Wilcoxon rank-sum test and the Friedman mean rank to disclose the MSA’s effectiveness and efficiency. The results of this comparison highlight the effectiveness of this new approach and its potential for future optimization applications.
... Modified artificial ecosystem optimisers coupled with the LSHADE-EpSin optimisers have all been experimented as suitable options in terms of parametric investigation into unknown parameters for fuel cell estimation [19]. A marine predator optimiser as well as political optimisers have also been reported [20]. Similarly improved fluid search optimisers [21] have also been presented as most ideal in estimating the unknown parameters of the cell. ...
... Accordingly, after constructing a reliable Energies 2023, 16,4743 11 of 16 fuzzy model, the AEO is applied to define the optimum values for the input parameters. The argument of objective function can be stated by (20). ...
... Accordingly, after constructing a reliable fuzzy model, the AEO is applied to define the optimum values for the input parameters. The argument of objective function can be stated by (20). ...
The main target is the maximization of the output power of PEM “proton exchange membrane” fuel cell via fuzzy modelling and optimization. In the beginning, using the experimental data, a robust fuzzy model is designed for simulating the PEM fuel cell using the relative humidity (%) and stoichiometric ratio at the anode and cathode. Then, the artificial ecosystem optimiser (AEO) is applied to determine the best values of the controlling input parameters. During the optimization process, the four controlling input parameters of the PEMFC are used as the decision variables, whereas as the cost function is required to be at the maximum of the output power density of the PEMFC. For the fuzzy model of the power, the RMSE values are 1.5588 and 3.1906, respectively, for training and testing data. The coefficient of determination values are 0.9826 and 0.8743 for training and testing, respectively. This confirms a successful modelling phase. Finally, the integration between fuzzy and AEO boosted the power of the PEMFC from 57.95 W to 78.44 W (by around 35%). Under this optimal condition, the controlling input parameters values are 26.65%, 56.77%, 1.14, and 1.68, respectively, for anode relative humidity, cathode relative humidity, anode stoichiometric ratio and cathode stoichiometric ratio. The present study, however, intends to highlight the importance of fuzzy modelling and metaheuristic algorithms in the development of digital twins to accelerate the commercialization of fuel cells as well as its applicability in diverse global economic sectors where a higher power requirement is needed. It is also aimed at informing the fuel cell research community and policy makers on strategies that could be adopted in boosting fuel cell performance and therefore could be a good reference source in decision-making for fuel cell commercialization and its practical implementation.
... Adapun Persentase perhitungan yang dihasilkan akan digunakan sebagai pembanding antara jumlah cluster [9]. Adapun rumus SSE adalah [17]: ...
Pusintek merupakan unit pengelola tugas dan fungsi terkait TIK di instansi pemerintahan di Indonesia. Salah satu tugasnya berkaitan dengan fungsi penanganan gangguan TIK yang dilaporkan oleh Unit Pengguna. Pencatatan gangguan TIK menggunakan sistem pencatatan layanan dan gangguan berbasis Customer Relationship Management (CRM). Tujuan dari penelitian ini adalah untuk mengelompokkan jumlah laporan gangguan pada Unit Pelapor dan membantu divisi teknis dalam menganalisis seberapa sering gangguan yang dilaporkan tiap unit dan kategori gangguannya sehingga divisi teknis dapat merencanakan dan mempersiapkan pengambilan keputusan terkait tindak lanjut penyelesaian gangguan TIK pada instansi Unit Pelapor. Metode Elbow dignakan dalam proses penentuan jumlah cluster gangguan yang optimal. Pengujian dilakukan dengan membagi data gangguan TIK dan menghitung cluster distance performance sampai dengan 7 cluster. Tools yang digunakan untuk pengujian menggunakan Rapidminer. Hasil pengujian memperlihatkan bahwa penggunaan k=3 akan menghasilkan cluster yang optimal untuk metode K-Means Clustering dan Elbow, dengan nilai Average Centroid Distance sebesar 69110.233 dan nilai Davies Bouldin sebesar 0.458. Abstract Pusintek is a task and function management unit related to ICT in government agencies in Indonesia. One of its duties relates to the function of handling ICT disturbances reported by the User Unit. The recording of ICT disturbances uses a Customer Relationship Management (CRM) based service and disturbance recording system. The purpose of this study is to classify the number of disturbance reports in the Reporting Unit and assist the technical division in analyzing how often disturbances are reported for each unit and the disturbance category so that the technical division can plan and prepare for decision-making related to the follow-up of ICT disturbance resolution at the Reporting Unit agency. The Elbow method is used in the process of determining the optimal number of disturbance clusters. The test was carried out by dividing the ICT interference data and calculating the cluster distance performance of up to 7 clusters. The tools used for testing use Rapidminer. The test results show that using k = 3 will produce optimal clusters for the K-Means Clustering and Elbow method, with an Average Centroid Distance value of 69110.233 and a Davies Bouldin value of 0.458.
... Hybrid Marine Predators-Slime Mould Algorithm [195] HMPA 14 Marine Predators and Political Optimizers [196] MPA- PO 15 Integrating Marine Predators Algorithm and Particle Swarm Optimization [197] MPA- PSO 16 Improved Marine Predators Algorithm and Particle Swarm Optimization [198] Fig. 7. The citations as per Google scholar for different revised variants of MPA belonging to different categories is portrayed in Fig. 8. ...
Marine Predators Algorithm (MPA) is the existing population-based meta-heuristic algorithms that falls under the category of Nature-Inspired Optimization Algorithm (NIOA) enthused by the foraging actions of the marine predators that principally pursues Levy or Brownian approach as its foraging strategy. Furthermore, it employs the optimal encounter rate stratagem involving both the predator as well as prey. Since its introduction by Faramarzi in the year 2020, MPA has gained enormous popularity and has been employed in numerous application areas ranging from Mathematical and Engineering Optimization problems to Fog Computing to Image Processing to Photovoltaic System to Wind-Solar Generation System for resolving continuous optimization problems. Such huge interest from the research fraternity or the massive recognition of MPA is due to several factors such as its simplicity, ease of application, realistic execution time, superior convergence acceleration rate, soaring effectiveness, its ability to unravel continuous, multi-objective and binary problems when compared with other renowned optimization algorithms existing in the literature. This paper offers a detailed summary of the Marine Predators Algorithm (MPA) and its variants. Furthermore, the applications of MPA in a number of spheres such as Image processing, classification, electrical power system, Photovoltaic models, structural damage detection, distribution networks, engineering applications, Task Scheduling, optimization problems etc., are illustrated. To conclude, the paper highlights and thereby advocates few of the potential future research directions for MPA.
