Yazar "Tejani, Ghanshyam G." seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Application of the 2-archive multi-objective cuckoo search algorithm for structure optimization
    (Nature Portfolio, 2024) Tejani, Ghanshyam G.; Mashru, Nikunj; Patel, Pinank; Sharma, Sunil Kumar; Celik, Emre
    The study suggests a better multi-objective optimization method called 2-Archive Multi-Objective Cuckoo Search (MOCS2arc). It is then used to improve eight classical truss structures and six ZDT test functions. The optimization aims to minimize both mass and compliance simultaneously. MOCS2arc is an advanced version of the traditional Multi-Objective Cuckoo Search (MOCS) algorithm, enhanced through a dual archive strategy that significantly improves solution diversity and optimization performance. To evaluate the effectiveness of MOCS2arc, we conducted extensive comparisons with several established multi-objective optimization algorithms: MOSCA, MODA, MOWHO, MOMFO, MOMPA, NSGA-II, DEMO, and MOCS. Such a comparison has been made with various performance metrics to compare and benchmark the efficacy of the proposed algorithm. These metrics comprehensively assess the algorithms' abilities to generate diverse and optimal solutions. The statistical results demonstrate the superior performance of MOCS2arc, evidenced by enhanced diversity and optimal solutions. Additionally, Friedman's test & Wilcoxon's test corroborate the finding that MOCS2arc consistently delivers superior optimization results compared to others. The results show that MOCS2arc is a highly effective improved algorithm for multi-objective truss structure optimization, offering significant and promising improvements over existing methods.
  • Küçük Resim Yok
    Öğe
    MOPDO: a multi-objective prairie dog optimizer for engineering design problems
    (Springer Heidelberg, 2025) Tejani, Ghanshyam G.; Kumar, Sumit; Mehta, Pranav; Jangir, Pradeep; Celik, Emre
    This research introduces a novel multi-objective version of the recently proposed prairie dog optimizer, the multi-objective prairie dog optimizer (MOPDO). Inspired by the foraging and burrowing activities of prairie dogs, which entail search exploration and particular responses to distinctive alarms for exploitation, MOPDO is proposed. This is a Pareto dominance-based approach to a modified and enhanced version of its single objective counterpart. MOPDO is able to deal with multiple objectives, explore, and exploit promising regions in the optimization landscape, and identify non-dominated solutions, providing decision makers with valuable trade-off choices. To demonstrate its practical applicability, MOPDO is applied to tackle five challenging structural design problems, each characterized by two conflicting objectives: two objectives, minimizing structure weight and minimizing maximum nodal displacement. The algorithm is compared against two other state-of-the-art multi-objective algorithms and rigorous evaluation is conducted using Hypervolume testing. The results show that MOPDO performs better than the comparison algorithms and is able to find a diverse set of non-dominated solutions. Statistical analysis of the experimental results using Friedman's rank test is conducted to further investigate the experimental results. MOPDO's solutions and convergence behaviour show that MOPDO is a very efficient method to solve complex design problems and is superior to the existing multi-objective algorithms in terms of effectiveness and efficiency.
  • Küçük Resim Yok
    Öğe
    Novel distance-fitness learning scheme for ameliorating metaheuristic optimization
    (Elsevier - Division Reed Elsevier India Pvt Ltd, 2025) Celik, Emre; Houssein, Essam H.; Abdel-Salam, Mahmoud; Oliva, Diego; Tejani, Ghanshyam G.; Ozturk, Nihat; Sharma, Sunil Kumar
    An important portion of metaheuristic algorithms is guided by the fittest solution obtained so far. Searching around the fittest solution is beneficial for speeding up convergence, but it is detrimental considering local minima stagnation and premature convergence. A novel distance-fitness learning (DFL) scheme that provides better searchability and greater diversity is proposed to resolve these. The method allows search agents in the population to actively learn from the fittest solution, the worst solution, and an optimum distance-fitness (ODF) candidate. This way, it aims at approaching both the fittest solution and ODF candidate while at the same time moving away from the worst solution. The effectiveness of our proposal is evaluated by integrating it with the reptile search algorithm (RSA), which is an interesting algorithm that is simple to code but suffers from stagnating in local minima, converging too early, and a lack of sufficient global searchability. Empirical results from solving 23 standard benchmark functions, 10 Congresses on Evolutionary Computation (CEC) 2020 test functions, and 2 real-world engineering problems reveal that DFL boosts the capability of RSA significantly. Further, the comparison of DFL-RSA with popular algorithms vividly signifies the potential and superiority of the method over most of the problems in terms of solution precision.
  • Küçük Resim Yok
    Öğe
    Reconfigured single- and double-diode models for improved modelling of solar cells/modules
    (Nature Portfolio, 2025) Celik, Emre; Karayel, Mehmet; Maden, Dincer; Abdel-Salam, Mahmoud; Ozturk, Nihat; Kaplan, Orhan; Tejani, Ghanshyam G.
    Proper modeling of PV cells/modules through parameter identification based on the real current-voltage (I-V) data is important for the efficiency of PV systems. Most related works have concentrated on the classical single-diode model (SDM) and double-diode model (DDM) and their parameter extraction by various metaheuristic algorithms. In order to render more accurate and representative modeling, this paper adds a small resistance in series with the diodes in SDM and DDM. The new models are named reconfigured SDM (Reconfig-SDM) and reconfigured DDM (Reconfig-DDM), and they have not been studied so far as we know. A squirrel search algorithm (SSA) is employed to globally find the parameters of the new models. The performance achieved is experimentally tested on both a commercial RTC France solar cell and a CS6P-220P polycrystalline PV module located at D & uuml;zce University in T & uuml;rkiye. A vivid comparison of experimental findings, observation, and analysis clearly demonstrates that the proposed Reconfig-SDM and Reconfig-DDM tuned by the SSA have better capacity and effectiveness for modeling PV devices than some cutting-edge approaches. Specifically, compared with the best-performing approach in the literature, Reconfig-SDM and Reconfig-DDM could reduce the error rate up to 0.37% and 2.58% for the solar cell, and 3.21% and 29.0% for the solar module.