This study presents a novel neighborhood centroid opposition-based flood algorithm (NCO-FLA) for optimizing fractional-order proportional-integral-derivative (FOPID) controllers aimed at precise temperature regulation in nonlinear shell-and-tube heat exchanger systems. By integrating opposition-based learning (OBL) and neighborhood centroid mechanisms into the conventional flood algorithm (FLA), the proposed NCO-FLA significantly improves global search efficiency and mitigates premature convergence in high-dimensional parameter spaces. The FOPID controller, with its five tunable parameters, provides a more flexible and robust framework than traditional PID structures, especially under nonlinear and dynamic conditions commonly encountered in industrial heat exchange processes. Extensive simulations conducted in MATLAB/ Simulink demonstrate that NCO-FLA outperforms benchmark metaheuristic algorithms, including the marine predators algorithm (MPA), reptile search algorithm (RSA), catch fish optimization algorithm (CFOA), and the original FLA as well as classical algorithms such as differential evolution (DE), particle swarm optimization (PSO), evolution strategy with covariance matrix adaptation (CMA-ES), DE variants with linear population size reduction (L-SHADE) and NCOPSO. Quantitative results show that he proposed NCO-FLA achieved 10-15 % lower ITAE values compared to the other optimizers, confirming its enhanced control accuracy and convergence stability. The proposed NCO-FLA also exhibited a smoother and faster convergence trend compared to other algorithms, as confirmed by the convergence profiles, and achieved the lowest standard deviation (0.9183), indicating superior consistency and reliability. Additionally, the NCO-FLA-tuned FOPID controller achieves zero overshoot, near-zero steady-state error, and significantly shorter rise (5.16 s) and settling times (19.05 s). Statistical significance was confirmed through Friedman and Wilcoxon signed-rank tests, as well as Mann-Whitney U test where all p-values were below 0.05, affirming the superiority and robustness of the proposed method. These findings underscore the algorithm's strong potential for real-world deployment in complex thermal systems where high accuracy, stability, and adaptive control are critical. The proposed NCO-FLA represents a promising advancement in metaheuristic optimization for industrial control systems. Future work will focus on integrating the algorithm with machine learning models and evaluating its performance in large-scale, real-time environments.

Accurate and energy-efficient temperature regulation in electric furnace systems remains a challenging control problem due to nonlinear dynamics, significant thermal inertia, and inevitable time delays. Conventional proportional-integral-derivative (PID) and PID-acceleration (PIDA) controllers, though widely used, often exhibit degraded performance under such conditions, particularly when implemented in a single-degree-of-freedom. To address these limitations, this study proposes, for the first time, a two-degree-of-freedom (2-DOF) PIDA controller tailored for electric furnace temperature control. The controller structure allows independent tuning of set-point tracking and disturbance rejection by introducing separate feedforward paths in the proportional and derivative channels while maintaining integral and acceleration actions on the error signal. To optimize the controller parameters, the recently developed greater cane rat algorithm (GCRA) is employed for the first time in this context. A novel adaptive objective function (combining normalized overshoot, normalized settling time, and cumulative tracking error) guides the tuning process to achieve a balanced improvement in both transient and steady-state performance. The proposed GCRA-based 2-DOF PIDA controller is evaluated through extensive simulations and compared against state-of-the-art metaheuristic tuning approaches, including polar fox optimization (PFA), hiking optimization (HOA), success-history based adaptive differential evolution with linear population size reduction (L-SHADE), and particle swarm optimization (PSO), as well as several benchmark furnace control methods. Results demonstrate that the proposed method consistently achieves faster settling times, reduced overshoot, and near-zero steady-state error, while maintaining robustness under external disturbances and measurement noise. For instance, in the nominal case, the method yields an overshoot of 1.8382% and a settling time of 3.4542 s, outperforming PFA, HOA, L-SHADE, and PSO. Robustness tests under load disturbances and measurement noise confirm stable operation with minimal performance degradation, achieving less than 2.5% overshoot and under 4 s settling time across all evaluated scenarios. These findings highlight the potential of the GCRA-based 2-DOF PIDA controller as a high-precision and energy-efficient solution for temperature regulation in industrial time-delay systems.

The objective of this paper is to enhance the swarm-based metaheuristic dandelion optimizer (DO) algorithm by incorporating various strategies to address early convergence and mitigate the risk of becoming trapped in local optima. This integration is intended to yield optimal and favorable outcomes for real-world optimization problems. To achieve this objective, a novel hybrid algorithm called the random walks dandelion optimizer (RW-DO) was introduced. This new algorithm addresses the limitations of the dandelion optimizer DO when handling optimization problems by incorporating at random walks strategy. By leveraging the random walks strategy, the RW-DO algorithm addresses the issue of premature convergence. This strategy enhances the diversity of solutions, thereby preventing the DO algorithm from becoming trapped in the local optima during the exploitation phase. To assess its performance, the RW-DO algorithm was compared with alternative algorithms by using the CEC 2020 and CEC 2019 function sets. Across all the test sets, the RW-DO algorithm consistently generateds more advantageous solutions. For the CEC 2020 function set, the RW-DO algorithm demonstrated superior performance compared with the DO algorithm from 3% to 11% in 5-dimensional problems. In 30-dimensional problems, the RW-DO algorithm exhibited superior performance compared to the DO algorithm from 14% to 46%. For the CEC 2020 function set in 50-dimensional problems, the RW-DO algorithm demonstrated superior performance compared to the DO algorithm from 11% to 188%. In the CEC 2019 function set, this ratio ranges from 3% to 38%. In engineering problems, the RW-DO algorithm also achieved superiority over the DO algorithm from 2% to 3%. Statistical analyses were performed to validate the superiority of RW-DO. The Kolmogorov-Smirnov normality test was used to select appropriate statistical tests for evaluating the performance of the algorithm based on the CEC 2020 and CEC 2019 function sets. Because the data set is not normally distributed, non-parametric tests such as the Wilcoxon signed-rank test and Kolmogorov-Smirnov for two sample tests were employed. These tests confirm that RW-DO yields distinct and superior solutions compared with the different data sets. Furthermore, the effectiveness of the RW-DO algorithm in solving real-world problems was demonstrated through its application to six engineering design problems. The experimental results highlight its competency in comparison to other algorithms. Overall, this research demonstrates the enhanced capabilities of the RW-DO algorithm in optimizing complex problems and its competitiveness when pitted against alternative methods.

This paper aims to enhance the success of the Wild Horse Optimization (WHO) algorithm in optimization processes by developing strategies to overcome the issues of stuckness and early convergence in local spaces. The performance change is observed through a Multi-Layer Perceptron (MLP) sample. In this context, an advanced Wild Horse Optimization (IWHO) algorithm with a random walking strategy was developed to provide solution diversity in local spaces using a random walking strategy. Two challenging test sets, CEC 2019, were selected for the performance measurement of IWHO. Its competitiveness with alternative algorithms was measured, showing that its performance was superior. This superiority is visually represented with convergence curves and box plots. The Wilcoxon signed-rank test was used to evaluate IWHO as a distinct and powerful algorithm. The IWHO algorithm was applied to MLP training, addressing a real-world problem. Both WHO and IWHO algorithms were tested using MSE results and ROC curves. The Energy Efficiency Problem dataset from UCI was used for MLP training. This dataset evaluates the heating load (HL) or cooling load (CL) factors by considering the input characteristics of smart buildings. The goal is to ensure that HL and CL factors are evaluated most efficiently through the use of HVAC technology in smart buildings. WHO and IWHO were selected to train the MLP architecture, and it was observed that the proposed IWHO algorithm produced better results.

Accurate classification of wheat varieties is vital for enhancing agricultural productivity and maintaining food quality standards. However, conventional methods based on manual inspection are time-consuming, labor-intensive, and prone to human error. This paper introduces an innovative methodology that integrates the tuna swarm optimization algorithm with a multi-layer perceptron neural network to achieve high-accuracy classification of wheat species. The SEEDS dataset, containing three wheat species (Kama, Rosa, and Canadian), was used to evaluate the effectiveness of the proposed model. Initially, the tuna swarm optimization algorithm’s robustness was validated using the CEC 2019 benchmark suite, where it demonstrated superior performance against alternative metaheuristics such as the Archimedes optimization algorithm, prairie dog optimization, and Harris hawks optimization. Tuna swarm optimization achieved a 79.29

This study presents an enhanced reptile search algorithm (ImRSA) optimized tilt-integral-derivative (TID) controller for load frequency control (LFC) in a two-area power system consisting of photovoltaic (PV) and thermal power units. The ImRSA integrates Lévy flight and logarithmic spiral search mechanisms to improve the balance between exploration and exploitation, resulting in more efficient optimization performance. The proposed controller is tested against the original reptile search algorithm (RSA) and other state-of-the-art optimization methods, such as modified grey wolf optimization with cuckoo search, black widow optimization, and gorilla troops optimization. Simulation results show that the ImRSA-optimized TID controller outperforms these approaches in terms of undershoot, overshoot, settling time, and the integral of time-weighted absolute error metric. Additionally, the ImRSA demonstrates robustness in managing frequency deviations caused by solar radiation fluctuations in PV systems. The results highlight the superior efficiency and reliability of the proposed method, especially for renewable energy integration in modern power systems.

The imperative shift towards renewable energy sources, driven by environmental concerns and climate change, has cast a spotlight on solar energy as a clean, abundant, and cost-effective solution. To harness its potential, accurate modeling of photovoltaic (PV) systems is crucial. However, this relies on estimating elusive parameters concealed within PV models. This study addresses these challenges through innovative parameter estimation by introducing the logarithmic spiral search and selective mechanism-based arithmetic optimization algorithm (Ls-AOA). Ls-AOA is an improved version of the arithmetic optimization algorithm (AOA). It combines logarithmic search behavior and a selective mechanism to improve exploration capabilities. This makes it easier to obtain accurate parameter extraction. The RTC France solar cell is employed as a benchmark case study in order to ensure consistency and impartiality. A standardized experimental framework integrates Ls-AOA into the parameter tuning process for three PV models: single-diode, double-diode, and three-diode models. The choice of RTC France solar cell underscores its significance in the field, providing a robust evaluation platform for Ls-AOA. Statistical and convergence analyses enable rigorous assessment. Ls-AOA consistently attains low RMSE values, indicating accurate current-voltage characteristic estimation. Smooth convergence behavior reinforces its efficacy. Comparing Ls-AOA to other methods strengthens its superiority in optimizing solar PV model parameters, showing that it has the potential to improve the use of solar energy.

This work introduces novel advancements in automatic voltage regulator (AVR) control, addressing key challenges and delivering innovative contributions. The primary motivation lies in enhancing AVR performance to ensure stable and reliable voltage output. A crucial innovation in this work is the introduction of the random walk aided artificial rabbits optimizer (RW-ARO). This novel optimization strategy incorporates a random walk approach, enhancing the efficiency of AVR control schemes. The proposed cascaded RPIDD2-PI controller, fine-tuned using the RW-ARO, stands out as a pioneering approach in the AVR domain. It demonstrates superior stability, faster response times, enhanced robustness, and improved efficiency compared to existing methods. Comparative analyses with established controller approaches reaffirm the exceptional performance of the proposed method. The new approach results in shorter rise times, quicker settling times, and minimal overshoot, highlighting its effectiveness and speed in achieving desired system responses. Moreover, the novel approach attains higher phase and gain margins, showcasing its superior performance in the frequency domain. The disturbance rejection and harmonic analysis are performed in order to demonstrate the efficacy of the proposed approach for potential real-world applications. The latter analyses further cement the superior capability of the proposed approach for the automatic voltage regulation.

The aim of this paper is to evaluate the optimization capabilities of the salp swarm algorithm (SSA), a metaheuristic algorithm capable of addressing contemporary global challenges. The paper focuses on assessing SSA as an optimizer and observing its impact as a predictor in an example energy problem to gauge its predictive power. Salp swarm algorithm (SSA) distinguishes itself with its optimization capabilities, providing effective solutions to optimization problems. The quality, competitiveness, and efficiency of the algorithm were initially assessed using the CEC 2019 and CEC 2020 function sets. The results demonstrated that SSA is a competitive, effective, and up-to-date algorithm. This competitive nature suggests that SSA can be effectively employed across a wide range of problems. Therefore, the paper aims to evaluate its success in providing solutions to an energy prediction problem. In addressing the challenge of effective energy utilization, the accurate prediction of heat loading (HL) and cool loading (CL) factors, critical in building design, contributes significantly to the solution. In solving this problem, machine learning algorithms, specifically the multi-layer perceptron (MLP) as an artificial neural network architecture, were chosen. SSA was approached in a supervised manner, and a comparison with alternative metaheuristic algorithms was conducted. The obtained results indicate that the SSA-based MLP architecture (SSA-MLP) exhibits effective predictive capabilities in energy problems. By combining the optimization power of SSA and the learning capabilities of MLP, a robust solution with a competitive advantage in energy efficiency is presented.

To enhance controller performance, the optimization of control parameters has emerged as a critical research area. Among the array of optimization algorithms, the modified elite opposition-based artificial hummingbird algorithm (m-AHA) stands out for its ability to emulate behavioral strategies of hummingbirds and elite opposition-based technique. This paper, therefore, proposes m-AHA optimizer as a novel approach to optimize control parameters in a three-tanks liquid level system. By fine-tuning the parameters of proportional-integral-derivative (PID) controller, superior performance is achieved. Comparative evaluations with competitive algorithms, including the arithmetic optimization algorithm with Harris hawks optimization and covariance matrix adaptation evolution strategy, assess the m-AHA optimizer-based approach for three-tank liquid level system control. The ITAE (integral of time multiplied absolute error) performance index analyzes time domain and frequency metrics, revealing the outstanding performance of the m-AHA optimizer-based approach.

This paper aims to compare the gradient descent-based algorithms under classical training model and swarm-based metaheuristic algorithms in feed forward backpropagation artificial neural network training. Batch weight and bias rule, Bayesian regularization, cyclical weight and bias rule and Levenberg-Marquardt algorithms are used as the classical gradient descentbased algorithms. In terms of the swarm-based metaheuristic algorithms, hunger games search, gray wolf optimizer, Archimedes optimization, and the Aquila optimizer are adopted. The Iris data set is used in this paper for the training. Mean square error, mean absolute error and determination coefficient are used as statistical measurement techniques to determine the effect of the network architecture and the adopted training algorithm. The metaheuristic algorithms are shown to have superior capability over the gradient descent-based algorithms in terms of artificial neural network training. In addition to their success in error rates, the classification capabilities of the metaheuristic algorithms are also observed to be in the range of 94%-97%. The hunger games search algorithm is also observed for its specific advantages amongst the metaheuristic algorithms as it maintains good performance in terms of classification ability and other statistical measurements.

The hunger games search (HGS) algorithm is designed to tackle optimization problems, however, issues such as local minimum stagnation and immature convergence hinder its effectiveness. To address these limitations, this study introduces a novel improved HGS (Imp-HGS) algorithm. The Imp-HGS algorithm uses pattern search (PS) and elite opposition-based learning (OBL) mechanisms to enhance exploitation and exploration, respectively. The algorithm's performance is tested across the CEC2019 and CECE2020 test suites along with three different engineering design problems, including identifying an infinite impulse response (IIR) model, training a multilayer perceptron (MLP), and designing a proportional-integral-derivative (PID) controller for a doubly fed induction generator (DFIG)-based wind turbine system. The test functions demonstrated superior performance of the Imp-HGS algorithm over a wide range of state-of-the-art algorithms. The ablation tests using CEC2020 test suite also demonstrate the wisely integration of the PS and elite OBL mechanisms as significant improvements are achieved. The statistical results demonstrate the significance of Imp-HGS in the IIR system identification as it consistently achieved lower average errors, lower standard deviations, competitive best results, and satisfactory worst results compared to the other algorithms. Moreover, the Imp-HGS algorithm consistently demonstrates better performance in terms of average classification rates across various datasets, showcasing its effectiveness in solving classification problems, making it a good tool for MLP training. Lastly, the Imp-HGS algorithm’s ability to eliminate overshoot, achieve faster rise time, shorter settling time, and minimal peak time showcases its effectiveness in achieving stable and efficient operation of the wind turbine system. The computational times also confirm the efficacy of the Imp-HGS algorithm for all considered real-world engineering problems. Overall, the results show that the proposed algorithm outperformed other competitive approaches, cementing its status as a highly promising tool for tackling a wide range of complex engineering optimization problems.

Metaheuristic algorithms have become very common in the last two decades. The flexibility and ability to overcome obstacles in solving global problems have increased the use of metaheuristic algorithms. In the training of multilayer perceptron (MLP), metaheuristic algorithms have been preferred for many years due to their good classification capabilities and low error values. Therefore, this study evaluates the performance of the Prairie dog optimization (PDO) algorithm for MLP training. In this context, there are two main focuses in this study. The first one is to test the performance of the PDO algorithm through test functions and to compare it with different metaheuristic algorithms for demonstration of its superiority, and the second is to train MLP using the IRIS dataset with the PDO algorithm. As the PDO is one of the most recent metaheuristic algorithms, the lack of any study on this subject is the motivation for the article. PDO algorithm can be used in real-world problems as a powerful optimizer, as it reaches the minimum point in functions, and can also be used as a classification algorithm because it has successfully performed in MLP training.

The purpose of this paper is to demonstrate the superiority of the Capuchin Search Algorithm (CapSA), a metaheuristic, in competitive environments and its advantages in optimizing engineering design problems. To achieve this, the CEC 2019 function set was used. Due to the challenging characteristics of the CEC 2019 function set in reaching a global solution, it effectively showcases the algorithm's quality. For this comparison, sea-horse optimizer (SHO), grey wolf optimizer (GWO), sine-cosine algorithm (SCA), and smell agent optimization (SAO) were chosen as current and effective alternatives to the CapSA algorithm. Furthermore, the gear train design problem (GTD) was selected as an engineering design problem. In addition to the CapSA algorithm, a hybrid of SCA and GWO algorithm (SC-GWO) and genetic algorithm (GA) were chosen as alternatives for optimizing this problem. The performance superiority and optimization power of the CapSA algorithm were assessed using statistical metrics and convergence curves, then compared with alternative algorithms. Experimental results conclusively demonstrate the significant effectiveness and advantages of the CapSA algorithm.

The aim of this paper is to show that the artificial gorilla troops optimization (GTO) algorithm, as an optimizer, can cope with test functions such as CEC2019, and also to best optimize the three bar truss design problem as a constrained optimization problem. As a method, two statistical measures such as the best values provided by the algorithms and the standard deviation showing the distance between the values were studied. At the same time, the convergence rate of the algorithms compared by the convergence curves were examined. For this purpose, it has been competed against two other swarm-based algorithms, sine-cosine algorithm (SCA) and golden eagle optimization (GEO). The optimization of the three bar truss design problem, which is another side of the study, has been made. The GTO algorithm reached the best values in the optimization of the parameters of the problem. In addition to the convergence curve, statistical results have examined, and the advantages of GTO are revealed through box-plot figures that evaluate the relationship between median and quartiles and the distribution among all results.

In this paper, the integration of a modified opposition-based learning (mOBL) mechanism into the arithmetic optimization algorithm (AOA) is presented. The proposed novel mOBL based AOA (mAOA) was demonstrated to have better capability for optimization problems by using four classical benchmark functions. For further evaluation, the proposed mAOA was also used to tune a proportional-integral-derivative controller (PID) adopted in a functional electrical stimulation (FES) system for the first time. The latter system is a challenging biomedical system that helps revealing the potential of the mAOA for real-world engineering optimization problems. The comparative transient response analysis was performed for PID controlled FES system using the original arithmetic optimization algorithm and Ziegler-Nichols based tuning schemes. The latter comparative analysis has shown better capability of the proposed mAOA algorithm for such a biomedical system.

This study focuses on construction of novel enhanced metaheuristic algorithm using a modified opposition‐based learning technique and the hunger games search algorithm. The proposed modified opposition‐based hunger games search (mOBL‐HGS) algorithm is aimed to be used as an efficient tool to tune a fractional order proportional‐integral‐derivative (FOPID) controller in order to control a magnetic ball suspension system with greater flexibility. The challenging benchmark functions from CEC2017 test suite are used to confirm the greater performance of the proposed mOBL‐HGS algorithm. The proposed mOBL‐HGS algorithm is also utilized to reach the optimum values of a FOPID controller employed in a magnetic ball suspension system in order to demonstrate its capability in terms of a complex real‐world engineering problem. The latter case is confirmed through comparative evaluations of statistical analysis, convergence profile, transient response, frequency response, disturbance rejection, and robustness. The demonstrated results confirm the greater ability of the proposed approach to control a magnetic ball suspension system.

A functional electrical stimulation (FES) system holds a significant importance for the paralyzed individuals as it can help them to perform the tasks they are unable to do. It is crucial to develop an efficient control mechanism for the FES system as it acts on the human musculoskeletal system which presents noise and uncertainties. Therefore, this paper proposes a novel control method for efficient operation of the FES system. In this regard, a proportional-integral-derivative controller with filter (PID-F) mechanism is proposed for the first time in literature for efficient operation of the FES system. Besides, a novel multi-strategy based weighted mean of vectors algorithm (m-INFO) is also developed using a modified opposition-based learning and Lévy flight mechanism together with Nelder-Mead simplex search method. Unimodal, multimodal, low-dimensional and CEC2019 benchmark functions are used to demonstrate the excellent performance of the proposed m-INFO algorithm against several other metaheuristic optimizers. The proposed m-INFO algorithm is then used as an efficient tool to design the PID-F controlled FES system. To achieve optimal tuning, a simple yet effective objective function is also proposed. The excellent ability of the developed m-INFO algorithm-based PID-F controller for FES system is demonstrated through comparative statistical, transient response and frequency response analyses using original weighted mean of vectors, marine predators and moth-flame optimization algorithms based PID-F controlled FES systems.

This paper explains the construction of a novel augmented hunger games search algorithm using a logarithmic spiral opposition-based learning technique. The proposed algorithm (LsOBL-HGS) is used as an efficient tool for both function optimization and controller design. To assess the performance of the algorithm for function optimization, benchmark functions from the CEC2017 test suite were employed and comparisons were made with available and good performing algorithms. In terms of controller design, the proposed LsOBL-HGS algorithm was utilized to design a FOPID controlled magnetic ball suspension system. Comparative assessments were also performed for FOPID controller design, as well using other state-of-the-art methods reported for the magnetic ball suspension system. The results showed that the proposed LsOBL-HGS algorithm has good capability for FOPID controller design employed in a magnetic ball suspension system as it provided an improvement of more than 13% in terms of the transient response-related parameters and more than 34% in terms of bandwidth compared to the best-reported approach used for comparisons.