Parallel compact artificial protozoa optimizer algorithm and its application in 3D coverage

Hydropower stations, as critical infrastructure for basic energy supply, play a pivotal role in ensuring the reliability of power systems through their safe and stable operation. Grounding grids operating long-term in complex soil environments are prone to corrosion and degradation, disrupting current distribution balance and causing spatial asymmetry in the voltage field, thereby compromising system safety. Corrosion branch resistance increment identification based on the electrical network method is typically modeled as a parameter inversion optimization problem. However, this problem exhibits underdetermination and other characteristics, making it difficult for traditional analytical methods to obtain stable solutions. To address this, this paper proposes a quantum perturbation scheduling candidate pool-guided sine–cosine algorithm (QSPSCA). Building upon the classical sine–cosine algorithm framework, it incorporates a dynamic candidate pool with multi-source attractor points and a quantum-inspired long-tail scheduling local refinement operator. This achieves an enhanced and smooth transition between global exploration and local refinement. Comparative experiments based on the CEC2017 benchmark and a hydropower station grounding grid corrosion diagnosis case demonstrate that QSPSCA outperforms multiple comparison algorithms in terms of average optimality and result stability. Furthermore, QSPSCA is applied to three typical engineering-constrained optimization problems. Results demonstrate that, whilst satisfying engineering constraints, this method consistently yields higher-quality feasible solutions with superior convergence accuracy and stability compared to alternative algorithms. Therefore, QSPSCA is not only applicable to underdetermined inversion diagnostics but also provides a solution framework with broad applicability for complex engineering optimization problems under structural symmetry perturbations.

Effective control of motorized wheelchairs needs methods with capabilities for stability, rapid response, accuracy, and robustness against nonlinearities and disturbances common in electromechanical systems. In this article, an optimized PID controller based on an Arithmetic Optimization Algorithm (AOA), known as AOA-PID, strategy is introduced. A full wheelchair model and an optimization model are used, offering a chance for a reduction in computation cost with retention of basic system dynamics. Experimental research on the role of PID factors will be conducted, followed by performance analysis on two axes: firstly, comparative research with multiple references on PID optimization methods, including Sine Cosine Algorithms (SCA), Kepler Optimization Algorithms (KOA), Salp Swarm Algorithms (SSA), Puma Optimizer Algorithms (POA), and Particle Swarm Optimization Algorithms (PSO); and secondly, comparative research on traditional and modern methods. The research result illustrates that AOA-PID exhibits quicker response and controlled overshoots with zero error and an extremely low IAE value, indicating simultaneous enhancement on stability, accuracy, and robustness. Additionally, Model-in-the-Loop (MIL), Software-in-the-Loop (SIL), and Processor-in-the-Loop (PIL) testing confirms the controller's capability to maintain high performance within an embedded system with low CPU consumption that meets real-time processing. As a result, AOA-PID strategy proves an efficient and highly capable strategy on assistive mobility control with significant improvements on safety, stability, and accuracy.

This paper proposes a Black Kite Algorithm (BKA)-based hyperparameter optimization method for Artificial Neural Network (ANN) training, mitigating local minimum issues associated with conventional training techniques. The resulting BKA-ANN model is then employed to estimate PID controller parameters for DC motor speed regulation. A large-scale dataset of 100,000 samples was generated via MATLAB simulation, with reference speed and load torque stochastically varied, and optimal PID parameters determined by minimizing the ITAE criterion for each operating condition. The optimized controller was evaluated under various operating conditions including transient response, frequency domain analysis (phase margin and bandwidth), parametric robustness, and load disturbance suppression, along with control effort and energy consumption assessments. The proposed BKA-ANN approach was benchmarked against nine algorithms: hybrid atom search optimization-simulated annealing (hASO-SA), harris hawks optimization (HHO), Henry gas solubility optimization with opposition-based learning (OBL/HGSO), atom search optimization (ASO), henry gas solubility op-timization (HGSO), stochastic fractal search(SFS), grey wolf optimization (GWO), sine-cosine algorithm (SCA), and Standard ANN. Simulation results indicate that BKA-ANN achieves stable performance across all tested scenarios, with minimal oscillation and competitive settling time compared to the evaluated algorithms.

ABSTRACT This research introduces a sine cosine algorithm with pattern search (SCAPS), a hybrid optimization algorithm for digital infinite impulse response (IIR) filter system identification. SCAPS combines the global exploration of SCA with the local exploitation of pattern search, addressing SCA’s limitations in complex optimization landscapes. It was benchmarked against SCA, genetic algorithm, particle swarm optimization, and cooperation search algorithm. Performance was evaluated using fifth-order IIR plant models and reduced-order fifth- and sixth-order systems representing diverse dynamics. A mean square error (MSE)-based fitness function was used, with statistical metrics (best, worst, mean, standard deviation) and Wilcoxon’s rank-sum test for evaluation. Sensitivity and computational cost analyses were also conducted. Results show that SCAPS achieves faster convergence, lower MSE, and improved robustness, demonstrating its potential for accurate system identification and engineering applications requiring precise parameter estimation.

Abstract This paper describes a high-fidelity Digital Twin-driven framework for the sustainable operation of hybrid power systems, which balances economic efficiency with environmental mandates by integrating real-world spatio-temporal wind and solar data from Gujarat, India. The research models Plug-in Electric Vehicles (PEVs) as a single Virtual Power Plant (VPP) with bidirectional Vehicle-to-Grid (V2G) and Grid-to-Vehicle (G2V) capabilities, thus eliminating the stochasticity issue of renewableheavy grids. The non-convex optimization problem that arises is solved by the Sine Cosine Algorithm (SCA) which is very effective in exploring the complex search landscapes such as those resulting from turbine valve-point loading effects. The proposed method, tested on 10-unit and 20-unit thermal systems, manages to lower the operating expenses dramatically and achieves a net annual emission reduction of more than 1.6 million tons in the larger test scenario. A comparative benchmarking with the state-of-the-art metaheuristics demonstrates that the SCA is a better performer in terms of convergence stability and technical proficiency in dealing with the complexities of the modern, sustainable energy infrastructure.

Strong electrical connections between countries and regions are essential for large-scale energy investments and for mitigating power deficits caused by generation and demand uncertainties. However, interconnected power systems are highly vulnerable to load disturbances, which can lead to significant frequency deviations and undesired power exchanges, threatening system stability and operational reliability. Load frequency control (LFC) plays a critical role in maintaining stable frequency and tie-line power in such interconnected environments. Although metaheuristics have been widely applied for LFC controller design, many existing approaches suffer from limited population diversity, resulting in premature convergence and reduced solution accuracy. To address these limitations, this paper suggests memory-based political optimizer (mPO) to optimize fractional-order proportional integral derivative (PID) controller for LFC in multi-sources, multi-interconnected microgrids. The optimal-guidance random-based exploration method and memory-based election campaign strategy are proposed to prevent local minima and achieve exploration/exploitation balance. Several CEC benchmarks have been analyzed to assess the suggested mPO in comparison to other approaches of traditional PO, sand cat swarm optimization algorithm (SCSO), Chernobyl disaster optimizer (CDO), smell agent optimization (SAO), sinh cosh optimizer (SCHO), grey wolf optimizer (GWO), and sine cosine algorithm (SCA). Two and four interconnected microgrids are the two systems under consideration. Each microgrid includes thermal, hydro, and wind turbines (WT) in addition to energy storage systems (ESSs) of redox flow batteries (RFB) and hydrogen aqua-electrolyzer fuel cells (HAFC). The integral time absolute error (ITAE) of the frequency and exchanged power deviations is the fitness function to be minimized under load disruption. Numerous topologies of the interconnected system as well as different load disruptions are analyzed. In the presence of the HAFC-RFB storage system, the proposed mPO decreased the fitness value in the two-interconnected system by 8.023% as compared to the traditional one. However, in the case of four interconnected microgrids, it decreased the ITAE by 20.071% instead of the PO. The obtained findings validated the mPO-optimized recommended controller’s superiority over the others.

An improved Sinh Cosh optimizer (ISCHO) is proposed to resolve load frequency control (LFC) tasks. The original Sinh Cosh optimizer (SCHO) employs a fixed iteration-based switching function to balance exploration and exploitation, which lacks awareness of search dynamics and leads to inefficient optimization. Therefore, this paper proposes a “first grabbing then washing” strategy to dynamically balance exploration and development. The proposed ISCHO technique is tested on 13 benchmark functions and compared with Particle Swarm Optimization, Sine Cosine Algorithm, and Grey Wolf Optimizer, demonstrating superior optimization performance. Furthermore, a new controller based on the two-degree-of freedom PID controller (2DOF-PID), the two-degree-of freedom with double integral feedback PID controller (2DOF-PIDF-II), is proposed. A two-area multi-source interconnected power system, incorporating thermal, hydraulic, wind, and solar generation units with nonlinearities (GRC and GDB), uncertainties, and load fluctuations, is employed to validate the proposed approach. Quantitative results under step load perturbation demonstrate that the ISCHO-optimized 2DOF-PIDF-II controller significantly outperforms other methods. For area 1 frequency deviation, ISCHO reduces the maximum overshoot by 38.37%, 19.09%, and 21.48% compared to PSO, SCA, and SCHO. For tie-line power deviation, maximum overshoot is reduced by 53.00% compared to PSO. These results confirm that the proposed ISCHO-tuned 2DOF-PIDF-II controller substantially enhances system frequency stability under various operating conditions.

With the increasing number of large-scale problems, traditional hybrid algorithms are prone to falling into local optima, insufficient diversity, and low convergence accuracy, which urgently need to be solved. In order to improve the efficiency of solving such problems, an improved sine cosine algorithm was designed by introducing dynamic position correction and orthogonal crossover mechanism. And combined with particle swarm optimization algorithm, Sine Cosine particle swarm optimization algorithm is proposed. The results indicated that the average and standard deviation of the Shere benchmark test function for this method were both 0. The dynamic position correction and orthogonal crossover mechanism of this algorithm ensured fast acquisition of optimal fitness values and high convergence accuracy. For the Quartic benchmark test function, the average and standard deviation of the research algorithm were 3.48 × 10-5 and 2.72 × 10-5, respectively. Therefore, this method had the best performance, with good search ability and solution accuracy. In the application of robot path planning, this method achieves zero collisions, a path smoothness of 0.12rad/m, an average planning time of 2.45s, and an emergency obstacle avoidance success rate of 98.6%, significantly improving the efficiency and reliability of path planning in large-scale complex environments. This provides a relatively efficient solution for large-scale optimization problems and has a promoting effect on the application of intelligent optimization algorithms in the field of robotics.

This paper addresses the challenges posed by the unpredictable nature of renewable energy sources (RES) and electric vehicle (EV) loads, which can impact power system reliability through issues like power quality degradation, increased losses, and voltage instability. To mitigate these effects, it proposes an innovative method for the combined optimal placement and sizing of RES and EV charging stations, along with a coordinated charging management strategy. The approach uses a multi-objective optimization framework aimed at minimizing power losses, voltage fluctuations, costs related to charging and energy supply, as well as EV battery expenses. The model incorporates factors such as wind speed, solar radiation, and hourly peak demand, to encourage EV charging during off-peak periods, thereby improving system efficiency and stability. The paper proposes a hybrid metaheuristic algorithm called Harris Hawk Optimization–Sine Cosine Algorithm (HHO-SCA) for optimizing renewable energy sources (RES) and electric vehicle (EV) charging systems. By integrating features of the Sine Cosine Algorithm (SCA) into Harris Hawk Optimization (HHO), the hybrid algorithm enhances both exploration and exploitation capabilities, leading to improved global search efficiency and optimized energy use. The HHO-SCA's performance was validated using benchmark functions and then applied to solve the proposed optimization problem under five different scenarios. Its effectiveness for the simultaneous optimal siting and sizing of RES and EV charging stations was demonstrated on the IEEE 33-bus system. Results show that HHO-SCA outperforms other methods by effectively avoiding local optima and achieving superior convergence behavior.

This paper presents a novel adaptive nonsingular terminal sliding mode control (NSTSMC) strategy with a variable exponent approach for robust quadrotor attitude tracking under external disturbances. The proposed controller introduces, for the first time, an adaptive variable exponent NSTSMC framework that achieves practical fixed-time (FxT) convergence and robust performance without requiring prior knowledge of the disturbance bounds. Unlike existing FxT control methods, the proposed scheme employs an adjustable exponent that varies according to the system state’s proximity to the reference trajectory, leading to faster convergence and reduced control effort. Multiple adaptive switching control gains are designed for individual control axes, while the nominal controller parameters are optimized using the Sine Cosine Algorithm (SCA) to further minimize control effort. The proposed controller design enhances both transient response and steady-state accuracy, while guaranteeing practical FxT stability, which is rigorously established through Lyapunov theory. Simulation results and comparative studies validate the effectiveness of the proposed approach, demonstrating a reduction in tracking error of up to 74% and a decrease in control effort of 19.5% compared to state-of-the-art NSTSMC methods. Real-time experiments on a Quanser 3D Hover platform further validate the robustness, accuracy, and practical applicability of the proposed control scheme.

Accurate estimation of daily precipitation is essential for effective water resource management and climate risk assessment. Satellite precipitation products (SPPs) offer valuable spatial coverage but remain limited by uncertainties, particularly in arid and semi-arid regions. To address these challenges, this study develops a robust merging framework that integrates four SPPs with auxiliary topographic and meteorological data using ensemble machine learning models (EMLMs). Within this framework, we introduce for the first time the Multiple Linear Regression–based Sine Cosine Algorithm (MLR-SCA), designed to improve merging performance relative to the widely used Bayesian Model Averaging (BMA). Daily precipitation observations from 80 synoptic stations across Iran (2014–2022) were employed for training and validation. Results demonstrate that the proposed MLR-SCA significantly outperforms BMA, increasing the correlation coefficient (CC) by 132%, reducing RMSE by 34% and MAE by 19%, and achieving substantial improvements in KGE (+ 1142%), POD (+ 40%), and CSI (+ 47%), while reducing FAR (–24%) and BIAS (–7%). Although merging slightly reduced categorical event-detection skill in some cases, the EMLM framework consistently produced more accurate, stable, and reliable precipitation estimates across diverse climatic zones. Compared with existing approaches, the proposed framework offers three main advantages: (1) stronger performance across arid, semi-arid, and semi-humid climates; (2) improved detection of extreme precipitation events, which are often underestimated by raw SPPs; and (3) greater robustness through the simultaneous integration of multiple SPPs and auxiliary datasets. These findings highlight the potential of the EMLM–MLR-SCA framework to support operational hydrology, water resource planning, and climate adaptation in data-scarce regions.

We investigated benzene variability in an urban environment using an interpretable, setting-based artificial intelligence framework. A seven-year dataset (2017-2023) of hourly pollutant concentrations (benzene, NO2, SO2, CO, O3) measured in Zagreb (Croatia) was analyzed, as were meteorological variables. Multiple-ensemble decision tree models were developed, with hyperparameters optimized using metaheuristic algorithms. The best-performing model, Extra Trees optimized by the Sine Cosine Algorithm, achieved an R2 of 0.87. Model interpretation employed Shapley additive explanations (SHAP), followed by PaCMAP embedding and HDBSCAN clustering to identify coherent environmental settings. Seven settings (C0-C6) and one residual group were identified, representing pollution-enhancing, suppressing, and transitional regimes. Two settings dominated benzene extremes. C6 reflected winter stagnation, characterized by strong combustion influence (CO contribution of 11.9%), shallow boundary layers (~290 m), weak winds, and high humidity. C4 represented a synoptic stability regime with enhanced heat fluxes and diminished after the COVID-19 period, consistent with altered anthropogenic activity. Low-benzene settings (C0, C1, C3) were associated with stronger mixing and higher oxidizing capacity, while transitional settings (C2, C5) reflected moderate conditions. Overall, the results show that a small number of environmental settings governed the benzene extremes, providing a transferable and interpretable framework for air quality assessment and policy support.

Gas turbine is a kind of dual-purpose rotating thermal machinery, widely used in power generation, shipbuilding and aviation power, etc., with the advantages of high efficiency, fast start and low emissions. In this study, an improved Circle-SCA-BSO algorithm (IC-SCA-BSO) is proposed to optimize PID parameters to ease the complicated parameter setting of gas turbine controller. Optimization of beetle swarm optimization algorithm (BSO) usually comes with slow convergence speed, low accuracy and prone to fall into local optimum, hereby our optimization is carried out from three aspects: population initialization, optimization weight and learning factors. First, a uniformly distributed circle mapping is utilized for population initialization. Second, the nonlinear decreasing idea is employed for weight optimization. Considering characteristics of global search in the early stage and local development in the later stage of algorithm optimization, the nonlinear decreasing function expression is designed. Third, combined with the sine cosine algorithm (SCA), the sine and cosine factors are introduced into the learning factors and combined with the nonlinear decreasing coefficient to make the learning factors show a trend of oscillatory attenuation in the set interval. According to probability p, sine or cosine factor is switched as the learning factors. The optimized PID controller and other four controllers are compared by tracking test and anti-interference test. The test results show that IC-SCA-BSO-PID yields faster response, higher steady-state accuracy and stronger anti-interference control effect, which is significantly outperforming the other four controllers. The proposed IC-SCA-BSO-PID tuning framework offers plant engineers an automated, low-cost alternative to labor-intensive manual calibration, enabling faster commissioning, reduced fuel consumption, and lower emissions for gas turbines in power-generation, marine, and aero-derivative applications.

The Combined Heat and Power Economic Dispatch (CHPED) problem represents a significant optimization challenge in modern power systems due to its inherent complexity arising from multiple operational constraints. This complexity is further exacerbated when considering the effect of power losses (PLs), valve-point loading effect (VPLE), and prohibited operating zones (POZs). Consequently, an efficient and robust optimization algorithm is essential for obtaining a globally optimal solution while satisfying all constraints. To address these challenges, this work evaluates the effectiveness of the Modified Dung Beetle Optimizer (MDBO) for solving the CHPED problem, considering PLs, VPLE, and POZs. The MDBO enhances the search process and mitigates the limitations of the conventional Dung Beetle Optimizer, particularly stagnation and premature convergence to local optima. The novelty in this paper is proposing a modified version of the traditional DBO (MDBO) by integrating three improvement strategies, including the fitness distance balance (FDB), Chaotic mutation (CM), and adaptive local search approach (ALSA), to solve the CHPED problem. The proposed MDBO has the ability to overcome the shortcomings of traditional DBO, such as its premature convergence and tendency to local optima. The effectiveness of the proposed MDBO has been evaluated on CHPED problems involving 4-unit, 7-unit, 24-unit, and 48-unit systems under various operating conditions. Moreover, MDBO performance has been rigorously assessed using standard benchmark test suites, including CEC-2019. The results demonstrate a significant reduction in operating costs, confirming the superior performance of the MDBO in comparison to existing optimization techniques like Sand Cat Swarm Optimizer (SCSO), African vultures optimization algorithm (AVOA), Sine Cosine Algorithm (SCA), Harris Hawks Optimization (HHO), Grey Wolf Optimizer (GWO), Liver cancer algorithm (LCA), Zebra Optimizer Algorithm (ZOA), and Whale Optimization Algorithm (WOA). Furthermore, the proposed algorithm consistently outperforms alternative methods reported in the literature, offering a more efficient and reliable solution for CHPED optimization.

This paper presents an Adaptive Model Predictive Control (AMPC) strategy for robust load-frequency control (LFC) in single-area and double-area power systems under load variations, parameter uncertainty, and renewable energy disturbances. The controller integrates online system identification using Recursive Least Squares (RLS) with a receding-horizon optimization framework to ensure real-time model adaptation and constraint-aware predictive regulation. Simulation results demonstrate that the proposed AMPC significantly improves transient and steady-state performance compared with conventional PI/PID controllers. In single-area systems, the AMPC achieves settling times of 0.5-1s, compared with 30s for PI, and eliminates overshoot while reducing undershoot from 4.5 × 10⁻³ to 1 × 10⁻³. Under dynamic and wind disturbances, peak-to-peak deviations are reduced to ≈ 0, whereas PI exhibits deviations up to 26.5 × 10⁻³. In double-area systems, the AMPC reduces settling time from 20 to 40s (PID) to 1-2s and minimizes undershoot by up to an order of magnitude. Comparative studies further confirm the proposed AMPC's superiority over Harmony Search (HS), Sine-Cosine Algorithm (SCA), Teaching-Learning-Based Optimization (TLBO)-optimized PID/PIDA controllers and the Marine Predator Algorithm (MPA)-based cascaded PIDA, establishing AMPC as an effective and scalable solution for low-inertia grids with high renewable penetration.

This paper presents an innovative algorithm, termed the Fractional Optimization Algorithm (FOA), which utilizes the properties of fractional functions to enhance the integration of photovoltaic (PV) systems and distribution static compensators (D-STATCOMs) into distribution systems (DSs). The FOA employs a discrete-continuous encoding approach to determine the optimal placement and sizing of PV and D-STATCOM devices. A master-slave optimization framework is adopted, where the FOA operates in the master stage, and the successive approximations method is used for power flow analysis in the slave stage. The algorithm's efficacy is tested on 33- and 69-bus grids, demonstrating significant cost reductions over traditional optimization approaches such as the Vortex Search Algorithm (VSA) and the Sine-Cosine Algorithm (SCA). Furthermore, the FOA achieves superior computational efficiency, underscoring its promise as a robust optimization strategy.

We introduce AHA–SCA, a compact hybrid optimiser that alternates the wave-based exploration of the Sine–Cosine Algorithm (SCA) with the exploitation skills of the Artificial Hummingbird Algorithm (AHA) within a single population. Even iterations perform SCA moves with a linearly decaying sinusoidal amplitude to explore widely around the current best solution, while odd iterations invoke guided and territorial hummingbird flights using axial, diagonal, and omnidirectional patterns to intensify the search in promising regions. This simple interleaving yields an explicit and tunable balance between exploration and exploitation and incurs negligible overhead beyond evaluating candidate solutions. The proposed approach is evaluated on the CEC2014, CEC2017, and CEC2022 benchmark suites and on several constrained engineering design problems, including welded beam, pressure vessel, tension/compression spring, speed reducer, and cantilever beam designs. Across these diverse tasks, AHA–SCA demonstrates competitive or superior performance relative to stand-alone SCA, AHA, and a broad panel of recent metaheuristics, delivering faster early-phase convergence and robust final solutions. Statistical analyses using non-parametric tests confirm that improvements are significant on many functions, and the method respects problem constraints without parameter tuning. The results suggest that alternating wave-driven exploration with hummingbird-inspired refinement is a promising general strategy for continuous engineering optimisation.

Data serves as the foundation for training and testing machine learning and artificial intelligence models. The most fundamental part of data is its attributes or features. The feature set size changes from one dataset to another. Only the relevant features contribute meaningfully to classification accuracy. The presence of irrelevant features reduces the system’s effectiveness. Classification performance often deteriorates on high-dimensional datasets due to the large search space. Thus, one of the significant obstacles affecting the performance of the learning process in the majority of machine learning and data mining techniques is the dimensionality of the datasets. Feature selection (FS) is an effective preprocessing step in classification tasks. The aim of applying FS is to exclude redundant and unrelated features while retaining the most informative ones to optimize classification capability and compress computational complexity. In this paper, a novel hybrid binary metaheuristic algorithm, termed hSC-FPA, is proposed by hybridizing the Flower Pollination Algorithm (FPA) and the Sine Cosine Algorithm (SCA). Hybridization controls the exploration capacity of SCA and the exploitation behavior of FPA to maintain a balanced search process. SCA guides the global search in the early iterations, while FPA’s local pollination refines promising solutions in later stages. A binary conversion mechanism using a threshold function is implemented to handle the discrete nature of the feature selection problem. The functionality of the proposed hSC-FPA is authenticated on fourteen standard datasets from the UCI repository using the K-Nearest Neighbors (K-NN) classifier. Experimental results are benchmarked against the standalone SCA and FPA algorithms. The hSC-FPA consistently achieves higher classification accuracy, selects a more compact feature subset, and demonstrates superior convergence behavior. These findings support the stability and outperformance of the hybrid feature selection method presented.

In today’s digital era, the prevalence of cyberattacks requires robust security measures to keep sensitive and confidential information and infrastructure safe and secure. The intrusion detection system (IDS) plays the most vital role in this aspect by serving as a first‐line defense against these malicious activities and potential breaches. This paper presents a hybrid approach to improve the security and safety of networks through an efficient IDS. The proposed approach for the new IDS optimizes the fast learning network (FLN) through a fuzzy adaptive metaheuristic algorithm. A Mamdani‐based fuzzy adaptive strategy (FAS) is incorporated into four metaheuristic algorithms: the equilibrium optimizer (EO), growth optimizer (GO), sine cosine algorithm (SCA), and arithmetic optimization algorithm (AOA). The FAS dynamically balances the exploration and exploitation operations of these algorithms to enhance their performance. FAS is a two‐input, one‐output fuzzy technique that selects the best search operator during the optimization process. The proposed hybrid models that combine FLN with the fuzzy‐based implementations of the four stated metaheuristic algorithms are trained and tested on benchmark intrusion datasets known as NSL‐KDD and CIC‐IDS2017. Based on the results of our experiments, the fuzzy‐based optimized FLN models outperform the FLN models optimized using the four fundamental metaheuristic algorithms in terms of testing accuracy and training time. Moreover, fuzzy adaptive AOA (FAAOA)–based FLN outperformed all competing models by generating the best overall accuracies as well as by taking less training time for different numbers of neurons in the hidden layer of FLN. Finally, all proposed fuzzy optimized FLN‐based IDS models exhibited resilience against the fast gradient sign method (FGSM) and projected gradient descent (PGD) adversarial attacks.