Grey Wolf Optimizer Research Articles (Page 1)

This study investigates the reliability of a machine dual-repair system (MDRS) with limited capacity and multiple operational vacations (OV). Multiple operational vacation is a mechanism that involves the process of the two types of vacation, one as operational vacation (OV) and another one is non-operational vacation (NOV). In this machining system, there are M operating machines, to prevent redundant breakdowns of machines and S spare machines are used to ensure smooth functioning. The server can be in a busy state, an operational vacation state, or on Non-operational vacation state. State-transition equations are formulated based on the Chapman-Kolmogorov differential-difference equations, and with the help of these equations stationary probability distribution is obtained. The Runge-Kutta IV order numerical method is used to evaluate system performance measures. The cost has been optimized using Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) techniques by testing convergence as well as comparison of the outcomes of both PSO and GWO. The exploration of the essential performance measures and graphical representations has been conducted.

MYIGWO: A grey wolf optimizer with dual mutation and chaotic adaptive neighborhood for engineering problems and path planning

Thermodynamic analysis and performance enhancement of an integrated solar–geothermal polygeneration system using grey wolf optimization and LSTM-based forecasting with Monte Carlo uncertainty analysis: A case study on Tenerife Island

A novel combined framework for short-term wind speed forecasting based on data preprocessing with sequence reconstruction and Grey Wolf optimization

Design and dual-objective optimization of a methanol hydrogen reformer with a back propagation neural network and grey wolf optimization algorithm

Alzheimer's disease (AD) is one of the common forms of dementia and is tremendously increasing throughout the world. There are many biomarkers currently available to detect the AD progression. In AD, brain cell death occurs, leading to memory loss, impaired calculation ability, and difficulty in remembering recent events. Early detection of AD is crucial for managing the symptoms and providing effective medical intervention. AD symptoms usually develop gradually and become worse over time, and interfere with daily activities. Hence, this research proposes the Fuzzy scoring based ResNet-Convolutional Neural Network (FS-ResNet CNN) to discriminate AD patients having AD, Mild Cognitive Impairment (MCI), and cognitively normal (CN) using a hybrid deep learning architecture to leverage more complete spatial information from the ADNI data. Initially, the pre-processing is carried out using the z-score normalization. To reduce the time complexity and to select the prominent features, the Adaptive Grey Wolf Optimization Algorithm (AGWOA), harnessing the swarm intelligence, has been proposed. Finally, the Hybrid Deep Learning Architecture is applied for the classification of AD. Specifically, the proposed method introduces a novel method known as the Fuzzy Scoring to optimize the network performance. Furthermore, the proposed FS-ResNet CNN model is computationally efficient, less sensitive to noise, and efficiently saves memory. Experimental results demonstrate the effectiveness of the proposed method on the ADNI dataset, showing high classification accuracy of 97.89%, surpassing the other state-of-the-art methods.

Enhanced binary grey wolf optimizer based on quantum computing and multi-strategy for feature selection on high-dimensional data classification

Multi-objective performance optimization analysis of biconical segmented annular thermoelectric generator based on grey wolf optimization algorithm

The chest X-ray imaging (CXR) is a key diagnostic instrument in COVID-19 diagnosis, wherein more than 600,000 tests are performed worldwide annually and the misdiagnosis rate is estimated to be 15-20 percent, largely contributed by human error. Conventional manual reading of CXR images is time-consuming, labor-intensive, and heavily reliant on the skill of the radiologist, typically resulting in a series of uneven and sluggish diagnostic outcomes. To overcome these limitations, the current research introduces an innovative state-of-the-art CXR segmentation model based on rigorous preprocessing techniques in combination with the optimisation of deep-learning algorithms to obtain precise lung parenchyma and pathological lesion outlines. Block-matching 3D filtering (BM3D) was applied to suppress noise without loss of anatomical details following curation of the COVID-19 CXR Dataset. The Optimization U-Net (OU-Net) architecture, which served as the backbone of the proposed approach, was carefully designed with adaptive encoder-decoder paths and strengthened skip connections to better subdivide real lung regions and manifestations of diseases. Additionally, the training schedule utilizes Modified Grey Wolf Optimization (MGWO) for the optimization of network parameters, and this accelerates convergence and enhances segmentation accuracy. Empirical results confirm that the OU-Net with MGWO is superior to conventional and standard deep-learning models, as the suggested approach enhances accuracy by 4.58%, sensitivity by 5.22%, specificity by 4.60%, precision by 4.85%, recall by 1.78%, F1-score by 5.07%, Jaccard index by 5.23%, and Dice score by 5.31%.

Predictive and early warning analysis of infectious gastroenteritis based on the BiLSTM-BiGRU model.

The Fuzzified Grey Wolf: An improved grey wolf optimizer based on dynamic fuzzy system FGWO

Knowledge-aware Attentional Neural Network based healthcare big data analytics optimized with Weighted Velocity-Guided Grey Wolf Optimization Algorithm

Many-Objective Grey Wolf Optimizer (MaOGWO) for solving real-world problems

Abstract Purpose This work applies a computational framework for vibration attenuation in periodic structures by combining the established wave and finite element (WFE) method with nature-inspired optimization algorithms. The purpose of this work is to provide a systematic comparison of various nature-inspired algorithms across both low-cost analytical and high-fidelity simulation-driven design problems. Methodology Two numerical examples are investigated. The first considers a semi-infinite beam with periodic masses, where the dynamic stiffness matrix is obtained analytically. Two optimization scenarios are addressed within the first example. The second example involves a periodic beam with alternating thick and thin segments, modeled using WFE, where the objective is to minimize transmissibility over a lower frequency range. Five nature-inspired optimization algorithms: Genetic Algorithm (GA), Differential Evolution (DE), Grey Wolf Optimizer (GWO), Improved Grey Wolf Optimizer (IGWO), and Particle Swarm Optimization (PSO) are compared. In the first example, a fixed number of function evaluations ensures fair comparison; in the second, equal runtime account for the high computational cost of each function evaluation. Results In the first example, all algorithms achieved similar optimal solutions in the two optimization scenarios, with differences arising primarily in computational efficiency. For the first optimization scenario, distribution-free analysis showed that at intermediate function evaluation budgets, detectable differences emerge among algorithms, whereas in the second scenario, these differences diminish at higher evaluation budgets (with no significant pairwise contrasts), indicating convergence. GA incurred the highest computational overhead; DE was fast but tended to plateau while GWO, IGWO, and PSO exhibited strong accuracy-efficiency trade-offs within the tested budgets. In the second example, which operated under fixed runtime budgets, Kruskal–Wallis tests indicated significant differences at all time budgets: PSO consistently attained the lowest transmissibility, with GWO and IGWO close behind, GA showing modest improvement with longer runtime, and DE stagnating early. Across both cases, the effect-size analysis (Cliff’s $$\delta$$ ) confirms that observed gaps are generally small to medium at moderate budgets and tend to narrow at higher budgets as solutions converge. This highlights that the efficiency with which evaluations are translated into meaningful search progress is just as critical as raw accuracy in expensive, simulation-driven problems. The WFE-based framework therefore provides a general and effective tool for optimizing periodic structures for targeted vibration attenuation.

Abstract Magnesium Phosphate Cement (MPC) is recognized as an effective rapid repair material, with compressive strength serving as a key mechanical property indicator for its mortar formulations. Nevertheless, due to MPC's complex composition and formulation, predicting its compressive strength remains a significant challenge. In this study, a comprehensive database was developed, incorporating four key input variables: the magnesium-to-phosphate (M/P) molar ratio, water-to-cement (W/C) mass ratio, sand-to-binder (S/B) weight ratio, and the borax-to-magnesia(B/M) weight ratio. This dataset was used to train and validate eight machine learning models, including the Lightweight Gradient Boosting (LGB) algorithm, Support Vector Machine (SVM), Decision Tree (DT), Extreme Gradient Boosting (XGB), Ridge Regression (RR), Random Forest (RF), Backpropagation Neural Network (BP), and Gradient Boosting (GB) models. The eight machine learning models were evaluated using performance metrics, including Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), Correlation Coefficient, and Root Mean Square Error (RMSE), to identify the optimal model, which was then optimized via the Gray Wolf Optimizer (GWO). The most accurate prediction of MPC compressive strength was attained using the XGB model, with the GWO-optimized XGB model showing enhancement in MAPE, MAE, R2, and RMSE by 21.8%, 60.6%, 43.9%, and 55.3% respectively, relative to the unoptimized XGB model. Employing Shapley Additive exPlanations (SHAP) values and Partial Dependence Plots (PDP), this study facilitates the identification of the most influential input variables and quantifies their effects on MPC compressive strength. The optimized model was validated against experimental data, demonstrating robust and conservative prediction behavior. While the model is trained solely to predict compressive strength, its interpretability enables rational insights into how formulation variables influence strength, thereby supporting informed mix design decisions. This framework offers a reliable and transparent computational tool for preemptive strength assessment of MPC and guides the optimization of mechanical performance in structurally demanding applications.

Solid oxide fuel cells (SOFCs) are highly efficient and fuel-flexible energy conversion devices, but accurately estimating their governing parameters remains a challenge due to the nonlinear behavior of electrochemical processes. This study presents the first application of the black widow optimization (BWO) algorithm for estimating six critical SOFC parameters—open-circuit potential (E 0 ), Tafel slope (A), exchange current density (I 0 ), concentration loss coefficient (B), limiting current density (I l ), and ohmic resistance (R ohm )—under varying pressure conditions (1–5 atm). The objective was to minimize the mean squared error (MSE) between experimental and predicted polarization curves while ensuring computational efficiency. The proposed BWO framework achieved superior accuracy, with an MSE of 0.52 at 5 atm and convergence within 3.74 s, significantly outperforming benchmark metaheuristic algorithms such as particle swarm optimization (PSO), gray wolf optimization (GWO), and the whale optimization algorithm (WOA). Robustness was confirmed through cross-validation, where polarization curves predicted at unseen conditions deviated by less than 5% from experimental results. This demonstrates that the estimated parameters effectively capture intrinsic SOFC electrochemical behavior rather than overfitting specific datasets. Beyond numerical accuracy, the optimized parameters enhanced the predictive stability of voltage–current (V–I) and power–current (P–I) characteristics across all studied pressures, directly supporting improved operational reliability and long-term stack durability. The combination of higher precision, faster convergence, and strong generalizability positions BWO as a promising tool for real-time SOFC optimization. The findings establish a robust framework for parameter identification that not only reduces uncertainty in SOFC modeling but also contributes to practical advances in performance optimization and system longevity. Future extensions of this research will include real-time implementation under dynamic operating environments and integration with hybrid renewable energy systems to improve scalability, efficiency, and sustainability.

This article investigates a wind–solar–biogas complementary integrated energy system (IES) for achieving combined cooling, heating, and power (CCHP) supply in agricultural parks. The system consists of wind power, photovoltaic power, biogas-based combined heat and power (CHP), waste heat boilers, electric heating/cooling units, absorption chillers, and energy storage devices. Using Changma Village, Baiwu Town, Yanyuan County, Sichuan Province as a case study, a multi-objective optimization model was established with the objectives of minimizing operating costs and carbon emissions. An improved multi-objective grey wolf optimizer (MOGWO) was applied to solve the model. The results show that the proposed method yielded a well-distributed Pareto front. In the optimal compromise solution, the total operating cost decreased from CNY 6461.77 to CNY 2070.51, a reduction of 67.96%, and the carbon emissions decreased from 13,740.72 kg to 2370.45 kg, a reduction of 82.75%. The proposed wind–solar–biogas complementary IES can enhance both the overall economic performance and low-carbon sustainability of the agricultural park energy systems.

GWO-RF: A Grey Wolf Optimized Random Forest Model for Predicting Employee Turnover

To investigate the characteristic pressure distribution patterns when gripping ski poles during skiing, this study addresses the challenges of measuring grip force on the complex curved surfaces of ski poles. A dataset of experimental samples was established, and grip force data were extracted using deep neural network (DNN) training. To reduce errors caused by dynamic force distribution and domain shifts due to varying hand postures, a hybrid method combining deep neural networks with the bio-inspired Gray Wolf Optimization (GWO) algorithm was proposed. This approach enables the fusion of hand-related feature data, facilitating the development of a high-precision grip force prediction model for skiing. A multi-point flexible array sensor was selected to detect force at key contact points. Through system calibration, grip force data were collected and used to construct a comprehensive database. A backpropagation (BP) neural network was then developed to process the sensor data at these characteristic points using deep learning techniques. The data fusion model was trained and further optimized through the GWO-BPNN (Gray Wolf Optimizer–backpropagation neural network) algorithm, which focuses on correcting and classifying force data based on dominant force-bearing units. Experimental results show that the optimized model achieves a relative error of less than 2% compared to calibration experiments, significantly improving the accuracy of flexible sensor applications. This model has been successfully applied to the development of intelligent skiing gloves, offering a scientific foundation for performance guidance and evaluation in skiing sports.

Abstract The presented research article highlights the systematic approach of weight calculation for determination of approximated order model (AOM) for higher order (HO) underwater robotic autonomous submarine (URAS) system. The AOM for URAS system is determined by employing expansion parameters of URAS system and its desired URAS AOM. In this determination, two-point matching (TPM) between expansion parameters of URAS system and its desired URAS AOM is performed. For the minimization of errors between expansion parameters of URAS system and its desired URAS AOM, fitness function is formulated. By employing TPM, the improved steady-state characteristics (SSC) and transient characteristics (TC) of desired URAS AOM with respect to its HO URAS system can be achieved. For providing suitable importance to SSC and TC, systematic weight calculation (SWC) approach based proximity index value (PIV) method is incorporated. After assigning appropriate weights in fitness function using PIV method, comparatively better URAS AOM is ascertained by exploiting greywolf optimization algorithm (GOA). While obtaining AOM, two crucial constraints are also considered to solve the fitness function using GOA. These constraints are ensuring stable URAS model, and confirming zero steady-state error. In support of URAS AOM, by comparing proposed URAS AOM with benchmark approximation approaches, the analytically presented results and findings are demonstrated in the form of responses and data tabulation.