Visual servoing using image registration is a method employed in robotics to control the movement of a system using visual information. In this context, we propose a new intensity-based image registration algorithm (I...
详细信息
Visual servoing using image registration is a method employed in robotics to control the movement of a system using visual information. In this context, we propose a new intensity-based image registration algorithm (IBIR) that uses information derived from images acquired at different times or from different views to determine the parameters of the geometric transformations needed to align these images. The Arithmetic optimization Algorithm (AOA) is used to optimize these parameters, minimizing the difference between the images to be aligned. The proposed algorithm, Intensity-Based Image Registration via Arithmetic Optimisation Algorithm (IBIRAOA), is robust to image data fluctuations and perturbations and can avoid local optima. Simulation results prove the importance and efficiency of the proposed algorithm in terms of computation time and similarity of aligned images compared to other methods based on various metaheuristics. In addition, our results confirm a significant improvement in the trajectory of the wheeled mobile robot, thus reinforcing the overall effectiveness of our method in practical navigation and robotic control applications.
The metaheuristicoptimization algorithm(MHS) is a global optimization method inspired by natural phenomena, demonstrating superior performance in specific application scenarios. Traditional optimizationalgorithms ut...
详细信息
The metaheuristicoptimization algorithm(MHS) is a global optimization method inspired by natural phenomena, demonstrating superior performance in specific application scenarios. Traditional optimizationalgorithms utilize two main concepts: exploration, to expand the search range, and exploitation, to enhance solution accuracy. However, as problem complexity and application scenarios increase, MHS struggles to balance exploration and exploitation to find the optimal solution. Therefore, this paper introduces innovative characteristics of individual thinking and proposes a new Thinking Innovation Strategy (TIS). TIS does not aim for an optimal solution but seeks global optimization based on successful individuals, enhancing algorithm performance through survival of the fittest. This paper applies TIS strategies to improve various MHS algorithms and evaluates their performance on 57 engineering problems and the IEEE CEC2020 benchmarks. Experimental results indicate that the TISenhanced algorithms outperform the original versions across 57 engineering problems, according to Friedman ranking and Wilcoxon rank-sum test results. Some algorithms show significant improvement, demonstrating the feasibility and practicality of TIS for optimization problems. The TIS (LSHADE_SPACMA) of the source code can be accessed through the following ways: https://***/LIANLIAN-Serendipity/TIS
This study investigates hybrid energy systems (HESs) integrating photovoltaic (PV) panels, batteries, fuel cells (FCs), electrolyzers (ELs), and hydrogen tanks (HTs) to address the energy needs of remote Australian co...
详细信息
This study investigates hybrid energy systems (HESs) integrating photovoltaic (PV) panels, batteries, fuel cells (FCs), electrolyzers (ELs), and hydrogen tanks (HTs) to address the energy needs of remote Australian communities. Two configurations are analyzed: Type-A (PV/Batt/FC/EL/HT) and Type-B (PV/FC/EL/HT), focusing on cost-efficiency, energy reliability, and hydrogen production. Several optimization techniques, including the cuckoo search algorithm, non-dominated sorting genetic algorithm-II (NSGA-II), and sequential quadratic programming algorithm (SQPA), flower pollination algorithm, constrained PSO , and harmony search algorithm, are employed to determine optimal system configurations. Type-A emerges as the most cost-effective configuration when optimized with NSGA-II, achieving a net present cost (NPC) of $226,500, a levelized cost of electricity (LCOE) of $0.193/kWh, and a levelized cost of hydrogen (LCOH) of $4.88/kg. Battery integration in Type-A enhances both cost-efficiency and energy reliability. For hydrogen-focused applications, SQPA yields the highest hydrogen production at 4737 kg/year, supported by higher EL (14 kW) and FC (18.63 kW) capacities. System efficiency is found to be highly sensitive to PV tilt angle, with 30 degrees identified as optimal. Increasing the tilt to 70 degrees can raise system costs by up to 75 %. Sensitivity analyses reveal that improving component efficiencies dramatically impacts costs. For example, increasing fuel cell efficiency from 40 % to 60 % reduces NPC, LCOE, and LCOH by $40,000, $0.04/kWh, and $0.1/kg, respectively, especially in Type-A systems. Collectively, adjustments to PV tilt angles and component efficiencies can reduce overall costs by up to 40 %. These insights offer a strategic foundation for designing HESs that balance electricity and hydrogen generation, tailored for sustainable operation in off-grid and remote settings.
The elastic modulus (E) of rocks is an essential parameter in mining and rock engineering projects, as it directly affects their stability and structural integrity. This study investigates the application of metaheuri...
详细信息
The elastic modulus (E) of rocks is an essential parameter in mining and rock engineering projects, as it directly affects their stability and structural integrity. This study investigates the application of metaheuristic optimization algorithms, specifically Cuckoo Search (CS) and Harris Hawks optimization (HHO), to fine-tune the hyperparameters of ensemble regression models, including extreme gradient boosting (XGBoost), decision tree (DT), and adaptive boosting (AdaBoost). A dataset of 122 rock samples, including input parameters such as wet density, moisture, dry density, Brazilian tensile strength, and uniaxial compressive strength, was used to predict E. A dataset was split into training and testing datasets with a 70:30 ratio. Model performance was evaluated using metrics like coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) in %, and severity index (SI). The results show that CS-HHO-optimized models significantly outperformed the unoptimized models, with the optimized stacking model providing superior prediction accuracy for predicting E. Both the unoptimized and optimized Stacking Models exhibited superior performance on the test data. The unoptimized Stacking Model achieved an R2 of 0.980, RMSE of 0.0483, MAE of 0.0223, MAPE of 12.412%, and SI of 0.1737, while the CS-HHO-optimized Stacking Model yielded a similar R2 of 0.980, with slight variations in RMSE (0.0497), MAE (0.0234), MAPE (13.5736%), and SI (0.1786). This study provides a robust predictive framework for rock behavior analysis, contributing to the field of mining and rock engineering project design.
Accurate parameter identification of lithium-ion (Li-ion) battery models is critical for understanding battery behavior and optimizing performance in electric vehicle (EV) applications. Traditional methods often rely ...
详细信息
Accurate parameter identification of lithium-ion (Li-ion) battery models is critical for understanding battery behavior and optimizing performance in electric vehicle (EV) applications. Traditional methods often rely on manual adjustments or trial-and-error processes, leading to inefficiencies and suboptimal outcomes. This study introduces a novel parameter identification approach using the marine predators algorithm (MPA), applied to a Shepherd model for EV applications. The proposed technique was validated under various dynamic test conditions, including the urban dynamic driving cycle (UDDC), the new European driving cycle (NEDC), and the worldwide harmonized light vehicles test procedure (WLTP). The MPA-based method systematically identifies optimal parameters, achieving a voltage error of 2.743 x 10-3, a state of charge (SOC) error of 0.7693 x 10-3, and a root mean square error (RMSE) of 8.37 x 10-3 between the model and real data. Compared to other optimization techniques, the MPA demonstrated superior performance, achieving an optimization efficiency of 97.69%. These results validate the robustness and reliability of the method for accurately capturing battery dynamics under realistic driving conditions. These results highlight the potential of the MPA-based approach in improving the accuracy of Li-ion battery parameter identification, leading to more efficient energy management in EVs and contributing to enhanced battery performance and reliability.
The Optimal Power Flow (OPF) problem has become increasingly pivotal in the planning and operation of modern power systems. With the expansion of the grid scale, the advent of smart grid technologies, and the unpredic...
详细信息
The Optimal Power Flow (OPF) problem has become increasingly pivotal in the planning and operation of modern power systems. With the expansion of the grid scale, the advent of smart grid technologies, and the unpredictable nature of renewable energy sources (RESs), interest in OPF has surged. These challenges with new energy storage have introduced a heightened level of uncertainty into the power system's operation as well as planning. Because of this, OPF is seen as an important tool for achieving different goals, such as optimizing the distribution of resources, making electrical networks more efficient, and so on. However, the OPF problem is inherently difficult to solve because of its non-linear characteristics. Different constraints and limitations intrinsic to real power system grids further accentuate this complexity. Moreover, modern power systems have incorporated new constraints, which make the OPF problem more complex in terms of mathematical formulation and solution. This paper offers a comprehensive and foundational review of OPF, covering the main concept, mathematical formulation, OPF types, comprehensive OPF optimization problem concepts, and the various methods developed to solve it. Additionally, it explores the evolution of these methods from conventional approaches to advanced and recent techniques, including mathematical methods and artificial intelligence methods, which include metaheuristic (search-based) and machine learning algorithms (data-driven). The paper also discusses various types of convex relaxation methods in depth. Ultimately, the paper highlights key gaps, challenges, and opportunities for future research.
In football economics, a player's transfer market value extends beyond performance metrics, with popularity playing a crucial role in clubs' decisions. Reputation indexes, reflecting a player's standing in...
详细信息
In football economics, a player's transfer market value extends beyond performance metrics, with popularity playing a crucial role in clubs' decisions. Reputation indexes, reflecting a player's standing in the industry, are derived from various sources. Traditional metrics include goals, assists, and defensive prowess, while social media activity (likes on Facebook and Instagram), press citations, and Wikipedia page views add a new dimension. This study utilized F & eacute;d & eacute;ration Internationale de Football Association 19 data and a real-world statistical dataset, encompassing 54 features for 491 players across various leagues. After adding valuable data and removing ineffective features and outliers, two filtering-based feature selection methods identified the 20 most critical features for predicting market value. The study applied Extreme Gradient Boosting and Adaptive Boosting regression models, along with their hybrid forms optimized by metaheuristicalgorithms. The Extreme Gradient Boosting optimized with the Ali Baba and Forty Thieves algorithm model showed the best performance, with a 99% match to actual values and a misestimation of around 1.9 million. Ensemble models, averaging predictions from all hybrid models, provided reliable market value estimates. These insights help managers make informed decisions to improve team performance and secure financial benefits for the club.
This study uses advanced metaheuristicalgorithms to solve energy-saving problems in the loop distribution network. An initiative energy management system (EMS) is suggested to deliver optimal commands to the loop pow...
详细信息
This study uses advanced metaheuristicalgorithms to solve energy-saving problems in the loop distribution network. An initiative energy management system (EMS) is suggested to deliver optimal commands to the loop power controller (LPC) whose operation is optimized by combining a metaheuristic algorithm with a ladder iterative technique. Here, the performance of state-of-the-art metaheuristicalgorithms applied in the proposed EMS-LPC solution is compared and evaluated by simulation in a real-world case study. Simulation results show that all metaheuristicalgorithms meet the optimization objective of reducing distribution loss in which the artificial ecosystem-based optimization (AEO) algorithm outperforms with both the lowest optimum value and the fastest convergence time. Consequently, the proposed EMS-LPC method results in a daily energy savings of 18% in comparison with the base case. Then, the proposed solution has potential for real-time applications to save grid power and reduce operating expenses due to the perfect performance of the suggested EMS-LPC approach.
Surface and surrounding building settlement is frequently caused by soil disturbance during subway tunnel construction, significantly impacting construction safety and structural stability. Traditional machine learnin...
详细信息
Surface and surrounding building settlement is frequently caused by soil disturbance during subway tunnel construction, significantly impacting construction safety and structural stability. Traditional machine learning models have shown some effectiveness in settlement prediction but often fail to capture the underlying physical mechanisms. This study proposed a novel physics-informed optimized extreme learning machine (PIOELM) to enhance prediction accuracy and physical interpretability. Based on the extreme learning machine (ELM), the model integrated the chaos adaptive sparrow search algorithm (CASSA) for parameter optimization and incorporated the Pasternak foundation model using automatic differentiation. The model's accuracy was validated using precise engineering data and compared against the physics-informed neural network (PINN), physicsinformed extreme learning machine (PIELM), and traditional data-driven models. The results show that the PIOELM model outperforms others in handling extreme values and maintains high accuracy across various scales of data prediction. Prediction accuracy improved by up to 85.29%, with a minimum improvement of 30.68%, demonstrating strong stability and generalization capabilities.
The optimal parameter identification of lithium -ion (Li -ion) battery models is essential for accurately capturing battery behavior and performance in electric vehicle (EV) applications. Traditional methods for param...
详细信息
The optimal parameter identification of lithium -ion (Li -ion) battery models is essential for accurately capturing battery behavior and performance in electric vehicle (EV) applications. Traditional methods for parameter identification often rely on manual tuning or trial-and-error approaches, which can be time-consuming and yield suboptimal results. In recent years, metaheuristic optimization algorithms have emerged as powerful tools for efficiently searching and identifying optimal parameter values. This paper proposes an optimal parameter identification strategy using a metaheuristicoptimization algorithm applied to a Shepherd model for EV applications. The identification technique that was based on the Self -adaptive Bonobo Optimizer (SaBO) performed extremely well when it came to the process of identifying the battery's unidentified properties. Because of this, the overall voltage error of the suggested identification technique has been lowered to 4.2377 x 10-3, and the root mean square error (RMSE) between the model and the data has been calculated to be 8.64 x 10-3. In addition, compared to the other optimization methods, the optimization efficiency was able to attain 96.6%, which validated its efficiency.
暂无评论