Explore the vast range of titles available.

Hyperspectral image classification stands as a pivotal task within the field of remote sensing, yet achieving high-precision classification remains a significant challenge. In response to this challenge, a Spectral Convolutional Neural Network model based on Adaptive Fick’s Law Algorithm (AFLA-SCNN) is proposed. The Adaptive Fick’s Law Algorithm (AFLA) constitutes a novel metaheuristic algorithm introduced herein, encompassing three new strategies: Adaptive weight factor, Gaussian mutation, and probability update policy. With adaptive weight factor, the algorithm can adjust the weights according to the change in the number of iterations to improve the performance of the algorithm. Gaussian mutation helps the algorithm avoid falling into local optimal solutions and improves the searchability of the algorithm. The probability update strategy helps to improve the exploitability and adaptability of the algorithm. Within the AFLA-SCNN model, AFLA is employed to optimize two hyperparameters in the SCNN model, namely, “numEpochs” and “miniBatchSize”, to attain their optimal values. AFLA’s performance is initially validated across 28 functions in 10D, 30D, and 50D for CEC2013 and 29 functions in 10D, 30D, and 50D for CEC2017. Experimental results indicate AFLA’s marked performance superiority over nine other prominent optimization algorithms. Subsequently, the AFLA-SCNN model was compared with the Spectral Convolutional Neural Network model based on Fick’s Law Algorithm (FLA-SCNN), Spectral Convolutional Neural Network model based on Harris Hawks Optimization (HHO-SCNN), Spectral Convolutional Neural Network model based on Differential Evolution (DE-SCNN), Spectral Convolutional Neural Network (SCNN) model, and Support Vector Machines (SVM) model using the Indian Pines dataset and Pavia University dataset. The experimental results show that the AFLA-SCNN model outperforms other models in terms of Accuracy, Precision, Recall, and F1-score on Indian Pines and Pavia University. Among them, the Accuracy of the AFLA-SCNN model on Indian Pines reached 99.875%, and the Accuracy on Pavia University reached 98.022%. In conclusion, our proposed AFLA-SCNN model is deemed to significantly enhance the precision of hyperspectral image classification.

An improved particle swarm optimization (PSO) with adaptive weighted delay velocity (PSO-AWDV) is proposed in this paper. A new scheme blending weighted delay velocity is firstly presented for a new PSO with weighted delay velocity (PSO-WDV) algorithm. Then, to adaptively update the velocity inertia weight, an adaptive PSO-AWDV algorithm is developed based on the evolutionary state of the particle swarm evaluated via a new estimation method. The newly proposed adaptive PSO-AWDV algorithm is tested based on some famous benchmark functions, which can confirm that the performance of PSO-AWDV is superior to several well-known PSO variants and intelligent optimization algorithms in literature.

This study introduces the Quick Group Search Optimizer with Passive Congregation (QGSOPC) coupled with the influence-matrix method to optimize cable forces in a completed 1 070 m, five-span, twin-tower cable-stayed bridge. Compared with the original design, QGSOPC reduces maximum tower-top displacement by 83.8% (84.1 → 13.6 mm), girder deflection by 41.9% (236.7 → 137.5 mm) and peak bending moment by 11% (118 078 → 105 120 kN·m), while lowering the composite objective function by 40.7%. A comparative analysis using GSO confirms the enhanced performance of the proposed algorithm. The results demonstrate that QGSOPC offers a practical, efficient tool for achieving the “straight-tower & level-beam” completion state of long-span cable-stayed bridges.

The LLC resonant converter, which is extensively utilized across various industrial fields, significantly depends on its parameters for performance optimization. This paper establishes a time-domain analytical model for the LLC resonant converter under Pulse Frequency Modulation (PFM) and proposes a multi-objective parameter optimization design method with stepwise constraints. The proposed method limits the resonant capacitor voltage while ensuring that the converter meets the voltage gain requirement and realizes Zero-Voltage Switching (ZVS). The converter’s performance is then optimized with the objective of minimizing the switching frequency range, the resonant inductor current, and the RMS value of the switching current on the secondary side. Compared with the existing methods, the proposed method has the advantages of comprehensive consideration and wide application scenarios. Finally, a 1200 W experimental prototype was fabricated, with experimental results verifying the feasibility of the proposed optimization design method and demonstrating that the prototype’s maximum efficiency reaches 96.54%.

Most of toolpaths for machining is composed of series of short linear segments (G01 command), which limits the feedrate and machining quality. To generate a smooth machining path, a new optimization strategy is proposed to optimize the toolpath at the curvature level. First, the three essential components of optimization are introduced, and the local corner smoothness is converted into an optimization problem. The optimization challenge is then resolved by an intelligent optimization algorithm. Considering the influence of population size and computational resources on intelligent optimization algorithms, a deep learning algorithm (the Double-ResNet Local Smoothing (DRLS) algorithm) is proposed to further improve optimization efficiency. The First-Double-Local Smoothing (FDLS) algorithm is used to optimize the positions of NURBS (Non-Uniform Rational B-Spline) control points, and the Second-Double-Local Smoothing (SDLS) algorithm is employed to optimize the NURBS weights to generate a smoother toolpath, thus allowing the cutting tool to pass through each local corner at a higher feedrate during the machining process. In order to ensure machining quality, geometric constraints, drive condition constraints, and contour error constraints are taken into account during the feedrate planning process. Finally, three simulations are presented to verify the effectiveness of the proposed method.

In response to the problems of slow convergence speed and overfitting in current machine learning models for slope stability prediction, this paper proposes a Global Search Whale Optimization Algorithm (GSWOA) based on a global search strategy to optimize the slope stability prediction model of the Kernel Extreme Learning Machine (KELM). Six parameters were selected as slope stability prediction indicators, including slope height ( H ), slope angle ( β ), unit weight ( γ ), cohesion ( c ), internal friction angle ( φ ) and pore water pressure ratio ( r u ). By collecting slope stability sample data from multiple literature sources, a slope stability prediction database containing 167 sets of slope engineering cases was established. Three global search strategies were introduced to optimize the Whale Optimization Algorithm (WOA), including adaptive weighting, variable spiral strategy, and optimal neighborhood perturbation strategy, the Extreme Learning Machine (ELM) was improved by kernel function, the GSWOA-KELM model for slope stability prediction was constructed. Comparing the model proposed in this paper with the unimproved WOA-KELM model, the results show that the testing set accuracy, precision, recall, and F1-score are 88.00%, 92.55%, 96.39%, and 0.9328, respectively, which are all superior to the compared model. The GSWOA-KELM model was applied to a construction project slope for verification, and the predicted results were completely consistent with the actual working conditions, indicating that the research results in this paper have certain guiding significance and application value for slope stability prediction.

With the progressive exploitation of hydropower resources, Pelton turbines have attracted growing global attention due to their significant potential in adapting to high-head, low-flow operating conditions. The complex nature of Pelton turbine regulation systems, characterized by nonlinearity and time delay, presents a significant challenge to traditional linear control approaches, which struggle to maintain stability and achieve desired regulation performance across diverse operating regimes. This study focuses on the nonlinear dynamic behavior of Pelton turbine regulation systems, establishing a detailed nonlinear dynamic model that integrates turbine dynamics, governor mechanisms, generator model and guide apparatus. To address the limitations of conventional PID control, including weak disturbance rejection, suboptimal regulation performance, and insufficient stability assurance, a novel active disturbance rejection PID (ADRC-PID) controller is proposed and comparatively analyzed with conventional control strategies. An improved intelligent optimization algorithm is employed to globally optimize the parameters of the ADRC-PID controller, and its efficacy is rigorously validated. Numerical simulations based on Simulink, and theoretical calculations collectively confirm the rationality of the optimized ADRC-PID parameters derived from the enhanced algorithm. The optimized parameters demonstrate significant improvements in regulation quality, including reduced overshoot, shortened settling time, and effective suppression of external disturbances, thereby enhancing both the operational reliability and cost-effectiveness of Pelton turbines.

This paper introduces an improved walking load model contemplating the influence of damping. The model employs the Hunt-Crossley model to guarantee the ground reaction forces generated when the support leg interfaces with the ground is zero. The model’s energetic compensation is realized by adjusting the leg’s rigidity. Lagrange’s equation is utilized to establish the equations of motion. To verify the accuracy of the proposed model, an intelligent optimization algorithm is employed to identify the initial parameters. The model simulated ground reaction forces are compared well with the measured ones. The model parameters are compared between the proposed ant-lion optimization algorithm and three other walking load models for simulating pedestrian walking loads. The parametric analysis reveals that: the walking duration increases with increasing roller radius and decreases with increasing walking speed and leg stiffness, and the peak ground reaction forces increase with increasing leg stiffness, damping ratio, walking speed, and impact angle and decrease with increasing roller radius. The proposed model is suitable for accurate prediction of the ground reaction forces induced from human walking and is a good way for simulating human-induced vibrations.

The internal structure of wind turbines is intricate and precise, although the challenging working conditions often give rise to various operational faults. This study aims to address the limitations of traditional machine learning algorithms in wind turbine fault detection and the imbalance of positive and negative samples in the fault detection dataset. To achieve the real-time detection of wind turbine group faults and to capture wind turbine fault state information, an enhanced ASL-CatBoost algorithm is proposed. Additionally, a crawling animal search algorithm that incorporates the Tent chaotic mapping and t-distribution mutation strategy is introduced to assess the sensitivity of the ASL-CatBoost algorithm toward hyperparameters and the difficulty of manual hyperparameter setting. The effectiveness of the proposed hyperparameter optimization strategy, termed the TtRSA algorithm, is demonstrated through a comparison of traditional intelligent optimization algorithms using 11 benchmark test functions. When applied to the hyperparameter optimization of the ASL-CatBoost algorithm, the TtRSA-ASL-CatBoost algorithm exhibits notable enhancements in accuracy, recall, and other performance measures compared with the ASL-CatBoost algorithm and other ensemble learning algorithms. The experimental results affirm that the proposed algorithm model improvement strategy effectively enhances the wind turbine fault detection classification recognition rate.

This paper aims to implement the path planning problem for mobile robot in complex environments by golden jackal optimization algorithm (GJO). To address the shortcomings of original GJO algorithm, such as poor exploitation ability and ease of getting stuck in a local optimal region, a multi-strategy improved GJO algorithm (MSGJO) is proposed. Firstly, the random selection strategy of the nonlinear composite adaptive convergence factor is designed to realize the reasonable balance between the exploration ability and the exploitation ability of GJO algorithm. Furthermore, an enhanced sparrow explorer location update strategy is proposed to further search the optimal individual of current iteration, which improves the efficiency of GJO algorithm moving in target direction. Then, the genetic algorithm’s variation strategy is added to randomly transform the disadvantaged individuals in the population into the dominant individuals. The performance of MSGJO algorithm is verified both on classical and CEC test functions (CEC2019 and CEC2022). Meanwhile, when applied to path planning problems, the proposed algorithm can effectively obtain the global optimal and smoother path. Through the results of simulations and experiments, it is demonstrated that the proposed algorithm has better performance than other compared algorithms in environment with both static and dynamic obstacles, which proving the global convergence, robustness, and local obstacle avoidance ability of the proposed algorithm.