The underground coal mine environment is complex, and traditional drilling path planning relies on experience, leading to issues such as high target deviation rates and excessive ineffective footage. This study constructs a three-dimensional trajectory geometric model, integrates geological and engineering constraints, and proposes an improved adaptive intelligent optimization algorithm. These measures enable precise planning and efficient optimization of underground directional drilling paths, providing technical support for safe and efficient coal mine drilling.

With advancements in simulation technology, fluid–thermal interaction (FTI) has become a vital tool in machinery powertrain development. Traditional engine cooling systems, with mechanically coupled components like water pumps and fans, lack adaptive cooling control. Electronic cooling systems, however, use variable-speed components to enhance performance. Combining FTI simulations with intelligent optimization algorithms offers a novel approach to designing control strategies for these systems. This study establishes a multi-objective optimization model for pump and fan speed control in electronic cooling systems. Using MATLAB/Simulink 2018 and Fluent 2022R1, co-simulations were performed, and an elite-strategy-based NSGA-II algorithm was implemented. Different weights were assigned to optimization objectives based on engine performance requirements. The results provide fitted functions for heat exchange capacity and cylinder liner temperature versus flow rates, along with optimal solutions for a 65 kW engine under three weight configurations. These findings support control strategy design and demonstrate the integration of FTI with genetic algorithms.

Abstract Deep learning techniques have been widely used in various fields. However, they face significant security challenges due to the existence of adversarial examples. Traditional black-box adversarial attack methods mainly rely on swarm intelligence optimization algorithms to identify optimal perturbation pixels, which requires intensive computational resources. In some typical applications such as medical image recognition, public datasets are often used to train deep learning models. It is worth noting that such dataset inherently contains some basis features for deep learning models to learn discriminative representations. And these features can serve as critical cues for constructing adversarial samples. Inspired by this observation, a novel adversarial attack method was proposed. First, some sensitive locations are identified within the dataset without querying the target model. Moreover, the adversarial attack samples are constructed based on these locations. Different from white-box and black-box attack, dataset characteristics are utilized to construct adversarial attack samples. The proposed method investigates naturally occurring vulnerabilities in the data, offering new insights for enhancing data augmentation techniques and attack strategies, while also providing a promising direction for improving model robustness. Experimental results demonstrate that this method can achieve attack effectiveness comparable to the Particle Swarm Optimization (PSO) algorithm.

The Pathfinder Algorithm (PFA) is a bionic swarm intelligence optimization algorithm inspired by simulating the cooperative movement of animal groups in nature to search for prey. Based on fitness, the algorithm classifies search individuals into leaders and followers. However, PFA fails to effectively balance the optimization capabilities of leaders and followers, leading to problems such as insufficient population diversity and slow convergence speed in the original algorithm. To address these issues, this paper proposes an enhanced pathfinder algorithm based on multi-strategy (EODE-PFA). Through the synergistic effects of multiple improved strategies, it effectively solves the balance problem between global exploration and local optimization of the algorithm. To verify the performance of EODE-PFA, this paper applies it to CEC2022 benchmark functions, three types of complex engineering optimization problems, and six sets of feature selection problems, respectively, and compares it with eight mature optimization algorithms. Experimental results show that in three different scenarios, EODE-PFA has significant advantages and competitiveness in both convergence speed and solution accuracy, fully verifying its engineering practicality and scenario universality. To highlight the synergistic effects and overall gains of multiple improved strategies, ablation experiments are conducted on key strategies. To further verify the statistical significance of the experimental results, the Wilcoxon signed-rank test is performed in this study. In addition, for feature selection problems, this study selects UCI real datasets with different real-world scenarios and dimensions, and the results show that the algorithm can still effectively balance exploration and exploitation capabilities in discrete scenarios.

The existing research on multi-component systems mostly assumes that the faults between components are independent and ignores their practical correlation, which will inevitably affect the calculation of system warranty cost and warranty availability. In order to quantitatively analyze the impact of fault independence and fault correlation between components on the minimum two-dimensional extended warranty (EW) cost-availability ratio of the system, this paper establishes a two-dimensional EW cost model and availability model for multi-component systems considering fault correlation based on incomplete periodic preventive maintenance (PM), and forms a warranty cost-availability ratio model accordingly. Subsequently, the artificial bee colony (ABC) intelligent optimization algorithm was introduced to solve the model, and a case study was conducted on the transmission system of a certain new energy vehicle. Through numerical comparison, it was found that considering fault correlation compared to the assumption of fault independence would increase the warranty cost-availability ratio of the system by 20%, providing more practical warranty references for users and manufacturers, and verifying the superiority of the model. Finally, a sensitivity analysis was conducted on the model to guide its more effective implementation and application.

A hybrid wind speed forecasting framework with decomposition denoising and intelligent optimization algorithms

ABSTRACT The proliferation of Open Radio Access Network (O‐RAN) architectures in 5G/6G networks introduces unprecedented cybersecurity challenges. Strategic base station deployment constitutes a fundamental determinant of network security posture and cyberattack resilience. In this paper, a novel cybersecurity‐driven deployment strategy for resilient base station positioning using an intelligent Resilient Ant Colony Optimization (iResACO) algorithm. The algorithm integrates security considerations directly into deployment optimization, employing bio‐inspired collective intelligence to discover patterns that balance coverage efficiency with attack resilience. Through extensive simulations in a 3.6 km 3.6 km urban environment in Riyadh, Saudi Arabia, experimental results demonstrate superior performance achieving 92.04% overall effectiveness with 96.0% coverage probability and 100% critical infrastructure protection. Under various cyberattack scenarios ranging from random to coordinated sophisticated attacks, the algorithm maintains coverage above 87% while preserving complete protection of critical facilities. The proposed approach provides a practical framework for deploying secure, resilient 5G/6G networks capable of withstanding evolving cyber threats while ensuring uninterrupted service to essential infrastructure.

The growing demand for customization in manufacturing industries such as automotive and home appliances has brought significant production challenges, making Mixed-Model Assembly Lines (MMALs) widely adopted in mass customization due to their flexibility advantages. The integrated optimization of order allocation and lot-sizing sequencing for MMALs under the Assembly-To-Order (ATO) mode is crucial, which needs to balance the minimization of assembly completion time, production line load balancing, and material consumption equalization. This paper addresses this integrated optimization problem by constructing a multi-objective mathematical model for joint decision-making. Furthermore, an improved multi-objective evolutionary algorithm (INSGA-II) is proposed. Specific encoding-decoding methods and neighborhood operators are designed to achieve effective search. Variable Neighborhood Descent (VND) is embedded to enhance local search capability. An elite archive with information feedback combined with the population diversity detection strategy is adopted to improve algorithm diversity. The purpose of this study is to enhance the efficiency of the production system and ensure the flexible production of multi-variety products and on-time delivery of orders through the proposed optimization scheme. By constructing multiple instances and conducting comparative experiments with other competitive algorithms, the results demonstrate that the performance of the improved algorithm is superior to that of other algorithms.

Shield thrust is a key control parameter for ensuring the safety and efficiency of tunnel construction. Under complex geological conditions and strong data nonlinearity, conventional prediction methods often fail to achieve sufficient accuracy. This study proposes a hybrid prediction model in which a bidirectional long short-term memory (BiLSTM) network is optimized by intelligent algorithms. A multidimensional input dataset comprising tunnel geometry, geomechanical parameters and tunnelling parameters is constructed, and BiLSTM is used to capture bidirectional temporal dependencies in the tunnelling data. To adaptively determine key BiLSTM hyperparameters (number of neurons, dropout rate and learning rate), four intelligent optimization algorithms—genetic algorithm (GA), particle swarm optimization (PSO), sparrow search algorithm (SSA) and Hunger Games Search (HGS)—are employed for hyperparameter tuning, using the root-mean-square error (RMSE) between predicted and measured values as the fitness function. Four hybrid models, GA–BiLSTM, PSO–BiLSTM, SSA–BiLSTM and HGS–BiLSTM, are validated using real engineering data from Beijing Metro Line 22, Guanzhuang–Yongshun shield-driven section. The results show that HGS–BiLSTM outperforms the other models in terms of RMSE, mean absolute error (MAE), mean absolute percentage error (MAPE) and coefficient of determination (R2) and exhibits faster convergence, supporting real-time prediction and decision-making in shield thrust control.

This research addresses the issues of low efficiency, high error rates in traditional manual railway brake shoe replacement, and the mismatch between existing automated equipment and actual needs due to insufficient technical adaptability. It designs an intelligent management and control system integrating NFC technology and intelligent optimization algorithms, adopting a hierarchical architecture (perception, transmission, decision-making layers). NFC realizes automatic data acquisition; SVM and GAM models achieve data matching and traceability; a hybrid GA-PSO algorithm optimizes scheduling. Experimental verification shows the system significantly improves recognition accuracy, scheduling efficiency, and anomaly response speed. Innovations include an NFC-based full-link data acquisition pathway, an SVM-KNN integrated model for accurate data alignment, and a GA-PSO hybrid mechanism for optimal resource allocation. It shifts from manual to algorithm-driven operations, providing a promotable paradigm for digital transformation of railway operation and maintenance.

Purpose. The purpose of this paper is to investigate ways to enhance the efficiency of transport and logistics systems in the context of global digital transformation and economic decarbonization. The study focuses on the optimization of transport routes using artificial intelligence technologies as a tool for reducing logistics costs and the carbon footprint of enterprises. Methodology. The research is based on a comprehensive methodological framework that integrates systemic, analytical, logical-structural, and comparative approaches. The study employs mathematical modeling, machine learning algorithms, big data analytics, and multi-criteria optimization techniques. To evaluate the model’s performance, a digital twin of the transport network was developed, allowing the simulation of various transportation scenarios in real time. The optimization model combines three key parameters-logistics costs, CO₂ emissions, and delivery time-using adjustable weighting coefficients according to enterprise-specific priorities. Findings. The results of simulation modeling demonstrate that the implementation of AI-driven routing technologies enables a reduction in fuel consumption by 18.7%, a decrease in average delivery time by 12.3%, a reduction in CO₂ emissions by 20.1%, and an overall decrease in logistics costs by 22.4%. These outcomes are consistent with global trends in the digital transformation of logistics and confirm the effectiveness of intelligent transport systems in achieving sustainable development objectives. The application of machine learning, genetic algorithms, and particle swarm optimization provided superior stability of solutions and adaptability to changing operational conditions. Practical implications. The developed model can be applied by enterprises of different sizes to increase competitiveness, reduce operational costs, and meet climate targets. The findings may also support the design of public policies aimed at promoting sustainable transport, digitalization, and decarbonization across the economy. Value / originality. The study contributes to the advancement of green logistics and the concept of sustainable digital supply chains by integrating intelligent optimization algorithms into transport management. It presents a conceptual and methodological framework for AI-based optimization of transport operations, which bridges economic efficiency and environmental sustainability. Future research should focus on developing industry standards for AI integration in logistics systems, creating hybrid optimization algorithms, and exploring the socio-economic impacts of digital transformation in the transport sector.

In the background of sustainable development in the construction industry, recycled cement mortar (RCM) has emerged as a research hotspot due to its eco-friendly features, where mechanical properties serve as critical indicators for evaluating its engineering applicability. This study proposes an artificial neural network (ANN) model optimized by intelligent algorithms, including the GWO (grey wolf optimizer), PSO (particle swarm optimization), and a GA (genetic algorithm), to predict the compressive strength of recycled mortar. By integrating experimental and prediction data, we establish a comprehensive database with eight input variables, including the water–cement ratio (W/C), cement–sand ratio (C/S), fly ash content (FA), aggregate replacement rate (ARR), and curing age. The predictive performance of neural network models with different database sizes (database 1: experimental data of RCM; database 2: experimental data of RCM and ordinary mortar; database 3: model prediction data of RCM, experimental data of RCM, and ordinary mortar) is analyzed. The results show that the intelligent optimization algorithms significantly enhance the predictive performance of the ANN model. Among them, the PSO-ANN model demonstrates optimal performance, with R2 = 0.92, MSE = 0.007, and MAE = 0.0632, followed by the GA-ANN model and the GWO-ANN model. SHAP analysis reveals that the W/C, C/S, and curing age are the key variables influencing the compression strength. Furthermore, the size of the dataset does not significantly influence the computation time for the above models but is primarily governed by the complexity of the optimization algorithms. This study provides an efficient data-driven method for the mix design of RCM and a theoretical support for its engineering applications.

Purpose The purpose of this study is to introduce a novel swarm intelligence optimization algorithm, termed Anolis Optimizer (ANO), which emulates the behavior of Anolis lizards in their quest for optimal territorial habitat locations, thereby addressing optimization problems. Design/methodology/approach The ANO utilizes a three-stage framework. First, the population dynamically divides into invaders and defenders, simulating Anolis’s territory awareness. Second, territory exploration employs an exploration operator mimicking the invaders’ movement. Finally, territory competition incorporates violent disputes via competition/escape operators, while dewlap conversion and escape operators simulate non-violent competition; uninvaded defenders undergo free movement modeling. Findings Evaluation results across the 23 classical test functions, as well as CEC 2017, CEC 2021 and CEC2022 benchmark suites, demonstrate that ANO achieves a 60.8% optimization rate, significantly outperforming the best result (39.2%) among 10 comparative algorithms. The algorithm exhibits exceptional performance in solving unimodal, fixed-dimensional multimodal and hybrid composition functions, with progressively enhanced convergence stability in later iterations. And it performs outstandingly in engineering optimization problems. Originality/value This study pioneers the first competitive algorithm based on Anolis territorial behavior, establishing a dynamically decoupled population architecture that enables real-time agent role partitioning and innovatively developing a multi-attack coordination mechanism. This work delivers the inaugural lizard-competition-behavior-driven optimization paradigm in swarm intelligence, overcoming the inherent limitations of abstract single-mode competition in existing algorithms, thereby establishing new theoretical foundations for engineering optimization problems. The source code is currently available for public from: https://www.mathworks.com/matlabcentral/fileexchange/181614-anolis-optimizer-ano

As a product of the deep integration between next-generation information technology and industrial systems, digital twin technology has demonstrated significant advantages in real-time monitoring, predictive maintenance, and optimization decision-making for thermal power plants. To address challenges such as low equipment efficiency, high maintenance costs, and difficulties in safety risk management in traditional thermal power plants, this study developed a digital twin simulation system that covers the entire lifecycle of power generation units. The system achieves real-time collection and processing of critical parameters such as temperature, pressure, and flow rate through a collaborative architecture integrating multi-source heterogeneous sensor networks with Programmable Logic Controllers (PLCs). A three-tier processing framework handles data preprocessing, feature extraction, and intelligent analysis, while establishing a hybrid storage system combining time-series databases and relational databases to enable millisecond-level queries and data traceability. The simulation model development module employs modular design methodology, integrating multi-physics coupling algorithms including computational fluid dynamics (CFD) and thermal circulation equations. Automated parameter calibration is achieved through intelligent optimization algorithms, with model accuracy validated via unit-level verification, system-level cascaded debugging tests, and virtual test platform simulations. Based on the modular layout strategy, the user interface and interaction module integrates 3D plant panoramic view, dynamic equipment model and multi-mode interaction channel, supports cross-terminal adaptation of PC, mobile terminal and control screen, and improves fault handling efficiency through AR assisted diagnosis function.

In modern times, magnetic resonance imaging-based brain tumor detection has gained significant attention due to its ability to provide high-quality images across various spatial resolutions, which improves diagnostic accuracy. Despite that, imbalanced classes and poor-quality images are the main challenges that complicate training models. Besides, many researchers have established various methods to address these aforementioned issues, but have suffered from interpretability issues and poor accuracy due to the lack of sufficient information. Therefore, this research proposes an automated intelligent tracking scout optimization-based shuffle attention-enabled deep convolutional neural network (ISADCN) model for accurate brain tumor detection. The proposed model integrates shuffle attention and the intelligent tracking scout optimization (ITSO) algorithm, which highlights proper semantic features and adjusts the hyperparameters to improve accuracy in brain tumor detection. In line with this, the proposed model integrates an ITSO-optimized ResUNet to enable accurate and adaptive segmentation of tumor regions. Additionally, the proposed model addresses interpretation issues and overcomes computational complexity, also quite significant for accurately detecting brain tumors in real-world scenarios. On top of that, the ISADCN model greatly achieves an overall accuracy of 96.84%, a positive predictive value of 97.91%, and a negative predictive value of 95.97% when compared with other state-of-the-art methods.

In plateau and high-altitude areas, freeze-thaw cycles often alter the uniaxial compressive strength (UCS) of rock, thereby impacting the stability of geotechnical engineering. Acquiring rock samples in these areas for UCS testing is often time-consuming and labor-intensive. This study developed a hybrid model based on the XGBoost algorithm to predict the UCS of rock under freeze-thaw conditions. First, a database was created containing longitudinal wave velocity (Vp), rock porosity (P), rock density (D), freezing temperature (T), number of freeze-thaw cycles (FTCs), and UCS. Four swarm intelligence optimization algorithms—artificial bee colony, Newton–Raphson, particle swarm optimization, and dung beetle optimization—were used to optimize the maximum iterations, depth, and learning rate of the XGBoost model, thereby enhancing model accuracy and developing four hybrid models. The four hybrid models were compared to a single XGBoost model and a random forest (RF) model to evaluate overall performance, and the optimal model was selected. The results demonstrate that all hybrid models outperform the single models. The XGBoost model optimized by the sparrow algorithm (R2 = 0.94, RMSE = 10.10, MAPE = 0.095, MAE = 7.22) performed best in predicting UCS. SHapley Additive exPlanations (SHAP) were used to assess the marginal contribution of each input variable to the UCS prediction of freeze-thawed rock. This study is expected to provide a reference for predicting the UCS of freeze-thawed rock using machine learning.

Big data and artificial intelligence technologies are driving a paradigm shift in smart farming, yet intelligent decision-making faces critical bottlenecks. At the data level, challenges include fragmentation, high acquisition costs, and inadequate secure sharing; at the model level, issues involve regional heterogeneity, weak adaptability, and insufficient explainability. To address these, this paper systematically reviews global research to establish a theoretical framework spanning the entire production cycle. Regarding data governance, trends favor federated systems with unified metadata and layered storage, utilizing technologies like federated learning for secure lifecycle management. For decision-making, approaches are evolving from experience-based to data-driven intelligence. Pre-harvest planning now integrates mechanistic models and transfer learning for suitability and variety optimization. In-season management leverages deep reinforcement learning (DRL) and model predictive control (MPC) for precise regulation of seedlings, water, fertilizer, and pests. Post-harvest evaluation strategies utilize spatio-temporal deep learning architectures (e.g., Transformers or LSTMs) and intelligent optimization algorithms for yield prediction and machinery scheduling. Finally, a staged development pathway is proposed: prioritizing standardized data governance and foundation models in the short term; advancing federated learning and human–machine collaboration in the mid-term; and achieving real-time, ethical edge AI in the long term. This framework supports the transition toward precise, transparent, and sustainable smart agriculture.

To address the inherent limitations of the standard Sine Cosine Algorithm (SCA) in multi-threshold image segmentation, this paper proposes an enhanced algorithm named the Reinforcement Learning–Thermal Conduction–Sine Cosine Algorithm (RLTC-SCA), with symmetry as a core guiding principle. Symmetry, a fundamental property in nature and image processing, refers to the invariance or regularity of grayscale distributions, texture patterns, and structural features across image regions; this characteristic is widely exploited to improve segmentation accuracy by leveraging consistent spatial or intensity relationships. In multi-threshold segmentation, symmetry manifests in the balanced distribution of optimal thresholds within the grayscale space, as well as the symmetric response of segmentation metrics (e.g., PSNR, SSIM) to threshold adjustments. To evaluate the optimization performance of RLTC-SCA, comprehensive numerical experiments were conducted on the CEC2020 and CEC2022 benchmark test suites. The proposed algorithm was compared with several mainstream metaheuristic algorithms. An ablation study was designed to analyze the individual contribution and synergistic effects of the three enhancement strategies. The convergence behavior was characterized using indicators such as average fitness value, search trajectory, and convergence curve. Moreover, statistical stability was assessed using the Wilcoxon rank-sum test (at a significance level of p = 0.05) and the Friedman test. Experimental results demonstrate that RLTC-SCA outperforms all comparison algorithms in terms of average fitness, convergence speed, and stability, ranking first on both benchmark test suites. Furthermore, RLTC-SCA was applied to multi-threshold image segmentation tasks, where the Otsu method was adopted as the objective function. Segmentation performance was evaluated on multiple benchmark images under four threshold levels (2, 4, 6, and 8) using PSNR, FSIM, and SSIM as evaluation metrics. The results indicate that RLTC-SCA can efficiently obtain optimal segmentation thresholds, with PSNR, FSIM, and SSIM values consistently higher than those of competing algorithms—demonstrating superior segmentation accuracy and robustness. This study provides a reliable solution for improving the efficiency and precision of multi-threshold image segmentation and enriches the application of intelligent optimization algorithms in the field of image processing.

Based on the air-ground collaborative logistics distribution model using UAVs and vehicles, this paper addresses the logistics scenario of delivering before picking up. Considering factors such as customer priority, vehicle cost, and UAV cost, with the objective of minimizing the total travel cost, we propose the Air-ground Collaborative Logistics Transportation Scheduling Problem with Pickup and Delivery Considering Customer Priority (ALTSPPDCP). Based on the characteristics of the model, the use of heuristic algorithms can efficiently solve such optimization problems, avoiding the time-consuming exhaustive search and improving the quality of the solutions. This paper designs a multi-layer, multi-stage encoding and decoding strategy based on the Three-Learning Strategy Particle Swarm Optimization algorithm, integrating the ascending order sorting method and dynamic segmentation method to transform the particle space into the model space. An intelligence optimization algorithm for solving ALTSPPDCP is proposed. Finally, In the 50-node scenario of the model comparison, the vehicle-UAV schema achieved a total cost that was 14.86% lower than that of the vehicle-only schema. In the algorithm comparison experiment, the optimal solution obtained by TSLPSO reduced costs by 39.99% and 27.94% compared to PSO and RPSO, respectively.

To detect underwater targets with low energy consumption in complex ocean environments, a model of seabed topography and currents is established based on the actual ocean environment. Additionally, a model for AUV motion, energy consumption, and sonar detection is established to effectively accomplish the task of detecting underwater targets. To address the issue of insufficient search space with increasing iterations in the Whale Optimization Algorithm, this paper proposes a Multi-Strategy Whale Optimization Algorithm (MSWOA) by incorporating initial reverse learning, stochastic inertia factor, and Cauchy mutation strategy. This modification effectively accelerates convergence speed and prevents convergence to local optimal solutions. Finally, simulation experiments and statistical analysis confirm the effectiveness of the detection target task model proposed in this paper, based on the principle of low energy consumption. The MSWOA exhibits superior performance in terms of solution accuracy, convergence speed, and stability compared to other intelligent optimization algorithms, meeting the path planning requirements for AUV navigation.