Search Results (76)

Medical and pharmaceutical last-mile deliveries are simultaneously expected to be fast, reliable and temperature-safe for patients and to become measurably greener, yet these objectives often pull transport operations in opposite directions. Third-party logistics (3PL) providers are therefore increasingly required not only to report transport CO₂ emissions, but also to learn from them; however, it remains unclear whether the routine operational data they collect are sufficiently informative to enable such emission-based learning in this regulated and service-critical setting. This study examines the predictive limits of machine learning models in estimating CO₂ emissions in medical and pharmaceutical last-mile deliveries performed by a 3PL operator. Using operational data from six customers, we compare global and customer-specific models for the following two dependent variables: total CO₂ emissions per transport operation and CO₂ emissions per pallet. Linear and non-linear models, including linear regression, ElasticNet, Random Forest, HistGradientBoosting and XGBoost, are evaluated using chronological train-test splitting and cross-validation. The results show that global models fail to outperform a naïve benchmark, with negative R² values for both emission measures. Customer-level models reveal substantial heterogeneity as follows: for selected customers, especially those with more regular operational patterns, moderate predictive performance is achieved, while for others, emissions remain largely unpredictable using the available variables. The findings suggest that routine shipment-level data are insufficient for robust emission prediction in 3PL last-mile operations. Emission-based learning requires richer contextual, vehicle, route, traffic and telematics data, as well as customer-sensitive modelling approaches. The study contributes by identifying the data and modelling limits of sustainability intelligence in medical and pharmaceutical last-mile logistics. Full article

The Artificial Bee Colony (ABC) algorithm is widely used for continuous optimization, but the standard ABC still suffers from insufficient use of neighborhood information, limited adaptability of search behavior, and random restarts in the scout bee phase, which may lead to slow convergence and reduced solution quality on complex problems. To address these limitations, this paper proposes an artificial bee colony algorithm with dual groups and multiple strategies based on reinforcement learning, named RLDMS-ABC. In the employed bee phase, Q-learning is used to adaptively adjust the neighborhood size of each food source according to search feedback, and the best individual selected from the sampled neighborhood guides candidate solution generation. In the onlooker bee phase, selected food sources are divided into elite and ordinary groups according to relative quality, and different search strategies are assigned to balance exploration and exploitation. In the scout bee phase, a guided restart mechanism combining opposition-based learning and the current global best solution is designed to help stagnated individuals escape local optima. Experiments on the CEC 2014 benchmark set show that RLDMS-ABC outperforms several representative ABC variants on most functions in terms of solution quality, convergence speed, and robustness. Full article

In modern power-system load frequency control (LFC), proportional–integral–derivative (PID) controllers are widely used because of their simple structure and ease of implementation. However, the combined effects of communication delay and nonlinear constraints can degrade control performance. To address this issue, this paper proposes a model-constraint-aware optimal PID tuning method based on a Hybrid Differential Evolution–Chaotic Grey Wolf Optimizer (HDE-CGWO). First, a nonlinear LFC model incorporating data sampling, communication delay, governor deadband (GDB), and generation rate constraint (GRC) is established, and a PID-based LFC model is formulated. Next, an objective function based on the integral of time-weighted absolute area control error (ACE), namely ACE-based integral of time-weighted absolute error (ITAE), is constructed. Accordingly, quasi-opposition-based learning (QOBL), chaotic warm-up, Lévy flight, and differential evolution (DE) are incorporated into the standard Grey Wolf Optimizer (GWO) to develop an HDE-CGWO-based PID design scheme for LFC under sampled-data delay and nonlinear unit constraints. Finally, simulation studies are carried out on a multi-area LFC system. The resulting time-domain responses and statistical results show that, compared with standard GWO in the single-area test, HDE-CGWO reduces the ACE-based ITAE by about 43.3%. In the three-area system, the ACE-based ITAE is reduced by about 3.0% under step disturbances and about 1.4% under random disturbances compared with the warm-up Grey Wolf Optimizer (WGWO), indicating that the proposed method can reduce frequency deviations, attenuate post-disturbance oscillations, and accelerate the dynamic recovery process under the considered disturbance conditions. Full article

As critical underground engineering structures, wellbores may suffer complex structural deterioration and hidden safety hazards may be encountered during drilling. Multi-source sensor monitoring data provides an effective data basis for structural health perception and early warnings for wellbore structures at risk. The inherent diversity of formation conditions and the dynamic disturbances during drilling jointly lead to the differentiated presentation of drilling loss types, among which fractured, permeable, and vuggy losses are the most typical. This paper focuses on fractured wellbore leakage, regards wellbore leakage as an important structural failure form of underground drilling engineering structures. In-depth analysis and research on the structural deterioration mechanism of wellbore leakage were conducted, and we propose a wellbore leakage prediction method based on the improved sparrow search algorithm (ISSA) optimized gradient boosting decision tree (XGBoost). First, the Sobol sequence is adopted to replace the random initialization strategy, combined with the opposition-based learning mechanism; then, an adaptive Levy flight search mechanism is introduced to dynamically adjust the population ratio of discoverers and vigilantes; finally, intelligent optimization technologies are integrated to reconstruct the position update strategies of discoverers, followers, and vigilantes, enhancing the optimization adaptability of the algorithm. Relying on multi-field sensor monitoring datasets collected from actual drilling engineering, this paper compares the proposed model with wellbore leakage prediction models built by classical machine learning algorithms, and verifies its generalization ability on different datasets. Experimental data indicate that the improved algorithm exhibits significant advantages in optimization accuracy, enabling the proposed model to achieve an AUC improvement of 4.46%, along with accuracy (95.1%), precision (94.9%), recall (94.7%), and F1-score (94.2%). On this basis, the ISSA was applied to the hyperparameter optimization of XGBoost, constructing the ISSA-XGBoost prediction model. The method has high accuracy and good generalization ability in fractured wellbore leakage prediction, and it can realize intelligent health monitoring of underground wellbore structures, including early warnings. This study provides a reliable sensing data analysis scheme and technical support for structural health monitoring and hazard prevention in drilling engineering. Full article

Lake Taihu is a vital source of surface water for the Yangtze River Delta region, so effective monitoring of its water quality is essential for protecting the water source. However, most existing studies on unmanned aerial vehicle (UAV)-based water quality remote sensing have focused on single large rivers or lakes, primarily employing validation methods involving randomly selected samples. This makes it difficult to assess the generalisability of the models to unfamiliar watercourses. This study focuses on 13 inflow rivers on Xishan Island, a central island in Lake Taihu, which are characterized by short flow paths, independent catchment areas, and varying land use influences. Using a UAV multispectral remote sensing platform, we have designed a water quality monitoring and assessment framework tailored to multi-river systems with small sample sizes. First, various water body indices were developed and analysed for correlation with measured water quality parameters. Then, machine learning algorithms such as Backpropagation (BP) neural networks, Random Forest, XGBoost, Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) were selected to construct retrieval models. For accuracy evaluation, a spatial independent validation strategy was employed whereby one sample was forcibly set aside from each river to constitute the validation set. Using this method, we generated spatial distribution maps of water quality parameters for the inflow rivers and evaluated the influencing factors of spatial variation in water quality by area, taking into account water body functional types and ecological characteristics. The experimental results indicate that under the conditions of spatial independent validation strategy, the SVM model achieved the highest retrieval accuracy for dissolved oxygen (R² = 0.892, RMSE = 0.414 mg/L and MRE = 0.057), whereas the XGBoost model achieved the highest retrieval accuracy for turbidity (R² = 0.853, RMSE = 0.632 NTU and MRE = 0.065). The spatial pattern of water quality exhibited a pronounced gradient: dissolved oxygen (DO) concentrations followed the order of aquaculture area rivers > agricultural area rivers > urban area rivers, while turbidity displayed the opposite trend, reflecting that surrounding land use types, phytoplankton density, and human activity intensity are the dominant factors driving the spatial differentiation of river water quality on Xishan Island in spring. The full-chain technical framework of “multi-river synchronous retrieval—spatially independent validation strategy—area mechanistic assessment” proposed in this study provides a replicable evaluation paradigm for rapid water quality monitoring of Lake Taihu islands and similar watersheds, and holds significant implications for the construction of the Lake Taihu Eco-Island and the protection of the water environment. Full article

Aiming at the inherent limitations of the basic White Shark Optimizer (WSO), such as insufficient population diversity, unbalanced global and local search mechanisms, and weak convergence in the later stage, this paper proposes an Improved White Shark Optimizer (IWSO). The algorithm is improved from the following three aspects: Firstly, the Tent chaotic map is introduced to replace the traditional random initialization in the population initialization stage. Secondly, an adaptive nonlinear convergence factor and a dynamic inertia weight adjustment strategy are designed to focus on the fine search in the neighborhood of the optimal solution. Thirdly, the Levy flight perturbation mechanism and the elite opposition-based learning strategy are integrated to expand the search range and further accelerate the convergence speed. To verify the effectiveness and superiority of the IWSO algorithm, the CEC2017 test suite is selected for simulation experiments, and the IWSO is systematically compared with seven other representative swarm intelligence algorithms. The experimental results show that the IWSO is significantly superior to all comparison algorithms in multiple evaluation indicators, including minimum makespan, average convergence value, standard deviation, and successful convergence rate, on scheduling instances of different scales and difficulties. The convergence curve remains leading throughout the iteration process and shows a smoother convergence trend. The multi-strategy enhanced white shark optimizer proposed in this paper effectively overcomes the inherent defects of the basic algorithm, significantly improves the solution accuracy and convergence efficiency of the job shop scheduling problem, and has high theoretical research value and practical engineering application prospects. In the future, the multi-strategy improved White Shark Optimizer will be extended to multi-objective job shop scheduling, dynamic disturbance job shop scheduling, and large-scale production scheduling scenarios with numerous workpieces and machines. Full article

The black-winged kite algorithm (BKA) integrates the Cauchy mutation strategy and the leader selection strategy to simulate high-altitude circling exploration, fixed-point diving attack, and group cooperative migration of the black-winged kites to approximate the global optimal solution. The BKA exhibits deficiencies in ponderous convergence efficacy, inefficient calculation precision, and insufficient population diversity. To strengthen the convergence property and computational practicability, an enhanced BKA with multiple strategies (MSBKA) is advocated to accommodate global optimization and constrained engineering applications. The objective is to systematically verify its advancement and competitiveness and accurately actualize the global optimal solution. The ranking-based differential mutation can strengthen population information interaction, accelerate convergence efficiency, restrain premature convergence, diminish homogenization competition, promote exploration and exploitation, intensify elite individual guidance, downscale ineffective iterations, and materialize orderly population renewal. The simplex method can execute the local refinement operations of reflection, expansion, compression and contraction, strengthen local mining efficiency, ameliorate solution accuracy, abate parameter sensitivity, eschew local optimal traps, accelerate accurate convergence, and preserve the optimal individual potential. The elite opposition-based learning strategy can fabricate reverse solutions, expand the monolithic detection space, shorten the convergence process, elevate the quality of initial and iterative solutions, boost population diversity, guide intelligent search direction, and relieve premature convergence. The MSBKA utilizes deficiency orientation, strategy adaptation, and collaborative search to accomplish the realistic demands of high-precision, high-efficiency and strong constraint adaptation, surmount the static trade-off dilemma, endow a strong directional abscond mechanism to replace random perturbation, and actualize the inertia of directional exploration and the blind spots of solution exploitation. Twenty-three benchmark functions and six real-world engineering designs are employed to authenticate theoretical superiority and engineering practicability. The experimental results demonstrate that the MSBKA incorporates strong practicability and reliability to strengthen information interaction, restrain search stagnation, diminish convergence oscillation and fluctuation, facilitate globalized discovery and localized extraction, expedite convergence efficacy, ameliorate solution precision, and consolidate stability and robustness. Full article

The large-scale grid integration of distributed renewable energy enhances the flexible regulation capacity of the power system. However, the inherent randomness and volatility of its output, coupled with weak coupling access characteristics, pose severe challenges to the safe and stable operation of the power system. To address these issues, this paper proposes a power system planning method suitable for urban power grids. To accurately characterize the uncertainty of renewable energy output, the method incorporates the concept of multi-scenario stochastic optimization and introduces a dynamic scenario generation method for wind and solar power based on nonparametric kernel density estimation and standard multivariate normal distribution sequence sampling. This method generates a set of typical daily dynamic output scenarios for wind and solar power that closely match actual output characteristics. Considering the spatiotemporal response characteristics of flexible resources, the Soft Open Point (SOP) DC link enables flexible cross-node power transmission and spatiotemporal coupling regulation of flexible resources. Therefore, this paper constructs a mathematical model for the grid integration of flexible resources based on the SOP DC link. By integrating operational constraints such as power flow constraints in the power grid and source-load uncertainty constraints, a power system planning model is established. However, traditional convex optimization methods require approximate simplifications of the model, which can easily lead to a loss of accuracy. Although the Particle Swarm Optimization (PSO) algorithm is suitable for nonlinear optimization, it is prone to getting trapped in local optima. Therefore, this paper introduces an improved PSO algorithm based on refraction opposite learning, which enhances the algorithm’s global optimization capability by expanding the particle search space and increasing population diversity. Finally, simulation verification is conducted based on an improved IEEE-39 bus test system, and the results show that the proposed scenario generation method achieves a sum of squared errors of only 4.82% and a silhouette coefficient of 0.94, significantly improving accuracy compared to traditional methods such as Monte Carlo sampling. Full article

Many complex engineering problems can be formulated as mathematical optimization tasks, for which bio-inspired metaheuristic algorithms have demonstrated outstanding effectiveness. Drawing inspiration from snake behavior, the Snake Optimizer (SO) algorithm provides a promising framework but suffers from random population initialization, insufficient global search capability, and slow convergence. To address these drawbacks, the study proposes a Modified Snake Optimizer (MSO) that integrates three key strategies: a dual mapping strategy based on Latin hypercube sampling and logistic mapping for population initialization; an opposition-based learning mechanism with scaling factors for exploration; and integration of the soft-rime search strategy from RIME optimization during exploitation. The performance of MSO was benchmarked against nine representative algorithms using the CEC2017 and further validated on three engineering application problems—pressure vessel, tension/compression spring, and hydrostatic thrust bearing design, and two UAV path planning scenarios. Experimental results show that MSO achieves faster convergence speed, stronger robustness and greater stability, effectively extending the biomimetic principles of the original SO and confirming its superiority for solving optimization problems. Full article

Due to their complexity and nonlinearity, metaheuristic algorithms have become the standard in problem solving for problems that cannot be solved by standard computational solutions. However, the global performance of these algorithms is strongly linked to the population structuring and the mechanism of replacing the worst solutions within the population. In this paper, an Adaptive Artificial Hummingbird Algorithm (AAHA), a new version of the basic AHA, is introduced and designed to enhance performance by studying the impacts of different population initialization methods within a broad and continual migration form. For the initialization phase, four methods—the Gaussian chaotic map, the Sinus chaotic map, opposite-based learning (OBL), and diagonal uniform distribution (DUD)—are proposed as an alternative to the random population initialization method. A new strategy is proposed as a replacement for the worst solution in the migration phase. The new strategy uses the best solution as an alternative to the worst solution with simple and effective local search. The proposed strategy stimulates exploitation and exploration when using the best solution and local search, respectively. The proposed AAHA is tested through various benchmark functions with different characteristics under many statistical indices and tests. Additionally, the AAHA results are benchmarked against those of other optimization algorithms to assess their effectiveness. The proposed AAHA outperformed alternatives in terms of both speed and reliability. DUD-based initialization enabled the fastest convergence and optimal solutions. These findings underscore the significance of initialization in metaheuristics and highlight the efficacy of the AAHA for complex continuous optimization problems. Full article

To achieve accurate voltage sag prediction and early warning, thereby improving power quality, a hybrid voltage sag prediction framework is proposed by integrating Kernel Entropy Component Analysis (KECA) with an improved Northern Goshawk Optimization (NGO) algorithm for hyperparameter tuning of a CNN-LSTM model. First, to address the limitations of the original NGO, such as proneness to falling into local optima and high randomness of the initial population distribution, a refraction-opposition-based learning mechanism is introduced to enhance population diversity and expand the search space. Furthermore, a sine–cosine strategy (SCA) with nonlinear weight coefficients is integrated into the exploration phase to dynamically adjust the search step size, optimizing the balance between global exploration and local exploitation, thereby boosting convergence speed and accuracy. The improved algorithm (SCNGO) is then utilized to optimize the hyperparameters of the CNN-LSTM model. Second, KECA is applied to voltage-sag-related data to extract key features and eliminate redundant information, and the resulting dimensionally reduced data are fed as input to the SCNGO-CNN-LSTM model to further improve prediction performance. Experimental results demonstrate that the SCNGO-CNN-LSTM model outperforms other comparative models significantly across multiple evaluation metrics. Compared with NGO-CNN-LSTM, GWO-CNN-LSTM, and the original CNN-LSTM, the proposed method achieves a mean squared error (MSE) reduction of 53.45%, 44.68%, and 66.76%, respectively. The corresponding root mean squared error (RMSE) is decreased by 25.33%, 18.61%, and 36.92%, while the mean absolute error (MAE) is reduced by 81.23%, 77.04%, and 86.06%, respectively. These results confirm that the proposed framework exhibits superior feature representation capability and significantly improves voltage sag prediction accuracy. Full article

The rapid growth of electric vehicle (EV) adoption poses significant challenges for the rational planning of charging infrastructure, where economic efficiency and service quality are inherently conflicting. To support scientific decision-making in charging station siting, this study proposes an integrated multi-objective optimization and decision-support framework that combines an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II) with an entropy-weighted TOPSIS method. A bi-objective siting model is developed to simultaneously minimize total operator costs and maximize user satisfaction. User satisfaction is explicitly characterized by a nonlinear charging distance perception function and a queuing-theoretic waiting time model, enabling a more realistic representation of user service experience. To enhance convergence performance and solution diversity, the NSGA-II algorithm is improved through variable-wise random chaotic initialization, opposition-based learning, and adaptive crossover and mutation operators. The resulting Pareto-optimal solutions are further evaluated using an improved entropy-weighted TOPSIS approach to objectively identify representative compromise solutions. Simulation results demonstrate that the proposed framework achieves superior performance compared with the standard NSGA-II algorithm in terms of operating cost reduction, user satisfaction improvement, and multi-objective indicators, including hypervolume, inverted generational distance, and solution diversity. The findings confirm that the proposed NSGA-II–TOPSIS framework provides an effective, robust, and interpretable decision-support tool for EV charging station planning under conflicting objectives. Full article

Accurate prediction of shallow soil temperature is essential for agriculture, geotechnical design, and ground-coupled energy systems. This study proposes a novel hybrid machine-learning framework in which four tree-based regressors (Decision Tree, Random Forest, XGBoost, and Bagging) are optimized using a newly developed Tri-phase Opposition Adaptive Random Search (TOARS) algorithm. Soil temperature measurements collected in 2024 at depths of 1.0 m and 2.0 m were combined with meteorological variables to train and evaluate the models. TOARS optimization reduced prediction errors by up to 32% for MAE and 28% for RMSE compared with default hyperparameters. At 1.0 m, the optimized Decision Tree achieved MAE = 0.29 °C, RMSE = 0.41 °C, and R² = 0.9993, while at 2.0 m, XGBoost reached MAE = 0.35 °C, RMSE = 0.47 °C, and R² = 0.9991. The TOARS-based hybrid ensemble provided the most stable performance across both depths. The results demonstrate that integrating TOARS with tree-based models substantially enhances predictive accuracy and offers a robust solution for soil-temperature forecasting in shallow layers. Full article

Digital microfluidic biochips (DMFBs) find extensive applications in biochemical experiments, medical diagnostics, and safety-critical domains, with their reliability dependent on efficient online testing technologies. However, traditional random search algorithms suffer from slow convergence and susceptibility to local optima under complex fluidic constraints. This paper proposes a hybrid optimization method based on priority strategy and an improved sparrow search algorithm for DMFB online test path planning. At the algorithmic level, the improved sparrow search algorithm incorporates three main components: tent chaotic mapping for population initialization, cosine adaptive weights together with Elite Opposition-based Learning (EOBL) to balance global exploration and local exploitation, and a Gaussian perturbation mechanism for fine-grained refinement of promising solutions. Concurrently, this paper proposes an intelligent rescue strategy that integrates global graph-theoretic pathfinding, local greedy heuristics, and space–time constraint verification to establish a closed-loop decision-making system. The experimental results show that the proposed algorithm is efficient. On the standard 7 × 7–15 × 15 DMFB benchmark chips, the shortest offline test path length obtained by the algorithm is equal to the length of the Euler path, indicating that, for these regular layouts, the shortest test path has reached the known optimal value. In both offline and online testing, the shortest paths found by the proposed method are better than or equal to those of existing mainstream algorithms. In particular, for the 15 × 15 chip under online testing, the proposed method reduces the path length from 543 and 471 to 446 compared with the IPSO and IACA algorithms, respectively, and reduces the standard deviation by 53.14% and 39.4% compared with IGWO in offline and online testing. Full article

Dam displacement monitoring is crucial for assessing structural safety; however, conventional models often prioritize single-task prediction, leading to an inherent difficulty in balancing monitoring data quality with model performance. To bridge this gap, this study proposes a novel two-stage analytical framework that synergistically integrates an improved isolation forest (iForest) with a metaheuristic-optimized random forest (RF). The first stage focuses on data cleaning, where Kalman filtering is applied for denoising, and a newly developed Dynamic Threshold Isolation Forest (DTIF) algorithm is introduced to effectively isolate noise and outliers amidst complex environmental loads. In the second stage, the model’s predictive capability is enhanced by first employing the LASSO algorithm for feature importance analysis and optimal subset selection, followed by an Improved Reptile Search Algorithm (IRSA) for fine-tuning RF hyperparameters, thereby significantly boosting the model’s robustness. The IRSA incorporates several key improvements: Tent chaotic mapping during initialization to ensure population diversity, an adaptive parameter adjustment mechanism combined with a Lévy flight strategy in the encircling phase to dynamically balance global exploration and convergence, and the integration of elite opposition-based learning with Gaussian perturbation in the hunting phase to refine local exploitation. Validated against field data from a concrete hyperbolic arch dam, the proposed DTIF algorithm demonstrates superior anomaly detection accuracy across nine distinct outlier distribution scenarios. Moreover, for long-term displacement prediction tasks, the IRSA-RF model substantially outperforms traditional benchmark models in both predictive accuracy and generalization capability, providing a reliable early risk warning and decision-support tool for engineering practice. Full article