Search Results (1,826)

Soil and groundwater contamination across multiple plots in industrial parks is an important environmental management challenge. Because plots often differ in contamination characteristics and remediation requirements, remediation decision-making needs to generate sustainability-oriented alternatives that account for explicit management preferences and trade-offs among carbon emissions, remediation duration, and cost. Although technology screening for individual contaminated plots has been widely investigated, how to use plot-level screening results to support the selection of multi-plot remediation alternatives under multiple objectives remains insufficiently addressed. This study developed a preference-guided multi-objective decision framework for selecting remediation alternatives in contaminated industrial parks. The framework first generates cross-plot remediation alternatives by assigning one feasible technology to each plot and removes alternatives that violate technological compatibility or project-level engineering constraints. It then identifies Pareto non-dominated alternatives using NSGA-II, retains preference-consistent alternatives through LO-based filtering, and selects the final recommendation using ideal-point distance comparison. The framework was applied to a five-plot contaminated industrial park in northern China. Compared with the LO and NSGA-II benchmarks, the hybrid NSGA-II–LO model selected less imbalanced alternatives that retained the preferred-objective advantage while improving the balance among the remaining objectives. The results show that management priorities can substantially affect remediation technology allocation across plots and that preference screening can support the adjustment of remediation alternatives when low-carbon targets, remediation schedules, or budget constraints change. This study provides an operational decision framework for translating plot-level technology screening into sustainability-oriented multi-plot remediation decision-making. Full article

In wheat threshing, reducing total grain loss and energy consumption is crucial for both economic and sustainable food security. This study investigates the effects of threshing drum type (straight and helical row), drum peripheral speed (36.73–48.98 m s⁻¹), and drum-concave clearance (35–50 mm) on total grain loss and specific fuel consumption in a stationary threshing machine using a full factorial design. The optimum machine settings (drum type, peripheral speed and drum–concave clearance) that simultaneously minimize these two outputs were then determined. We systematically compared three surrogate modelling approaches—Response Surface Model (RSM), Gaussian Process Regression (GPR), and Artificial Neural Network (ANN)—to identify the most effective method for small-dataset optimization in threshing machine design. The best model was selected through cross-validation, and optimization was performed using the NSGA-II multi-objective genetic algorithm. GPR yielded the highest prediction accuracy for both outputs (R² in prediction data: 0.99 for total grain loss and 0.91 for specific fuel consumption). Multi-objective optimization revealed a conflict between the two objectives; the best balance was achieved for the helical drum at a peripheral speed of approximately 41.5 m s⁻¹ and a drum–concave clearance of 50 mm (predicted total grain loss approximately 3.7%, specific fuel consumption approximately 2.98 mL kg⁻¹). Compared to the straight-row drum, the helical drum provided lower losses and fuel consumption, as well as approximately 3.5 times wider safe operating range. It should be noted that this optimum was predicted by the surrogate model and agreed closely with the best measured treatment; it was not confirmed by an independent validation experiment. The results demonstrated that combining a surrogate model with a genetic algorithm is an effective tool for optimizing threshing machine parameters. Full article

To address the low production efficiency and insufficient cross-enterprise collaboration in wallboard outsourcing for coating equipment manufacturing, this study proposes a wallboard manufacturing service composition optimization method based on an improved NSGA-III algorithm. First, the service composition optimization problem in wallboard manufacturing is analyzed, and a mathematical model for wallboard outsourcing service composition optimization is established. Next, an improved NSGA-III method integrating Latin hypercube sampling, greedy local search, and Lévy flight-based global search strategies is proposed, alongside a similarity measurement method for the objective-space structure based on statistical features and distribution differences, which is used to select benchmark functions that closely match the characteristics of actual business data. Finally, comparative experiments using benchmark functions and real-world business data are conducted to verify the effectiveness and superiority of the proposed method in solving service composition optimization problems. The experimental results demonstrate that the proposed method achieves excellent performance in both solution quality and computational efficiency, significantly improving the utilization of wallboard outsourcing manufacturing resources across enterprises and facilitating efficient business process flows. Full article

The agro-industrial complex of Kazakhstan faces increasing pressure to improve the efficiency of marketing activities under conditions of limited budgets, regional heterogeneity, seasonal demand, and uneven digital infrastructure. Traditional marketing planning methods often rely on expert judgment or single-objective optimization and therefore cannot adequately address the conflicting objectives of maximizing marketing effectiveness, expanding audience coverage, and minimizing campaign expenditure. This study proposes a hybrid decision-support framework that combines the Non-dominated Sorting Genetic Algorithm II (NSGA-II) with machine learning-based clustering for multi-objective marketing budget optimization in the agro-industrial sector. The model considers five major promotion channels: digital media, television, radio, print media, and events. NSGA-II is used to generate Pareto-optimal budget allocation strategies, while K-means clustering classifies the resulting solutions into interpretable strategy groups. The framework was evaluated using synthetic data and enterprise-level data reflecting marketing conditions in Kazakhstan. Results show that strategies combining digital media and television achieve the highest marketing effectiveness and audience coverage, although they require greater campaign expenditure. Radio and print media remain relevant for cost-sensitive strategies, particularly for enterprises with limited resources. Cluster analysis identified three main strategy groups: cost-efficient, balanced, and high-performance configurations. The findings confirm that marketing budget allocation in the agro-industrial sector should be treated as a multi-objective optimization problem rather than a single-criterion decision. The proposed framework provides both computational optimization and managerial interpretability, supporting data-driven, adaptive, and resource-aware marketing planning for agro-industrial enterprises in Kazakhstan. Full article

Renewable-rich industrial microgrids require scheduling strategies that convert uncertain renewable generation into reliable and physically feasible decisions. This challenge is particularly significant in oilfield microgrids, where photovoltaic (PV) uncertainty is coupled with crude-oil transportation and temperature requirements. This paper proposes a data-driven stochastic scheduling framework for PV-integrated oilfield microgrids using electric thermal storage boilers (ETSBs) as industrial flexibility resources. A convolutional neural network-gated recurrent unit (CNN-GRU) model is combined with probabilistic scenario generation and reduction to characterize PV uncertainty, while a physics-informed multi-objective model coordinates grid-interaction smoothing, operating cost, PV absorption, ETSB dynamics, and pipeline temperature safety. To improve schedule executability, an oilfield-specific non-dominated sorting genetic algorithm II (NSGA-II) solver is developed with thermo-hydraulic simulation, feasibility projection, ramping correction, and terminal sustainability evaluation. Case studies show that the proposed stochastic strategy reduces net-load variance by 56.82% and increases PV absorption by 17.58 percentage points, while maintaining pipeline temperature within 42.0–42.3 °C. Compared with deterministic scheduling, it limits the real-time cost deviation to 0.11%, indicating stronger day-ahead-to-real-time consistency under PV uncertainty. The proposed framework provides practical decision support for renewable-rich oilfield microgrids balancing renewable accommodation, operating economy, and thermo-hydraulic safety. Full article

Multi-objective optimization provides the mathematical foundation for reasoning about trade-offs in complex decision problems, from engineering design to resource allocation. Software testing exemplifies such problems: practitioners must simultaneously optimize for fault detection capability, code coverage, execution cost, and test suite diversity—objectives that are fundamentally incommensurable. Since the early 2000s, multi-objective evolutionary algorithms (MOEAs) such as NSGA-II, MOEA/D, and their many-objective extensions (MOSA; DynaMOSA) have served as the dominant mathematical framework for navigating these trade-offs through Pareto-front approximation with hand-crafted fitness functions. However, the recent emergence of reinforcement learning (RL) and large language models (LLMs) is shifting the optimization paradigm from numerical Pareto-front approximation toward neural, semantically aware decision making over learned representations. This paper presents a systematic mapping study of multi-objective optimization algorithms, tracing their evolution from classical Pareto-based methods toward AI-driven and hybrid approaches, with software testing as the primary application domain. We survey 120+ papers published from 2000 to 2025 and propose a novel five-level taxonomy (L1–L5) that classifies optimization approaches along the intelligence spectrum: classical MOEAs, ML-guided MOEAs, RL-driven optimization, LLM-driven optimization, and hybrid neuro-evolutionary systems. For each level, we analyze the mathematical problem formulations (Pareto optimality conditions, Markov decision processes, and neural loss landscapes), objective function design, algorithmic convergence properties, and computational complexity. We further conduct a cross-cutting mathematical analysis comparing these paradigms along dimensions of convergence, diversity, scalability, and interpretability. Our survey identifies critical open mathematical challenges: the lack of formal convergence guarantees for LLM-driven optimization, the under-exploration of many-objective ($m\ge 4$) formulations in AI-driven testing, the sample complexity of reinforcement learning for combinatorial test optimization, and the absence of standardized benchmarks with known Pareto-optimal frontiers. We conclude by outlining a research roadmap for the next generation of multi-objective optimization systems that combine the complementary mathematical strengths of neural function approximation and evolutionary diversity preservation. Full article

The construction sector accounts for 34% of global energy-related CO₂ emissions, yet existing Digital Twin (DT) applications in construction remain largely descriptive, lacking the predictive and prescriptive capabilities required for proactive execution management. This study presents and evaluates, as a simulation-based proof of concept, a risk-informed DT framework integrating a formalized DT state transition model, a dual deep learning prediction engine (Long Short-Term Memory (LSTM) and Transformer), Monte Carlo-based probabilistic carbon quantification for lifecycle modules A1–A5 (S = 10,000), and a risk-adjusted, Non-dominated Sorting Genetic Algorithm II (NSGA-II) optimizer incorporating carbon variance, within a closed weekly feedback loop. The framework is evaluated across five European case studies (residential, education, and commercial office; the Netherlands, the UK, and France) anchored to published project data, with primary calibration on a hybrid real–synthetic mid-rise residential building (CS1; 7200 m², eight stories, the Netherlands) and a fully documented synthetic layer generating the execution records that the published sources do not provide. Under common random number simulation with 50 execution realizations per case, the full framework achieved simultaneous improvements of 5.8–13.2% in expected schedule duration and 10.4–16.4% in expected embodied carbon relative to a static Critical Path Method (CPM) baseline; for CS1, mean intensity fell from 476 to 426 kgCO₂e/m². Component ablation identified the bi-objective optimizer as the dominant contributor, producing an 11.7–20.2% carbon increase when removed, and the selected Pareto solution was invariant to the risk-aversion parameter λ over [0, 1], indicating that risk adjustment functions as a conservatism margin on the reported carbon target rather than a decision-altering preference. The framework advances construction DTs from descriptive monitoring tools toward risk-informed decision support, offering a transparent and reproducible benchmark that advances data-driven sustainability in construction scheduling and embodied carbon management. Full article

With the accelerating global population aging process, home health care (HHC) has emerged as a promising service mode to satisfy surging elderly medical care needs and alleviate the pressure of offline medical institutions. As a core operational optimization problem in the HHC service system, the home health care routing and scheduling problem (HHCRSP) has attracted extensive research attention in recent years. Different from traditional HHCRSP research, this work proposes a bi-objective mixed-integer programming model for HHC, which integrates facility location, caregiver allocation, route planning and skill-matching rules. The model simultaneously minimizes two competing objectives: total operational cost and total penalty incurred from time window violations. To tackle the high-complexity NP-hard characteristics of this integrated optimization problem, an enhanced non-dominated sorting genetic algorithm (E-NSGA) is designed by introducing dedicated local search operators to improve solution quality. Comparative numerical experiments are carried out on 12 test instances extended from the classic Vidal benchmark, covering four patient scales of 70, 80, 90 and 100 patients. Four state-of-the-art multi-objective metaheuristics, i.e., MOEA/D, MOGWO, NSGA-II and NSGAII-MLS, are selected as baseline comparison algorithms. Experimental results reveal prominent performance advantages of E-NSGA over all comparison methods. In terms of the IGD metric, E-NSGA achieves IGD reductions of 20.19%, 86.30%, 24.98% and 37.72% against MOEA/D, MOGWO, NSGA-II and NSGAII-MLS, respectively. In terms of the Hypervolume metric, E-NSGA obtains performance improvements of 6.22%, 2019.42%, 10.36% and 18.04% relative to the four baseline algorithms. Such quantitative evidence verifies the strong comprehensive optimization capacity of the proposed E-NSGA for addressing the investigated problem. Full article

Fused deposition modeling (FDM) of polylactic acid (PLA) is widely used, yet most parameter studies tune one mechanical property at a time and leave the conflicts between properties unresolved. This work treats three responses of FDM PLA together: ultimate tensile strength, flexural strength, and Shore D hardness. A Taguchi L9 orthogonal array varied infill density, raster angle, and layer thickness; signal-to-noise ratios and analysis of variance ranked the factors, linear regression linked the parameters to each response, and the NSGA-II algorithm mapped the trade-off surface between them. Layer thickness proved the leading factor for tensile and flexural strength, while hardness answered mainly to infill density; raster angle stayed weak for every response. The Pareto front showed that low infill favors tensile strength while high infill favors flexural strength and hardness, all at the finest layer setting, and these trends were converted into parameter guidelines for tensile-led, flexure-led, and balanced parts. The statistical limits of the screening design are stated openly, the flexural and hardness campaigns are flagged as provisional, and a replicated, standard-compliant confirmation study is set out as the next step. Full article

In regression tasks, point estimates are insufficient—interval uncertainty must be quantified. The two main criteria for evaluating prediction intervals—Prediction Interval Coverage Probability (PICP) and Normalized Average Width (PINAW)—are conflicting, forming a Pareto front. This paper presents GA-PC, a novel genetic algorithm that modifies NSGA-II by introducing auxiliary calibration variables with a quadratic penalty. Unlike heuristic approaches, the introduction of these variables is theoretically justified via Noether’s second theorem and Bianchi identities: they correspond to gauge degrees of freedom, and the penalty acts as gauge fixing, improving convergence without altering the Pareto set. On ZDT2, GA-PC yields results that match the best reported values. On real financial data, the method provides full PICP coverage (0.000–1.000) and a wider PINAW range than NSGA-II and MOEA/D. The algorithm is scalable, exhibits transferability of hyperparameters, and is applicable to any number of criteria. Code available in the Supplementary File. Full article

The efficiency of ammunition support operations in the aircraft carrier intermediate ordnance staging deck is critical to sortie generation rates in naval aviation, yet joint scheduling and personnel allocation in this multistage, resource-constrained environment remains a challenging bi-objective optimization problem. This study develops a framework integrating an improved Nondominated Sorting Genetic Algorithm II (NSGA-II) with a marginal-benefit-based iterative feedback mechanism. The intermediate ordnance staging deck support process is decomposed into individual ammunition processing stations and formulated as a processflow model incorporating operation sequencing and personnel specialization constraints. A constraint decision model then dynamically reconciles the minimization of total makespan and personnel workload equilibrium through iterative marginal-benefit comparison across support teams. The NSGA-II is enhanced with an adaptive crossover-mutation mechanism and an improved elitism preservation strategy to strengthen global search capability. Validation on a typical carrier intermediate ordnance staging deck scenario demonstrates that the improved NSGA-II outperforms the conventional NSGA-II in convergence speed and Pareto front quality. Under the optimized configuration, the total makespan remains 3600 s with a workload balance metric of 1075 even as ammunition quantity doubles from two to four units. The proposed framework offers practical decision support for carrier ammunition operations and extends to other resource-constrained multi-objective scheduling domains. Full article

The explosive growth of artificial intelligence workloads has triggered unprecedented data center construction, yet environmental assessment remains focused on operational energy efficiency. This paper introduces DC-WLC3O, a framework that simultaneously optimizes three objectives across the full data center lifecycle: whole-life cost, whole-life carbon, and material circularity index. The framework integrates cradle-to-cradle lifecycle assessment with dynamic material flow analysis, employing a four-layer analytical stack: Monte Carlo simulation with Latin Hypercube Sampling and Iman–Conover rank correlation; NSGA-III tri-objective Pareto optimization; Sobol’ variance-based global sensitivity analysis; and Many-Objective Robust Decision Making (MORDM). The framework evaluates 192 design configurations for a 30 MW hyperscale facility under three carbon pricing scenarios. Results reveal a carbon rebound paradox: operational carbon dominates grid-dependent configurations (96.2%), but low-carbon energy produces an 8.5× inversion (Welch’s t = 22.2, p < 10⁻³⁹). Sobol’ analysis confirms energy strategy dominates carbon outcomes (S1 = 0.87). MORDM identifies on-site renewable energy with a full circular economy strategy as unconditionally robust (R = 0.056, stable across 94.2% of weight permutations). The cost–circularity correlation is negative (rho = −0.488, p < 10⁻¹²), overturning the assumption that circular strategies increase lifecycle costs. A post hoc stress test confirms this finding is robust to moderate perturbations in renewable LCOE (+71%), with stability declining to ≈80% under worst-case capital cost assumptions and to ≈61% when generation degradation and battery replacement are jointly considered. Full article

This paper addresses the multi-objective optimization of cooperative dual-arm robotic manipulation, focusing on the reduction and balancing of interaction forces during the coordinated transport of a shared payload. The manipulation task is formulated from an object-centric perspective, where candidate trajectories are defined through intermediate object poses that are simultaneously mapped to both robotic manipulators under rigid grasping assumptions. Within this framework, the optimization problem is posed as a constrained multi-objective search in which the force demands associated with each robot are minimized while preserving kinematic feasibility and collision-free cooperative motion. Two representative population-based multi-objective algorithms, Multi-Objective Particle Swarm Optimization (MOPSO) and Non-dominated Sorting Genetic Algorithm II (NSGA-II), are evaluated under equivalent trajectory bounds and objective definitions. The results provide a set of non-dominated cooperative trajectories that support the selection of force-efficient motions with lower peak demands and improved load-sharing behavior. The comparative analysis demonstrates the potential of multi-objective metaheuristic optimization for force-aware dual-arm manipulation and highlights the different convergence and solution-distribution behaviors of MOPSO and NSGA-II in a constrained robotic manipulation scenario. Full article

The high-temperature sealing reliability of flange–bolt–gasket systems is governed by the coupled gasket leakage, flange cracking, and bolt yielding. This study investigates a DN200 PN40 (nominal diameter 200 mm and nominal pressure 4.0 MPa) weld-neck flange assembly operating under 300 °C superheated steam at 4 MPa internal pressure. Exploiting the assembly’s 12-fold cyclic rotational symmetry, a 1/12 periodic-sector finite element model with steady-state thermal–structural sequential coupling was developed in ANSYS Workbench and validated against the Omiya–Sawa 3-inch weld-neck flange benchmark at two levels (Level 1: bolt load vs. experiment; Level 2: 250 °C gasket contact pressure vs. reference finite element method (FEM)), with maximum errors below 1.5% in both levels; the benchmark thus establishes the reliability of the modeling procedure rather than constituting a direct experimental validation of the DN200 PN40 configuration. Using a central composite design, second-order response surface models (RSM) and Kriging surrogate models were constructed and compared, followed by Sobol global sensitivity analysis, multi-objective optimization using the non-dominated sorting genetic algorithm II (NSGA-II), and decision-making using the technique for order preference by similarity to ideal solution (TOPSIS), with bolt preload F and gasket width b as design variables. Baseline analysis revealed a differential contact pressure distribution—lower at the inner radius and higher at the outer radius—driven by a −0.308° flange rotation, identifying the inner gasket edge as the critical sealing failure path. RSM outperformed Kriging for the primary objective (mean absolute percentage error (MAPE): 0.72% vs. 3.61%), and the Pareto front collapsed to b = 19 mm. The TOPSIS-recommended optimum (F = 59,942 N, b = 19.00 mm), verified by ANSYS back-substitution, increased the minimum gasket contact pressure by 31.01% while reducing the flange membrane-plus-bending stress by 2.26%, achieving a coordinated improvement of both sealing performance and structural safety. Full article

This article presents an optimised deep rolling process, implemented using a single-toroidal-roller burnishing method, to improve the surface integrity and high-cycle fatigue strength of 42CrMo4 steel axles and shafts. A second-order composition plan, regression analyses, and multi-objective optimisation were employed. The solution was based on a non-dominated sorting genetic algorithm (NSGA-II) and Pareto front search approach. The compromise optimal solution yields an average roughness Ra of 0.190 μm, average surface microhardness of 503 HV, and average surface residual axial stress of –855 MPa. Deep rolling conducted using the selected optimal values (a burnishing force of 1000 N and feed rate of 0.11 mm/rev) of the governing factors achieves stable surface integrity characteristics under multiple repetitions of the process. Rotating bending fatigue tests showed that the positive effect of deep rolling begins to manifest itself after 10⁴ cycles, i.e., in the second half of the high-cycle fatigue field and in the mega-cycle region, where the fatigue strength increases from 390 (after turning and polishing) to 440 MPa (after turning and subsequent deep rolling). Full article