Search Results (10,419)

To address the issues that carbon trading fails to cover the full life cycle and that traditional demand response achieves poor emission reduction due to a lack of accurate carbon-intensity feedback in park integrated energy systems (PIESs) during low-carbon transition, this study proposes a two-layer optimal scheduling method synergizing life-cycle stepwise carbon trading and low-carbon demand response (LCDR) to balance low-carbon performance and economic efficiency. Firstly, based on life cycle theory, embodied carbon from new energy equipment manufacturing and transportation is incorporated into accounting, with a stepwise carbon trading mechanism designed. Secondly, corrected dynamic carbon emission factors for power and heating networks are constructed to quantify real-time carbon intensity. A dual-driven LCDR model (electricity price and carbon factor) is established to coordinate shiftable and sheddable electric-thermal loads and is combined with a two-layer scheduling model (pre-scheduling and re-scheduling) targeting the minimal total operation cost. Simulation results of a South China park show that life-cycle stepwise carbon trading reduces emissions by 16.7%, and LCDR further cuts 4.05%. Their synergy achieves significant carbon reduction with a slight cost increase, while supplementary sensitivity analyses further confirm the scalability and robustness of the proposed framework under varying load levels and demand response capabilities. Full article

Cyber-physical systems (CPSs) represent sophisticated intelligent architectures that tightly couple computational elements, communication networks, and physical processes. Their deployments now span virtually every industrial and civilian domain—from power grids and manufacturing plants to autonomous transportation networks. Ensuring the secure operation of CPSs relies fundamentally on effective time series anomaly detection, which remains a challenging task due to the complex, often unknown system dynamics and non-negligible sensor noise present in real-world environments. To address these challenges, we introduce a Neural Network-Enhanced Kalman Filter (NNEKF), a novel anomaly detection framework that combines model-based filtering with data-driven learning. The NNEKF employs a two-stage trained neural network with a specialized architecture: the first stage learns the underlying dynamics of the CPS, while the second stage optimizes the computation of the Kalman gain during the update step. At inference time, the enhanced Kalman filter recursively estimates the likelihood of observed sensor measurements to identify anomalies, supported by a batched parallel inference scheme that delivers substantial speedups. Extensive experiments on benchmark datasets demonstrate that the NNEKF attains an average F1-score of 0.935, coupled with rapid inference and minimal model footprint—surpassing all competitive baselines and facilitating dependable real-time anomaly detection for CPS environments. Full article

Anomaly detection is crucial in maintaining the safety, reliability, and optimal performance of complex systems across diverse domains, such as industrial manufacturing, cybersecurity, and autonomous systems. While conventional methods typically handle single data modalities, recently, there has been an increase in the application of multimodal detection in dynamic real-world environments. This paper presents a comprehensive review of recent research at the intersection of agentic artificial intelligence and large language-based multimodal anomaly detection. We systematically analyze and categorize existing studies based on the agent architecture, reasoning capabilities, tool integration, and modality scope. The main contribution of this work is a novel taxonomy that unifies agentic and multimodal anomaly detection methods, alongside benchmark datasets, evaluation methods, key challenges, and mitigation strategies. Furthermore, we identify major open issues, including data alignment, scalability, reliability, explainability, and evaluation standardization. Finally, we outline future research directions, with a particular emphasis on trustworthy autonomous agents, efficient multimodal fusion, human-in-the-loop systems, and real-world deployment in safety-critical applications. Full article

Aluminum–vanadium (Al–V) master alloy is a key raw material for manufacturing high-end alloys, but the internal temperature transient field during its self-propagating high-temperature synthesis (SHS) is nearly impossible to measure in situ. This work develops a numerical simulation framework for Al–V master alloy SHS, featuring a novel temperature–time dual-criteria adaptive moving heat source and a gas–liquid–solid three-phase heat transfer model coupled with temperature-dependent thermophysical properties. The model, implemented in ANSYS Fluent via a customized user-defined function (UDF), is experimentally validated with a maximum temperature error below 7%. Results reveal that higher compact relative density accelerates combustion wave propagation, while increased slagging agent content exerts an inhibitory effect. This study provides a theoretical and quantitative tool for mechanism analysis and industrial process optimization of Al–V master alloy SHS production. Full article

Aggregate production planning (APP) helps medium-term production, manpower, inventory, and subcontracting decisions match expected demand. Deterministic planning models are generally ineffective in manufacturing due to demand and operational variability. Fuzzy linear programming (FLP) has been frequently used to describe imprecision using membership functions and satisfaction levels. Despite its versatility, accurate approaches for solving multi-objective FLP-based APP models become computationally expensive as issue size and complexity increase. Thus, metaheuristic algorithms are widely used, although many still have premature convergence, parameter sensitivity, and restricted scalability. This study investigates the Narwhal Optimization Algorithm (NO) as a population-based metaheuristic framework. It proposes two hybrid variants to improve convergence reliability and constraint-handling capability: NO combined with the Super Modified Simplex Method (SMS) for local refinement and NO integrated with a Runge–Kutta-based optimizer (RK) for search stability. These hybrid techniques are tested for solution quality, convergence behavior, and robustness using eight response-surface benchmark functions and four constrained optimization problems. A real-parameter fuzzy APP problem with three goods and a six-month planning horizon uses the best variations. The Elevator Kinematic Optimization (EKO) algorithm, chosen for its compliance with the same mathematical framework and consistent parameter values, is used to compare the offered solutions fairly and controlled. Fuzzy programming uses a max–min satisfaction framework with linear membership functions from positive and negative ideal solutions. Computational experiments assess solution quality, stability, and efficiency for nominal and ±10% demand disturbances. The hybrid NO variants better resist premature convergence, stabilize solutions, and satisfy users more than the original NO and benchmark approaches. For small and medium-sized organizations in dynamic situations, hybrid narwhal-based optimization appears to be a reliable and scalable decision-support solution for APP problems under uncertainty. Full article

The production and leasing of electric construction machinery play a critical role in the low-carbon transition. However, from a multi-cycle dynamic perspective, there is a lack of targeted research on how to enhance electric goodwill and AI-enabled maintenance service levels while maximizing enterprise profits. To fill this gap, this study incorporates AI-enabled O&M effort, R&D technology, AI-enabled maintenance effort, and advertising effort into a long-term dynamic framework to examine optimal decisions for the manufacturer and the lessor. We assume that the information in the leasing supply chain is symmetric, that the marginal profits of the manufacturer and the lessor are fixed parameters, and that the AI-enabled maintenance service effort level and the electric goodwill are taken as state variables. We develop differential game models across four decision cases: centralized (Case C), decentralized (Case D), unilateral cost-sharing contract (Case U), and bilateral cost-sharing contract (Case B). Results demonstrate monotonic state variable trajectories. Both Case U and Case B can achieve supply chain coordination, with the profit-sharing mechanism in Case B proving superior. In addition, the optimal cost-sharing proportion depends on the relative sizes of the manufacturer’s and the lessor’s marginal profits in both Case U and Case B. The AI-enabled maintenance service plays a significant role in enhancing equipment reliability and supply chain resilience. In addition, the impacts of key parameters on optimal decision variables, state variables, profits, and coordination of the leasing supply chain are comprehensively discussed. Full article

Material considerations are often neglected when developing digital twins, particularly at the relevant length scales that drive material and structural performance. For reinforced composite materials, the microscale has the largest impact on nonlinear material behavior and progressive damage, and thus accurately representing the disordered microstructure of a composite due to processing and manufacturing is critical to developing the material digital twin in the multiscale hierarchy. Automating microstructure characterization is typically done by either training convolutional neural network models using a pretrained encoder or using prompt-based segmentation tools. In this work, a toolset for developing segmentation models is presented, combining these two methods to enable rapid annotation, training, and deployment of microscopy segmentation models for automated material digital twin development without user knowledge of machine learning. Additionally, a Bayesian optimization framework is developed for generating statistically equivalent representative volume elements (SRVE) to a segmented microstructure using a random microstructure generator that implements soft body dynamics. Progressive failure analysis of random, statistically equivalent, and ordered microstructures is compared to the segmented microstructure subject to transverse loading to demonstrate the importance of accurately representing the driving material length scale of a composite digital twin. Ordered microstructures over-predicted crack initiation and ultimate strength and strain. Random and optimized RVE microstructures better agreed with the segmented simulation results, with no significant difference observed between the two methodologies. The improvement in predicted macroscale behavior for models that capture disordered microstructures due to manufacturing processes demonstrates the importance of capturing microstructure features in composites modeling and indicates that SRVEs that capture microstructural features of the physical material can be used in material digital twin development. Further, the toolsets provided in this work allow for rapid development of composite material digital twins without user expertise in machine learning. This has enabled the development of an integrated workflow to automatically characterize and idealize composite microstructures and generate representative geometric models for efficient micromechanics analysis. Full article

The relevance of this study is driven by the need to develop new mechanisms and tools aimed at improving the technological, resource, and economic efficiencies of industrial businesses while minimizing their negative environmental impacts and enhancing their environmental performances. Although such approaches as the theory of constraints, the concept of sustainable development, and principles of Best Available Techniques have garnered attention individually, their combined, interdisciplinary application to the streamlining of business processes in industry has not yet been fully explored. The purpose of this study is to demonstrate the advisability of managing business processes based on the principles of resource efficiency enhancement by preventing irrational resource consumption, production losses, pollution and waste in the context of the Sustainable Development Goals. This article analyzes the current state of research business process optimization for a greener future. The proposed methodological approach is based on ranking business processes according to their levels of resource efficiency. Business process engineering and an evaluation of its outcomes in terms of resource efficiency were conducted using a case study of a building materials manufacturer in Northwest Russia. Various business management scenarios were developed to improve resource efficiency through process engineering initiatives. The findings of this study can inform the development of strategic approaches for building materials manufacturers as they transition toward sustainable development. Full article

This study proposes EvoDeep-Quality, a closed-loop hybrid framework integrating deep learning-based perception with multi-objective evolutionary optimization for adaptive quality control in smart manufacturing. The architecture combines a CNN-LSTM network for real-time spatiotemporal quality prediction with an NSGA-III-based optimization unit to balance conflicting objectives of quality, cost, and energy efficiency. A continuous adaptive learning loop addresses concept drift and process variability. Evaluated on an industrial-inspired synthetic dataset of textile blends (N = 5000) and validated on the real-world SECOM semiconductor manufacturing dataset, the framework demonstrates strong predictive capability (R² = 0.947 ± 0.012, MAE = 0.035 ± 0.003) and significant manufacturing performance improvements, including a 23.5% quality enhancement and an 8.7–12.3% operational cost reduction compared to traditional and standalone AI models. Statistical significance testing (paired t-test, p < 0.01) confirms the superiority of the proposed approach. This deep-evolutionary framework advances proactive quality assurance and adaptive process control, offering a scalable solution aligned with Industry 4.0 and 5.0 paradigms. Full article

Position-independent geometric errors crucially impact the accuracy of five-axis machine tools, yet their identification remains challenging due to computational complexities, inadequate measurement pose selection, and disturbances arising from thermal drift and residual uncompensated errors. Existing methods typically rely on linearized kinematic models, heuristic sampling of measurement poses, or computationally expensive global optimization procedures, which collectively limit their effectiveness in industrial environments. This study presents a unified identification framework that overcomes these limitations; it incorporates 3D offset parameters to enhance the decoupling of true geometric errors from non-PIGEs, an observability-driven measurement pose selection strategy to maximize the parameter sensitivity, and an ANN-surrogate model to accelerate high-dimensional global optimization. A genetic algorithm is used to optimize the measurement points based on the observability index of the machine tool. The ANN-surrogate model enhances the identification accuracy of error parameters (11 PIGEs + 3 offsets) through precise kinematic models, global exploration, and final refinement. Experimental validation on a five-axis machine tool demonstrates a volumetric error reduction of 88.615% after compensation, with RMSE decreasing to 0.4337 μm. Sensitivity analysis reveals that PIGEs contribute up to 75.26% of the total inaccuracy, while offset parameters capture 24.74% of the error from thermal and non-PIGE sources. The results confirm the method’s superiority over other techniques in terms of identification accuracy, efficiency, and robustness, providing a practical solution for high-precision applications in the manufacturing industries. Full article

To address the issues of uneven grayscale distribution, weak defect features, and small target scales on the coating surface of LCD polarizers during manufacturing, an improved YOLOv10-N-based method is proposed for surface defect detection. First, a polarizer coating defect dataset is constructed based on the LCD polarizer coating process and the characteristics of coating defects. Adaptive median filtering is then employed for image denoising, while a particle-swarm-optimization-based improved histogram equalization method is adopted for image enhancement. Next, the Scale-aware Pyramid Pooling (SCPP) module is introduced into the C2f module of the backbone network to construct the C2f_SCPP feature extraction module, thereby improving the model’s ability to detect coating defects with different morphologies through multi-scale semantic feature fusion. In addition, rotation-equivariant convolution PreCM is incorporated into the SPPF module of the backbone network to build the SPPF_PreCM module, which effectively suppresses feature redundancy and scale conflicts while strengthening the representation of tiny defects. Finally, while retaining the original Distribution Focal Loss (DFL) branch of YOLOv10, WIoU is used to replace CIoU as the IoU loss term in bounding box regression, thereby improving localization accuracy and accelerating model convergence during training. Experimental results show that, compared with YOLOv10-N, the proposed method improves mAP@0.5 and mAP@0.5:0.95 by 1.8 and 2.8 percentage points, respectively, demonstrating its effectiveness for polarizer coating defect detection. However, its generalization capability under diverse production environments, varying illumination conditions, and complex noise scenarios still requires further investigation. Full article

With the rapid development of e-commerce and smart manufacturing, automated warehouse systems have become critical infrastructure for modern logistics. In China’s vast market, the dynamic scheduling of Rail-Guided Vehicles (RGVs) faces significant challenges due to complex task uncertainties, hierarchical supply chain structures, and real-time collision avoidance requirements. Traditional rule-based methods and static optimization models often fail to adapt to such dynamic environments. To address these issues, this paper proposes a novel hybrid deep reinforcement learning framework integrating a Dynamic Graph Neural Network (DGNN) and a Transformer model. The DGNN captures the spatiotemporal dependencies of the warehouse network topology, while the Transformer mechanism enhances long-range feature extraction for task prioritization. Furthermore, we design a centralized Deep Q-network (DQN) framework with parameterized action spaces to coordinate multiple RGVs collaboratively. While the system manages multiple physical vehicles, the learning architecture employs a single-agent global scheduler to avoid the non-stationarity issues inherent in multi-agent reinforcement learning. Experimental results based on real-world data from a large-scale electronics manufacturing warehouse demonstrate that our method reduces average task completion time by 18.5% and improves system throughput by 22.3% compared to state-of-the-art baselines. The proposed approach demonstrates potential for intelligent warehouse management in dynamic industrial scenarios. Full article

Optimizing the parameters of the manufacturing process for products in terms of metalworking equipment is one of the key tasks in technological preparation for production. This process is structurally complex, characterized by an ordered set of actions of various types. The basis for improving the efficiency of the technological process is the comprehensive optimization of the parameters of individual elements that form its structure. To solve this problem, an integrated model for comprehensive multi-criteria optimization of a structurally complex process has been developed, establishing a clear hierarchical relationship between its elements. The model is based on the structural decomposition of two processes: the process of forming individual design elements and the technological process of manufacturing a product. Structural hierarchical models have been developed for each process. The structure of the integrated model contains six levels of control. For each level of control, a set of target indicators and control parameters has been formed. The article presents the results of testing the proposed model using the example of optimizing the technological process of mechanical processing for the “Housing” product. As part of the study, structural and parametric optimization of the manufacturing process for this part was carried out. During the study, the structure of the technological processing route was optimized, as well as individual technological operations and technological transitions. Over the course of the work, the technological equipment and processing methods used for shaping a number of surfaces were replaced. As a result of the optimization, the overall labor intensity of the technological process for manufacturing the “Housing” product was reduced by 19.8%, and the manufacturing accuracy of the most critical surfaces was increased by 16.4%. The results confirm the effectiveness of the proposed model for comprehensive optimization of the mechanical processing technological process. Full article

As an important part of green manufacturing, remanufacturing has important practical significance for alleviating resource shortage and waste, developing circular economy and promoting sustainable development. In recent years, remanufacturing scheduling (RS), which can achieve high efficiency and green remanufacturing through the reasonable allocation of resources, has become a research hotspot in the field of remanufacturing. To offer a comprehensive evaluation of the research dynamics and development trends of RS, this paper systematically reviews the publications from 2010 to 2025 via Scopus, Web of Science, and the IEEE Xplore database. Firstly, the research background of RS, related remanufacturing policies and the generalized connotation of remanufacturing are introduced. Then, selected and valid publications are analyzed from time aspect, country aspect, and keyword aspect through Citespace software. In addition, based on remanufacturing level, modeling idea, optimization objectives, solution method, production scenarios and practical application, publications are further grouped and reviewed. In addition, according to the research gap existing in recent studies, some future development trends are accordingly pointed out, aiming to provide valuable insights for research related to RS. Finally, meaningful conclusions are drawn and the importance of RS is emphasized once again. Full article

This study addresses virtual metrology for the taping process of chip electronic components, in which partial observability, unmeasured disturbances, and severe label imbalance make direct batch-wise yield prediction unstable. Rather than proposing a new standalone learning algorithm, we develop a data-centric VM framework that reformulates the task as the prediction of operating-condition-level typical yield. First, physically relevant features are retained based on process knowledge and analyzed using Pearson correlation, Spearman correlation, and mutual information. We then perform multidimensional equal-frequency binning to partition the observable feature space into locally homogeneous operating condition groups, and define the within-bin median yield as the typical yield, thereby constructing an operating condition dictionary. Based on this dictionary-based representation, low-yield-oriented sample weighting is combined with nested cross-validation and Bayesian optimization for model comparison and hyperparameter tuning. Using desensitized production data from an electronic component taping process, the results under this representation show more stable prediction than direct modeling on unbinned batch samples while also improving tail-oriented fitting relative to unweighted baselines. These findings suggest that, for partially observable manufacturing data, operating condition stratification provides a practical basis for stabilizing VM prediction, while low-yield-oriented sample weighting further improves sensitivity to the low-yield tail, supporting picture yield early warning and process-level decision making. Full article