Search Results (1,848)

Unmanned aerial vehicles (UAVs) and deep learning (DL) have introduced a new framework for intelligent building façade defect detection, yet existing studies often focus on isolated technical components and lack a systematic evaluation of the entire pipeline. To address this gap, this paper conducts a systematic literature review of 135 peer-reviewed journal articles retrieved from the Web of Science database over the period 2021–2026. This review investigates four key domains: (1) UAV inspection path planning and data acquisition; (2) multi-modal data fusion; (3) DL-driven defect detection algorithms; and (4) 3D reconstruction and digital twin integration. Our analysis reveals the following main findings. Real-time perception-aware planning is central to UAV path planning, yet most studies lack robustness evaluations under real-world deployment conditions. Multi-modal data fusion improves detection across multiple defect types, yet edge deployment requires balancing lightweight design with recognition stability. Defect recognition algorithms increasingly adopt task-driven architectures, but limited edge-device resources demand joint optimization of efficiency and accuracy. In digital twins, systematic research is still lacking on semantically integrating recognition results into BIM for O&M decision-making, leaving the closed loop from defect detection to maintenance unresolved. This review aims to help researchers and practitioners advance UAV-based inspection from an auxiliary tool to a fully autonomous, reliable intelligent agent for refined management of the urban built environment. Full article

Artificial intelligence (AI) is increasingly influencing nanopharmaceutical development by supporting the transition from empirical formulation screening toward predictive, data-driven, and translationally oriented design. Nanocarrier-based therapeutics are governed by nonlinear relationships among material composition, physicochemical attributes, manufacturing parameters, biological identity, pharmacokinetics, toxicity, and therapeutic performance. In this review, we examine how AI can contribute to nanopharmaceutical development from predictive formulation design to clinical translation. We synthesize current applications of machine learning, deep learning, physics-informed modeling, hybrid mechanistic–AI approaches, and automated optimization workflows, with emphasis on critical quality attribute modeling, multi-objective optimization, design of experiments, quality-by-design, process analytical technology, digital twins, and continuous manufacturing. We also discuss applications involving nano–bio interactions, pharmacokinetics, toxicity, immunogenicity, and precision nanomedicine. AI-based approaches can support rational nanocarrier design, identify nonlinear formulation–property relationships, guide optimization, improve process understanding, and integrate heterogeneous experimental, biological, and manufacturing datasets across diverse nanopharmaceutical platforms. These methods are particularly relevant for modeling protein corona formation, cellular uptake, intracellular trafficking, biodistribution, pharmacokinetics, toxicity, immunogenicity, and patient-specific responses. However, translational implementation remains limited by fragmented datasets, inconsistent reporting standards, limited interpretability, insufficient external validation, uncertain predictions, poorly defined applicability domains, and evolving regulatory expectations for adaptive computational models. Overall, AI should be viewed not only as an optimization tool, but also as a translational framework connecting formulation science, biological prediction, manufacturing control, and clinical implementation. Future progress will depend on standardized data infrastructures, explainable and externally validated models, uncertainty quantification, applicability-domain definition, hybrid mechanistic–AI frameworks, regulatory-ready documentation, and clinically relevant case studies. Full article

The increasing integration of distributed electricity–heat adjustable resources into distribution networks poses significant challenges for virtual power plant (VPP) dispatch, as conventional aggregation models often neglect network constraints, leading to infeasible or unsafe operation plans. To address this issue, this paper proposes a source-grid-load-storage aggregation optimization method that explicitly incorporates both distribution network power flow constraints and district heating network hydraulic–thermal coupling constraints. The network constraints are integrated into the optimization objective as penalty terms, and the dispatch problem is formulated as a Markov decision process. A deep reinforcement learning framework, combining twin delayed deep deterministic policy gradient (TD3) and deep deterministic policy gradient (DDPG) algorithms, is employed to solve the sequential decision-making problem. Simulation results demonstrate that the proposed method effectively ensures distribution network security and heating quality while maintaining economic efficiency, providing a feasible and safe dispatch strategy for VPPs in coupled electricity–heat systems. Full article

Smart Mobility plays a key role in Smart Cities, given its ability to support the rollout of intelligent transport systems, allowing for more sustainable urban transportation and greater interoperability across diverse mobility modes. Furthermore, Smart Mobility is essential to maximize the quality of life for the community while advancing principles of sustainability, economic development, technological innovation, and collaborative governance. Real-Time Traffic Management (RTTM) emerges as a vital technology for optimizing traffic management in Smart Mobility. Using the PRISMA framework, the proposed systematic literature review examines 165 peer-reviewed publications related to RTTM research work published between 2019 and 2025. This review identified eleven application domains, with Urban Traffic Management Systems (36.97%) and Artificial Intelligence (AI) and Predictive Analytics (12.73%) representing the most prominent areas. A retrospective analysis of the literature on control architecture used in closed-loop feedback systems indicates that most studies (89%) have adopted a more dynamic control model, while 7.8% adopted a Digital Twin (DT)-based approach. However, several implementation barriers persist, including limited integration of online optimization and learning loops into RTTM systems, gaps in performance comparisons between simulation and reality, scalability issues due to heterogeneous environments, inconsistent data quality caused by various sensor types, and difficulties integrating sensors into a control system. In addition, this paper proposes a taxonomy of RTTM applications and control architectures, while outlining key practical barriers to implementation and charting future research directions for advancing Smart Mobility through robust RTTM. Full article

Consolidated bioprocessing (CBP) is difficult to monitor because enzyme production, lignocellulose degradation, sugar release, and fermentation occur simultaneously under sparse measurement, feedstock variability, and plant–model mismatch conditions. This study proposes a computational sensor-set design framework for digital-twin-assisted CBP monitoring. A five-state virtual plant, consisting of active biomass, cellulolytic enzyme activity, residual insoluble substrate, soluble sugar, and ethanol, was used to evaluate all 16 ethanol-mandatory measurement packages formed from ethanol, sugar, biomass, enzyme, and residual-substrate proxy channels. Candidate sensor sets were assessed using finite-difference output sensitivities, Fisher-information-based state-observability and parameter-identifiability analyses, eigenvalue and parameter-correlation diagnostics, and paired Monte Carlo unscented Kalman filter soft-sensing reconstruction. Within the tested five-state virtual-plant benchmark and with the specified excitation schedule, noise assumptions, burden indices, and scoring objective, ethanol-only sensing provided the weakest support for state-aware CBP digital-twin reconstruction. At a $6\mathrm{h}$ sampling interval, the state-observability log-pseudodeterminant increased from 4.18 with ethanol-only sensing to 8.56 after adding soluble sugar and to 16.42 with full-proxy monitoring. The ethanol–sugar–biomass–substrate package also gave strong reduced state-observability performance, with log-pseudodeterminants of 15.12, 13.76, and 12.51 at 6, 12, and $24\mathrm{h}$, respectively. Biomass and enzyme proxies contributed strongly to parameter learning, and the ethanol–sugar–biomass–enzyme package gave the strongest active parameter-identifiability performance, with log-pseudodeterminants of 10.82, 9.06, and 6.67 at 6, 12, and $24\mathrm{h}$, respectively. In the paired soft-sensing analysis, full-proxy monitoring reduced the mean latent-state RMSE from 1.1899 to 0.3756, followed by ethanol–biomass–enzyme–substrate with 0.3843 and ethanol–sugar–biomass–substrate with 0.4121. The primary aggregate ranking identified ethanol–sugar–biomass–substrate as the best overall package, with a sensor-value score of 0.8432 and a burden index of 7.0, followed by full-proxy monitoring with a score of 0.8173 and a burden index of 10.0. Robustness tests showed that ethanol–sugar–biomass–substrate remained top-ranked under uniform noise scaling, full UKF missingness, delay and bias stress test conditions, most scoring-weight scenarios, and all tested sensor-specific burden workflows. Full-proxy monitoring remained a close competitor under independent sensor-specific noise variation conditions and became top-ranked for some alternative operating trajectories. The proposed framework provides a simulation-based method for prioritizing informative measurement packages before implementing CBP digital twins in laboratory and pilot-plant settings. Full article

Fringe projection profilometry (FPP) is widely used for 3D reconstruction, but conventional single-view FPP systems suffer from inherent occlusions and shadow regions, leading to incomplete surface recovery. In this study, we propose CVA-Net, an end-to-end deep learning framework with cross-view attention (CVA) that directly reconstructs dense depth maps from multi-view fringe patterns. CVA-Net simultaneously processes four fringe images acquired from orthogonal projection directions and leverages a CVA module to explicitly model inter-view dependencies, enabling adaptive fusion of complementary information. A 3D U-Net backbone with attention gates, atrous spatial pyramid pooling (ASPP), and an auxiliary parameter estimation branch further enhances reconstruction accuracy and structural consistency via multitask learning. To support Sim2Real network training, we build a Blender-based digital twin of a multi-view FPP system and generate a large-scale synthetic dataset with perfect ground truth. Extensive experiments on both synthetic and real-world objects demonstrate that CVA-Net significantly outperforms state-of-the-art single-view methods. With a symmetric four-view configuration and fringe period of 8, CVA-Net achieves an MAE of 0.0359 mm, an MSE of 0.0379 mm² and an RMSE of 0.1947 mm, reducing the MAE, MSE, and RMSE by 32.8%, 54.1%, and 32.2%, respectively, compared to the best single-view competitor. Ablation studies validate the contribution of each architectural component, while real-system experiments demonstrate the feasibility of transferring a network trained purely on synthetic data to practical FPP measurements without domain adaptation. Although further improvements are required to enhance reconstruction accuracy under real imaging conditions, the proposed framework provides an effective initial step toward bridging the gap between digital-twin-based training and real-world multi-view FPP applications. CVA-Net provides a robust, occlusion-aware solution for multi-view FPP reconstruction. Full article

The paper proposes a Digital Twin (DTw) framework, constructing a circuit model replicating the pulse transmission and reception processes for devices with high sensitivity to noises, such as wearable ultrasound transducers. The model is suitable to train supervised AI algorithms denoising the noisy ultrasound signal received. The DTw combines the circuit simulations with the AI data processing by training the model with the cleaned pulsed signals and by correcting the noises modeled by ‘white-noise’ voltage generators. Specifically, the voltage outputs of the circuit simulations are used to train the AI models and to test noisy signals for reconstruction. The DTw model is based on the transmission line theory combined with the perturbation impedance approach, supporting human body tissue discrimination based on noises. Two open-source tools are used for the DTw construction, the LTSpice and the Orange Mining tool, which are used for the circuit simulation and for the AI data processing, respectively. The theoretical work proves that the methodology is able to reconstruct correctly, with a good performance in the time domain and the frequency domain, noisy voltage signals, by addressing the analysis on cancer detection by combining circuit, AI and Monte Carlo approaches. Full article

Traditional global localization systems frequently struggle with perceptual ambiguities in dynamic environments and structurally similar scenes, which severely compromises navigation robustness. Concurrently, conventional path planning methodologies rarely integrate proactive safety considerations regarding high-risk environmental features. To resolve these critical limitations, this paper introduces a comprehensive semantic-assisted framework for mobile robots to enhance both global localization and navigation. First, we develop a semantic-aware place representation derived from LiDAR point clouds. By explicitly filtering dynamic objects and assigning category-specific weights, this approach mitigates perceptual aliasing and ensures robust scene recognition. Furthermore, we implement a Hyper-Semantic Point Histogram (HyperSPH) to embed semantic encoding directly into local geometric features. A Semantic Geometric Consistency Filter is subsequently applied to eliminate matching outliers and maximize registration accuracy. For secure navigation, we propose the Semantic-guided Twin Delayed Deep Deterministic Policy Gradient with Long Short-Term Memory (S-TD3-LSTM) algorithm within a deep reinforcement learning architecture. This strategy extracts temporal correlations via Long Short-Term Memory networks and integrates a dedicated semantic cost function to optimize obstacle avoidance policies. Extensive experiments demonstrate that the proposed localization module achieves superior retrieval and pose estimation precision over conventional methods. In complex path planning scenarios, the S-TD3-LSTM algorithm ensures stable convergence and generates highly adaptive trajectories. By proactively identifying and bypassing semantic hazards, the integrated system drastically minimizes exposure to dangerous zones, successfully establishing a rigorous balance between path efficiency and execution safety. Full article

Under the dual constraints of global food security and ecological protection, conventional agriculture is hampered by low resource efficiency and sluggish environmental response. Crop digital twin technology establishes a dynamic virtual reality system that integrates crops, environment, and water to enable real-time interaction and optimization. Based on the existing literature, this paper reviews the concept, architecture, and core modules of this technology and summarizes its applications in precision irrigation and crop monitoring. There are three major bottlenecks that persist, including limited high-frequency multi-source sensing and spatiotemporal fusion, insufficient parameter calibration and dynamic updating, and weak cross-scale integration from plant to watershed. Water is increasingly recognized as the key constraint and control variable and acting as both the central physiological driver of crop growth and the mass-flow link that connects the soil–plant–atmosphere continuum. The spatiotemporal dynamics of crop water deficit, compensatory root water uptake, evapotranspiration feedback, and the hydraulic behavior of irrigation-district canal systems constitute the core hydrological processes that must be simulated within the digital twin. Synchronizing crop water demand, soil moisture dynamics, atmospheric evapotranspiration, and irrigation scheduling within a unified spatiotemporal framework establishes a complete sensing, diagnosis, prediction and regulation technical chain. This chain offers a core pathway for alleviating agricultural water scarcity, improving irrigation efficiency, and ensuring food security. Full article

Robotic belt grinding is an effective and widely adopted finishing method for superalloys, offering notable advantages such as high material removal capability, low heat input, and reduced workpiece damage. In addition, robots can readily integrate multiple sensors—such as infrared radiation cameras, force sensors, and high-speed cameras—which facilitate real-time monitoring of the grinding process and thereby enhance grinding quality control. With the establishment and continuous advancement of large-scale artificial intelligence (AI) data models, new breakthroughs have emerged in the optimization of robotic grinding processes. Owing to its dexterous workspace and advantages in high flexibility and cost-effectiveness, robotic belt grinding has become a critical process for the precision forming of complex curved components such as aero-engine blades and blisks. However, factors such as the limited absolute accuracy of industrial robots, time-varying grinding contact states, and significant transient boundary effects make it difficult for the current constant-parameter open-loop machining mode to simultaneously meet the demands for high material removal efficiency and high surface integrity on complex profiles. This paper systematically reviews the technologies for precision control and process optimization of robotic belt grinding aimed at pointwise precise material removal. First, the structural composition of the robotic belt grinding system and the material removal mechanism are analyzed. Then, centered on the compensation concept, a hierarchical progressive technical framework is outlined, covering geometric calibration compensation, force/position hybrid online compensation, transient entry boundary compensation, and system-level comprehensive compensation of multi-source errors, with a comparison of the applicable scenarios and the effects on shape and property control at each level. Furthermore, under the support of effective compensation, the collaborative optimization methods of material removal modeling, multi-objective optimization of process parameters, force-constrained trajectory planning, and intelligent adaptive processes are elaborated. Finally, current technical bottlenecks are summarized, and future trends in next-generation adaptive grinding technology driven by digital twins and embodied intelligence are envisioned. This review aims to provide a systematic theoretical reference for the high-precision and intelligent upgrading of robotic precision grinding systems. Full article

Preserving cultural heritage sites requires an interoperable digital framework capable of integrating heterogeneous spatial data and supporting immersive interaction for inspection and management. This study investigates the integration of multiple heritage data representations—including IFC-based Heritage Building Information Modeling (HBIM), terrestrial and UAV LiDAR point clouds, and 3D Gaussian Splatting reconstructions—into a unified digital management environment for the East Hall (Aula Timur) heritage site within the Bandung Institute of Technology (ITB) campus. A semantic–spatial interoperability workflow is proposed to harmonize BIM, point cloud, and landscape-scale data within a common georeferenced context, supported by a CityGML-based base map of the surrounding site. An immersive virtual environment was implemented using a head-mounted display to enable walkthrough-based inspection and damage annotation. All datasets were georeferenced within a unified coordinate system, allowing spatial registration between digital objects and the physical heritage site. The results demonstrate that multi-source heritage datasets can be integrated with high geometric accuracy, achieving TLS registration errors of approximately 2 mm and georeferencing residuals within 11.1 cm (horizontal) and 0.95 cm (vertical), while preserving semantic information and ensuring spatial coherence across HBIM, GIS, and immersive environments. The system is implemented in VR, with an architecture designed to support future MR-based on-site annotation and visualization. The proposed framework establishes a foundation for future heritage digital twin deployments and supports informed conservation decisions. Full article

Heterogeneous fault information and a lack of real-time synchronization in CNC machine tools hinder effective Prognostics and Health Management (PHM). This paper designs and implements a digital twin-driven PHM framework for machine tools that integrates a unified machine-tool fault information dictionary and a mechanism-data dual-driven diagnostic model (ResNet-TCN). A cyber–physical platform was developed using OPC UA and RESTful APIs to ensure real-time data synchronization. Experiments on the PHM 2010 dataset demonstrate that the proposed ResNet-TCN model achieves a root mean square error (RMSE) of 5.46 μm for tool wear prediction. Its performance surpasses that of traditional LSTM models, and the proposed framework effectively eliminates information silos, providing a responsive, scalable and accurate PHM solution for smart manufacturing. Full article

The seamless integration of real-time operational technology (OT) with big data architectures remains a critical bottleneck in developing robust robotic Digital Twins. Furthermore, evaluating stochastic motion planners strictly within pristine simulations obscures vital real-world challenges such as sensor noise, communication latency, and mechanical stress. This study presents a high-throughput, real-time Hardware-in-the-Loop (HIL) pipeline integrating ROS 2, Apache Kafka, and Functional Mock-up Units (FMUs). Using a UR10e manipulator in a constrained industrial environment, we conducted extensive physical benchmarking of 11 Open Motion Planning Library (OMPL) algorithms across 10 repetitions, generating a comprehensive dataset of 785,192 samples. The proposed IT/OT architecture achieved deterministic millisecond-level synchronization, bounding end-to-end communication latency between 0.09 and 15.51 ms. Physical executions revealed a macroscopic “topological divergence” between simulation and reality, with spatial deviations peaking at 457.65 mm due to real-world point-cloud noise. While algorithms like EST and KPIECE demonstrated optimal geometric efficiency (e.g., a mean path length of 14.57 m) and hardware-friendly dynamics, traditional planners like RRT generated severe inertial spikes of up to 100 N, demonstrating substantial unsuitability for continuous industrial deployment. The primary contribution is a methodologically novel, rigorously validated big data pipeline and the release of an open-source, 50 Hz multimodal dataset (spatial, temporal, and dynamic forces), bridging the sim-to-real gap and providing a foundational benchmark for future data-driven robotic applications. Full article

Multi-source heterogeneous data in discrete manufacturing shop floors, including vibration signals, equipment logs, visual monitoring data, and handwritten production reports, exhibit significant differences in modality and semantic representation. Traditional fusion methods often fail to bridge the semantic gap between low-level sensing signals and high-level manufacturing cognition, limiting intelligent anomaly analysis and decision-making capability. To address this issue, this paper proposes a semantic translation and fusion framework for industrial heterogeneous data based on Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs). First, a unified semantic translation mechanism is developed to convert multimodal industrial data into structured semantic representations for cross-modal alignment. Second, an industrial knowledge graph and RAG mechanism are introduced to integrate process knowledge, maintenance manuals, and historical fault records into the reasoning process. Third, an LLM-driven reasoning framework is designed for multimodal semantic fusion, anomaly identification, causal analysis, and optimization recommendation generation. In addition, a digital twin-based visualization interface is constructed to realize real-time interaction between production lines, industrial data, and intelligent cognitive reports. Experimental results demonstrate that the proposed framework significantly improves industrial reasoning accuracy, anomaly analysis correctness, and response efficiency compared with general-purpose LLMs, providing an effective solution for intelligent cognition and decision-making in discrete manufacturing systems. Full article

In today’s manufacturing industry, work-related musculoskeletal disorders (WMSDs) remain among the most prevalent occupational health issues. Collaborative robots (cobots) represent a promising technology to address this challenge. Consequently, ergonomics assessment in human–robot collaboration (HRC) has gained increasing attention in recent years. This study investigates the feasibility of using a coupled digital twin system consisting of a digital human model (DHM) and a cobot digital twin to assess detailed ergonomic parameters such as muscle activations and joint reaction forces in an HRC task. Selected parameters are used to develop an ergonomics map that condenses the effects of human–robot interaction into a single scalar value for each working position in the coronal plane in front of the user. The ergonomics mapping approach is presented, key influencing factors are identified, and critical workspace design implications are discussed. Full article