Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 136

Liczba wyników na stronie
first rewind previous Strona / 7 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  digital twin
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 7 next fast forward last
PL
Cyfrowy bliźniak stanowi jedno z kluczowych pojęć Przemysłu 4.0 i 5.0, oznaczając dynamiczny, stale aktualizowany model rzeczywistego obiektu, zasilany danymi pomiarowymi oraz wspierający podejmowanie decyzji technicznych. W ostatnich latach koncepcja ta znalazła szerokie zastosowanie w lotnictwie, motoryzacji i energetyce, natomiast sektor opakowań z tektury falistej dopiero rozpoczyna wykorzystanie podobnych narzędzi. Artykuł przedstawia możliwości wdrożenia cyfrowego bliźniaka do opakowań tekturowych, obejmującego cały cykl życia wyrobu – od projektu konstrukcyjnego, poprzez produkcję, magazynowanie i transport, aż po użytkowanie oraz recykling. Omówiono źródła danych niezbędnych do budowy takiego modelu, w tym parametry materiałowe papierów składowych, geometrię fali, warunki klimatyczne, historię obciążeń oraz dane z linii produkcyjnych. Przedstawiono również rolę metod numerycznych, sztucznej inteligencji i systemów IoT w bieżącej aktualizacji modelu oraz przewidywaniu nośności, trwałości i ryzyka uszkodzeń opakowań. Szczególną uwagę zwrócono na możliwość szybkiej oceny wpływu wilgotności, składowania oraz zmian jakości surowca na zachowanie gotowego opakowania. Wskazano, że pełny cyfrowy bliźniak opakowania z tektury falistej jest już technicznie osiągalny, jednak jego praktyczne wdrożenie wymaga standaryzacji danych, integracji systemów produkcyjnych oraz uproszczonych modeli obliczeniowych możliwych do zastosowania w warunkach przemysłowych. Technologia ta może w przyszłości znacząco ograniczyć liczbę kosztownych testów fizycznych, skrócić czas projektowania oraz poprawić efektywność materiałową opakowań.
EN
The digital twin is one of the key concepts of Industry 4.0 and 5.0, referring to a dynamic and continuously updated virtual representation of a real object, supported by measurement data and used for engineering decision-making. In recent years, this concept has been widely adopted in aerospace, automotive, and energy sectors, while the corrugated packaging industry is only beginning to explore similar solutions. This paper discusses the feasibility of implementing a digital twin for corrugated board packaging, covering the entire product life cycle: structural design, manufacturing, storage, transport, use, and recycling. The study presents the main data sources required for such a model, including material parameters of paper constituents, flute geometry, climatic conditions, load history, and production-line data. The role of numerical methods, artificial intelligence, and IoT systems in continuous model updating and in predicting strength, durability, and failure risk is also discussed. Particular attention is given to the rapid assessment of humidity effects, warehousing conditions, and raw material variability on packaging performance. It is concluded that a full digital twin of corrugated packaging is already technically feasible; however, its industrial implementation still requires data standardization, integration of production systems, and simplified computational models suitable for real-time applications. In the future, this technology may significantly reduce costly physical testing, shorten development time, and improve material efficiency of packaging solutions.
PL
Technologia cyfrowego bliźniaka (DT – Digital Twin) może stać się przełomowym narzędziem wspierającym transformację sektora elektroenergetycznego, obejmującą zarówno operatorów systemów dystrybucyjnych (OSD), jak i przesyłowych (OSP). Artykuł prezentuje koncepcję opracowania cyfrowego bliźniaka sieci dystrybucyjnej niskiego napięcia (nn) w oparciu o doświadczenia z realizowanego aktualnie projektu cyfrowego bliźniaka europejskiego systemu elektroenergetycznego TwinEU. Dla OSD uczestniczących w tworzeniu ekosystemu TwinEU kluczowym wyzwaniem jest zwiększenie obserwowalności własnych sieci dystrybucyjnych nn. Autorzy proponują, aby część obliczeń brzegowych cyfrowego bliźniaka realizowana była w aktywnych regulatorach napięcia linii (ALVR), coraz chętniej wybieranych przez OSD do sterowania napięciem w sieciach nn i wyposażonych w zaawansowane układy mikroprocesorowe oraz interfejsy komunikacyjne.
EN
Digital twin (DT) technology has the potential to become a breakthrough tool supporting the transformation of the power sector, encompassing both distribution system operators (DSOs) and transmission system operators (TSOs). This article presents a concept for developing a digital twin of a low-voltage (LV) distribution network, based on experience from the ongoing TwinEU project. For DSOs participating in the TwinEU ecosystem, a key challenge is increasing the observability of their own LV distribution networks. The authors propose that some of the digital twin’s edge computations be implemented in active line voltage regulators (ALVRs), increasingly being installed by DSOs to control voltage in LV networks. These regulators are equipped with advanced microprocessor systems and communication interfaces.
EN
Digital Twin implementation in production engineering requires a reliable instrumentation layer between the physical system and its digital representation. This paper proposes a platform-independent, requirement-oriented virtual instrumentation framework for staged Digital Twin-based monitoring. The framework distinguishes three levels of digital representation: Digital Model, Digital Shadow and Digital Twin. For each level, implementation requirements are organized using Ishikawa diagrams adapted as requirement maps. The framework covers modeling, sensing, data acquisition, signal processing, visualization, synchronization and feedback-oriented support. A beam-deflection monitoring setup illustrates the intended measurement and representation chain. National Instruments data-acquisition hardware and LabVIEW software are used as one implementation option, not as limiting components of the framework. The proposed methodology supports systematic planning of monitoring, diagnostics, predictive maintenance and decision-support applications in smart manufacturing.
EN
Low-altitude photogrammetry for the digital documentation of truss bridges was evaluated using the Niestępowo railway viaduct as a case study. A global reconstruction was compared with local modeling of a truss joint based on a subset of images from the same UAV survey (Agisoft Metashape 2.1.2). The results show that the global model is sufficient for general geometric inventory (dimensional differences <2%), whereas the local model markedly improves the measurement accuracy of structural details (error reduction of 83 – 100%) while requiring a short processing time (<30min).
PL
W artykule oceniono możliwości fotogrametrii niskopułapowej w dokumentacji mostów kratownicowych na przykładzie wiaduktu kolejowego w Niestępowie. Porównano rekonstrukcję globalną oraz modelowanie lokalne węzła bazujące na podzbiorze zdjęć z tej samej kampanii UAV (Agisoft Metashape 2.1.2). Wykazano, że model globalny jest wystarczający do inwentaryzacji ogólnej (różnica wymiarów <2%), natomiast model lokalny znacznie poprawia wymiarowanie detali (redukcja błędu 83 – 100%) przy krótkim czasie opracowania (<30 min).
EN
Background: Last-mile delivery accounts for over 50% of total logistics costs, representing a major operational and sustainability challenge in Saudi Arabia’s rapidly expanding e-commerce sector. Conventional siloed fleet models often result in underutilized capacity, delivery inefficiencies, and elevated carbon emissions. This study proposes a machine learning–driven smart-sharing framework that integrates predictive analytics with operations research to optimize last-mile delivery in the Kingdom of Saudi Arabia. Methods: Using the Regional Delivery Data in Saudi Arabia (2024), which aggregates quarterly order volumes across 13 regions, this study develops demand forecasting models (SARIMAX, LightGBM, and CatBoost) as well as ETA predictions enriched with event- and calendar-based features. These outputs inform a vehicle routing problem with time windows (VRP-TW) implemented using Google OR-Tools and a CP-SAT facility location model for parcel locker siting. A digital twin simulation built in SimPy is then used to stress test performance under peak demand conditions (e.g., Ramadan) and weather-related disruptions. Results: The findings show that pooled fleet sharing reduces routing costs by more than 65%, decreasing traveled distance from 7,906 to 2,370 units, while increasing the share of on-time deliveries from 37% to nearly 100%. The introduction of parcel lockers further improves system efficiency, reducing kilometers traveled per parcel by up to 90% and lowering CO₂ emissions from 0.77 to 0.06 kg per parcel. Stress-test experiments confirm the resilience of the shared model, which maintains service-level agreement (SLA) compliance even under demand surges and operational disruptions. Conclusions: This research presents the first reproducible, Colab-native machine learning and optimization pipeline applied to Saudi Arabia’s regional delivery data. The proposed framework provides actionable insights for logistics managers, urban planners, and policymakers seeking data-driven approaches aligned with Saudi Arabia’s Vision 2030 sustainability and efficiency goals.
EN
Background: Perishable supply chains face persistent challenges arising from product perishability, demand fluctuations, and frequent disruptions. Conventional models lack the real-time adaptability required to effectively manage spoilage while maintaining service levels. This paper proposes an integrated decision-support framework that leverages Digital Twin (DT) technology, Mixed-Integer Programming (MIP), and Agile Quality Tools to enhance resilience and quality preservation in perishable supply chains. Methods: The proposed framework integrates DT-enabled real-time monitoring, predictive analytics, and adaptive re-optimization. MIP is employed to support routing and inventory decisions, while Agile Quality Tools, such as Failure Mode and Effects Analysis (FMEA) and control charts, are used to dynamically adjust model parameters in response to freshness deviations and disruption signals. Case studies from food and pharmaceutical supply chains were conducted to evaluate performance under both stable and disrupted operating conditions. Results: The DT-driven framework significantly outperformed baseline models in both domains. In the food supply chain, spoilage was reduced by more than 35%, service levels improved by over 7%, product freshness increased, and total costs declined by nearly 9%. In the pharmaceutical cold chain, spoilage was reduced by over 60%, service levels exceeded 97%, and recovery from disruptions was 37% faster, with costs reduced by about 12%. Across all scenarios, the framework demonstrated high adaptability and operational efficiency, achieving near real-time optimization with an average CPU time of 2.45 seconds. Conclusions: Integrating DT, MIP, and Agile Quality Tools offers a robust, adaptive, and cross-domain solution for perishable supply chains. The proposed framework enhances resilience, minimizes spoilage, reduces operational costs, and ensures higher service levels under uncertainty. Its multidisciplinary nature offers clear value for both academic research and industrial practice.
EN
The article discusses the application of digital twins in modern production plants. Challenges for the industry are presented. Next, the concept of a Digital Twin (DT) is introduced. An overview of technologies utilised by DT is provided and specific applications of the DT are discussed: to the logistics and manufacturing processes. The predictive quality control is covered as an important element of a DT. Finally, the problem of integration of digital technologies into plants systems is addressed. The modern challenges for the industry are mainly related to contradictive market requirements, such as high quality v. low price. There are difficulties for workers, too, who lose their positions or are forced to retrain or change their specialisations. The DT technologies are mostly related to sensorics and communications, which enable a bidirectional relation between the DT and the process. This constitutes an actual advantage and contributes to the effectiveness of production plants.
PL
Artykuł porusza tematykę zastosowania cyfrowych bliźniaków w nowoczesnych zakładach produkcyjnych. Przedstawiono wyzwania stojące przed przemysłem, a następnie omówiono koncepcję cyfrowych bliźniaków (DT). Zaprezentowano przegląd technologii wykorzystywanych w DT oraz przedstawiono ich specyficzne zastosowania w procesach logistycznych i produkcyjnych. Omówiono także predykcyjną kontrolę jakości jako ważny element DT. Na koniec wskazano problem integracji technologii cyfrowych z systemami zakładów. Współczesne wyzwania stojące przed przemysłem wiążą się głównie ze sprzecznymi wymaganiami rynku, takimi jak wysoka jakość przy jednoczesnym utrzymaniu niskiej ceny. Występują również trudności dla pracowników, którzy tracą pracę lub są zmuszeni do zmiany branży. Technologie DT są w dużej mierze związane z sensoryką i komunikacją, umożliwiającymi dwukierunkową relację między DT a rzeczywistym procesem, co stanowi istotną korzyść i przyczynia się do zwiększenia efektywności funkcjonowania zakładów produkcyjnych.
EN
A cross-domain diagnosis approach combining Digital Twin (DT) and Federated Learning (FL) is proposed to further optimize the issues of sample scarcity and privacy protection in early defect diagnosis of wind turbine transmission systems. Firstly, a DT which combines both mechanism- and data-driven approaches is proposed to generate multi-condition virtual fault data. Next, the feature alignment strategy is used to reduce the domain difference between simulated and real data. Finally, a cross-wind FL framework is proposed, which uses dualpath feature learning and dynamic aggregation strategy combined with data quality evaluation for synchronous training. The experimental results on Coverage, Accuracy, Reliability and Earliness (CARE) dataset show that: 1) the average F1 score of the proposed DT-FL model on three wind farm test sets is 0.942, which is better than that of the FL (F1 score is 0.907) and the standard federated average algorithm (F1 score is 0.925) which only use measured data. 2) In the cross-wind migration task, the average performance attenuation of DT-FL model is 7.6%, and it has better generalization ability. The above results show that the proposed model can effectively use virtual data to enhance the diagnostic capabilities and improve the early fault identification performance under the premise of protecting data privacy.
EN
Centrifugal pumps often suffer from low operating efficiency and present challenges in accurately diagnosing impeller blade fracture faults. Therefore, this study develops a method for improving centrifugal pump efficiency and diagnosing faults based on digital twins. For efficiency improvement, a digital twin optimization framework for the centrifugal pump impeller is established. Initial samples are generated through Latin hypercube sampling, and a surrogate model is constructed by combining computational fluid dynamics numerical simulations with an approximate model. A PSO algorithm is applied to solve a multi-objective programming problem with the objectives of minimizing entropy production and maximizing efficiency. For fault diagnosis, the generated pressure and velocity contour map datasets are input into a target detection network for training, and subsequently, a stacked ensemble strategy is introduced to fuse the two types of detection results for decision-making. The findings reveal that the optimized impeller’s hydraulic efficiency is improved by 4.6%, while entropy production is reduced by 18.6%. The proposed method can enhance centrifugal pumps’ performance and achieve accurate diagnosis of blade fracture faults, thereby providing a new technical path for intelligent efficiency improvement and accurate fault diagnosis of centrifugal pumps.
EN
This paper presents a city-scale digital documentation and analysis workflow for cultural heritage assets, demonstrated on the example of the UNESCO-listed historic centre and fortress area of Zamość (Poland). The study integrates terrestrial laser scanning (TLS) with unmanned aerial vehicle (UAV) and terrestrial photogrammetry to produce a geometrically consistent 3D dataset covering over 100 buildings and key public-space elements. The processing pipeline includes scan registration, image-based reconstruction, and cross-sensor alignment, followed by the creation of an analytical 3D model segmented by address and parcel identifiers to enable linkage with municipal datasets. A semantic layer is implemented by assigning a structured set of building- and neighbourhood-level parameters and mapping them into building information modelling (BIM)/openBIM structures (Revit shared parameters and industry foundation classes (IFC) Property Sets), targeting a level of information adequate for conservation-oriented diagnostics and urban-scale assessments rather than detailed component-level historic building information modelling (HBIM). Geometric quality is verified using independent checkpoints and registration statistics (e.g., root mean square error (RMSE) where applicable), yielding a typical spatial agreement on the order of 4 cm to 5 cm for the integrated model in representative test areas. The resulting environment supports multi-criteria querying and visualisation, including functional categorisation, technical condition screening (e.g., moisture-related indicators), and energy-related attributes for prioritisation at the district scale. The main contribution is a reproducible integration of multi-source survey data with an explicit semantic/BIM mapping and verifiable accuracy reporting for a heritage city context, clarifying which outputs stem from the proposed method (data integration, segmentation, semantic schema, and validation) versus the standard capabilities of the employed software.
PL
Artykuł stanowi kompleksową analizę zastosowania sztucznej inteligencji (AI) w branży budowlanej, jednym z największych sektorów gospodarczych odpowiadającym za około 13% światowego produktu krajowego brutto. Mimo swojej znaczącej roli gospodarczej, budownictwo od dekad zmaga się z chroniczną luką produktywności – wzrost wydajności w ostatnich 20 latach wyniósł zaledwie 10%, podczas gdy globalna gospodarka osiągnęła wzrost ponad 50%. Artykuł analizuje ewolucję AI w budownictwie od systemów ekspertowych z lat 80. i 90. XX wieku, poprzez uczenie maszynowe, aż do współczesnych rozwiązań opierających się na głębokim uczeniu, sieciach neuronowych i integracji z technologią BIM oraz cyfrowymi bliźniakami. Omówiono praktyczne zastosowania AI w projektowaniu, planowaniu i harmonogramowaniu, automatyzacji procesów wykonawczych, zarządzaniu bezpieczeństwem oraz optymalizacji zasobów. Wskazano kluczowe korzyści, takie jak redukcja kosztów, skrócenie harmonogramów i poprawa bezpieczeństwa, jednocześnie analizując istotne bariery wdrożeniowe. We wnioskach podkreślono, że pełne wykorzystanie potencjału AI w budownictwie wymaga nie tylko dalszego rozwoju technologicznego, ale przede wszystkim zmian organizacyjnych i przystosowania kompetencji pracowników.
EN
This article provides a comprehensive analysis of the application of artificial intelligence (AI) in the construction industry, one of the largest sectors of the economy, responsible for approximately 13% of global gross domestic product. Despite its major economic role, construction has for decades struggled with a chronic productivity gap – productivity growth over the last 20 years has been only 10%, while the global economy achieved growth of more than 50%. The article analyses the evolution of AI in construction from expert systems of the 1980s and 1990s, through machine learning, to contemporary solutions based on deep learning, neural networks, and integration with BIM technology and digital twins. Practical applications of AI in design, planning and scheduling, automation of execution processes, safety management, and resource optimisation are discussed. Key benefits are identified, such as cost reduction, shorter schedules, and improved safety, while important implementation barriers are also analysed. The conclusions emphasise that full use of AI’s potential in construction requires not only further technological development, but above all organisational change and the adaptation of workers’ competences.
EN
In civil engineering, information systems are increasingly being utilized, particularly Building Information Modeling (BIM) technology. BIM is currently most prominently used in the design and construction phases, with less intensity observed in the implementation of solutions in later phases of operation and/or demolition. However, these issues mainly concern recently constructed objects, for which a digital twin was created at the design stage, greatly facilitating the decision-making process for managers to implement such solutions. In this article, the authors focus on presenting an example of using the Common Data Environment (CDE) platform for managing an existing building, for which 3D documentation was not created in earlier stages of the lifecycle. For analysis and as an attempt to implement the use of BIM technology, building D-2 located on the AGH campus was selected. Virtual documentation in the form of a “digital twin” was prepared for the selected object. The traditional and currently practiced property management plan was analyzed. Firstly, a plan for repetitive tasks was presented, including required building inspections and cyclical work performed. Subsequently, a process of action in case of a selected failure was developed. The traditional management plan was compared with the one prepared using the digital platform. The advantages and disadvantages of each solution were identified, and the validity of introducing process improvement for building administration using the selected tool was verified.
PL
W przemyśle budowlanym od kilkunastu lat obserwuje się dynamiczny rozwój cyfryzacji pracy, który stopniowo wprowadzany jest we wszystkie fazy cyklu życia obiektu. W niniejszym artykule autorki skupiły się szczególnie na możliwościach, jakie oferuje technologia BIM w kontekście siódmego wymiaru BIM 7D, czyli fazy użytkowania obiektu. Na rynku pojawiły się systemy informatyczne, w skład których wchodzą platformy CDE, które stanowią ważny element wspomagający procesy zarządzania obiektem. Platforma cyfrowa staje się niezwykle wartościowym narzędziem, które może znacznie ułatwić i usprawnić procesy związane z eksploatacją budynków. W artykule omówiono możliwości, jakie oferuje wykorzystanie platformy cyfrowej w zarządzaniu budynkiem w fazie eksploatacji. Przedstawiono korzyści, jakie może przynieść dla zarządców nieruchomości oraz jakie funkcjonalności i rozwiązania są dostępne na rynku, aby sprostać rosnącym wymaganiom w obszarze zarządzania nieruchomościami. Platformy CDE mogą być używane już od fazy projektowania, im wcześniej rozpoczniemy pracę w jednym środowisku tym szybciej zauważymy korzyści jakie z jej używania płyną. Cechy, jakimi powinna się charakteryzować platforma wskazują, że przede wszystkim ma ona na celu zapewnić stałą aktualizację danych, obieg dokumentów i komunikacji w jednym wspólnym środowisku i przede wszystkim ma ona być cyberbezpieczna podczas jej użytkowania. Obiektem dla którego utworzono cyfrowego bliźniaka jest obiekt znajdujący się na kampusie AGH oddany do użytkowania w 2020 roku o nazwie D2.
EN
Urban public space, as a core component of the urban, is an important carrier for the residents’ quality of life, social interaction and cultural inheritance. With the deepening of urbanization, urban public space is facing unprecedented challenges, including aging space, single function, environmental degradation, and mismatch with residents’ needs, etc. This paper comprehensively discusses the application of digital twin technology in urban public space renewal, and systematically analyzes its core role in enhancing the function of public space, promoting the optimization of resource allocation, and reinforcing the ability of predictive analysis from the theoretical framework to specific countermeasures. Through the introduction of genetic algorithm and ARIMA model, the technical support of complex resource allocation and future trend prediction is shown; and the successful application and significant effect of digital twin technology in actual projects are demonstrated with the examples of The Bund in Shanghai and Marina Bay Gardens in Singapore. In addition, a detailed assessment of data security, technical compatibility, public participation and cost-effectiveness is made, and targeted countermeasures and recommendations are proposed.
EN
One of the technical developments is a shift towards the use of the finite element method (FEM) simulation and artificial intelligence and digital twins to improve die-design applications. It is a huge discussion of how the traditional methodologies of the empirical designs are being complemented by the new computational methodologies, in which there is high production efficiency and quality products. By a combination of computational modeling, materials characterization, nondestructive testing validation, and machine learning algorithms, the performance will significantly increase; experiments on industrial applications show that the design period can be cut down to 4-6 weeks with a 90-95 percent productivity increase. The given article is a deep examination of the FEM modeling methods that may be applied to the process of drawing optimization, the synthesis of the non-destructive testing tools that may be used to guarantee the validity of the process, and the rising uses of machine learning and Industry 4.0. The integration of technologies presents important possibilities to enhance the production efficiency, level the environmental sustainability, and gain competitive advantages in metal forming operations. The implementation process would be done appropriately based on the computing requirements, validation, and interface with the existing production systems.
EN
Planarization technologies such as lapping and chemical-mechanical polishing (CMP) are critical in achieving high-precision surface quality in various industrial applications. While predictive models of tool wear and material removal rate have been developed in previous studies, recent advances in digital twins open new possibilities for integrating physics-based and data-driven approaches into a comprehensive decision-making framework. This paper proposes a digital twin-driven methodology for selection of process parameters in planarization technology. The framework combines lapping kinematic models, tribological equations and machine learning methods into a dynamic, adaptive system capable of predicting tool wear, optimizing parameters, and supporting real-time control. Case studies demonstrate the integration of predictive models into the proposed framework. Potential applications, limitations, and future research directions are discussed.
EN
Purpose: The objective of the paper is twofold: firstly, to analyze the applications of Digital Twin (DT) technology in ensuring cybersecurity in manufacturing processes; and secondly, to identify key thematic areas, research gaps, and potential practical applications. Design/methodology/approach: The research was conducted based on a systematic literature review, using bibliometric analysis and advanced data analysis tools such as VOSviewer and Latent Dirichlet Allocation (LDA). Findings: The literature analysis revealed that current studies focus on the analysis of DT use in risk management and security testing without interference in real manufacturing systems. DT facilitates the emulation of a variety of threat scenarios, the evaluation of the efficacy of implemented security measures, and the optimization of preventive strategies. However, the analysis also identified significant research gaps, including the lack of unified implementation methodologies and insufficient exploration of the impacts of DT deployment in cybersecurity at operational and strategic levels. Practical implications: The implementation of DT has the potential to enhance cybersecurity risk management in manufacturing enterprises by facilitating earlier threat detection, minimizing potential losses, and expediting incident response times. DT provides enterprises with tools for continuous monitoring of manufacturing processes, enabling proactive threat management and increasing system resilience. Originality/value: The study proposes an interdisciplinary approach, with a view to identifying a research niche related to the integration of DT with other information technologies. Furthermore, it outlines directions for developing methodologies and standards for DT implementation in manufacturing processes, with a view to ensuring their cybersecurity.
PL
Segmentacja semantyczna ma kluczowe znaczenie w zastosowaniu metodyki Heritage Building Information Modelling (HBIM), umożliwiając nie tylko precyzyjną dokumentację geometrii, ale także zachowanie wartości kulturowych i historycznych. Technologie takie jak naziemne skanowanie laserowe (TLS) czy fotogrametria stanowią podstawę do tworzenia tzw. cyfrowych bliźniaków, jednak same modele 3D, pozbawione semantycznego wzbogacenia, nie odzwierciedlają pełnego kontekstu obiektów zabytkowych. Manualna segmentacja, przeprowadzana we współpracy z konserwatorami i historykami architektury, pozostaje nieodzownym elementem procesu HBIM. Pozwala uchwycić niuanse dotyczące materiałów, technik budowlanych czy detali artystycznych, które zautomatyzowane algorytmy często pomijają. W efekcie cyfrowe kopie, wiernie odzwierciedlające nie tylko układ przestrzenny, ale także integralność kulturową i historyczną obiektów, stają się narzędziem niezbędnym do efektywnej konserwacji i wieloaspektowego zarządzania dziedzictwem. W artykule omówiono metodologie i wyzwania związane z segmentacją semantyczną w HBIM, podkreślając jej podwójną rolę: w tworzeniu cyfrowych bliźniaków i wspieraniu współpracy interdyscyplinarnej. Łącząc precyzję geometryczną z głębią semantyczną, HBIM wspiera wieloaspektowość tworzonych modeli i zapewnia zachowanie integralności kulturowej.
EN
Semantic segmentation is crucial in Heritage Building Information Modelling (HBIM), enabling not only precise geometric documentation, but also the preservation of cultural and historical values. Technologies such as terrestrial laser scanning (TLS) or photogrammetry provide the basis for so-called “digital twinning” of heritage, but 3D models alone—lacking semantic enrichment—do not reflect the full context of heritage buildings. Manual segmentation, carried out in collaboration with conservators and architectural historians, remains an indispensable part of the HBIM process. It captures the nuances of materials, construction techniques or artistic details that automated algorithms often miss. The result is digital twins that faithfully reflect not only the spatial layout but also the cultural and historical integrity of the buildings, becoming an essential tool for effective conservation and multi-faceted heritage management. This paper discusses the methodologies and challenges of semantic segmentation in HBIM, highlighting its dual role in creating meaningful digital twins and fostering interdisciplinary collaboration. By combining geometric precision with semantic depth, HBIM supports interdisciplinary collaboration and ensures the preservation of cultural integrity.
EN
Accurate, traceable characterisation of proton-exchange membrane (PEM) fuel cells at the single-cell level is pivotal for material screening, degradation studies and control-algorithm development. However, commercial diagnostic benches typically cost €20,000-150,000, limiting access for many research and teaching laboratories. This paper introduces a fully open-hardware, modular test stand that delivers 0.1 mV voltage resolution and a 0-50 A current envelope for a bill of materials of only €14,000. The architecture is split into a measurement & regulation layer built around temperature-controlled shunts and a 12-bit delta-sigma ADC, a control & SCADA layer based on an ESP32-S3 micro-controller and CompactDAQ interface, and a hydrogen-supply layer equipped with SIL-2 safety instrumentation. A rigorously quantified Type-A/Type-B uncertainty budget, prepared in accordance with ISO/IEC Guide 98-3 and validated via a 10,000-run Monte-Carlo simulation, yields an expanded cell-voltage uncertainty of ±0.38 % (k = 2). A built-in real-time digital twin couples an equivalent-circuit model with reduced-order CFD to enable what-if analyses and predictive maintenance. Comparative benchmarking against the AVL E-Load 2 and ZSW single-cell rigs shows equal or better metrological performance at ≤ 25% of their cost. A proof-of--concept dynamic-load experiment confirms the stand’s fidelity, establishing a low-cost pathway towards scalable, open and safe PEM fuel-cell diagnostics.
PL
W pracy przedstawiono budowę cyfrowego bliźniaka środowiska radiowego przy użyciu metody śledzenia promieni (ang. ray tracing). Zaprezentowano jak uwzględnić rzeczywisty układ budynków i materiałów z którego są zbudowane. Zaprezentowano wyniki badań dla różnych konfiguracji obliczeń propagacyjnych. Przeanalizowano ich wpływ na wybrane metryki radiowe, a także miary właściwe dla systemów wieloantenowych. Otrzymane wyniki pozwalają ocenić, jak bardzo typowe modele odbiegają od zbliżonych do rzeczywistych warunków propagacyjnych, a także które zjawiska propagacyjne mają największy wpływ na złożoność obliczeniową i jakość kanału radiowego.
EN
The paper presents the construction of a digital twin of the radio environment using the ray tracing method. It shows how to take into account the real layout of buildings and the materials they are made of. It presents the results of research for different configurations of the propagation model. Their impact on selected radio metrics, as well as measures specific to multi-antenna systems, is analyzed. The obtained results allow us to assess how much typical models deviate from propagation conditions close to reality, and which propagation phenomena have the greatest impact on computational complexity and radio channel quality.
first rewind previous Strona / 7 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.