1,634 research outputs found
Artificial Intelligence assisted Building Digitization using Mixed Reality
No full textIl Facility Management in edifici complessi richiede una grande quantità di informazioni che possono essere archiviate in un modello funzionale dell’edificio. Un modello funzionale è una rappresentazione strutturata dell'edificio che include informazioni cruciali per funzioni specifiche come la sicurezza, le azioni di ristrutturazione o il funzionamento e la manutenzione. Il rilevamento di questo tipo di dati, come le proprietà tecniche dei componenti dell'edificio, è un processo costoso. Per questo motivo, è necessario uno strumento avanzato il rilievo ingegneristico. Oggi molti studi si concentrano ancora sull'acquisizione della geometria, trascurando il fatto che molte azioni ricorrenti sono condotte su componenti all'interno degli edifici. Molti sistemi proposti sfruttano tecniche di rilevamento altamente accurate, come la scansione laser o la fotogrammetria, ma che richiedono lunghi sforzi di post-elaborazione per interpretare i dati raccolti. Inoltre, queste operazioni non vengono eseguite sul posto, portando a imprecisioni causate da un’interpretazione errata dei dati. In queste circostanze, la possibilità di eseguire la maggior parte delle operazioni in loco renderebbe sicuramente il processo più efficiente e ridurrebbe gli errori.
Questa ricerca propone un sistema di digitalizzazione che sfrutta la collaborazione uomo-macchina evitando fasi di post-elaborazione del dato. A questo scopo, vengono sfruttate le potenzialità della Mixed Reality quali la sua capacità di interagire con il mondo reale, creando un ambiente ideale per la collaborazione uomo-macchina. La capacità della Mixed Reality di sovrapporre i dati digitali all'ambiente reale rende possibile il controllo dei dati direttamente in sito. Per il processo di riconoscimento degli oggetti il sistema proposto in questa ricerca si avvale di rete neurale. La rete neurale YOLO (You Only Look Once) è stata scelta per la sua velocità e funzionalità di rilevamento multiplo, ideale per applicazioni in tempo reale. Il sistema è stato sviluppato e le sue prestazioni sono state valutate per il rilevamento di componenti del sistema antincendio. Il primo set di allenamenti è stato testato ed ha raggiunto sempre più dell'85% del fattore F1. Quindi l'intero sistema è stato testato in sito per dimostrare la sua fattibilità in uno scenario del mondo reale.Facility Management in complex buildings requires a large amount of information that can be stored in a functional building model. A functional building model is a structured representation of the building including information crucial for specific functions such as safety, refurbishment actions or operation and maintenance. Surveying this kind of data, such as technical properties of building components, is a costly process. For this reason, an advanced tool for engineering surveys is needed. Nowadays many studies still focus on capturing
geometry, overlooking the fact that many recurring actions are conducted on assets inside buildings. Many systems proposed exploit highly accurate survey techniques, like laser scanning or photogrammetry, but they need long postprocessing efforts to interpret data collected. Moreover, these operations are not pursued on site leading to inaccuracies for the incorrect interpretation of
data. Under these circumstances, the possibility of performing the majority of operation on-site would definitely make the process more efficient and it would reduce errors. This research proposes a system for digitization exploiting manmachine intelligence collaboration without post-processing. To this aim, Mixed Reality with its capability of interacting with real world is applied giving an environment for man-machine collaboration. The capability of Mixed Reality of overlapping digital data to the real environment makes possible checking data directly on site. For the object recognition process the system proposed in this research make use of Neural Network. YOLO (You Only Look Once) Neural Networks has been chosen for its speed and multiple detection features, ideal for real-time applications. The system has been developed and its performance evaluated for the detection of fire protection system components. First single Neural Network have been tested reaching always more than 85%of F1 factor. Then the whole embedded system proposed has been tested on site to prove its feasibility in a real-world scenario
Circular economy in the built environment management supported by Digital Twin. A review.
No full textManaging the built environment according to the principles of the Circular Economy (CE), with the aim of limiting energy consumption and environmental pollution, is a highly topical issue. In this context, digitization can play a crucial role in promoting virtuous scenarios.
However, the review of the literature reveals a distinct lack of in-depth investigation of the intersection between promotion of strategies related to the CE of the built environment using a digital approach, as Digital Twin (DT). In fact, in a sector characterized by low permeability to the introduction of new technologies, introducing digitization with the aim of greater efficiency is not easy. In recent years the DT approach has been gaining ground, namely, the development of digital copies that make it possible to investigate or simulate scenarios in real time.
This brief review aims to examine the existing studies and to identify challenges and further research needs. The results will ensure a deeper understanding of the topic, facilitating its development and promoting circular building management practices
A Decision Support System for Scenario Analysis in Energy Refurbishment of Residential Buildings
No full textThe energy efficiency of buildings is a key condition in the implementation of national sustainability policies. Energy efficiency of the built heritage is usually achieved through energy contracts or renovation projects that are based on decisions often taken with limited knowledge and in short time frames. However, the collection of comprehensive and reliable technical information to support the decision process is a long and expensive activity. Approximate assessment methods based on stationary thermal models are usually adopted, often introducing unacceptable uncertainties for economically onerous contracts. Hence, it is important to develop tools that, by capitalizing on the operators’ experience, can provide support for fast and reliable assessments. The paper documents the development of a decision support system prototype for the management of energy refurbishment investments in the residential building sector that assists operators in the energy performance assessment, using a limited set of technical information. The system uses a Case Based paradigm enriched with probabilistic modelling to implement decision support within the corporate’s knowledge management framework
Framework based on building information modeling, mixed reality, and a cloud platform to support information flow in facility management
No full textThe quality of information flow management has a remarkable effect on the entire life cycle of buildings. Manual retrieval of technical specifications and features of building components and their performance assessment leads to increased cost and time and efficiency reduction, especially during the facility management (FM) stage. The introduction of building information modeling (BIM) in the construction industry can provide a valuable means of improving the organization and exchange of information. BIM tools integrate multiple levels of information within a single digital model of a building. Nevertheless, the support given by BIM to FM is far from being fully effective. Technicians can benefit from real-time communication with the data repository whenever the need for gathering contextual information and/or updating any data in the digital model arises. The framework proposed in this study aims to develop a system that supports on-site operations. Information requirements have been determined from the analyses of procedures that are usually implemented in the building life cycle. These studies set the standard for the development of a digital model of a building, which will be shared among various actors in charge of FM and accessed via a cloud platform. Moreover, mixed reality is proposed to support specific information that is relevant to geometric features and procedures to be followed by operators. This article presents three use-cases supported by the proposed framework. In addition, this research article describes the first proof of concept regarding real-time support for FM
Development of a framework to support the information flow for the management of building
No full textInefficient control of information flow in projects is one of the critical aspects that affects the entire lifecycle of buildings. Besides allowing for a simpler and more efficient transfer of information, the dramatic growth of the digitalization process in the AEC industry underlines the need for a common data environment, which manages and shares these data. The increasingly widespread adoption of Building Information Modeling (BIM) is partially leading to a union of multiple levels of information in a single digital model of the building. However, many challenges are still posed in terms of information transfer from the model to operators responsible for keeping building functioning and in good conditions. In fact, technicians could benefit from the immediate availability of data on the current state of buildings and from the level of information detail that can be obtained from digital buildings. The purpose of this work is to create a framework for data management related to the maintenance phase of the building asset. Starting from the study of maintenance processes it was possible to define the information needs that will be managed by a common data environment support associated with BIM models of buildings. Furthermore, thanks to the aid of Mixed Reality (MR), the flow of information is transferred directly to the last user both as regards geometric features and for the standard procedure to be followed. This will allow a maximum optimization of data management procedures due to an automation of processes that will result in a lower incidence of errors in the processes leading eventually to an increase in quality and productivity
Augmented Reality and Deep Learning towards the Management of Secondary Building Assets
No full textThe retrieval of as-is information for existing buildings is a prerequisite for effectively operating facilities, through the creation or updating of Building/Asset Information Models (BIM/AIM), or Digital Twins. At present, many studies focus on the capture of geometry for the modelling of primary components, overlooking the fact that many recurring actions need to be conducted on assets inside buildings. Furthermore, highly accurate survey techniques like laser scanning need long offsite processing for object recognition. Performing such process on site would dramatically impact efficiency and also prevent the need to revisit the site in the case of insufficient/incomplete data. In this paper, an Augmented Reality (AR) system is proposed enabling inventory, information retrieval and information update directly on-site. It would reduce post-processing work and avoid loss of information and unreliability of data. The system has a Head-Mounted Display (HMD) AR interface that lets the technician interact handsfree with the real world and digital information contained in the BIM/AIM. A trained Deep Learning Neural Network operates the automatic recognition of objects in the field of view of the user and their placement into the digital BIM. In this paper, two uses cases are described: one is the inventory of small assets inside buildings to populate a BIM/AIM, and the second is the retrieval of relevant information from the AIM to support maintenance operations. Partial development and feasibility tests of the first use case applied to fire extinguishers, have been carried out to assess the feasibility and value of this system
Reti Bayesiane per i Digital Twin nelle costruzioni
No full textLe Reti Bayesiane costituiscono uno strumento computazionale molto affidabile per l'analisi di grandi moli di dati ai fini della conduzione di inferenze finalizzate alla gestione dell'ambiente costruito.Il presente volume inizia fornendo una trattazione critica del concetto di digital twin per le costruzioni, che, evidenziandone gli aspetti paradigmatici, definisce il quadro metodologico generale a cui saranno ricondotti i successivi approfondimenti. I capitoli seguenti analizzano, attraverso dei casi esemplificativi, il ruolo fondamentale e le possibilità di integrazione delle Reti Bayesiane nel digital twin per le costruzioni. Le Reti Bayesiane così integrate sono un potente strumento di analisi di scenario e di supporto alle decisioni, perfettamente contestualizzato nel data stream e veloce da interrogare, grazie ai modelli analitici di inferenza probabilistica consolidati negli ultimi decenni. La trattazione affronta gli aspetti tecnici con dettaglio tale da garantire la replicabilità di quanto descritto dagli autori anche in settori affini a quello della gestione dell'ambiente costruito
Technology Framework for Real-Time Assessment of Spatial Conflicts in Building Retrofitting
No full textIn the field of construction works planning, workspaces must be considered as limited resources, in the same way as labour crews and equipment. Being the work-related spatial information both contextual and affected by construction site's dynamics, a real-time management approach based on lean principles must be adopted. In this paper, a BIM-based serious game engine, framed within a high-level system architecture, is presented to enhance work progress management. The generation of a geometric model to perform look-ahead simulations for predicting spatial conflicts is showcased relatively to a retrofitted residential building
- …
