149 research outputs found
Le piattaforme di gestione dei dati, il BIM che verrà oltre le geometrie 3D
No full textLa creazione di piattaforme digitali oltre gli ambienti di condivisione dei dati (ACDat) dicommessa rappresanta la sfida dei prossimi anni. Esiste ancora una forte criticità in termini di classificaizone di dati ed informazioni che di fatto impedisce un uso e riuso efficace ed efficiente della ocnoscenza nel settore delle costruzioni
Building Information Models are Dirty
No full textBuilding Information Modelling (BIM) processes imply an intensive use of information. Nevertheless, several studies revealed critical issues in the data quality of information models. While some studies presented interesting works in the evaluation of model quality with reference to IFC. The analysis of the data quality issues in native models remains a research gap as well as the understanding of where these issues are generated. This research proposes an analysis of four information models to evaluate and classify data quality issues according to three dimensions, i.e. accuracy, coherence and completeness. Results highlighted user behaviours and/or technological limitations in real-world applications
Methodology for classifying and extracting information with LLM: application on cost estimation case
No full textCost estimation in building industy largely relies on manually extracting and classifying textual descriptions, a process susceptible to human error. Although recent advancements in Large Language Models (LLMs) hold promise, their application in this domain requires further investigation.
This study proposes a methodology to optimize LLM performance validated through the development of a tool that classifies cost descriptions into a three-level hierarchical taxonomy and extracts relevant information organising the data in a database as output. Results demonstrate a F1 score of 0.96 on both tasks contributing to cost estimation automation, reducing manual processing, and enhancing knowledge management within the domain
DEVELOPMENT OF A FRAMEWORK FOR PROCESSING UNSTRUCTURED TEXT DATASET THROUGH NLP IN COST ESTIMATION AEC SECTOR
No full textCost estimation is one of the most critical steps in the building construction process. Currently, it requires humans to manually extract information from documents written in natural language, often resulting in human error.
This paper aims to investigate an automated technique for extracting data from documents with the support of NLP techniques, in order to automatize the task of structuring information.
A framework for automatically classifying information from unstructured text was developed leveraging NER techniques. This research supports the cost estimation activity minimizing the loss of resources coming from human error when interpreting NL documents
Information-Sharing and Technological Trends among Small and Medium-Sized Enterprises
No full textDigitalization is an important factor for small and medium-sized (SMEs) contractors. This study examines different elements impacting the digitalization process as well as innovation and technological trends amongst SMEs. An online questionnaire was designed, and 70 responses were collected. Four variables of organizational, technological, economical, and social were factor analyzed through which two components of ‘resources’ and ‘human force management’ were identified. The relationships between firm size, information-sharing, and software usage were further tested via Pearson Chi-Square Test of Independence. It was concluded that no association existed among those three variables and technology usage was found to be minimal among the firms
Integrated Approach to Construction Risk Management: Cost Implications
No full textManaging risk in construction projects has proven to be a challenge for many project managers and stakeholders involved in projects. The lack of a systematic approach and standardized processes are key factors influencing improper risk management techniques. This research introduces a new model to evaluate and assess risk in terms of cost impact, utilizing a fuzzy Monte Carlo simulation approach for the first time. The method consists of ranking the top risks using a fuzzy logic system utilized in an objective manner by setting criteria for experts to rank the risk based on cost impact and probability to reduce human biases, then evaluating their cost impact through a Monte Carlo simulation both pre- and postmitigation. This work proposes a new strategy to elicit risk for construction projects based on risk cost impact, project type, project location, project contract type, and project delivery method. Based on the findings, implementation of a risk mitigation response plan can decrease the project cost remarkably. This model proved to be beneficial in forecasting risk impact when executed on a commercial construction project in California. This model can be applied as a general tool for risk mitigation processes for the construction industry
CLASSIFICATION OF CONSTRUCTION FIRMS BASED ON BIM ROLES AND BIM LEVELS USING MACHINE LEARNING TECHNIQUES
No full textApplication of Building Information Modelling (BIM) within the AEC industry has been evolving. With new developments and increasing capabilities, BIM is reshaping the design, construction, and operation, and maintenance processes and revolutionizing the entire functions of building life cycles. To maximize BIM benefits and take advantage of its capabilities, it is imperative that project stakeholders define specific roles and responsibilities within projects; to employ professionals with high levels of BIM proficiency, expertise, and knowledge. This study aims to classify the construction firms into different clusters based on their BIM capabilities, implementation, BIM levels, and type of BIM roles they employ for construction projects. It will further predict and classify BIM levels at company level according to its usage. The methodology was based on a survey design which consisted of application an online questionnaire that was distributed to AEC professionals in the industry. 61 suitable responses were analysed, using different supervised and unsupervised machine learning algorithms, including Cluster Analysis, K-Nearest Neighbours algorithm (k-NN), Random Forest, and Gradient Boosting. The findings showed most firms were not applying BIM on their projects and the majority of those that did were not utilizing it in its full potential. Firms were further classified in terms of BIM levels and types of BIM applications they utilize on construction projects. The results showed that Random Forest had the highest performance and the most accuracy, comparing with KNN and Gradient Boosting, even though the performance and predictions results produced by all models were in proximity of one another
BIM: metodi e strumenti. Progettare , costruire e gestire nell'era digitale
No full textIl BIM (Building Information Modelling) rappresenta per la filiera delle
costruzioni la via maestra all’ingresso nell’era digitale, fenomeno già
intrapreso da tutti gli altri settori dei servizi e dell’industria e oggi
di grande attualità con l’avvento dell’Industria 4.0.
Questo libro vuol trasferire a tutti gli attori del settore il bagaglio
di esperienza pratica e ricerca accumulato dagli autori in anni
di studio e lavoro sul tema della digitalizzazione, al fine di una
cosciente acquisizione del metodo BIM e di una corretta introduzione
dei suoi strumenti.
Cos’è la programmazione a oggetti, come impostare correttamente
un modello, come gestire i dati attraverso un Common Data
Environment (CDE), quali funzioni svolgono il BIM Manager e il BIM
Coordinator, così come la corretta interpretazione di acronimi quali
4D, 5D, 6D e 7D, rappresentano alcuni degli argomenti trattati in via
teorica, ma soprattutto applicativa.
Il testo raffigura l’introduzione pratica dello standard italiano sulla
digitalizzazione del settore costruzioni (UNI 11337:2017) che tanto
interesse sta suscitando sui tavoli normativi comunitari CEN
e internazionali ISO: usi e obiettivi del modello, LOD per il restauro
e per le attrezzature di cantiere, livello di sviluppo delle geometrie
e delle informazioni (LOG e LOI), denominazione degli oggetti
attraverso la semantica degli attributi, piattaforma collaborativa
digitale per la gestione dei CDE, modello documentale e
multimediale, modello di progetto e di rilievo e molto altro
BIM implementation for micro, small and medium-sized enterprises
No full textLiterature discussion on BIM benefits and barriers for micro, small, and medium-sized enterprises is lacking. Testing the independence of statistic for nominal variables as such requires application of statistical techniques including Fisher’s Exact Test, and Factor Analysis. The nominal variables were tested across 14 variables as operational definitions for benefits, and six variables were selected as operational definitions for concept of barriers. After factor analysis, four components related to benefits and two for barriers showed the highest significant association. The four benefits factors influencing digitalization are operation, marketability, productivity, and information-exchange. The two barriers are lack of professionalism and knowhow
- …
