Search Results (258)

Machine learning and artificial intelligence have transformed fault detection and maintenance strategies for industrial machinery. This study applies well-established data-driven techniques to a rarely explored industrial application—the condition monitoring of high-precision paper cutting machines—enhancing condition-based maintenance to improve operational efficiency, safety, and cost-effectiveness. A key element of the proposed approach is the integration of an infrared pyrometer into vibration monitoring, utilizing accelerometer data to evaluate the state of health of machinery. Unlike traditional fault detection studies that focus on extreme degradation states, this work successfully identifies subtle deviations from optimal, which even expert technicians struggle to detect. Building on a feasibility study conducted with Tecnau SRL, a comprehensive diagnostic system suitable for industrial deployment is developed. Endurance tests pave the way for continuous monitoring under various operating conditions, enabling real-time industrial diagnostic applications. Multi-scale signal analysis highlights the significance of transient and steady-state phase detection, improving the effectiveness of real-time monitoring strategies. Despite the physical similarity of the classified states, simple time-series statistics combined with machine learning algorithms demonstrate high sensitivity to early-stage deviations, confirming the reliability of the approach. Additionally, a systematic analysis to downgrade acquisition system specifications identifies cost-effective sensor configurations, ensuring the feasibility of industrial implementation. Full article

LLMs are trained using many thousands of GPUs in well-known conventional models. It is necessary to address numerous issues in the training process, such as manual data collection organization, data parallel, model parallel, evaluation, testing, deployment, transferring large data streams, detecting errors, ongoing maintenance, and project management. A team of dozens of engineers is required to handle system problems in the training process. Therefore, it is time-consuming and expensive to build an efficient and fault-tolerant system based on Kubernetes. This paper develops SimpleScale for building LLMs based on FSDP and Slurm, which is a simple and efficient training system that includes the training agent, the efficient parallel strategy, the optimal step of checkpoint, and so on. Using the proposed system enables us to significantly accelerate the process of building the LLM without incurring substantial time spent on various manual issues. The proposed 1024-GPU cluster was tested on TinyLlama, which has 1.1 billion parameters and 300 billion tokens. For example, utilizing a 16-H100 GPU cluster accelerated the traditional TinyLlama training time costs from 89.05 days to 39.05 days. In the future, the project team plans to integrate Flash-Attention3, aiming for an MFU of more than 60% while maintaining the acceleration achieved in the present work. Full article

As climate change intensifies the frequency and severity of extreme weather events, the urgency for resilient and sustainable urban development becomes increasingly critical. This study investigates the role of digital twins in advancing climate-responsive urban strategies, with a focus on their integration into zero-energy buildings (ZEBs) and smart city frameworks. A systematic literature review was conducted following PRISMA guidelines, covering 1000 articles initially retrieved from Scopus and Web of Science between 2014 and 2024. After applying inclusion and exclusion criteria, 70 full-text articles were analyzed. Bibliometric analysis using VOSviewer revealed five key application areas of digital twins: energy efficiency optimization, renewable energy integration, design and retrofitting, real-time monitoring and control, and predictive maintenance. The findings suggest that digital twins can contribute to up to 30–40% improvement in building energy efficiency through enhanced performance monitoring and predictive modeling. This review synthesizes trends, identifies research gaps, and contextualizes the findings within the Middle Eastern urban landscape, where climate action and smart infrastructure development are strategic priorities. While offering strategic guidance for urban planners and policymakers, the study also acknowledges limitations, including the regional focus, lack of primary field data, and potential publication bias. Overall, this work contributes to advancing digital twin applications in climate-resilient, zero-energy urban development. Full article

Earthen flood protection structures are planned and constructed with an expected service life of several decades while being exposed to environmental impacts that may lead to structural or hydraulic failure. Current maintenance procedures involve only repairing external damage, leaving internal processes contributing to structural damage often undetected. Through structural health monitoring (SHM), structural deficits can be detected before visible damage occurs. To improve maintenance workflows and support predictive maintenance of dikes, this paper reports on the integration of digital twin concepts with SHM strategies, referred to as “digital-twin-based SHM”. A digital twin concept, including a standard-compliant building information model, is proposed and implemented in terms of a digital twin environment. For integrating monitoring and sensor data into the digital twin environment, a customized webform is designed. A communication protocol links preprocessed sensor data stored on a server with the digital twin environment, enabling model-based visualization and contextualization of the sensor data. As will be shown in this paper, a digital twin environment is set up and managed in the context of SHM in compliance with technical standards and using well-established software tools. In conclusion, digital-twin-based SHM, as proposed in this paper, has proven to advance predictive maintenance of dikes, contributing to the resilience of critical infrastructure against environmental impacts. Full article

This study aims to develop an information strategy plan (ISP) for the integrated management of airport facility information in South Korea by applying smart technologies such as building information modeling (BIM), digital twins, and openBIM. As the demand for intelligent lifecycle management and efficient facility operations continues to grow, airport infrastructure requires standardized and interoperable systems to manage complex assets and stakeholder collaboration. This research addresses three core challenges facing Korean airports: the lack of sustainable maintenance environments, the absence of data standards and systems, and the insufficiency of user-oriented platforms. Through system analysis, benchmarking, and SWOT assessment, the study proposes a stepwise implementation roadmap consisting of development, integration, and advancement phases and designs a “To-Be” model that incorporates 37 component technologies and a standardized information framework. The proposed ISP supports data-driven airport operations, enhances collaboration, and accelerates digital transformation, ultimately contributing to the development of smart and globally competitive airports. Full article

Green and cool roofs have significant potential to reduce energy consumption in buildings, but high initial costs and the need for local adaptation limit their adoption. This study aims to compare the life cycle energy assessment (LCEA) and life cycle cost analysis (LCCA) of green, cool, and standard (fibre cement) roofs in three Brazilian cities with different climatic and economic contexts. Computer simulations were carried out on a multifamily residential building model to assess the energy performance of the roofs. The simulation results and literature data were used to estimate the roofs’ energy consumption and cost over the life cycle. Over a 40-year life cycle, green and cool roofs reduced energy consumption by 13% to 22% compared to standard roofs. Cool roofs showed the lowest life cycle costs, while green roofs faced cost-effectiveness challenges due to high initial and maintenance costs. However, in areas with high energy demands and electricity tariffs, the life cycle cost of green roofs may be decreased. The study highlights the crucial role of material selection in embodied energy and emphasises the dominant impact of the operational phase on energy consumption and life cycle costs. These findings underscore the need for customised design strategies and localised assessments to support decision-making. Full article

The European Union’s 2050 targets for decarbonization and electrification are promoting the widespread integration of heat pumps for space heating, cooling, and domestic hot water in buildings. However, their energy and environmental performance can be significantly compromised by soft faults, such as refrigerant leakage or heat exchanger fouling, which may reduce system efficiency by up to 25%, even with maintenance intervals every two years. As a result, the implementation of self-fault detection, diagnosis, and evaluation (FDDE) tools based on operational data has become increasingly important. The complexity and added value of these tools grow as they progress from simple fault detection to quantitative fault evaluation, enabling more accurate and timely maintenance strategies. Direct fault measurements are often unfeasible due to spatial, economic, or intrusiveness constraints, thus requiring indirect methods based on low-cost and accessible measurements. In such cases, overlapping fault symptoms may create diagnostic ambiguities. Moreover, the accuracy of FDDE approaches depends on the type and number of sensors deployed, which must be balanced against cost considerations. This paper provides a comprehensive review of current FDDE methodologies for heat pumps, drawing insights from the academic literature, patent databases, and commercial products. Finally, the role of artificial intelligence in enhancing fault evaluation capabilities is discussed, along with emerging challenges and future research directions. Full article

The present research aims to assess, from both ecological and economic perspectives, a strategic solution applied to the building sector that can contribute to mitigating the planetary tragedy of the overconsumption of global fossil energy (coal, oil, and gas) and, thus, climate change, along with its dramatic negative impacts on the planet, humanity, and the world’s economy. Buildings are the largest consumers of fossil fuel energy, significantly contributing to Greenhouse Gas (GHG) emissions and, consequently, to climate change. Reducing their environmental impact is therefore crucial for achieving global sustainability goals. Existing buildings, mostly the historical ones, represent a significant part of the global building stocks, which, for the most part, consist of buildings built more than 70 years ago, which are aged, in a state of deterioration, and in need of intervention. Recovering, renovating, and redeveloping existing and historical buildings could be a formidable instrument for improving the energy quality of the international and national building stocks. When selecting the type of possible interventions to be applied, there are two choices: simple and unsustainable ordinary maintenance versus ecological retrofitting, i.e., a quality increase in the indoor environment and building energy savings using local bio-natural materials. The success of the “Ecological Retrofitting” Strategy strongly relies on its economic and financial sustainability; therefore, the goal of this research is to underline and demonstrate the economic and ecological benefits of the ecological transition at the building level through an integrated valuation applied in a case study, located in Southern Italy. First, in order to demonstrate the ecological benefits of the proposed strategy, the latter was tested through a new energy assessment tool in an updated BIM platform; subsequently, an economic valuation was conducted, clearly demonstrating the cost-effectiveness of the building’s ecological transition. The real-world experiment through the proposed case study achieved important results and reached the goals of the “Ecological Retrofitting” Strategy in existing (but not preserved) liberty-style constructions. First of all, a significant improvement in the buildings’ thermal performance was achieved after some targeted interventions, resulting in energy savings; most importantly, the economic feasibility of the proposed strategy was demonstrated. Full article

The awareness of global warming has boosted research on methods to reduce energy consumption and greenhouse gas (GHG) emissions. Livestock buildings, although essential for food production, represent a sustainability challenge due to their high maintenance energy costs, GHG emissions, and impact on the environment and rural landscapes. Since the environment, cultural heritage, and community identity deserve protection, research trends and current knowledge on livestock buildings, building sustainability, energy efficiency strategies, and landscape management were investigated using the Web of Science and Scopus search tools (2005–2025). Research on these topics was found to be uneven, with limited focus on livestock buildings compared to food production and animal welfare, and significant interest in eco-sustainable building materials. A total of 96 articles were selected after evaluating over 5400 records. The analysis revealed a lack of universally accepted definitions for building design strategies and their rare application to livestock facilities, where passive solutions and insulation prevailed. The application of renewable energy was rare and limited to rural buildings, as was the application of sustainable building materials to livestock, agriculture, and vernacular buildings. Conversely, increased attention was paid to the definition and classification of vernacular architecture features aimed at enhancing existing buildings and mitigating or facilitating the landscape integration of those that diverge most from them. Although not exhaustive, this review identified some knowledge gaps. More efforts are needed to reduce environmental impacts and meet the milestones set by international agreements. Research on building materials could benefit from collaboration with experts in cultural heritage conservation because of their command of traditional materials, durability-enhancing methods, and biodeterioration. Full article

The design and construction of adaptive façades have garnered increasing attention as a means to enhance the energy performance and sustainability of high-rise residential buildings. Adaptive façades can dynamically respond to environmental conditions, reducing reliance on energy-intensive systems and improving occupant comfort. Despite their potential, research on adaptive façade systems in the context of high-rise residential buildings, particularly in Australia, remains limited. This study aims to bridge this gap by identifying the key design parameters, challenges, and optimisation methods for adaptive façades. Through a combination of a comprehensive literature review and 15 semi-structured interviews with industry experts, this research provides insights into the design and performance of adaptive façades. The key findings reveal that the successful implementation of adaptive façades depends on a range of factors, including material choices, shading system typologies, and advanced simulation tools for energy performance analysis. A significant outcome of the study is the development of a conceptual framework that incorporates these design elements with environmental factors and building energy simulation, offering a structured approach to optimise adaptive façade performance. The framework assists architects and engineers in creating energy-efficient, sustainable high-rise residential buildings tailored to the Australian context. Additionally, the study highlights critical challenges, such as financial barriers, regulatory gaps, and the need for improved maintenance strategies, which must be addressed to facilitate the broader adoption of adaptive façades in the residential sector. Full article

Estimating Remaining Useful Life (RUL) is crucial in modern Prognostic and Health Management (PHM) systems providing valuable information for planning the maintenance strategy of critical components in complex systems such as aircraft engines. Deep Learning (DL) models have shown great performance in the accurate prediction of RUL, building hierarchical representations by the stacking of multiple explicit neural layers. In the current research paper, we follow a different approach presenting a Deep Equilibrium Model (DEM) that effectively captures the spatial and temporal information of the sequential sensor. The DEM, which incorporates convolutional layers and a novel dual-input interconnection mechanism to capture sensor information effectively, estimates the degradation representation implicitly as the equilibrium solution of an equation, rather than explicitly computing it through multiple layer passes. The convergence representation of the DEM is estimated by a fixed-point equation solver while the computation of the gradients in the backward pass is made using the Implicit Function Theorem (IFT). The Monte Carlo Dropout (MCD) technique under calibration is the final key component of the framework that enhances regularization and performance providing a confidence interval for each prediction, contributing to a more robust and reliable outcome. Simulation experiments on the widely used NASA Turbofan Jet Engine Data Set show consistent improvements, with the proposed framework offering a competitive alternative for RUL prediction under diverse conditions. Full article

In recent years, Facility Management has undergone significant technological and methodological advancements, primarily driven by Building Information Modelling (BIM), Computer-Aided Facility Management (CAFM), and Computerized Maintenance Management Systems (CMMS). These innovations have improved process efficiency and risk management. However, challenges remain in asset management, maintenance, traceability, and transparency. This study investigates the potential of blockchain technology and non-fungible tokens (NFTs) to address these challenges. By referencing international (ISO, BOMA) and European (EN) standards, the research develops an asset management process model incorporating blockchain and NFTs. The methodology includes evaluating the technical and practical aspects of this model and strategies for metadata utilization. The model ensures an immutable record of transactions and maintenance activities, reducing errors and fraud. Smart contracts automate sub-phases like progress validation and milestone-based payments, increasing operational efficiency. The study’s practical implications are significant, offering advanced solutions for transparent, efficient, and secure Facility Management. It lays the groundwork for future research, emphasizing practical implementations and real-world case studies. Additionally, integrating blockchain with emerging technologies like artificial intelligence and machine learning could further enhance Facility Management processes. Full article

Silicone structural glazing (SSG) sealants are crucial sealing materials in modern building curtain walls, whose performance degradation may lead to functional and safety issues, posing significant challenges to building safety maintenance. This study comprehensively investigated the effects of temperature, humidity, stress, and ultraviolet (UV) irradiance on the durability of SSG sealants through multi-gradient matrix aging tests, revealing the influence patterns of these four aging factors on tensile bond strength (TBS). Based on aging test data and degradation patterns, a novel degradation model for TBS aging was established by incorporating all four aging factors as variables, enabling the model to reflect their combined effects on TBS degradation. The unknown parameters in the model were calculated using the Markov chain Monte Carlo (MCMC) algorithm and validated against experimental data. A recursive algorithm was developed to predict TBS degradation under actual service conditions based on the degradation model and environmental records, with verification through outdoor aging tests. This study established a service life prediction methodology that combines the degradation model with environmental data through recursive computation and standard-specified strength limits. The results demonstrate that increasing temperature, humidity, stress, and UV irradiation accelerates TBS changes, with influence intensity ranking as UV irradiation > temperature > humidity > stress. Synergistic effects exist among all four factors, where UV irradiation shows the most significant coupling effect by amplifying other factors’ combined impacts, while UV’s primary influence manifests through such synergies rather than independent action. Among temperature, humidity, and stress combined effects, temperature contributes approximately 50%, temperature–humidity interaction about 35%, with temperature-related terms collectively accounting for 90%. The degradation model calculation results show excellent agreement with experimental data (R² > 0.9, MAE = 0.019 MPa, RMSE = 0.0245 MPa). The characteristic TBS minimum value considering material discreteness and strength assurance rate serves as a reliable criterion for service life evaluation. The proposed prediction method provides essential theoretical and methodological foundations for ensuring long-term safety and maintenance strategies for glass curtain walls. Full article

In order to explore the causative factors of falling accidents at high-rise building construction sites, this study collected 207 reports of these accidents from 2014 to 2024. We used the Human Factor Analysis and Classification System (HFACS) during sample collection, from the four perspectives of organizational impact, unsafe supervision, prerequisites for unsafe behavior, and unsafe behavior. In total, 21 important causal factors were identified, and the samples were classified according to these factors. Descriptive statistics, chi-square testing, and limit matrix analysis were mainly used. SPSS 27.01 was used to analyze the samples, and Super Decisions software was used to normalize the limit supermatrix and calculate the weight. Subsequently, innovative and comprehensive application of chi-square testing and correlation coefficients was applied to determine the correlation of factors, and ANP was used to determine the weight of the factors. According to the weight, we determined the key factors, levels, and paths, and the relationship between the causes of falling accidents in building construction was systematically studied. Finally, based on the key causal path and key factors, a corresponding pre-control strategy was proposed. The results show that the key factors are a lack of awareness of personnel safety, safety education and training, and on-site safety management and an absence of safety inspections and routine maintenance. The key causes are that labor companies are not qualified, there is a lack of on-site safety oversight, and personnel do not have a permit to work at significant heights and do not wear safety protection equipment properly. This study explores the shortcomings of safety management in the construction industry. In order to reduce the accident rate, it is very important to improve the level of decision-making regarding safety management by the government and construction industry. This study has the following limitations: firstly, the information obtained from the investigation report of high-rise building construction accidents is not adequate to fully reflect the situation of workers on-site, which inevitably leads to some deviations. Secondly, due to the high mobility of construction workers, it is very difficult to investigate psychological or physiological states that may have a potential impact on unsafe behavior. Full article

Digital Twin (DT) technology is emerging as a powerful tool for optimizing energy efficiency and industrial sustainability. By creating virtual replicas of physical systems, DTs enable real-time monitoring, predictive maintenance, and resource optimization, offering new opportunities to meet growing energy demands. Despite its potential, the comprehension of DT technology’s applications, benefits, and challenges remains limited. This systematic review explores the role of Digital Twins in energy efficiency across various industries. A structured literature search was conducted in IEEE Xplore, Elsevier, Springer, MDPI, and Google Scholar, following PRISMA 2020 guidelines. After applying the predefined inclusion criteria, 50 studies were selected for in-depth analysis. The findings highlight that DT implementation can lead to energy savings of up to 30%, reduce operational costs, and improve predictive maintenance strategies. Their impact is particularly notable in smart buildings, manufacturing, and industrial processes, where real-time data analytics contribute to better energy management. However, significant barriers remain, including high implementation costs, data security risks, and the complexity of integrating DTs with existing infrastructures. By synthesizing the current research, this review underscores the transformative potential of Digital Twins while identifying key challenges that need to be addressed for their wider adoption. Future efforts should focus on developing standardized methodologies, reducing implementation costs, and enhancing cybersecurity measures to maximize their benefits in energy efficiency and sustainability. Full article