Data-driven Models for Predicting Compressive Strength of 3D-printed Fiber-Reinforced Concrete using Interpretable Machine Learning Algorithms

Case Studies in Construction Materials, Journal Year: 2024, Volume and Issue: 21, P. e03935 - e03935

Published: Nov. 1, 2024

Language: Английский

---

Machine learning techniques for predicting the peak response of reinforced concrete beam subjected to impact loading

Results in Engineering, Journal Year: 2024, Volume and Issue: unknown, P. 103135 - 103135

Published: Oct. 1, 2024

Language: Английский

---

Enhancing Engineering and Architectural Design Through Virtual Reality and Machine Learning Integration

Buildings, Journal Year: 2025, Volume and Issue: 15(3), P. 328 - 328

Published: Jan. 22, 2025

This study introduces a framework that leverages the synergistic potential of Virtual Reality (VR) and Machine Learning (ML) to enhance graphical modeling in engineering architectural design. Traditional clash detection methods Building Information Modeling (BIM) systems are predominantly reactive, identifying discrepancies only after their occurrence, leading costly time-consuming design revisions. By integrating ML algorithms with VR-driven BIM, our approach proactively identifies resolves clashes, as demonstrated across 28 diverse projects. The results indicate reduction clashes by 16% iterative revisions 15%, culminating 12% decrease overall project timelines. research underscores transformative impact combining VR on additive manufacturing (AM) workflows, significantly improving efficiency reducing nature traditional methods. findings highlight framework’s scalability adaptability, promising substantial advancements architecture practices.

Language: Английский

---

Multi-objective maintenance strategy for complex systems considering the maintenance uncertain impact by adaptive multi-strategy particle swarm optimization

Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: unknown, P. 110671 - 110671

Published: Nov. 1, 2024

Language: Английский

---

Unpacking predictive relationships in graphene oxide-reinforced cementitious nanocomposites: An explainable ensemble learning approach for augmented data

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 144, P. 110123 - 110123

Published: Jan. 25, 2025

Language: Английский

---

Data-driven optimization design method and tool platform for green residential area layout

Journal of Asian Architecture and Building Engineering, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 17

Published: Jan. 28, 2025

Language: Английский

---

Synergizing GIS and genetic algorithms to enhance road management and fund allocation with a comprehensive case study approach

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 7, 2025

This study identifies a critical knowledge gap, revealing how the deterioration of roads, compounded by extensive usage and additional factors, poses significant risks to road networks' functionality. Without robust fund allocation prioritization strategy, extent this risk may be overlooked, adversely affecting performance essential infrastructure elements. Our research introduces an integrated decision-making model for existing infrastructures address gap. innovative approach combines Geographic Information System (GIS)-based management with enhanced optimization engine via genetic algorithm. The primary aim is precisely determine Maintenance Repair (M&R) interventions tailored condition states, thereby improving Pavement Condition Index (PCI) segments. structured around three key objectives: (1) develop detailed GIS-based database incorporating inspection data attributes proactive M&R decision-making; (2) efficiently allocate funds maintain service delivery on deteriorated roads; (3) pinpoint optimal type timing boost Anticipated results will provide asset managers comprehensive decision support system executing effective practices.

Language: Английский

---

Early warning study of field station process safety based on VMD-CNN-LSTM-self-attention for natural gas load prediction

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 21, 2025

As a high-risk production unit, natural gas supply enterprises are increasingly recognizing the need to enhance safety management. Traditional process warning methods, which rely on fixed alarm values, often fail adequately account for dynamic changes in process. To address this issue, study utilizes deep learning techniques accuracy and reliability of load forecasting. By considering benefits feasibility integrating multiple models, VMD-CNN-LSTM-Self-Attention interval prediction method was innovatively proposed developed. Empirical research conducted using data from field station outgoing loads. The primary model constructed is loads, implements graded mechanism based 85%, 90%, 95% confidence intervals real-time observations. This approach represents novel strategy enhancing enterprise Experimental results demonstrate that outperforms traditional reducing MAE, MAPE, MESE, REMS by 1.13096 m3/h, 1.3504%, 7.6363 1.6743 respectively, while improving R2 0.04698. These findings expected offer valuable insights safe management industry provide new perspectives industry's digital intelligent transformation.

Language: Английский

---

Developing a process model for inspection management of building facilities using financial analysis

Journal of Facilities Management, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 27, 2025

Purpose The purpose of this study is to develop a process model for inspection management building facilities based on financial analysis using assessment index (FAI). Design/methodology/approach A piping system surveyed implement optimal time and cost limited costs. Inspection technical sheets were sent 30 installation consultant companies in Iran. Financial hotel managers. There are three main stages the development process: Stage I: gathering data, II: developing draft model, III: testing IV: verification model. research applies decision-making techniques resolve various issues data. Findings By analyzing historical data author determined that most cost-effective approach inspect repair pipes when FAI (condition [CI]) reaches 70. At point, saving investment ratio (SIR) 1.69, indicating substantial economic benefits. For with CI below 55, replacement recommended due lower benefits from repair. When 40, considered be at end their useful life, course action. was rigorously tested ensure its accuracy predicting future scenarios. comparing predictions established solutions, found strong correlation between highest SIR 70 both predictive analyses. This consistency suggests can effectively predict timing wastewater system. Originality/value Any existing resource allocation buildings activities. issue very important: how allocate costs available achieve best return spending. method helps managers engineers make better decisions reduce increase facilities’ service life.

Language: Английский

---

Improving lung cancer pathological hyperspectral diagnosis through cell-level annotation refinement

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 8, 2025

Lung cancer remains a major global health challenge, and accurate pathological examination is crucial for early detection. This study aims to enhance hyperspectral image analysis by refining annotations at the cell level creating high-quality dataset of lung tumors. We address challenge coarse manual in datasets, which limit effectiveness deep learning models requiring precise labels training. propose semi-automated annotation refinement method that leverages data diagnosis. Specifically, we employ K-means unsupervised clustering combined with human-guided selection refine into cell-level masks based on spectral features. Our validated using squamous carcinoma containing 65 samples. Experimental results demonstrate our approach improves pixel-level segmentation accuracy from 77.33% 92.52% lower prediction noise. The time required accurately label each slide significantly reduced. While labeling methods an entire can take over 30 mins, requires only about 5 mins. To visualization pathologists, apply conservative post-processing strategy instance segmentation. These highlight addressing challenges improving analysis.

Language: Английский

---