Modular construction methods, where products are manufactured beforehand in a factory and then transported to the site for installation, are becoming increasingly popular for construction projects in many countries as this method facilitates the use of the advanced technologies that support sustainability in building projects. This approach requires dual factory–site process management to be carefully coordinated and the factory module manufacturing process must therefore be managed in a detailed and quantitative manner. However, currently, the limited algorithms available to support this process are based on mathematical methodologies that do not consider the complex mix of equipment, factories, personnel, and materials involved. This paper presents three new building information modeling-based 4D simulation frameworks to manage the three elements—process, quantity, and quality—that determine the productivity of factory module manufacturing. These frameworks leverage the advantages of 4D simulation and provide more precise information than existing conventional documents. By utilizing a 4D model that facilitates the visualization of a wide range of data variables, manufacturers can plan the module manufacturing process in detail and fully understand the material, equipment, and workflow needed to accomplish the manufacturing tasks. Managers can also access information about material quantities for each process and use this information for earned value management, warehousing/storage, fabrication, and assembly planning. By having a 4D view that connects 2D drawing models, manufacturing errors and rework can be minimized and problems such as construction delays, quality lapses, and cost overruns vastly reduced.

Monitoring heavy equipment in real time is crucial for ensuring safety and operational efficiency at construction sites, yet achieving both high detection accuracy and fast inference remains challenging under diverse environmental conditions. Although previous studies have attempted to improve accuracy and speed, their findings often lack generalizability, partly due to inconsistent datasets and the need for more advanced techniques. In response, this study proposes an enhanced object detection method that integrates transformer-based backbone networks into the You Only Look Once (YOLO-version 10) framework. Evaluations conducted on a large-scale dataset of construction-site images demonstrate notable improvements in detecting the heavy equipment of varying sizes. Comparisons with other detectors confirm that the proposed model not only achieves higher accuracy but also maintains competitive processing speed, making it suitable for real-time deployment. Additionally, the dataset is made available for broader experimentation and development. These findings underscore the method’s potential to strengthen on-site safety by providing more reliable and efficient heavy equipment detection in complex work environments, while also acknowledging areas for further refinement.

This study investigated defect risks in residential buildings using the Loss Distribution Approach (LDA), a method of identifying and quantifying operational risks in economic terms. Analysis was performed on 7554 defects in 48 residential buildings where defect disputes occurred between 2008 and 2017. Defects were classified into eight types: affected functionality, broken items, corrosion, detachment, incorrect installation, missing task, surface appearance, and water problems. Work types were classified into seven groups: reinforced concrete (RC), masonry, finish, mechanical, electrical, and plumbing (MEP), door and windows, furniture, and miscellaneous. Using a risk matrix from these categories, the frequency distribution and severity distribution for each matrix cell was used to calculate loss distributions; these were combined to find the total loss distribution. The defect risks centered on RC and MEP. For RC, broken items and water leaks due to cracks or damage represented the most severe defects. For MEP, severe defects occurred owing to malfunctions in products and installation problems. Loss distributions can be used to create scenarios and corresponding response plans; thus, when a defect dispute occurs, the cost can be assessed. Furthermore, residential buildings’ loss distributions for each cell can be used to evaluate the types of work where defects occur and to verify relevant subcontractor’s abilities.

Non-Protective Personal Equipment (PPE) detection is crucial on construction sites. Although deep learning models are adept at identifying such information from on-site cameras, their success relies on large, diverse, and high-quality datasets. Image augmentation offers an alternative for artificially broadening dataset diversity. However, its impact on non-PPE detection in construction environments has not been adequately examined. This study introduces a methodology applying eight distinct augmentation techniques—brightness, contrast, perspective, rotation, scale, shearing, translation, and a combined strategy incorporating all methods. Model performance was assessed by comparing accuracy across different classes and architectures, both with and without augmentation. While most of these augmentations improved accuracy, their effectiveness was found to be task-dependent. Moreover, the most beneficial augmentation varied by non-PPE class and architecture, suggesting that augmentation strategies should be tailored to the unique features of each class and model. Although the primary focus here is on non-PPE, the evaluated techniques could also extend to related tasks on construction sites, such as detecting heavy equipment or identifying hazardous worker behavior.

There are numerous applications for building dimension data, including building performance simulation and urban heat island investigations. In this context, object detection and instance segmentation methods—based on deep learning—are often used with Street View Images (SVIs) to estimate building dimensions. However, these methods typically depend on large and diverse datasets. Image augmentation can artificially boost dataset diversity, yet its role in building dimension estimation from SVIs remains under-studied. This research presents a methodology that applies eight distinct augmentation techniques—brightness, contrast, perspective, rotation, scale, shearing, translation augmentation, and a combined “sum of all” approach—to train models in two tasks: object detection with Faster Region-Based Convolutional Neural Networks (Faster R-CNNs) and instance segmentation with You Only Look Once (YOLO)v10. Comparing the performance with and without augmentation revealed that contrast augmentation consistently provided the greatest improvement in both bounding-box detection and instance segmentation. Using all augmentations at once rarely outperformed the single most effective method, and sometimes degraded the accuracy; shearing augmentation ranked as the second-best approach. Notably, the validation and test findings were closely aligned. These results, alongside the potential applications and the method’s current limitations, underscore the importance of carefully selected augmentations for reliable building dimension estimation.