Yu-Cheng Zhou

The collapse of engineering structures can cause significant casualties and have negative social effects. Collapse accident investigation can elucidate the potential causes and mechanisms of the collapse accident, thus remediating future structural collapse and enhancing the resilience. However, there are some obstacles to investigating complicated collapse accidents using conventional methods. For example, the out‐syncs between on‐site investigation and simulation analysis are intractable and can make discovering the cause of collapse accidents difficult. Hence, a digital twin‐based investigation method for collapse accidents was proposed. First, basic virtual digital building models are established using real‐world information. Then, after mapping the data from the real world into the virtual space, the corresponding highly realistic multistage models before and after the building collapse accident are constructed and synchronized. Using the digital twin method, investigators with multidisciplinary knowledge can efficiently integrate, update, and check the models. Finally, the potential collapse mechanism was revealed with the assistance of the corresponding models. To demonstrate the effectiveness of the proposed digital twin‐based investigation method, a real collapse accident investigation is utilized as an example. These results validated our method.

Accurate fire load (combustible objects) information is crucial for safety design and resilience assessment of buildings. Traditional fire load acquisition methods, such as fire load survey, which are time-consuming, tedious, and error-prone, failed to adapt to dynamic changed indoor scenes. As a starting point of automatic fire load estimation, fast recognition and detection of indoor fire load are important. Thus, this research proposes a computer vision-based method to automatically detect indoor fire loads using deep learning-based instance segmentation. First, indoor elements are classified into different categories according to their material composition. Next, an image dataset of indoor scenes with instance annotations is developed. Finally, a deep learning model, based on Mask R-CNN, is developed and trained using transfer learning to detect fire loads in images. Experimental results show that our model achieves promising accuracy, as measured by an average precision (AP) of 40.5% and AP ₅₀ of 59.2%, for instance segmentation on the dataset. A comparison with manual detection demonstrates the method’s high efficiency as it can detect fire load 1200 times faster than humans. This research contributes to the body of knowledge 1) a novel method of high accuracy and efficiency for automated fire load recognition in indoor environments based on instance segmentation; 2) training techniques for a deep learning model in a relatively small dataset of indoor images which includes complex scenes and a variety of instances; and 3) an image dataset with annotations of indoor fire loads. Although instance segmentation has been applied for several years, this is a pioneering research on using it for automated indoor fire load recognition, which paves the foundation for automatic fire load estimation and resilience assessment for the built environment.

This research reviews recent advances in the domain of Automated Rule Checking (ARC) and argues that current systems are predominantly designed to validate models in post-design stages, useful for applications such as e-permitting. However, such a design-check-separated paradigm imposes a burden on designers as they need to iteratively fix the fail-to-pass issues. Accordingly, the study reviews the best-practices of IFC-based ARC systems and proposes a framework for ARC system development, aiming to achieve proactive bottom-up solutions building upon the requirements and resources of end-users. To present and evaluate its capabilities, the framework is implemented in a real-life case study. The case study presents all the necessary steps that should be taken for the development of an ARC solution from rule selection and analysis, to implementation and feedback. It is explained how a rule checking problem can be broken down into separate modules implemented in an iterative approach. Results show that the proposed framework is feasible for successful implementation of ARC systems and highlight that a stable data standard and modeling guideline is needed to achieve proactive ARC solutions. The study also discusses that there are some critical limitations in using IFC which need to be addressed in future studies.

With the development of science and technology, cloud computing, big data and artificial intelligence and other new technologies have been applied in all aspects of life. The traditional manual tracking and processing production process has many defects. The application of computer technology to the production line to realize automatic production has the characteristics of high efficiency and integration. This paper studies the PLC control system of pneumatic robot automatic assembly line based on cloud computing platform system. In the research, we use PCL system to scan the data of automatic assembly of pneumatic manipulator processed by cloud computing platform, and write the program into the memory of PCL. At the same time, we connect the field input signal and the controlled actuator to the input end of the input module and the output end of the output module. The user can realize the automatic assembly by running the program. Compared with the number of Pneumatic Manipulators produced by manual production line, the system in this paper has high efficiency and superior performance. Thus, the PLC control system of pneumatic manipulator automatic assembly line based on cloud computing platform can improve the production efficiency.