2020-8-7

The sixth "BIM Lecture" hosted by Shanxi Road&Bridge Construction Group Co. Ltd., was successfully held in Taiyuan, the capital city of Shanxi Province. The "BIM Lecture" series are supported by The BIM specialty committee of China Graphics Society and Tsinghua-Glodon BIM Joint Research Center. My PhD supervisor, Prof. Jianping Zhang and me were both invited to give lectures. Yongchun Yao, the vice chief engineer of Shanxi Road&Bridge Construction Group Co. Ltd. chaired the activity. Over 2800 people have attended this online talk show.

Prof. Zhang in her talk illustrated the concept of smart-BIM and then showed the newly research achievement and application of smart-BIM from the aspects of BIM integrated application, BIM platform support and fusion of smart technologies. Then she presented the trend and coping strategy for the BIM development focusing on the "new infrastructures". In my lecture, through some projects demostration, I detailedly discussed the challenges of ground application of BIM and how does the computer understand and manage BIM data, as well as how do the data create domain knowledge. The main contents mainly include the definition and description of BIM, the management and application of BIM model, and the data mining and knowledge discover from BIM models.

2020-7-1

"Extraction Software for Dynamic Standardized Big Data of Buildings and Attached MEP Systems" has obtained the national computer software registration certificate (Registration No. 2020SR0267715; Certificate No. 5146411). The software was independently developed by the research group, which realized the extraction of standardized dynamic data from heterogeneous energy monitoring systems. Addressing the situation where energy monitoring systems from different manufacturers employ different data formats with no compatibility, causing massive waste of data, and where the original energy data principles were no longer sufficient for the ever-growing energy data analysis demands, the software proposed a energy consumption data model orienting dynamic monitoring, and realized the integration of data from heterogenous sources through implementing the interfaces and data structures in the data model. In the implementation, the software compiled and integrated heterogenous data into standardized big data through establishing relay servers between energy monitoring systems and cloud-end databases. The software hitherto has collected data from over 300 large public buildings nationwide, covering a total building area exceeding 10 million m2, providing large amounts of valuable data for energy consumption analysis and prediction applications.

2020-6-28

A new research article entitled "A Lightweight BIM-GIS Integration Method for Rural Building Design and Construction" has been published in the international academic conference "Creative Construction e-Conference 2020". The conference was held online due to the pandemic and the presentation has been uploaded in the "Resources" section. Welcome to download and any comments or questions are welcome.  

Focusing on the design and construction requirements of rural buildings in China, a geospatial visualization platform based on Cesium is proposed to integrate BIM and GIS. In this study, the integration and transformation of BIM and GIS data is realized by means of geometric semantic data decoupling, information alignment and format conversion. Then, in view of the backwardness of information application in rural areas, this paper further proposes a multi-scale BIM/GIS information lightweight method. According to the display requirements of different levels of rural residential buildings, the method divides the building information into three levels: the interior of a single building, the external of a single building, and the building group, and proposes corresponding lightweight algorithm for different levels. This method has been applied to real BIM/GIS model data, and its effectiveness has been verified. The first author of this paper is Shuo Leng, a PhD student under my supervision.

2020-6-8

A new research article entitled "Bibliometric review of visual computing in the construction industry" has been published in Visual Computing for Industry, Biomedicine, and Art. 

In the construction area, visuals such as drawings, photos, videos, and 3D models, play a significant role in the design, build and maintenance of a facility, bringing efficiency to generate, transfer, and store information. Advanced visual computing techniques facilitate the understanding of design contents, work plans, and other types of information shared in the construction industry. Automatic visual data collection and analysis provide many possibilities to the construction industry and a large number of works have investigated how visual computing can improve construction management processes and other problems in the construction area. This study uses bibliometric approaches to review the works published to date, and analyses the development of knowledge, significant research results, and trends.

2020-5-19

A new research article entitled “A Hybrid Data Mining Method for Tunnel Engineering Based on Real-Time Monitoring Data from Tunnel Boring Machines” has been online published in IEEE Access.

This study achieved automatic analysis of TBM real-time monitoring data based on a hybrid data mining (DM) model to ensure safety management of tunnel construction. Three different DM techniques that were designed for different safety management objectives were combined to form the hybrid DM framework and support safety management process. In order to provide people with the experience required for on-site abnormal judgement, the association rule algorithm is carried out to extract relationships among TBM parameters. To supplement the formation information required for construction decision-making process, a decision tree model is developed to classify formation data. Finally, the rate of penetration (ROP) is evaluated by BP neural network and convolutional neural network to find abnormal data and give early warning. The feasibility of the method was validated by on-site construction data. The first author of the paper is Mr. Leng, the second author is associate Prof. Lin, and the fourth author is Dr. Shen. In addition, we also acknowledge the Metro Supervision Department of the Guangzhou Metro for providing support.