Zhenzhong Hu

    He recieved both his BE and PhD degree in the Department of Civil Engineering at Tsinghua University, China. He was a visiting researcher in Carnegie Mellon University.
    He is now the associate professor in both the Department of Civil Engineering and Tsinghua Shenzhen International Graduate School, Tsinghua University. He is also the secretary general of the BIM Specialty Committee of the China Graphics Society.
    His research interests include information technologies in civil and marine engineering, building information modeling (BIM) and digital disaster prevention and mitigation.
  • 2021-04-12

    "Knowledge Extraction and Discovery Based on BIM: A Critical Review and Future Directions" has been published in Archives of Computational Methods in Engineering.

    The production activities of the Architecture, Engineering and Construction (AEC) industry are inseparable from the support of accumulated experience and knowledge. In addition to concluding from engineering practices, many studies also try to apply knowledge engineering technologies to extract industry knowledge and store it in documents and databases. In recent years, BIM has been popularized and applied in the AEC industry as an ideal medium for extracting, exchanging and managing building data. In particular, BIM also shows great potential in knowledge acquisition and management of the AEC industry. This paper conducts a comprehensive survey on the research of knowledge engineering based on BIM, and reviews related studies from the following five aspects: (1) knowledge description; (2) knowledge discovery; (3) knowledge storage and management; (4) knowledge inference; (5) knowledge application.

    The review indicates that BIM is capable of providing information for knowledge discovery and providing a platform for knowledge integration and application by adopting knowledge engineering techniques such as ontology, semantic web and data mining. This paper also reveals the potential value of knowledge in the AEC industry, but at present the management and application of knowledge is still at the beginning stage. In the future, BIM is expected to be deeply integrated with knowledge engineering to build a knowledge-driven system for building design, construction, and operation and maintenance, and lay a solid foundation for intelligent buildings and infrastructures.

  • 2021-03-01

    "Linking data model and formula to automate KPI calculation for building performance benchmarking" has been published in Energy Reports.

    Buildings consume a large proportion of global primary energy and building performance management requires massive data inputs. Key Performance Indicator (KPI) is a tool used for comparing different buildings while avoiding problems caused by heterogeneous data sources. However, silos of building and energy consumption data are separate, and the linkages between a KPI formula and different data sets are often non-existent. This paper develops an ontology-based approach for automatically calculating the KPI to support building energy evaluation. The proposed approach integrates building information from BIM and energy and environmental information collected by sensor networks. A KPI ontology is developed to establish a KPI formula, thereby linking static and dynamic data generated in the building operation phase. Each KPI can be defined by inputs, a formula and outputs, and the formula consists of parameters and operators. The parameters can be linked to building data or transformed into a SPARQL query. A case study is investigated based on the proposed approach, and the KPIs for energy and environment are calculated for a real building project. The result shows that this approach relates the KPI formula to the data generated in the building operation phase and can automatically give the result after defining the space and time of interest, thus supporting building performance benchmarking with massive data sets at different levels of details. This research proposes a novel approach to integrating the KPI formula and linked building data from a semantic perspective, and other researchers can use this approach as a foundation for linking data from different sources and computational methods such as formula created for building performance evaluation.

    Note: Energy Reports is an important academic journal in the field of energy research. Its impact factor in 2019 is 3.595, and it is listed in the Q2 SCI journals.

  • 2021-2-17

    A Framework for the Automatic Integration and Diagnosis of Building Energy Consumption Data has been published in Sensors .

    Buildings account for a majority of the primary energy consumption of the human society, therefore, analyses of building energy consumption monitoring data are of significance to the discovery of anomalous energy usage patterns, saving of building utility expenditures, and contribution to the greater environmental protection effort. This paper presents a unified framework for the automatic extraction and integration of building energy consumption data from heterogeneous building management systems, along with building static data from building information models to serve analysis applications. This paper also proposes a diagnosis framework based on density-based clustering and artificial neural network regression using the integrated data to identify anomalous energy usages. The framework and the methods have been implemented and validated from data collected from a multitude of large-scale public buildings across China. This research proposes a general framework for building energy consumption big data management and analysis, provides a basis for building energy consumption data application, and has certain reference significance on diagnosis and decision making of saving building energy consumption.

    ps. Information for Sensors: Impact Factor: 3.275 (2019);Ranked 17/129 (Q1) in 'Physics and Astronomy: Instrumentation' and 147/670 (Q1) in 'Electrical and Electronic Engineering' and 70/300 (Q1) in 'Computer Science: Information Systems'

  • 2021-01-20

    I was invited to to organize a special issue on "Smart Sensing in Building and Construction(SSBC)" in Sensors (Impact Factor: 3.275) together with Jia-Rui Lin from Tsinghua University, Jérômex Frisch from RWTH Aachen University, Qian Wang from National University of Singapore, Yichuan Deng from South China University of Technology and Yi Tan from Shenzhen University. The deadline for submission is 31st October this year. Welcome to submit your manuscript for potential publication.

  • 2021-01-06

    Beijing Cloud Jianxin Technology Co., Ltd. signed a strategic cooperation agreement with Haina Cloud Technology Holding Co., Ltd. of Haier Group. Based on their respective industry accumulation and advantageous resources, Cloud Jianxin and Haina Cloud will carry out in-depth strategic cooperation in BIM intelligent product development and other fields, build industry benchmark and model project through product development and project cooperation, and play a leading role in development and innovation. The two sides will work together to create intelligent BIM products and explore the road of Building Internet.

    Note: Beijing Cloud Jianxin Technology Co., Ltd., which is responsible for the transformation of research results of this research group, is committed to BIM and intelligent information technology products and services, and is a leading provider of BIM platform, software and service for the whole life cycle of building in China.