Posts

Paper: AI-Powered Digital Twin

AI-Powered Digital Twin for Sustainable Campus Facility Management

Nikolaenko, Mikhail, Ming Tang, Aayush Kumar, and Sid Thatham. 2026. “AI-Powered Digital Twin for Sustainable Campus Facility Management” Architecture 6, no. 4: 205. https://doi.org/10.3390/architecture6040205

University campus buildings consume significant energy through chilled water (CHW) systems, yet facility and energy managers lack tools that connect sensor data to actionable, spatially grounded decisions without requiring programming expertise. We present BearcatAI, an end-to-end analytics platform developed at the University of Cincinnati (UC) that unifies machine learning demand prediction, a large language model (LLM) conversational interface, and an interactive 3D campus visualization derived from geographic information system (GIS) data. All models were trained and evaluated on 271 days of daily meter data collected across the UC building portfolio (June 2025–February 2026); ten years of monthly CHW records (July 2015–July 2025) provided long-term context only. An ensemble of XGBoost and Random Forest models achieves an in-sample 𝑅2=0.988, mean absolute percentage error (MAPE) =20.4% (inflated by near-zero winter readings), and normalized mean bias error =−0.3% on DAAP (College of Design, Architecture, Art, and Planning), the priority building identified by the UC utility engineering team. Beyond building-specific models, we introduce use-type models that pool buildings by functional category (Academic, Research, Administrative, Housing, Recreation, Medical) without any building-specific identity features. Leave-One-Building-Out (LOBO) cross-validation shows that the Research type model generalizes to unseen research buildings with median 𝑅2=0.911, and the Academic model achieves 𝑅2=0.918 on DAAP without having seen it during training, whereas medical and hospital types do not generalize, demonstrating the feasibility of functional type models as campus-scale benchmarking tools within the study dataset. A natural language interface powered by BearcatGPT, UC’s hosted instance of GPT-4.1, allows utility managers to query anomalies, request forecasts, and generate building charts through conversation. Anomalous buildings are automatically highlighted in a 3D campus model spanning UC Main Campus, Medical Campus, and Digital Futures. The results are limited to a single campus and observation period; user evaluation and a robotic inspection module under development remain future work.

Read more

Tilted Deck. Design Build in China

Ming Tang, Yingdong Hu advised a group of BJTU students to participate in the “Xinzhaiping” Rural Design-Build Competition in China in 2021.

Project name: Titled Deck. 

BJTU Students: Bingxu Gao, Zhu Chen, Xiangyu Zhou, Haolong Guo.

Advisors: Yingdong Hu (BJTU), Ming Tang (UC)

Location: Hunan Province, China.

More info on the competition “2021乡见新寨坪·乡村建造大赛”

Award:

The build project won second place in the Rural Design Build competition 2021.

The build project also won the excellent award of the 19th 2021 Asian Design Awad.

   

3D print for cast-in-place concrete

Cast-in-place Freeform Concrete with Big Area AdditiveManufacturing Formwork

Ming Tang, Noah Shroyer. Cast-in-place Freeform Concrete with Big Area AdditiveManufacturing Formwork. International Journal of Architecture, Engineering and ConstructionVol 10, No 2, Vol 10, No 2 (2021) 1-9

Abstract: Parametric design and digital fabrication give precise control in the design and materialization of complex geometric forms. Large-scale additive manufacturing machines can fabricate digitally generated architectural forms quickly and economically at full scale. However, their application in building construction has been limited. Through a case study, this paper examines integrating parametric design with material and constructed reality through 3D printed formwork for cast-in-place concrete. The following details are presented: (1) creating a parametric model capable of designing, testing, and manipulating the customized freeform in response to construction and material constraints, (2) fabrication method of big area additive manufacturing of formwork with carbon fiber-reinforced acrylonitrile butadiene styrene plastic, and (3) construction process (studying material behavior, testing the formwork, and the final onsite concrete cast)

This project was supported by the computation team led by Ming Tang, the design team led by Jose Garcia Design, the structural engineering team led by Pinnacle EngineeringInc, formwork and fabrication led by Cincinnati Incorporated. The project was constructed by the general contractor Jose Garcia Construction. The rebar shop fabrication was provided by Artistic Ironworks.

Video from Cincinnati Incorporated

Rural Public Restrooms Design + Build, China

A group of UC DAAP students, led by Whitney Hamaker and Ming Tang, participated in the  “Yuzhang Construction*” workshop to design and build two public restrooms at the Pengyuan village, Yifeng County, Jiangxi Province of China in summer 2020. This workshop is a collaboration with Nanchang University (NCU),  Beijing Jiaotong University (BJTU), and cooperates with the local village to carry out the 2020 public facilities construction. Due to the COVID-19, all design was completed through virtual collaborations. The first designed restroom is under construction, started in September 2020.

Project location: Pengyuan village, Yifeng County, Jiangxi Province, China

Project scope: design and construction of two rural ecological restrooms

Design activity: June-August, 2020

Construction: 09.2020- 12.2020

  • Faculty advisors: Fen Xiao, Qong Wu ( NCU), Yingdong Hu (BJTU), Whitney Hamaker, Ming Tang (UC)
  • UC Students: Sabrina Ramsay, Alexandra Steigerwald, An Le, Pwint (Audrey) Wati Oo, Nathaniel Liesch
  • NCU students: Mingxuan Wu, Ding Wang, Xiaohu Cheng, Meile Gui, Xianhao Xie, Hao Xiao, Jiayi Wang, Jiaoao Li, Mo Jia, Zheng Li, Yijia Wang
  • BJTU student: Cilu Luo, Zhu Cheng, Lurui Lue, Jiayi Xu, Xiangyu Zhou, Yudang Wang

The project won the First Place in the 2021 Asian Design Award. Sustainable Design category. 

Picture Taken by Fen XIao, NCU.  Photography Credits Go To Fen Xiao, NCU.

* “Yuzhang Construction” workshop was founded in 2018, initiated by the School of Civil Engineering and Architecture, Nanchang University. Based on the concept of “innovation and construction,” the workshop works through the public welfare design and construction of social projects to serve the community and carry out a practical model of teaching. Through the construction activities of the mill building construction in Xikeng village in 2018, and the rice bridge building in Tianqiao village in 2019, students and faculties walked into the countryside to understand the rural, activate the countryside with design, and to help the local rural revitalization and sustainable development.

 

The project was also exhibited in 2021 DAAPcares and won the 2021 DAAPcares Sustainability award.

UIA-CBC Design Build Competition

Pear Orchard Cabins

Design + Build project in China. UIA-CBC Competition

2019 UIA-CBC International Colleges and Universities Competitive Construction Workshop walks into Guoyuan Village, Aiyuan Town, Siyang County, Suqian City, Jiangsu. UC + Beijing Jiaotong University (BJTU) team has won the UIA-CBC competition proposal as one of the top 15 teams from proposals submitted by 101 Universities across 23 nations. After the winning of Phase 1 proposal, UC+BJTU team was invited to join the Phase 2, and build the permanent structures from August.01 to 19 in China. The project won the third prize. Please check out the final result of all 15 projects .

Taking the century-old pear orchard as the site, this year’s Competitive Construction Workshop sets a theme of creating “Pear Orchard Cabins” that can improve the quality of living in the orchard. The participating teams designed and build 15 cabins in the orchard as well as infrastructure that connected the whole community in order to contribute to the revitalization of the “Century-old Pear Orchard”, and also to explore a path for changing villages by the power of design.

The theme of this year’s workshop is “Pear Orchard Cabins”, which takes the whole 100-year-old orchard as the site of design where 15 selected teams from renowned international and domestic universities will be involved to discuss how to “activate villages through design”. The teams will use a limited space to design and construct their cabin in order to provide more activity solutions to the villagers and visitors. The design will be based on the element of “pear” and picture future scenarios involving countryside spatial experience and pear-related themes all the way from design to constructions or construction. The design content is not limited to installations and may also include consideration of the site and the environment.

As an integral part of village revitalization plan, the workshop seeks to explore a rural public architectural form than can fit in with nature. By linking up the 15 “Pear Orchard Cabins” in the century-old orchard with a continuous infrastructure, it emphasizes the fun experience of exploring the place, activates the heart of the village and injects the power of design into the basic mode of rural production, driving the change and improvement of rural lifestyle and providing a paradigm for rural construction.

Phase II: Design+Build Team

Students: Lauren Figley, Jordan Micham, Pat McQuillen, Vu Tran, Jeremy Swafford,Tess Ryan

Faculty supervisor:  Whitney Hamaker, Ming Tang (UC); Yingdong Hu, Yunan Zhang, Yongquan Chen (BJTU)

 

Phase I: Design Proposal

UC Student Team, class from ARCH3014, digital media skills. Spring 2019, taught by Prof. Ming Tang.

Winning Team: Lauren Figley, Andi Moore, Jordan Micham, Pat McQuillen, Vu Tran 

Graduate assistant: Jeremy Swafford, Shreya Jasrapuria, Kenna Gibson, Alan Bossman, Tess Ryan

Faculty advisor: Ming Tang, Xiangbin Xu, Yuhui Song (UC); Yingdong Hu, Yongquan Chen ( BJTU)

early concept

Final concept

Photo of Phase II. China