HVAC design is a time-consuming process
Designing such systems is a crucial but complex phase, involving mechanical, thermodynamics engineering skills, and a complete understanding of the building.
BIM software already facilitate this design stage, allowing 3D visualization of a building and permitting to identify the potential ducts and HVAC elements’ location. Nevertheless, designing a whole network for large infrastructures such as tertiary buildings is a quite long and redundant process. Existing BIM software, such as Autodesk Revit, already provide HVAC network drawing aid tools, permitting to connect easily all the elements together. Unfortunately, no comprehensive network design solution exists on the market, making the design of a network mostly manual and time consuming for engineering offices. That is where A.I-powered tools can generate value.
DIANE: a breeding ground for reinventing HVAC network design
A major international leader in the construction and conception industry, VINCI had to step in when it comes to these technologies. The recent years saw the advent of numerous parametric and generative design initiatives and solutions in the company. This is particularly true when it comes to building design solutions, where DIANE (‘Digital et Intelligence Artificielle pour Nos Entreprises’), a business unit dedicated to leveraging AI and data was created two years ago. Solutions such as automated sprinklers network generation, fire detection systems implantation or lighting systems generative design have already been developed, deployed, and used across VINCI Energies group, proving the potential of AI for improving and simplifying the design engineers’ experience.
AI augmented HVAC network generation
Based on these successful stories, VINCI Energies has chosen once again to innovate in the field of construction: CVCIA was born, valuing DIANE’s experience on BIM, software engineering and AI. CVCIA is a generative design-driven solution that leverages data science and graph theory to optimize HVAC network generation. The solution is based on four independent bricks: automated room detection from a blueprint, HVAC requirements sizing, automated positioning of HVAC devices on a BIM model, and network generation, i.e., optimized interconnection of all the HVAC elements respecting field constraints. The different bricks are deployed and directly integrated into BIM software, allowing to generate a complete and valid network from a blank blueprint in a few minutes. The chosen project structure allows VINCI Energies’ engineers to intervene at each step in order to fine tune the results and take into account additional constraints. On-going work is still conducted to refine the different bricks based on field feedbacks.
In a nutshell, CVCIA is a step forward in designing optimized HVAC networks.
What’s next?
A first version of the product has already been industrialized and is ready for large scale deployment. DIANE will now concentrate on enlarging the target across all VINCI Energies’ Business Units. Field feedbacks and user behavior analysis will permit to improve the solution until it is 100% adopted across the group. DIANE is one more time reinventing VINCI engineers’ experience and doesn’t intend to stop there.
This article is part of a series involving the participants of the AI program by Leonard, the VINCI Group’s foresight and innovation platform. The program has been specifically designed to accelerate the adoption of AI technologies within VINCI. It consists in a five-month incubation period where selected VINCI collaborators follow a learning by doing process where they codevelop an AI-based use case under the coaching and mentoring of Leonard’s team and consultants from Eleven Strategy.
More about Leonard’s AI program: https://leonard.vinci.com/en/programmes/ia-course/
