Understanding Buildings using Machine Learning Javier VENEGAS - PowerPoint PPT Presentation

Understanding Buildings using Machine Learning Javier VENEGAS javier.venegas@novalian.fr Paris, France

OUR TEAM Jean-Paul BALOCHE Constantin CHEVANCE CEO Head of Product Javier VENEGAS Sergejs MIHAILOVS Diego ZUNIGA CTO Data Engineer Data Scientist

BIM : INDUSTRIALIZATION TIME 70’s Now Draw complex buildings Draw complex buildings with strong constraints with strong constraints

BIM : INDUSTRIALIZATION TIME Standard exchange data model : IFC PDF for BIM

GENERAL GEOMETRIC DATA INCONSISTENCY EXAMPLE Facade is one only wall, related to one floor. Take others floors = no wall

OBJECT GEOMETRIC DATA INCONSISTENCY EXAMPLE ● Language ● Measuring unit ● Definition of a door ● Modelisation length vs Metadata length ● Depth of the door = depth of the wall ? ● ... Thi his s is is not not a a doo oor.

OUR SOLUTION : DeepBIM Neural BIM Networks Platform & APP DATA DeepBIM WRANGLING Graph Transfo DOC 3D SQL

DeepBIM : ARCHITECTURE API Gateway Kubernetes Cluster APIs : Project API ● 3D retranscription ● Graph Creation ● IPC Ressources Queue Handler ● ... Deep Learning Neural Network

DeepBIM : BUILDING INFORMATION MODEL Documents IFC Exploration 3D Transformation

DeepBIM : FROM IMPLICIT DATA TO EXPLICIT DATA

DeepBIM : CREATING A NEW 3D REPRESENTATION

DeepBIM : DETECTING SPACES

DeepBIM : THE NEW DATA REPRESENTATION

DATA EXPLORATION EXAMPLE

Dashboard example

Javier VENEGAS javier.venegas@novalian.fr Thanks for your attention ! Any questions ?