Blog Post #323 AI in Building / engineering

AI in Building / engineering

Taken from:

The construction industry is one of the foundations of modern life (literally and figuratively).  

The article states:

“In order to plan and design the construction of an entire building, the 3D models need to take into account the architecture, structural engineering, mechanical engineering, electrical engineering, and plumbing – and the work schedule and timing of these respective teams. The challenge for the construction firms here is to ensure that the different models from each team mesh together and don’t ‘clash’ (which could result in unnecessary reconstruction).”

Project management software for the construction industry has been around for some time.  You have resources (like workers / bricklayers, plumbers, electricians, etc.) that you need to schedule.  Of course you can’t put in the plumbing until the basic foundation is in; you can’t put on the roof until the walls are up; you can’t put in the kitchen counters until there is a kitchen (with outlets and plumbing).  Quite a task.

The article adds: “The construction industry is attempting to leverage machine learning in the form of generative design (explained below) to identify and mitigate clashes between the different models generated by the individual teams in the planning and design phase itself (as opposed to finding clashes during the construction).” and “In essence, [the new AI / Machine Learning System leverages machine learning to specifically create 3D models of mechanical, electrical, and plumbing systems while simultaneously making sure that the entire routes for systems do not clash with the building architecture.”

With major buildings (say large hospitals, with special features, special equipment, the need for high speed fiber networks, and more, this can be a big problem.

I’m thinking of Lake Wobegone Minnesota – where when the town was founded years ago (fictious town of Garretson Keilor) four surveyers were involved in mapping the town.  They found that all their maps overlapped – so each one took out his/her part that overlapped with the others – and in that process there was NOT a map with the town of Lake Wobegone on any maps!

It would be extremely expensive to be finishing a building only to realize that heating and cooling systems were ignored; or there was no plumbing.

Using AI to maximize the systems with the least clashing of systems sounds like a great idea for building.


What do you think?


Have a great day!!



Posted by Bruce White

Leave a Reply