From the course: Grasshopper: Generative Design for Architecture
Unlock the full course today
Join today to access over 22,600 courses taught by industry experts or purchase this course individually.
Roof panel physics and classification
From the course: Grasshopper: Generative Design for Architecture
Roof panel physics and classification
- [Narrator] I have my (mumbles) file open already. We're in the process of building out our general design model. Specifically, we're working on the roof paneling. So we have a pattern here that we've created already, and we're going to finish mapping this onto the original surface and using a classification algorithm, neural network, to determine which panel lend themselves to being a skylight. So if I look here, I have my pattern coming out and I've added a couple of elements to the last script that we ended with. Specifically, some training data, which is a whole bunch of boundary curves, which I've already classified. And if you open this up, you can see basically similar patterns to this that have already been classified to tell the script which are appropriate for skylights. And then these components are the same, they're duplicates. Each of these extract of bunch of data from those curves. So this is what we're going to use to set up our machine learning neural network…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Contents
-
-
-
-
-
-
-
Design requirements and diagramming6m 44s
-
(Locked)
Sine surface points9m 24s
-
(Locked)
Roof surface7m 15s
-
(Locked)
Sides views and fitness value9m 23s
-
(Locked)
Optimizing with Galapagos6m 58s
-
(Locked)
ML structural regions7m 59s
-
(Locked)
Roof panel clusters8m 41s
-
(Locked)
Roof panel physics and classification6m 40s
-
(Locked)
Structure for optimization8m 54s
-
(Locked)
Goals and Kangaroo solver10m 43s
-
(Locked)
Visualization6m 49s
-
(Locked)
Adjustment and refinement4m 20s
-
-