Login required to started new threads

Login required to post replies

An Interesting Read on a Wheel Developed by "Ai"
Quote | Reply
https://bikerumor.com/...ficial-intelligence/

...the Ai part doesn't interest me that much. I found this section rather interesting:

Quote:
Smith’s AI optimization routine was first programmed to find the lowest drag cross section possible that would work with a 25mm tire. They constrained the depth to a maximum of 77mm and let it fly. The initial result was a rim that measured 42mm at its widest point, so they added a width constraint of 30mm so it would fit in traditional bicycle frames and forks.

I find it interesting that the "Ai" ended up using the maximum width available to it.

Quote:
Specs for the new rims and wheels are:
  • Width at brake track: 29mm
  • Maximum width: 30mm
  • Depth: 77mm
  • Weight: 625mm per rim
  • Clincher wheelset: Venn Var 77 TCC weight: 1894g
  • Disc brake wheelset: Venn Var 77 TCD weight: 1915g
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [GreenPlease] [ In reply to ]
Quote | Reply
I think the proof will be in the windtunnel.
I don't know a lot about AI, but it isn't magic...
I'm not sure how many watts are left to find in aero wheel shapes these days anyways.

What I found more interesting was their production process as they are at the cutting edge of filament wound rims.
The regular Venn wheels are already an insane bang for your buck.
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [GreenPlease] [ In reply to ]
Quote | Reply
https://www.flocycling.com/aero.php

They're a couple years behind on the optimization algorithm. I also think they started from a flawed premise that a 25mm tire is faster. I suspect a 23mm type would have resulted in a narrower wheel.
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [GreenPlease] [ In reply to ]
Quote | Reply
"Ai", AKA "optimization routine"...only as good as the constraints selected (as they found out) and the evaluation criteria selected.

It would be interesting to know how "lowest drag" was specified (i.e. under what conditions and yaw angle weighting?)

http://bikeblather.blogspot.com/
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [Tom A.] [ In reply to ]
Quote | Reply
I just found it interesting a program spit out 40mm as the optimal width for a 25mm tire. This lends credence to the few wind tunnel tests I’ve seen of the Jet+ rim with a 20mm SS (a very, very fast combo)
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [GreenPlease] [ In reply to ]
Quote | Reply
I'm not too suprised by this, but really we need to have an idea of how the "AI" is dealing with the tyre shape as this , being the leading edge kinda determines everything that comes after.
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [JRC] [ In reply to ]
Quote | Reply
JRC wrote:
I'm not too suprised by this, but really we need to have an idea of how the "AI" is dealing with the tyre shape as this , being the leading edge kinda determines everything that comes after.

...AND trailing (if they're doing the 2D optimization right).

http://bikeblather.blogspot.com/
Quote Reply
Re: An Interesting Read on a Wheel Developed by "Ai" [Tom A.] [ In reply to ]
Quote | Reply
True, True!
Quote Reply