Hacker News Reader

Comment by mygoodaccount | Hacker News Reader

Sorry, but I don't want a black box for stress testing bridges - or any other infrastructure for that matter. Do black boxes have their place in design? Sure. In validation? Absolutely not.

View on HN

"Don't worry, the AI says the bridge is okay. We've got fresh filler and paint over all the recognizable cracks!"

"Sorry about the broken skyscraper, a few workers through Mechanical Turk tagged polystyrene as indestructible"

We wrote “strong” on the bridge and now the AI thinks it’s indestructible

Then don't use it for that! Why so many naysayers dumping on interesting things. Engineers aren't idiots who're going to randomly rely on unknown techniques. Even traditional FEA is backed up by hand calculations.

It's not even really a black box. It's learned a subset of Abaqus's functionality so it's scope is known.

It doesn't appear to be stress testing anything, it's [edit: removed calculating] estimating where a structure or material is stressed. Stress testing is a physical process, and the article gives no indication that stress testing could or would be replaced but this.

Edit: Further elaboration from the article: product designers, for example, could test the viability of their ideas before passing the project along to an engineering team

This would seem to clearly indicate that the intended application is faster iteration in design, not a replacement for a rigorous engineering process that would include appropriate testing.

>calculating

Estimating

thanks, corrected

True, it can be quite concerning, I know that PDE's have issues too but they have served very well over the years and will continue to do so. I think that there is no shortcut to having a solid understanding of the principles at play.

They're useful for parallel construction. I.e. in identifying designs to be validated through more conventional and computationally-demanding methods.

I think (hope) techniques like this will provably be more useful for forensics and inspection than anything else.

agreed. in situations where you have pictures to analyze but no structure or greatly damaged structure, it makes sense.

It might even be good to analyze inspection photos for regular inspections to draw attention to situations where there might be more strain than anticipated and a human could be flagged to inspect more closely.

That's not the application. ML accelerated modeling allows for instantaneous iteration. It dramatically speeds up creative engineering and scientific work. You take the final product and run it through a classical simulator as a final QC - though in my experience (in a different domain, but similar principle) the ML model outputs tend to be smooth/continuous and ≈98% MSE accurate. Of course you need to carefully train your models to span the input space, but for finite element/finite difference modeling this is relatively straightforward.

ML model outputs tend to be smooth/continuous and ≈98% MSE accurate

In my experience building and working with such models in similar domains, they tend to be right in all the easy and uninteresting cases where there are no problems and in all the cases where the problem is super obvious, and wrong in all the hard and subtle corner cases that you actually care about.

The other problem is that traditional engineers hate models they don't understand. If you can't explain, at least roughly, why it gave the answer it gave, then they won't trust it and won't use it.

A better way would be for the neural network to generate input parameters for Finite Element Method solvers.

Reply on news.ycombinator.com