Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Open-Source Recycling

preciousplastic.com

Post reply on HN
Print view View original

11–20 of 41 posts

Re: Open-Source Recycling

#11

Post by maxerickson »

winterismute wrote: post #6

My wife was wondering whether this can be considered 100% healthy: don't you need plastic to reach a very high temperature to model it that way? Doesn't it start releasing whatever thing that might be carcinogenic or such?

Thermoplastics will melt before they start to chemically decompose. Whatever residue is in the plastic might be liberated by the heat (those residues will also migrate out at room temperature, so we tend to be somewhat careful about what residue ends up in products).

Thermoset plastics will not melt and will release all sorts of magnificent things when heated.

https://en.wikipedia.org/wiki/Thermoplastic

https://en.wikipedia.org/wiki/Thermosetting_polymer

Re: Open-Source Recycling

#12

Post by austinjp »

dzhiurgis wrote: post #5
pingec wrote: post #3

A positive thing for sure. But the hardest part is not the processing, it`s the sorting of different types of plastic and the washing phase if required.

How advanced are the sorting facilities? I assume they must use some image recognition and robotics already. Do they use deep learning yet?

I strongly suspect that the overwhelming majority of the world's recycling plants use cheap human labour, especially for tasks such as sorting.

http://www.aljazeera.com/programmes/witness/2015/05/unwasted...

Re: Open-Source Recycling

#14

Post by ska »

dzhiurgis wrote: post #5
pingec wrote: post #3

A positive thing for sure. But the hardest part is not the processing, it`s the sorting of different types of plastic and the washing phase if required.

How advanced are the sorting facilities? I assume they must use some image recognition and robotics already. Do they use deep learning yet?

   Do they use deep learning yet?
"yet" ? Deep learning is no panacea - it's not clear why this would even be on a top 5 list of approaches to try on a putative ML part of the process. There seems to be a lot of confusion on this, generally.

Most likely they just use cheap labor for sorting

Re: Open-Source Recycling

#15

Post by rvense »

ska wrote: post #14
dzhiurgis wrote: post #5

Earlier quoted context omitted.

How advanced are the sorting facilities? I assume they must use some image recognition and robotics already. Do they use deep learning yet?

Do they use deep learning yet? "yet" ? Deep learning is no panacea - it's not clear why this would even be on a top 5 list of approaches to try on a putative ML part of the process. There seems to be a lot of confusion on this, generally. Most likely they just use cheap labor for sorting

I'd think once you have built sensors that can digitize the whatever properties of the plastic that are relevant to sorting them, actually recognizing the different types of plastics would be rather simple.

Re: Open-Source Recycling

#16

Post by rvense »

ZenoArrow wrote: post #10
dzhiurgis wrote: post #5

Earlier quoted context omitted.

How advanced are the sorting facilities? I assume they must use some image recognition and robotics already. Do they use deep learning yet?

You can use spectrometers to identify different types of plastic, e.g. http://www.thermoscientific.com/content/tfs/en/product/micro... Deep learning isn't required. The main challenge is in sorting. I'm not sure how you could do this efficiently with machines that are as affordable as the Precious Plastic designs.

Sorting all the plastic waste of a major city is very hard.

Sorting your own or picking stuff out of a skip to gather enough to make a lampshade or a few coat hangers is probably more doable.

Re: Open-Source Recycling

#17

Post by albertojacini »

agumonkey wrote: post #4

Always wanted to do this, but I was afraid reprocessing plastics would release toxic fumes or hard to detect dangers for the average guy. I can't stand throwing things anymore.

I'm obsessed with not throwing away things and really appreciate a cool project like this. But nonetheless, I would like to emphasize that recycling is no substitute for not producing and not consuming plastic, which is by far the best way to fight what is depicted in the Why? section!

Re: Open-Source Recycling

#18

Post by ZenoArrow »

rvense wrote: post #16
ZenoArrow wrote: post #10

Earlier quoted context omitted.

You can use spectrometers to identify different types of plastic, e.g. http://www.thermoscientific.com/content/tfs/en/product/micro... Deep learning isn't required. The main challenge is in sorting. I'm not sure how you could do this efficiently with machines that are as affordable as the Precious Plastic designs.

Sorting all the plastic waste of a major city is very hard. Sorting your own or picking stuff out of a skip to gather enough to make a lampshade or a few coat hangers is probably more doable.

Sure, it works fine if you're selective about the plastics you use, especially if you avoid using objects that were made using a mixture of different plastics.

Re: Open-Source Recycling

#19

Post by rvense »

ZenoArrow wrote: post #18
rvense wrote: post #16

Earlier quoted context omitted.

Sorting all the plastic waste of a major city is very hard. Sorting your own or picking stuff out of a skip to gather enough to make a lampshade or a few coat hangers is probably more doable.

Sure, it works fine if you're selective about the plastics you use, especially if you avoid using objects that were made using a mixture of different plastics.

Honest question, what's likely to happen if you mix plastics? I understand how if melting points are different you might get odd results, and I'm guessing maybe very different materials won't bond at all leading to cracks in the final product. But if you doing something like they show in these videos, heating it to Note that I'm thinking entirely in terms of what I might do myself in my workshop, not what'd scale to a city-wide or country-wide recycling system.

Re: Open-Source Recycling

#20

Post by coldpie »

dzhiurgis wrote: post #5
pingec wrote: post #3

A positive thing for sure. But the hardest part is not the processing, it`s the sorting of different types of plastic and the washing phase if required.

How advanced are the sorting facilities? I assume they must use some image recognition and robotics already. Do they use deep learning yet?

Ars Technica has a few great articles about recycling: http://arstechnica.com/search/?ie=UTF-8&q=recycling

Including one that goes into depth about sorting: http://arstechnica.com/science/2015/12/recycling-matching-hi...

Post reply on HN