We are a group of students and we have created a low-cost machine for immediately identifying plastics using infrared rays – see our video here https://www.youtube.com/watch?v=aEFnh86olhg
And we would like to ask for your help! We are interested in how you currently sort plastics and if you have any good hacks for it. Additionally, if you would like to be one of the first people to test our machine, please do let us know!
Great idea and keep up the good work friends. Such techniques are the need of the hour.
I was wondering how the sensors would respond in your design to multi layer packaging waste. The difficulty with current machine sorters are they often mistake and misplace the multi layer waste depending upon their outer layer. Is there a way to overcome this ?
Maybe a stupid question, but I would like to ask:
Will be possible to use the NIR camera and led light of an smartphone to use it as a plastic identifier ???
Maybe will be not-perfect or have sorting errors but could work for at least identify some kinds of plastic?
** I use the word blind as a generalization of anyone who has low vision or is totally blind. In the US, one must have a visual acuity of 20 / 200 or greater, in order to be considered legally blind. I am one of these people.
With that being said, there are machines called cctvs, also known as closed circuit televisions. They are great for all sorts of tasks including: reading recipes, newspapers, excetera. I’ve also known some women to paint their nails underneath of one You may want to check them out online for curiosity sake. They are wonderful tools but alas, they are also expensive. I have a portable version, but a standalone version would be more practical for this use. This is another device that I will put into my business plan.
** Back to the topic at hand. I will mitigate the problem of films and thin plastics by, simply not accepting them. There is a grocery chain here in the States called, Publix. This store readily excepts that type of plastic, along with other recyclables. There is a company here in Georgia called, Georgia Industries for the blind. They were established I believe in, 1937. They employee blind people of all vision acuities. As part of my for starting my own PP, I am going to interview and visit some of the staff in their factory setting. This will help to give me more of an Insight on ways of making the production area safer. Mind you, this is far off in the future, of which I am speaking; at least a good 2 to 3 years. I want to make certain that I have everything prepared, when the time comes to hire employees. For now, I’m collecting plastic, and working on my business plan. The world’s problem with plastic didn’t happen overnight. As with this business venture, it will take time to get everything prepared.
We had a look at the samples you sent us (thank you!) and acquired the spectra. A detailed write-up with the spectra is here. In short, we found that the black composite is composed of one layer of pure HDPE and one layer of HDPE+additive/different polymer. The POM/acetal sample gave us some nice spectra!
Thanks again for sending the samples!
Martin / Matoha Ultrascience
I was wondering why do you need audible results, now it makes sense. We are quite curious how you will manage to overcome the inherent difficulties associated with employing blind people for sorting which even with our machine still requires at least some vision. For example, you know how there can be thick films wrapping PET bottles or yoghurt cups – it’s easy for a person with good vision to scan the piece of plastic outside the label/printing, the cleanest part. If you scan the label you might end up getting signals either for the plastic the label is made of (which is often different) or bad signals because of the inks from the labels also having a spectral signature – in both cases the identification reliability will be reduced. I mean you can feel the labels with your fingers (to some extent) – I’m just saying what is important from the point of view of our machine.
The new prototype is looking fantastic! Thank you very much for the detailed response. I am currently in the process of working on my business plan for a PP subsidiary in the US. I will definitely include this piece of technology in my business plan as a must-have. My ultimate goal is to hire all blind employees for my PP subsidiary. This will definitely make the plastic sorting go much quicker. Again, thank you, and keep up the excellent work!
This is a wonderful invention! :-). On what operating system does it run, Mac, PC? Also, are the results audible, so that someone who cannot see well sort plastic? I use a lighted magnifier to read the recycle markings on plastic. And even that proves very difficult at times. This would definitely speed up the sorting process. I would love to be a beta tester.
That looks very interesting! Please send us the samples and we will have a look at them (for sure please send us the oxymethylene as well!).
When we tried the flotation method ourselves it was really inconclusive, and there were instances where the same plastics behaved differently in the same solvent. In general many other factors are at work, which changes the buoyancy. So better to trust our machine!
I would love to build one to help you out with testing, we work on recycling plastics at user point. I see it still in development, but if we could work with you to improve it ready to release opensource then that would be great! Drop me a message if you want.
@imuh thank you! So one of the samples was marked ABS by the manufacturer, the other one ABS-PC by basman. So yes, his marking might be inaccurate. Or maybe it was a very clever way to see if we can actually distinguish things – if we said they are from different materials even though they are same that would be quite embarrassing
No worries, we are making plans how to release it open-source At the moment it’s somewhat a mess, so I don’t think anyone has spare couple of hundreds euros lying around to build something that doesn’t fully work (yet!).
@matoha (btw thank you so much for all the work you are doing on the plastic analyzer machine !)
I’m sorry but you got me lost in your last linked youtube video. Your “big machine” as you say so shows there is no presnece of polycarbonate.
I know you are not an all-seeing-&-knowing god, but what happened there?
Was the monitor piece marked (by constructor) ABS PC? Or was just a supposition from @basman ?
I’m sorry to bother asking this but if the error comes from constructor; it might be verry missleading for DIY activists (until you release your baby open source hehe :p)
Anyways, thanks again for all your commitment to this project !
@plastikfantastik Thank you! At the moment, the acquisition of a single spectrum is ~ 100 ms, though because of certain bugs on our PCB (which we’ll fix in the next revision) we have to employ heavy averaging (~10x) to get a decent signal-to-noise ratio. The machine learning classification afterwards is fairly quick, < 10 ms.
The signal intensities we are working with are like 1 nA spectrum peak size, which is obviously very tricky to get working – that means we need ~ 10 pA (10^-11 A) resolution with similarly low noise.
I wonder if clear plastics don’t pose a major issue. With light there’s less reflection and different refractory properties which would vary with the shape and thickness of the analysed plastics.
Is this a problem with IR sensors ?
Or do you instead use both clear and opaque plastic samples for the training process to capture different spectrum of the same plastic type/color ?
@armbouhali You are absolutely right With transparent plastics, you get much better spectra using transmittance rather than reflectance. That’s why at the moment we are working on adding a second lamp which will shine through the sample so that both reflectance and transmittance are supported.
In our experience, the reflected and transmitted spectra were not very different (the physical origins of the electromagnetic absorptions are the same). For some samples we observed minor differences, this was for example due to a thin coating layer on the sample.
Near-IR is reasonably immune to changes in colours, though black pigments usually make the samples very non-reflective and pose problems, as we said before.
You may want to check them out online for curiosity sake. They are wonderful tools but alas, they are also expensive. I have a portable version, but a standalone version would be more practical for this use. This is another device that I will put into my business plan.
