We've just launched our map. Add yourself by clicking here!
Our new machine to sort plastics
- This topic has 44 replies, 19 voices, and was last updated 2 years ago by
.
Hi guys,
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!
The best way to get in touch with us is to go to https://matoha.com/pp/.
Be sure to check out our Facebook and Twitter page as well!
Attachments:
Hi @jtdoma,
Thank you! The device is based on Raspberry Pi which runs Debian Linux. It connects to your internet / WiFi (to communicate with our cloud where the analysis is done) – which also means you can access the web interface from any other device which has an internet connection – your phone/computer/tablet, independent of the operating system.
In the latest version it now has an embedded touchscreen (see the attached photo). We are also working on adding a loudspeaker which could provide an audible indication that the item has been scanned (like barcode scanners in supermarkets) – I’m sure it could be modified to include the name of the identified plastic, if necessary.
Currently, it looks like we will provide the machines into long-term loans – machine+access to our Cloud, which could be around £55 / month – we are still working on getting everything working nicely so we don’t have any definite numbers. I know it’s not super-cheap, but definitely much much less than the £30k spectrometers currently out there.
Stay tuned for updates, we hope to have it ready for beta testing in 3 months!
Martin / Matoha Ultrascience
Attachments:
Hey thats cool, what did it cost to build?
Do it work with all the recyclable plastic?
Or even with other plastics?
Thanks for the interest – building it was more than a year of prototyping – starting with big setups on optical benches and gradually making it smaller and functional. And prototyping optics is neither cheap nor easy. If you are asking about the device itself in the current revision, our goal is to make it at least 10-30x times cheaper than the currently existing machines (priced at €20-30k), and most likely even less. We are still quite in the prototyping process, so hard to say.
The machine is able to identify mainly the 5 most common plastics PE/PET/PVC/PS/PP, though it is quite likely other plastics will be possible as well.
Thank you! The current ‘brain’ inside the machine is a Raspberry Pi – an Arduino won’t be powerful enough to do the analysis of the infrared spectra. We are considering making the device open-source hardware, though it’s not an easy decision – both closed and open-source have their advantages and disadvantages. In any case, it will definitely be closed-source (secret!) until it’s ready for the real world and perfectly functional.
ABS and ABS-PC – I must say we haven’t come across an ABS-PC sample, so I don’t really know. I assume it depends on the composition of the sample and also other factors. You could send us physical samples and we could simply measure them 😉
Hi @jtdoma ,
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.
Good luck!
Martin / Matoha Ultrascience
@chelbig Thank you! We are are working hard to get it fully functional, though it will take some months before it’s ready for beta-testers. We’ll keep you updated – if you are interested you could go to matoha.com/pp to tell us more about what you are doing – e.g. which plastics you normally sort&use and how.
Hi @xxxolivierxxx,
Unfortunately, I can’t get hold of a PDF of the article you have linked. But I also have good news – the technology has made a huge progress from 1993 when it was written. There is a wonderful Python library called SciKit Learn, which effectively means the neural net/ machine learning algorithms can run on a £25 Raspberry Pi (as a matter of fact, that’s what we are using).
Also, there are small machines that can do the identifications, priced at something like £30k – that’s obviously horrible and inaccessible. We are four students with very limited budgets, so rather than putting in super-expensive components, we are using our brains to find nice ways how to do it without them. I can’t promise any concrete numbers (still in development), but what I can promise is that it will be much much cheaper than the existing technology 🙂
Martin / Matoha Ultrascience
@matoha
it is still wornderfull what you are doing
a rasberry-pi is an awsome micro controller so keep up that work
i recycle old computer monitors and i have a batch of abs-pc for you if you are intrested i can send you some (free of charge) just to help you guys
if you are intreseted send me a pm i will send you my contact info
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.
Thanks @copypastestd , those are exactly the plastics we want to be able to sort: ones that look essentially identical to the eye! When we first started prototyping we encountered a lot of waste like that; indistinguishable, and often missing their numbering or were just wrong. The problem will be solved with our machine!
Hans
Matoha Ultrascience
It´s an amazing device, thanks for share it. How can i get it?
i really want to know more!!
This is so cool, I’m exited to heard back from you with more progress 🙂
I was doing some reading and found an interesting article from Sandia National Laboratories back from 1993 but it seems they used a high-resolution fourier-transform infrared spectroscopy device plus a well trained neural network. If you are using the same approach I highly doubt this will end up being cheap or open source.
@matoha
Your project is awesome. It is already looks cool for prototype.
Sometimes it is really difficult to recognize type of plastic.
There is an example: same manufacturer (Komus), same type of container (food), same color (transparent). But on the left PET, on the right PS.
Attachments:
Cheers! Our instrument does best with coloured and clear plastic items. The darker the plastic is, the more our machine struggles; however, industrial automated sorting lines can’t accurately categorise dark coloured nor black plastics either 🙂
Is it of particular importance to you?
Hans
Matoha Ultrascience
Hi guys,
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?
Thanks and keep the great work!
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!
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! 😉
@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.
Martin / Matoha Ultrascience
you guys have solved a major issue so far the floating method is what I have been using. I was wondering how long do you need at the sensor for it to read which plastic it is? I have also signed up to be a tester cant wait till its finished. If i can help in anyway just pm me.
Keep up the excellent work!
This is impressive. I’m curious what you’re using to detect the plastics’ spectrum. Sure beats £30k as far as accessibility is concerned!
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 ?
You must be logged in to reply to this topic.
