@Mialek
Hey. Did you 3D print your machine? I would love to see photos or video of how it’s made, and maybe you’d like to share any stl files you used?
I’m so excited this project is moving forward again!
1 Like
Hi, I just started folding the machine, I’m tossing the first pictures in the link.
High quality
The whole is based on an aluminum profile 10mm x 20mm, a few screws, a conveyor belt printed from TPU, and elements printed from PET-G, roller bearings.
I can make STL files available, but they are not yet perfected,
When I add the upper tape and finish the whole thing, I’ll share the film.
I’ve designed everything myself, and I can rewrite everything as required.
1 Like
Looking good! Can’t wait to see how it develops!
Hello, we are starting a webinar series on open source. The first one is this evening. would be great if some of you would join and share your experiences:
Hello, everyone, my name is Joshua Montgomery and I’ve decided to help finish this project.
I’m the founder of https://mycroft.ai ( the open source world’s voice assistant ) and last year I purchased a coffee farm in Kona, Hawaii.
I have a pretty nice makerspace here in Hawaii and would like to make this coffee sorter a reality. I think there is a lot of value to be created for the global community of coffee growers by creating an inexpensive sorter that can be built in a makerspace.
I’d like to make a rev 1.0 of this machine, then do a sprint here in Hawaii with some of the core members of this team in the fall ( during the harvest ) so we can test out the machine. I’ve got plenty of lodging here and am willing to help with airfare for core contributors.
In keeping with the open source ethos, all drawings, STL files, documentation, software and data will be open and available to the world. That said, we are building a coffee brand and want to build a machine to help sort our coffee accurately.
Here is our label, in case you’re interested.
I’m looking forward to meeting with everyone!
7 Likes
This is the greatest thing I have heard in ages. This made my week! Way to go!
hey Joshua, congratulations on what looks like a beautiful adventure The visuals are ace. Had no idea anyone was growing coffee on Hawaii, how common is this?
Super super cool. You rock, Joshua!
Hi Joshua! Interestingly, a month ago I met a farmer in Kenya who used to grow coffee before the market crashed and he has a coffee sorting machine from 60s (approx. I think) that did all this without cameras and used high-pressure, localized air stream to divert selected beans from a stream of pouring beans while in the air. Never heard about coffee bean sorters before.
I’m a software engineer with experience in computer vision and machine learning (some of my projects: https://gacka.space/) and I’m interested to know where you are on the software side and if I can be of any help. And if so, what kind of time involvement it would require.
I also have access to Kenyan coffee farms if there is a way I can help with distributing the blueprints to people that may need it in East Africa (I’m working with farmers here on measuring soil moisture using sensor technology).
3 Likes
Soil moisture is a tough problem. Sensors corrode quickly. Best of luck with that, looking forward to seeing a durable solution.
I’m going to ask the local computer meetup to help and have reached out to the University of Hawaii to see if any students are looking for a thesis.
Definitely work to do on software. It looks like the ML stuff is working ( which is a start ), but we’ll need it to run REALLY fast. I’d like to use an approach like this one: https://youtu.be/T1bpafUsP7Y but use compressed air to sort the beans as they come down the shoot. That means we need to image and classify each bean very quickly with the limited resources we have on a Raspberry Pi 4.
I think this is doable, but will need lots of help.
The coffee we grow here in Kona is among the best ( and most expensive ) in the world:
There are a ton of small hold farms up here on Hualalai earning a living by growing great coffee on 5 acres or less.
3 Likes
That’s ambitious for sure 
If you really want to go that route, perhaps implementing the ready-made CNN on a FPGA could work, and be more performant than GPU based acceleration. Since the machine would run only one classifier, the sluggishness of re-programming a FPGA would not be an issue. There is some promising research into that field …
The other route, which we chose so far, is to have a much slower machine that can run 24/7, and if necessary in parallel with other identical machines. One of the design ideas was to have a 5-10 cm wide machine that can be clipped together with identical machines left and right and all would be filled from a common fill funnel.
I propose you try to calculate what speed of machine you need for the setting where you want these machines to be used (a single farm, a coop, …).
I was thinking of using something that’s got a TPU on it. Might be cheaper to use a $150 board with a TPU designed to run models on the edge than it would be to use a Pi ( or similar ) and run it on the ARM.
1 Like
Ah, I see where you’re going with this. Amazing hardware find! It seems a lot has moved since I last looked into this area in early 2018.
The other hardware challenge in your proposal would be about how to integrate a compressed air system for bean ejection into a low-cost sorter. It seems you’re targeting a higher-performance, higher-priced machine. (1500 USD maybe? Do you have a goal for the price?) For that it could work with compressed air. Linear actuators like in the skittle sorter you mentioned would probably be cheaper. But since they are mechanical moving parts, long-term reliability is a bit of an unknown …
Hi, Toshota-san,
This is Wen. I am a coffee roaster in California. Looking for a small scale bean sorter.
Your bean sorter is lovely. Wondering how many pounds of beans can it process per hour? Any product spec can you share? When do you plan to take it to the market?
Regards,
Wen
Hi, Matthias,
Thanks for starting this project! Much needed!
While my heart goes to the smaller coffee farm owners and farmers, as a small boutique coffee roaster myself, I have endured enough pain of sorting green and roasted beans by hands. Like to address this asap. I am looking at two options: 1. to buy a commercial small scale bean sorter; 2. to participate the open source community to help to build a production quality bean sorter.
If you know of any commercial small scale bean sorters, which are GTM to close to GTM, please point it my way. I would much appreciate it.
On the other hand, in previous life, I was a software developer of embedded storage systems and ran product development before. I can help on UI development, script, driver, Linux, good at C/C++/Python/Java, some knowledge about iOS app as well … I also have a 3D printer, Nvidia boards and chips, and access to deep learning expertise. Let me know if any specific area that the community could utilize my skills and speed up the project development. Thank you!
Regards,
Wen
1 Like
Hello Wen, thank you for joining our little coffee sorter community here
I feel with you about the pain of manual sorting. Didn’t do too much of it before deciding I want a machine, but had found myself in the middle of manual sorting when our first batch of coffee imported from Nepal arrived in parchment shell (and obviously unsorted) due to miscommunication. So, blue skin is Nepali English for silver skin, and white skin is parchment shell. Now I know 
Then: you’re sorting roasted beans? I can imagine that makes good sense as it’s quite easy to tell unripe beans apart after roasting. I have never heard of doing that job with optical sorters so far … would be a novel thing, and certainly good for the flavor …
Unfortunately I have no machine to recommend from personal experience yet. There are several Chinese machines selling for 12 - 15 kUSD, very similar to the one introduced to us here by @smallcolorsorter above. I believe that’s the minimum possible price right now. If you can find one of recommendable quality, maybe you could band together with other artisanal roasters in your area and get one machine together? In that case, you could mount it to a trailer to allow simple sharing between 4-10 locations. We have done something similar with a 1960s shop roaster we restored and mounted into an old firefighter equipment trailer:
For that, definitely talk to @oojoshua from Hawaii, who is determined to make the open source coffee sorter a reality and, like you, is well-versed in software engineering, has a makerspace etc… I am tempted to propose you join forces and finish this project. Sadly I can’t invest much time personally until end of August this year due to too many full-time jobs. But I’ll support you the way I can: tech feedback, making connections, some design work maybe.
1 Like
Hi, Matthias,
Thanks for the feedbacks! I will reach out to @oojoshua.
Sharing a sorter sounds like a interesting idea. Never thought about that. And it’s interesting to know the blue skin and white skin difference in Nepal
-Wen
1 Like
Hi , @wyang san
Thank you for your comment.
The machine on youtube can process only one pound per hour. The future target is up to 20 pounds per hour. How many pounds/h do you need ? I am struggling to reach the target such as mechanism and algorithm. I will share the progress on youtube and at next Maker fair Tokyo.
2 Likes