Thank you for your comment. Unfortunately, it is not an open-source project but you can share my mechanical idea. I made a youtube movie of my sorter. Please check!
The software works good but the picking unit does not work 100%. It has some vibration problems on the conveyer so far.
Your beans flipping wheel is really creative, actually. I had thought about this a lot as well, and so far the best idea I had was a chute made from glass and imaging the beans while they slide down there. It seems that the crumpling of the conveyor that is introduced by the beans flipping wheel causes some mechanical issues with the ejection mechanism later … but of course that’s just a small issue, as any new machine will have in the first iteration.
Hello @cj23, that’s great news! And thanks so much for registering here and telling us about your success I’d be interested to know your final accuracy when training the model! A few percentage points lower than optimum is no big deal … the problem I had was that most of my models did not even converge, and if they did, they would mostly not go higher than 82% accuracy.
Yes, that was the enabling action to bring this project back to life!
No big challenge left now, as far as I can see. Just some rather simple robotics control stuff with a RPi, camera, stepper motors and 3D printed parts. I have all the electronics around already, my only challenge is now to find the time to get it all done. But since I promised above to restart the work if somebody can figure out the image classifier, I’ll get it done eventually
Hello, I’m Kamil and I also built a bean sorting machine.
But I stopped at the classification of my bean seeds, I don’t know if it’s the fault of the photos or mine.
Are the pictures of my beans well taken?
But I also designed 3D and built a sorting machine with a 3D printer similar to Toshota, but I have a better bean feed.
For me, the beans follow the beans at intervals.
I would like to cooperate, I can design a modular bean machine (easy replacement of broken elements and quick assembly).
Currently, my machine is lying undressed in a corner.
But I can create, show a video of the action.
Put it in a package and send it to Matthias so you can only do the program because I am weak in it.
Of course, the machine will be ready for operation with a power supply, a control unit and a stepper motor for an even grain feed.
If the project is alive and you are interested in it, I am able to create and send you work videos.
Of course, at the program keep an eye on my beans
I’m from Poland, I’m an electronics technician, I’m a farmer.
I’m waiting for an answer.)
@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!
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.
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:
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.
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?
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).