Welcome to our future plans for the Plastic Scanner project. We are excited to continue our progress from last year and make even more advancements in our understanding and application of infrared spectroscopy!
At the beginning of last year, our understanding of infrared light was limited, and we had no open source development board or clear vision of how the device should look like. But with the help of our dedicated team and the support of many individuals and organizations, we were able to make significant progress on all fronts. We developed a better understanding of infrared light and its applications, created an open source development board, and started to envision the embodiment of the device.
This year, we have some exciting plans that will take us even closer to our goal. We will continue to optimize the shape of the sensor cavity, use machine learning models, implement a continuous documentation system, and integrate all of the individual parts. With these plans in place, we are confident that we will be able to make a real step forward to the Plastic Scanner as a commodity and in the fight against plastic pollution. Here is a bit more detail about the different plans:
Get involved in the development of the Plastic Scanner, created for and by makers. We’re searching for problem-solvers with diverse backgrounds and skill sets who are willing to contribute their skills to address societal issues. With a focus on improving spectroscopy, writing coding, and continuous integration, we aim to create a practical and effective solution. Be a part of the progress and join us in making a difference.
🔬 Spectroscopy – determine Optimal distance between sample and sensor
🙋Taken by: Peter 🎉 We want to find the optimal distance between the PCB and the sample. Each LED has a little lens that shines light on a specific area of the plastic. Find out which height of spacer works best
➡️Prerequisites: Does not require a specific endeavor to be ready ⏱️Duration: 5 afternoons 📃Expected outcome: A document with the measured values and recommendation of the best measurement height
🔬 Spectroscopy – characterize optics
🙋Taken by: Queena 🎉 We want to know the spectral response of the infrared LEDs and the sensitivity of the InGaAs detector.
➡️Prerequisites: Requires the optimal distance to be known ⏱️Duration: 2 weeks 📃Expected outcome: Document and data about the LEDs and the compatibility with the InGaAs sensor.
🔬 Spectroscopy – Most important LEDs
We want to know which LEDs give the most information about the plastic type, and see if we can do with less LEDs. Can be done by theory or with practical experiments.
➡️Prerequisites: Does not require a specific endeavor to be ready ⏱️Duration: 5 afternoons 📃Expected outcome: A document with the tradeoffs of each LEDs
💻 Coding- Compare datasets
🙋Taken by: Hendrik 🎉 We have scanned quite different plastics with multiple spectrometers. what can we learn from comparing these different datapoints?
➡️Prerequisites: does not require any previous endeavor to be done ⏱️Duration: 5 afternoons 📃Expected outcome: A visualization of the good and bad of each dataset, and hopefully some interesting insights.
💻 Coding- Write Machine learning model
Based on the data we can get some 3D scatter plots, but the goal is to have a computer do the interpretation.
➡️Prerequisites: Does not require a specific endeavor to be ready ⏱️Duration: 2 weeks 📃Expected outcome: a pre-trained model with explanation, scikit learn or tensorflow
💻 coding- determine data flow/storage
The size of the measurement data is quite low, but ultimately we would like to function the device fully offline, with the possibility to update a pretrained model once in a while
➡️Prerequisites: Does not require a specific endeavor to be ready ⏱️Duration: 2 weeks 📃Expected outcome: a example program/setup with dummy data
💻 coding- Squeeze the bug
We sometime run in situations where we dont know whats happening. Help us what is wrong in our python programming
➡️Prerequisites: we need to have buggy code ⏱️Duration: ongoing 📃Expected outcome: code that works 😉
💻 coding- Streamline PS plot
We have the PS plot software to display the raw readings, but we would also like to make an advanced version that processes the data and displays it in a 3D scatter plot for example.
➡️Prerequisites: Knowing how to work with QT ⏱️Duration: 2 weeks max 📃Expected outcome: visualization software for the DB2.1
🎥 video- Capture the spirit
Throughout the year we are going to work on some cool projects, it would be cool to capture this by video or photo
➡️Prerequisites: can be done at any time ⏱️Duration: a couple of days 📃Expected outcome: Videos or photos of the project
🔧 Integration – build the measurement setup
To analyse if software improvements work, or if hardware modifications have a good outcome it is good to have a “standardized” platform to do a variety of tests.
➡️Prerequisites: some prior hardware prototyping skills ⏱️Duration: 3 weeks 📃Expected outcome: something like an optical breadboard to setup various experiments
🔧 integration- Build minimal viable product
Build a prototype to capture plastic scans in the work, so something that is battery-powered (with wifi connectivity?) to get more different readings.
➡️Prerequisites: Some prior hardware prototyping skills ⏱️Duration: 4 weeks 📃Expected outcome: A device with an interface for input and a screen for output, to capture data
Last year, in 2022 we already completed some quite cool endeavors, you can see them here:
Are you ready to join the Plastic Scanner team? and be the next to complete another endeavor? Drop us an email with some information about yourself and which of the previously mentioned endeavors you want to work on.
In order to place the endeavors in the greater scheme of things, we have specific milestones we want to reach. We want to achieve these milestones sequentially, this makes it a plan, not a planning. We do not make any promises about when these milestones will be reached, it needs to stay fun for us to develop.
Proof of concept
Can distinguish PET from other plastics
Minimal Viable Product
Can determine 4 types of plastic from each other
Decent Plastic Scanner
Can determine 4 types of plastic in a portable manner
Great Plastic Scanner
Is easy to replicate and can determine more than 4 types of plastic