Modern insulin pumps allow humans with medical conditions to continue participating in the society and increase the quality of life. In some cases, an occlusion of the mechanism leads to insufficient insulin delivery. It can be easily balanced if noticed, but might lead to severe health risks, if undetected. We have the possibility to find patterns throughout the different sensors available and aim to increase functionality and safety. The goal of the project is to use both an adapted simulator and build a (simple) hardware-in-the-loop test stand, to simulate both virtual and real occlusion failures and find smart ways to detect them. We provide support in using the simulator, as well as in the design and manufacturing of the test setups.
Modern insulin pumps allow humans with medical conditions to continue participating in the society and increase the quality of life. In some cases, an occlusion of the mechanism leads to insufficient insulin delivery. It can be easily balanced if noticed, but might lead to severe health risks, if undetected. We have the possibility to find patterns throughout the different sensors available and aim to increase functionality and safety. The goal of the project is to use both an adapted simulator and build a (simple) hardware-in-the-loop test stand, to simulate both virtual and real occlusion failures and find smart ways to detect them. We provide support in using the simulator, as well as in the design and manufacturing of the test setups.
- Literature research and expert interviews to define the critical function and requirements- Adapting the available simulator to simulate occlusions
- Invent different ways to detect the occlusions, and find the most promising through testing
- Build a test setup to create and measure real occlusions
-Implement and validate the detection approaches with the setup
- Literature research and expert interviews to define the critical function and requirements- Adapting the available simulator to simulate occlusions - Invent different ways to detect the occlusions, and find the most promising through testing - Build a test setup to create and measure real occlusions -Implement and validate the detection approaches with the setup
- are interested in medtech and early phase product development in an industry setting - have programming experience in python - have experience in machine learning techniques, ideally relating to anomaly detection and predictive maintenance - are motivated to apply your knowledge by developing a functioning prototype - can acquire knowledge and skills in new fields quickly - are a team player, curious and come up with innovative ideas - are able to work self-reliant and refine your scope continuously
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
We focus on human-centred product development and regard the link between research and education as the key to excellence in training. We see ourselves as a partner for industry and promote the continuous transfer of knowledge through cooperation, as well as the training and further education of students and graduates to strengthen the competitiveness of mechanical engineering industry.
Master Thesis open now for Engineering and Computer Science students
Stephan Fox (pd|z)
CLA G 19.2
sfox@ethz.ch
Feasibility Lab @ pd|z:
fl.ethz.ch