Nano Edge AI Studio Generalized Model for one type of gearbox.

[amars7]

Hi,

I am trying to use NanoEdge AI to develop an N-class fault classification model for helical gearboxes that will eventually run on an STM32 MCU.

The challenge is that I have many different helical gearboxes, and their physical parameters vary significantly, including:

• Input RPM and output RPM
• Gear ratios
• Number of teeth
• Bearing types and sizes
• Gearbox dimensions and load capacities

I currently have around 20 fault classes that I would like the model to detect.

Has anyone successfully created a generalized model that can classify gearbox faults across multiple gearbox variants rather than training a separate model for each gearbox?

What would be the recommended approach in NanoEdge AI for handling such variability while still achieving good fault classification accuracy on embedded hardware? 

Any guidance, examples, or best practices would be greatly appreciated.

Thanks!

[Julian E.]

Hi ​@amars7,

 

This is indeed a challenge. Creating a generalized model is no easy task.

Did you try for the moment being to separate your gearboxes by types? What kind of results do you get?

And when you use all types in a single project, what kind of results do you get?

 

I’ll send you a private message. We may be interested to work a bit with you if you’d like.

We could help you see what is possible to do, and on our side, working on real use cases is always helpful to improve our tools.

 

Have a good day,

Julian