Home >

Building A Tensorflow Lite Neural Network Vibration Classifier, With A Little Help From DSP

John Edwards - Watch Now - Duration: 01:03:14

Building A Tensorflow Lite Neural Network Vibration Classifier, With A Little Help From DSP
John Edwards
This presentation will walk through a Python Notebook that uses a combination of DSP and a Convolutional Neural Network (CNN) to classify multiple vibration modes of a rotating machine.
The key to developing an efficient vibration mode classifier is the use of DSP algorithms to optimize the task.
The DSP functions will pre-process the data to allow a simpler Neural Network to be used for the classification.
The CNN will use a Tensorflow model that is trained on the supplied data, it will then use the model to classify new data.
We will also include the code to generate and test both the Tensorflow and Tensorflow Lite models.
Once generated, we will test the Tensorflow Lite model to ensure it classifies the data as well as the floating point model.
M↓ MARKDOWN HELP
italicssurround text with
*asterisks*
boldsurround text with
**two asterisks**
hyperlink
[hyperlink](https://example.com)
or just a bare URL
code
surround text with
`backticks`
strikethroughsurround text with
~~two tilde characters~~
quote
prefix with
>

Kelly_C
Score: 0 | 2 months ago | 1 reply

Hi John, nice talk. Where would I find tutorial background information that would help with design tradeoffs?

john.edwardsSpeaker
Score: 0 | 2 months ago | no reply

Hi Kelly,
Thank you very much for your kind words.
Unfortunately, I'm not aware of any material of that kind, I guess because it is such a new topic of interest.
The best thing to do is search for published articles. This is a good example, although it uses Wavelets rather than the FFT - https://www.hindawi.com/journals/sv/2020/1650270/
Good luck in your search.
Best regards,
John

john.edwardsSpeaker
Score: 0 | 2 months ago | no reply

Please do submit any questions here and I will be glad to answer them.
I'll be online straight after the video finishes
Source code and test datasets can be downloaded from here: https://github.com/Numerix-DSP/DSP_And_ML_Examples

OUR SPONSORS