This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TMDSCNCD28P55X: About training with example data at model composer GUI under Arc Fault Detection using Embedded AI model

Part Number: TMDSCNCD28P55X
Other Parts Discussed in Thread: TIDA-010955

Tool/software:

Hi, I was looking through this device's design guide and application in arc fault detection using embedded AI models.

This device is composed with TIDA-010955 and control card C2000.

I've trained 3 models at model composer as listed below, using example data provided by TI. (it can be found at 'Arc Fault Detection using Embedded AI models' document, 6.2 Data Uploading)

1. ArcFault_model_200

2. ArcFault_model_300

3. ArcFault_model_700

However, when I tested with just the DC current source into CT (pin J8), model 300 and 700 shows 'arc' at model composer GUI even without the arc generation.

Can you please have a look at those models that whether they work fine in TI's test environment or not?

It would be kind of you if test environment when example data was made can be provided such as inverter's switching frequency... etc.

Thank you for your support.

  • Hello Seungwoo

    After the model training, Edge AI studio provides 3 sets of test vectors and golden output. Can you check if the model output matches with the golden output when corresponding test vector is used as input? The procedure for testing with test vector is explained in the userguide.

    Thanks

    Amir