cancel
Showing results for 
Search instead for 
Did you mean: 

NanoEdge AI Studio Not Receiving Data from STWINBX1 Despite Correct Configuration

Mahdouch
Associate III

Hi everyone,

I’m currently working on a project involving predictive maintenance and anomaly detection using the STWINBX1 (STEVAL-STWINBX1) board. I’ve successfully configured the board and flashed it using STM32CubeIDE, ensuring everything is set up as expected. I’ve also downloaded the NanoEdge Datalogger and flashed it using STM32 ST-Link Utility, but despite everything being correctly configured, NanoEdge AI Studio is not receiving any data from the board.

Here’s what I’ve checked so far:

  1. The board is properly connected to my PC.
  2. I’ve verified the COM port number, and I'm sure it's correct.
  3. The NanoEdge Datalogger has been flashed successfully.
  4. The board’s sensors are properly connected and powered.

Despite these steps, the data is not being received in NanoEdge AI Studio. I’ve also ensured that no other processes are using the COM port, and I’ve checked that all configurations are aligned with the expected setup.

Can anyone suggest what could be causing this issue or guide me on where I might be going wrong? I need to collect data for training my model, and this issue is blocking my progress.

Thanks in advance!

1 ACCEPTED SOLUTION

Accepted Solutions

Hello @Mahdouch ,

 

I did it on my side with your parameter and it works.

But, it takes quite some time to have data; So much so that NanoEdge writes a warning message, but you can just ignore it.

Can you try to do it again, select the right COM port but wait 2 mins to see if you receive anything?

(the frequency is very high, but it takes a lot of time to copy 3*4096 values via serial)

 

In any case, working with buffers of 3*4096 is overkill. I suggest you try with 3*512 or less first and change if needed.

 

Also, if you are really doing a project, the sensor you selected has a frequency of 26kHz which is a lot. Even with a buffer of 4096, you are collecting data representing 0.15 seconds. I believe your board has other sensor, you should try to collect data representing at least 1s: buffer size * 1/frequency = 1seconds

 

Let me know if you still encounter an issue

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

View solution in original post

9 REPLIES 9
Julian E.
ST Employee

Hello @Mahdouch ,

 

You need both a ST Link to flash the firmware and to connect the board via USB C to send data.

You need to make sure to have data cable in both cases.

JulianE_0-1741597115627.jpeg

 

If you forgot to use the second cable, the COM port that you were using is probably the one from the ST Link, so don't forget to change it in the emulator.

 

Can you test to retrieve data in the "SIGNAL STEP" via serial. The behavior should be the same.

But if you can log data in Signals but not in the emulator, then the issue may be different.

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

Hello @Julian E.E.,

I’m using both cables as you suggested, one for the ST-Link to flash the firmware and the other for power supply and data communication via USB-C. However, NanoEdge AI is not detecting anything from the board. I’ve double-checked the connections, and the COM port is correctly set, but I’m still facing the issue, i don't receive no data in Signals nor in Model Training, (I got my signals from the dataloger2 successfully). Could you suggest anything else I might be missing?

Thanks.

Hello @Mahdouch 

While waiting for the feedback from the expert, let me suggest you a further check on your setup.

STEVAL-STWINBX1 is based on STM32U5, a double-bank flash microcontroller. By default, the firmware is flashed onto the first bank. Instead, after the execution of a firmware update via FOTA using the BLESensor app or by using specific commands while running DATALOG2 firmware, it’s possible to change the running flash bank.

Maybe you did it by mistake and, if this is your case, you flashed the NanoEdge AI datalogger onto the bank 2, but still trying executing firmware from bank 1.

To overcome this issue, FP-SNS-DATALOG2 contains the script called reset_and_program.bat that resets the board. It’s available in the folder Utilities\BoardReset\STWIN.box.

In alternative, you can use STM32CubeProgrammer, the option bytes section > User configuration and check SWAP_BANK. It must be unchecked.

SimonePradolini_0-1741942049594.png

 

The full procedure is also available in the FP-SNS-DATALOG2 User Manual (chapter 2.1.4 How to handle double bank flash memory) and Quick Start Guide.

Try running it, and then flash the NanoEdge AI datalogger.

 

I wish this can help you.

Best regards,

Simone

In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

Hello @Mahdouch ,

 

When you say that use the NanoEdge datalogger, are you talking about data loggers generated in NanoEdge AI Studio (datalogger generator) or a Function Pack?

 

Can you use a tera term or putty and send me a screenshot (or a csv would be better) of the data that you get.

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

@SimonePradolini 

I did as you said but stand still,

@Julian E. 

i use data loggers generated in NanoEdge AI Studio (datalogger generator).

Hello @Mahdouch ,

 

Thank you, I don't have board with me right now, 

I will try to replicate on Monday/Tuesday.

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

Hello @Mahdouch ,

 

I did it on my side with your parameter and it works.

But, it takes quite some time to have data; So much so that NanoEdge writes a warning message, but you can just ignore it.

Can you try to do it again, select the right COM port but wait 2 mins to see if you receive anything?

(the frequency is very high, but it takes a lot of time to copy 3*4096 values via serial)

 

In any case, working with buffers of 3*4096 is overkill. I suggest you try with 3*512 or less first and change if needed.

 

Also, if you are really doing a project, the sensor you selected has a frequency of 26kHz which is a lot. Even with a buffer of 4096, you are collecting data representing 0.15 seconds. I believe your board has other sensor, you should try to collect data representing at least 1s: buffer size * 1/frequency = 1seconds

 

Let me know if you still encounter an issue

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

@Julian E. 

Hi Julian,

Thank you so much—really, I sincerely appreciate all your effort and help! The 2-minute wait was a tricky one, but it worked. I also followed your advice, changed the sensor, and lowered the samples as you suggested, and it worked perfectly.

I truly appreciate your support. Thanks again!

Best regards,
Mahdouch