BME688 AI Application fails

[bsec]

HI,

I created 2 AI models, one for coffee similar to the youtube video and one for foul vegetables. Both algorithms produce probabilities > 95%. I checked the configuration file output from AI Studio with 3 different applications: Arduino ESP32 (exact the ino example in BSEC 2.0), ESP32 in eclipse development environment and on a STM32 nucleo platform, all linked with libalgobsec.a (depending of the MCU used). In every test I get the result Gas Estimate 1 (normal air -> 1.0). Whatever I do I never get any probability > 0.0 in Gas Estimate 2, even if probe within the Coffee glas or in the fouled vegetable container. Any experience with BME688?

For sampling I used BME 688 dev kit board (8 sensors) on Adafruit HUZZAH32

BR

[BSTRobin]

Hello bsec,

Recommend you to put the trained config string into SD card of same EKB board(which is used to collect the data) and have a test on the target gas. Could have a try and give feedback?

[bsec]

Hi,

thanks for reply. I got a .config file from the AI. What happens, if I put it back to the SD Card? Does the ESP32 generate a log file instead of sampling new data? Any documentation for the steps you suggest?

BR

Bernd

[BSTRobin]

Hello bsec,

After you got config file, you could import it to BSEC example and run it. You could download BSEC package from here:

https://www.bosch-sensortec.com/software-tools/software/bme688-software/

There are deriver code, example code, integration guide under BSEC package. You could refer integration guide to do step by step operation.

[bsec]

Hi,

this ist exact the software I use and I have problems with! Whatever I measure coffee, foul vegetables, every time class normal air is returned 

BR

Bernd