AI helps 4-in-1 gas sensor become digital nose
These can range from the detection of spoiled food to bad breath and forest fires.
The BME688 measures gases, humidity, temperature and barometric pressure in a package measuring 3.0mm by 3.00mm by 0.9mm. The gas sensor detects the presence of multiple gases, including volatile organic compounds (VOCs), volatile sulfur compounds (VSCs) and other gas types such as carbon monoxide and hydrogen, in the parts per billion (ppb) range.
The sensor’s AI features and the BME AI-Studio software tool allow customers to develop custom solutions for their specific use cases. BoschSensortec also provides an Adafruit-compatible development kit.
The appropriate way to use the AI is to collect indicative real-life data directly in the field. For instance, by sampling gases in the vicinity of both fresh and decaying food, to thereby create different combination models for the VSCs present in the given air sample.
Once the sensor is trained, the final AI code runs on a system microcontroller in the customer’s end product. This AI code is generally lightweight and will run on the existing microcontroller that handles system control and management tasks.
The BME688 has been developed for mobile and connected applications where size and low power consumption play a critical role. Current consumption can be configured between 2.1microA and 11mA depending on the required data rates and functions. The BME688 is available now.
Related links and articles:
News articles:
Automotive sector helps AI chip startup raise $50 million
First self-learning edge AI sensor for wearables – video
Sensirion buys gas analysis startup
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
