Bosch Sensortec 4-in-1 gas sensor with artificial intelligence

     Whether at home, in the office, or outdoors, users want to make sure the air around them is clean and safe to breathe – and the COVID-19 pandemic has amply demonstrated the importance of air quality. The ubiquitous particulate matter, gases and even airborne viruses in the modern environment, poor air quality, have an increasing negative impact on our health.

     To meet this growing demand, Bosch Sensortec has released the BME688, the first air quality MEMS sensor that combines gas, humidity, temperature and barometric pressure sensing with innovative artificial intelligence capabilities, creating the world's most compact 4-in-1 air quality sensor Measurement Solutions. This self-contained device enables customers to reduce total cost of ownership, shorten development time and simplify design.

     The new BME688 is ideal for innovative custom applications such as detecting food spoilage or timely detection of forest fires by measuring current gases, tracking changes in temperature and humidity. The artificial intelligence capabilities of the sensors and Bosch Sensortec's new BME AI-Studio software tool allow customers to quickly develop custom solutions directly for their specific use cases. To further reduce time-to-market, Bosch Sensortec also offers an Adafruit-compatible development kit.

     Based on Bosch Sensortec's proven BME680 platform, an updated version of the gas sensor built into the BME688 enables a wider measurement range and features advanced artificial intelligence capabilities. This gas sensor can now detect a variety of gases, including volatile organic compounds (VOCs), volatile sulfur compounds (VSCs), and other types of gases such as carbon monoxide and hydrogen, with a detection range of parts per billion (ppb).

     "The BME688 combines a reliable, high-precision sensor with extensive gas detection and innovative artificial intelligence capabilities," said Dr. Stefan Finkbeiner, CEO of Bosch Sensortec. next-generation applications of approach and sustainability.”

     For example, a customer may wish to develop a sensor-based product to detect spoiled food, which can be indicated by VSCs produced by bacteria in the food. In addition, bad breath or body odor can also be detected based on VSCs produced by bacteria.

     The best approach is to collect indicative real-life data directly in the field. For example, different combinatorial models of VSCs present in a given air sample can be modeled by sampling the gas near fresh and decaying food. The BME688 detects VSCs very accurately by default, while the BME AI-Studio can be optimized for other gas mixtures and applications.

     By sampling the gas in the field rather than in the laboratory, the derived algorithms employed by the new detection equipment are more reliable in assessing actual conditions. Along with the gas data, the BME688 measures humidity, barometric pressure and temperature simultaneously and is fed as supplemental data for full AI modeling.

     In our example application, the client classifies this large amount of data, which is then used in the development of an artificial intelligence model in BME AI-Studio, namely training the BME688's ability to recognize obvious signs of bacterial growth on food. After the sensor training is complete, the final AI code runs on the system microcontroller of the customer end product. This AI code is generally lightweight and can easily run on microcontrollers currently used to handle system control and management tasks.

     The BME688 is developed for mobile and connected applications where sensor size and low power consumption are critical. The sensor package is compact, measuring only 3.0 x 3.0 x 0.9 mm3. Current consumption is configurable between 2.1 μA and 11 mA depending on the desired data rate and functionality and is optimized by BME AI-Studio.