Renesas adds neural network training to add AI to air quality sensor
Renesas has added embedded AI (e-AI) to its ZMOD4410 Indoor Air Quality (IAQ) sensor platform, enabling smart odour sensing for ventilation systems, bathroom monitoring and controls and air quality monitors.
The company has combined neural network-trained firmware on microcontrollers, such as the Renesas RL78, to provide higher resolution measurement results. With these new capabilities, the ZMOD4410 platform is capable of not only detecting gases in small enclosed rooms with higher accuracy and improved part-to-part deviation, but can also distinguish between sulphur- and ethanol-based odours, Renesas explains. The upgrades are the first in a family of e-AI-based firmware from the company.
The software-configurable ZMOD platform provides greater design flexibility for smart sensing systems, through firmware upgrades in the field to enable new, application-specific capabilities such as selective measurements to detect volatile organic compounds (VOCs). The upgrades enable IAQ measurement within international guidelines, allowing customers to measure total VOCs (TVOCs) and IAQ in the low parts-per-million range (ppm). The higher accuracy and consistency provides improved estimated carbon dioxide (eCO2) levels. The ZMOD4410 AI firmware can also be implemented on any Renesas microcontroller – including RE, RA, or RX devices – or other general-purpose microcontrollers.
The programmability, stability and sensitivity in measuring VOCs makes the ZMOD4410 suitable for use in smart HVAC systems, ventilator fans, and bathroom lights and switches.
The ZMOD4410 is based on proven metal oxide (MOx) material and each sensor is electrically and chemically tested to ensure consistency from lot to lot. The devices are also highly resistant to siloxanes for reliable operation in harsh applications.
The ZMOD4410 platform with AI and performance firmware is available now.