FP-AI-PREDMNT2 is an STM32Cube function pack that programs the STWIN as an IoT Edge node, connected to the cloud, able to acquire sensor data, process them and send the results to the DSH-PREDMNT cloud dashboard. It includes dedicated algorithms for advanced time and frequency domain signal processing and analysis of 3D digital accelerometers with flat bandwidth up to 6 kHz.
The function pack helps to jump-start the implementation and development of condition monitoring applications designed with the NanoEdge™ AI Studio solution, thus easily enabling an AI-based predictive maintenance solution (the NanoEdge™ AI library generation is out of the scope of this function pack and must be generated using NanoEdge™ AI Studio).
The package includes pressure, relative humidity and temperature sensor monitoring, as well as audio algorithms to check acoustic emission (AE), up to 20 kHz, and ultrasound emission analysis up to 80 kHz.
Using the STBLESensor app you can set up Wi-Fi credentials and exchange cloud certificates to enable the connection to the dedicated DSH-PREDMNT web-based dashboard. The dashboard allows monitoring and logging the algorithm output, sensor data and equipment status.
The FP-AI-PREDMNT2, together with the suggested combination of STM32 and ST devices, can be used to develop specific industrial predictive maintenance applications for early detection of warning signs of potential failure.
The software runs on the STM32 microcontroller and includes all the necessary drivers for the STEVAL-STWINKT1B evaluation kit.
FP-AI-PREDMNT2 firmware is based on application-level modules (Sensor Manager, Digital Processing Units, etc.) that you can reuse and easily extend to build a customized application.
These application modules adopt state-of-the-art design patterns and natively support low-power modes. To enable this solution, the function pack has been built on top of eLooM, an embedded Light object-oriented fraMework for STM32 applications specifically designed for embedded low-power applications powered by STM32.