FP-AI-PDMWBSOC is an STM32Cube function pack for the STEVAL-PROTEUS1, able to get motion sensor data, process them to make anomaly detection and faults classification, and send the results to the STBLESensClassic mobile app, a PC terminal console and on Azure IoT central dashboard.
The function pack helps to explore the implementation and development of a predictive maintenance application that embeds the NanoEdge AI library middleware, capable to provide an AI-based solution (the NanoEdge AI libraries are generated using NanoEdgeAIStudio).
Using the datalogging binary file, the raw data can be extracted from the sensors inside the STEVAL-PROTEUS1 board and provided to the NanoEdgeAIStudio software to extract machine learning libraries for anomaly detection and classification.
These NanoEdge AI libraries, customized and built on the classified set of data, can be easily updated inside the framework architecture proposed, facilitating the early detection of warning status and potential failure within the equipment.
FP-AI-PDMWBSOC implements two different HMI communication tools at user level: a wired interactive CLI (USB CDC) to configure the node and manage the learning, detecting and classifying phases, and the STBLESensClassic app with dedicated pages to provide the same functionalities. The STBLESensClassic mobile app works also as a bridge to display data on Azure IoT Central dashboard.
To start/stop the learning, detecting and classifying phases, an additional control, indicated by LEDs, can be performed by just pressing the user button.
The NanoEdge libraries functionalities are based on a set of application-level modules (Sensor Manager, Digital Processing Unit, EM Data, PnPLCompManager), useful to reuse and easily extendable to build other customized applications.