Build And Deploy Edge Devices Trained Using Machine Learning

- Advertisement -

• STMicroelectronics along with Cartesiam has introduced an STM32-based software pack for industrial condition monitoring
• It simplifies prototyping and validation without requiring any specialised AI expertise, facilitating data collection under any operating conditions

STMicroelectronics in collaboration with Cartesiam has developed an STM32-based software function pack, the FP-AI-NANOEDG1 software pack that allows users to quickly build, train, and deploy intelligent edge devices for industrial condition monitoring using a microcontroller Discovery kit.

The pack contains all the necessary drivers, middleware, documentation and sample code to capture sensor data, integrate and run Cartesiam’s NanoEdge libraries, thus simplifying prototyping and validation on STM32 development boards, before deploying on customer hardware. Without any specialist AI skills, users can quickly create and export custom machine-learning libraries for their applications using Cartesiam’s NanoEdge™ AI Studio tool. 

Complete data analysis

Cartesiam has implemented industrial-grade sensors on-board a Discovery kit such as the STM32L562E-DK for capturing vibration data from the monitored equipment both under normal and abnormal operating modes. Software to configure and acquire sensor data is included in the function pack. NanoEdge AI Studio analyses the benchmark data and selects pre-compiled algorithms from over 500 million possible combinations to create optimised libraries for training and inference. The function-pack software provides stubs for the libraries that can be easily replaced for simple embedding in the application. Once deployed, the device can learn the normal pattern of the operating mode using machine learning, during the initial installation phase as well as during the lifetime of the equipment.

- Advertisement -

Low cost development

Using the Discovery kit to acquire data, generate, train and monitor the solution, developers can quickly create a proof-of-concept model at low cost and easily port the application to other STM32 microcontrollers. As an edge device, unlike alternatives that rely on AI in the cloud, the solution allows equipment owners greater control over potentially sensitive information by processing machine data on the local device.

The FP-AI-NANOEDG1 function pack is available now from the website of STMicroelectronics. 

The STM32L562E-DK Discovery kit, which contains a STM32L562QEI6QU ultra-low-power microcontroller, an iNEMO™ 3D accelerometer and 3D gyroscope, as well as two MEMS microphones, a 240×240 colour TFT-LCD module, and onboard STLINK-V3E debugger/programmer is can be obtained from STMicroelectronics’ website or distributors.