Test Spin with ST’s Machine-Learning Software for Connected Devices and Industrial Equipment

By Rich Nass

Executive Vice President

Embedded Computing Design

July 28, 2022


Test Spin with ST’s Machine-Learning Software for Connected Devices and Industrial Equipment

Upon visiting the STMicroelectronics booth at the recent embedded world trade show, I stumbled across some interesting software aimed at developing your own machine-learning applications.

Dubbed NanoEdge AI Studio, the software is for designers looking to implement Edge-based AI applications versus those that run in the Cloud.

The software I saw was version 3, which ST acquired when it picked up Cartesiam earlier this year. Apparently, this version is a major upgrade of the software tool.

When I got home, I decided to take the NanoEdge AI Studio for a spin. The tool walks you through each of the various inputs, offering guidance along the way. Even for someone like me, with little experience with the technology, it was pretty easy to navigate.

I learned from the literature that this latest version contains enhanced algorithms, which can better predict the future behavior of equipment over time, as well as any anomalies you can expect. In addition, assuming you are using an ST development board, it was easy to acquire the sensor information and then understand what that information was telling me. Note that native support is included for all STM32 development boards, meaning that no configuration is required.

The goal of the software is to improve industrial processes, optimize maintenance costs, and deliver the necessary functions in equipment that can sense, process data, and act locally to improve latency and information security. Potential applications include connected devices, household appliances (white goods), and industrial automation. And the tool makes it easier to integrate machine-learning capabilities existing equipment.

Included in this latest release are the prediction capabilities for things like regression and outlying libraries. Security is enhanced with the help of local data storage and processing, eliminating the back and forth with the Cloud.

Richard Nass’ key responsibilities include setting the direction for all aspects of OSM’s ECD portfolio, including digital, print, and live events. Previously, Nass was the Brand Director for Design News. Prior, he led the content team for UBM’s Medical Devices Group, and all custom properties and events. Nass has been in the engineering OEM industry for more than 30 years. In prior stints, he led the Content Team at EE Times, Embedded.com, and TechOnLine. Nass holds a BSEE degree from NJIT.

More from Rich