Product overview
Key Benefits
Automatic ML model generator
NanoEdge AI Studio selects the best ML algorithm for a given MCU (low code / no code solution).
End-to-end edge AI deployment
No expertise required. Create tiny, state-of-the-art AI models for MCUs in record time.
Part of the ST Edge AI Suite
A collection of free online tools, case studies, and resources to support engineers at every stage of their edge AI development.
Description
NanoEdge™ AI Studio (NanoEdgeAIStudio) is a new machine learning (ML) technology to bring true innovation easily to the end-users. In just a few steps, developers can create an optimal ML library for their project, based on a minimal amount of data.
NanoEdge™ AI Studio, also called the Studio, is a PC-based push-button development studio for developers, which runs on Windows® or Linux® Ubuntu®.
One of its significant advantages is that NanoEdge™ AI Studio requires no advanced data science skills. Any software developer using the Studio can create optimal tinyML® libraries from its user-friendly environment with no artificial intelligence (AI) skills.
The Studio can generate four types of libraries: anomaly detection, outlier detection, classification, and regression libraries.
These libraries can be combined and chained to create a complete edge AI solution: anomaly or outlier detection to detect a problem on the equipment, classification to identify the source of the problem, and regression to extrapolate information and provide real insight to the maintenance team.
The input signals can range from vibration to pressure, sound, magnetic, time of flight just to name a few, or even a combination of several signals. Multiple sensors can be combined, either in a single library, or using multiple libraries concurrently.
Both learning and inference are done directly inside the microcontroller by means of the NanoEdge™ AI on-device learning library, which streamlines the edge AI process and significantly reduces development effort, cost and therefore time to market.
-
All features
- Desktop tool for the design and generation of STM32-optimized libraries with small datasets:
- Anomaly detection libraries: Learn normality directly on the STM32 microcontroller and detect defects in real time
- One-class classification libraries: Perform the acquisition during normal equipment operation and detect any abnormal pattern deviation
- N-class classification libraries: Classify signals in real time
- Extrapolation libraries: Predict discrete values based on data patterns never seen before
- Support for any type of sensor for a variety of physical quantities: multiaxis acceleration, current, magnetic field, voltage, temperature, acoustic pressure, and more
- Millions of possible algorithms are available to find the optimal library in terms of accuracy, confidence, inference time, and memory footprint
- Generation of very small footprint libraries running down to the smallest Arm® Cortex®‑M0 microcontrollers
- Integrated tools such as:
- Sampling finder tool to select the right data rate and the right data length easily
- Datalogger generator to get ready to log data in a few clicks
- Data manipulation tool for datasets
- ML libraries benchmark to find the best combination between preprocessing and machine learning models
- Embedded emulator to test library performance live with an attached STM32 board or from test data files
- Inference time estimation to help users make an informed choice for model selection
- Validation tool to compare the libraries given by NanoEdge™
- Native support for STM32 development boards, no configuration required, and easy portability across the various microcontrollers based on the Arm® Cortex®‑M processor
- Desktop tool for the design and generation of STM32-optimized libraries with small datasets:
Get Software
Featured Videos
Condition Monitoring solution for Predictive maintenance is available in FP-AI-NANOEDG1 function pack for STM32Cube.
