Ultra-compact system-in-package able to execute signal processing and AI algorithms in the edge for enhanced always-on industrial solutions

Running anomaly detection in sensors represents a major innovation in predictive maintenance for industrial applications and offers significant advantages in system-level power efficiency, downtime reduction, and maintenance costs.

The challenge for designers who want to monitor warning signs of imminent equipment failure is how to build reliable battery-operated sensor nodes for predictive maintenance applications.

We have created a new generation of smart sensors embedding an AI network accelerator, paired with a developer tool (NanoEdge AI Studio) that allows anyone to easily create powerful Machine Learning libraries. With this innovation, ML operations, such as anomaly detection with on-target learning, can be performed directly in the sensor with a very reduced power budget.

With ISM330ISN, leveraging AI in the edge, you can move part of the artificial intelligence closer to the data acquisition, so the anomaly detection application can run in the sensors. Once the anomaly is detected, the sensor wakes up the host processor for further intervention. NanoEdge AI Studio offers a quick and intuitive approach to build anomaly detection applications in sensors.


Key features

  • Embedded ISPU: ultra-low-power, high-performance programmable core to execute signal processing and AI algorithms in the edge for a seamless digital-life experience
  • Sensor hub feature to efficiently collect data from additional external sensors (up to 4 external sensors) and make them intelligent
  • 3-axis accelerometer with selectable full scale: ±2/±4/±8/±16 g
  • 3-axis gyroscope with selectable full scale: ±125/±250/±500/±1000/±2000 dps
  • Low-power consumption: 0.59 mA in high-performance mode, 0.46 mA in low-power mode (gyroscope + accelerometer only, ISPU not included



  • Low noise: 70 μg/√Hz in high-performance 
  • SPI / I²C serial interface
  • Analog supply voltage: 1.71 V to 3.6 V with independent IO supply (1.62 V)
  • Temperature range from -40 to +85 °C
  • Embedded temperature sensor
  • Compact footprint: 2.5 mm x 3 mm x 0.83 mm
  • ECOPACK and RoHS compliant

Application examples

predictive maintenance Anomaly detection and condition monitoring
industrial robot Industrial robots tilt calculation
asset tracking Asset tracking
home automation Event detection in alarms and smart homes


Recommended resources


NanoEdge AI Studio: automated Machine Learning (ML) software tool for ISPU

Our NanoEdge™ AI Studio is an easy-to-use Machine Learning (ML) tool that brings true innovation to companies. In just few steps, developers can create an optimal ML library for their project, based on a minimal amount of data, to enable motion pattern recognition or anomaly detection applications.

Sensor software expansion package for STM32Cube

The X-CUBE-ISPU software package provides libraries and examples to easily program ISPU MEMS devices. Developers can quickly implement custom C codes or configuration files created directly in the sensor using our NanoEdge AI Studio software tool.




Evaluation kit for always-on ISM330ISN 6-axis inertial module with embedded ISPU

Designed for use with NanoEdge AI Studio, this kit comes with a main sensing board and adapter board to ensure compatibility with our ready-to-use STM32 Nucleo boards (X-NUCLEO-F401RE X-NUCLEO-IKS01A3).




  • 予知保全への第一歩としての異常検出
  • ISPUの付加価値
  • NanoEdge AI Studioによるセンサのプログラミング
  • ファンでの異常検出のデモ
  • 結論と要点:絶対圧大気圧センサのためのMEMSピエゾ抵抗方式テクノロジーの概要