High accuracy 2-axis inclinometer embeds machine learning core - Embedded.com

High accuracy 2-axis inclinometer embeds machine learning core

A new high accuracy low-power, 2-axis digital inclinometer from STMicroelectronics includes an embedded programmable machine learning core to integrate AI algorithms in the sensor itself and reduce power consumption and reduce data transfer to the cloud.

Whereas many high accuracy inclinometers are single-axis devices, the new 2-axis IIS2ICLX accelerometer can sense the tilt with respect to a horizontal plane along two axes (pitch and roll) or, by combining the two axes, can measure the tilt with high and repeatable accuracy and resolution with respect to a single direction of the horizontal plane over a range of ±180°. The digital output simplifies system design and reduces bill-of-materials (BOM) cost by saving external digital-to-analog conversion or filtering.

Using MEMS accelerometer technology, the IIS2ICLX inclinometer has a selectable full scale of ±0.5/±1/±2/±3g and provides outputs over an I2C or SPI digital interface. Embedded compensation maintains stability over temperature to within 0.075mg/°C, ensuring high accuracy and repeatability even when ambient temperatures undergo extreme fluctuations. Its ultra-low noise density of 15μg/√Hz enables high-resolution tilt sensing as well as sensing of low-level, low-frequency vibration, as required in structural-health monitoring.

The sensing element is manufactured using a dedicated micromachining process developed by STMicroelectronics to produce inertial sensors and actuators on silicon wafers. The IC interface is manufactured using a CMOS process that allows a high level of integration to design a dedicated circuit which is trimmed to better match the characteristics of the sensing element.

The combination of high stability and repeatability, high accuracy and high resolution make the inclinometer particularly suited to industrial applications such as antenna pointing and monitoring, platform leveling, forklift and construction machines, leveling instruments, equipment installation and monitoring, and installation and sun tracking for solar panels, as well as Industry 4.0 applications such as robots and autonomous guided vehicles (AGVs).

In structural-health monitoring, accurately measuring inclination and vibration can help assess the integrity of structures such as tall towers and infrastructure like bridges or tunnels. Affordable, battery-powered MEMS tilt sensors containing the IIS2ICLX enable many more structures to be monitored for safety than has been economically viable using earlier, more expensive technologies.

Connecting external sensors and embedded machine learning core
The IIS2ICLX can be configured to generate interrupt signals activated by user-defined motion patterns. External sensors such as accelerometers, gyroscopes and pressure sensors can be connected to it using the sensor hub feature. This data can be used as input of up to 16 programs in the embedded finite state machine, all 16 of which are independent with each one having its dedicated memory area and being independently executed. An interrupt is generated when the end state is reached or when some specific command is performed.

ST IIS2ICLX machine learning core
The inclinometer embeds a dedicated core for machine learning processing, allowing some algorithms run in the application processor to be moved to the MEMS sensor. (Image: STMicroelectronics)

The inclinometer also embeds a dedicated core for machine learning processing that provides system flexibility, allowing some algorithms run in the application processor to be moved to the MEMS sensor, enabling a reduction in power consumption. The machine learning core logic provides the ability to identify if a data pattern (for example motion, pressure, temperature, magnetic data) matches a user-defined set of classes. Typical examples of applications could be anomalous vibration recognition, complex movement or condition identification and activity detection. The IIS2ICLX machine learning core works on data patterns coming from the accelerometer, but it is also possible to connect and process external sensor data (from a gyroscope or additional external inclinometer/ accelerometer, temperature or pressure sensors) by using the sensor hub feature. The results of the machine learning processing are available in dedicated output registers readable from the application processor at any time.

In order to develop applications using the IIS2ICLX, ST provides specific software libraries to support sensor calibration and real-time computation of tilt angle. These software libraries are part of the X-CUBE-MEMS1 expansion software package for STM32Cube.

The IIS2ICLX is housed in a high-performance ceramic-cavity LGA package measuring 5mm x 5mm x 1.7mm, with an operating temperature range of -40°C to +105°C. It is available now in sample quantities.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.