Dataset Description

This dataset is intended to accompany a hardware demo kit available from STMicroelectronics to show the potential for using the STMicroelectronics / SensiML solution to rapidly build time-series smart sensor data classification algorithms to translate raw physical sensor data into application-specific insight events using pattern recognition.  The hardware kit consists of the STMicroelectronics STBox evaluation board contained in a plastic enclosure and mounted atop a basic axial fan motor along with various fixtures that can be used to generate physical vibration events as might be deemed of interest for a fan monitoring application.  Such events include blade impingement, hub imbalance, and chassis shock.  Classification of motor state includes these events along with vibration detection of motor on and off states.

All classifications of fan events are based on monitoring only vibration/motion as detected by the STBox on-board inertial measurement unit (6-axis accelerometer and gyro sensor IC).  In such way, the demo simulates a common desired use case in industrial predictive maintenance applications for an over-the-top sensor system that can detect equipment usage, fault states, and degrading performance with minimal or no incursion into existing electromechanical systems used for control and operation.

The dataset consists of captured sessions of raw IMU sensor values sampled at 416Hz.  Each session contains labeled segments of a given fan state/classification type from amongst the following class map of events for recognition:

Event # Name Description
0 Unknown Board is undergoing some unrecognized movement
1 Blade Fault Fan unit has an obstruction in the blades
2 Flow Blocked Air input of the fan is blocked
3 Off Fan unit is turned off
4 On Fan unit is turned on and in ‘normal’ operation state
5 Guard Tamper Something is touching/tapping the blade guards of the fan unit
6 Mount Fault Frame of the fan unit is not stable
7 Tapping Something is tapping the fan unit from the top side

Depending on various factors like table surface, AC frequency, and other unknowns in your work space the demo may not work well under your specific conditions. We suggest you to collect data with your own fan demo unit and combine with the data we provided.

This is a perfect example of how-to retrain the demo with more variance data so that it can build a more advanced algorithm that works under all conditions.

The tutorial we are going to build a predictive maintenance application for a fan unit can be found here.