Elevator Failure Prediction: Predictive Maintenence Dataset

Datasets from a variety of IoT sensors for predictive maintenance in the elevator industry. The data is useful for predictive maintenance of elevators doors in order to reduce unplanned stops and maximize equipment life cycle.

The dataset contains operation data, in the form of time series sampled at 4Hz in high-peak and evening elevator usage in a building (between 16:30 and 23:30). For an elevator car door the system we consider: Electromechanical sensors (Door Ball Bearing Sensor), Ambiance (Humidity), and Physics (Vibration).

Target: Vibration (predict the absolute value of vibration)

Acknowledgements

Cristian Axenie; Stefano Bortoli,
https://zenodo.org/record/3653909