Condition monitoring of elevator using deep learning and frequency analysis approach

Krishna Mohan Mishra, John-Eric Saxen, Jerker Björkqvist, Kalevi Huhtala

Research output: Other contributionpeer-review


In this research, we propose automated deep learning feature extraction technique to calculate new features from fast fourier transform (FFT) of data from a accelerometer sensor attached to an elevator car. Data labelling is performed with the information provided by maintenance data. Calculated features attached with class variables are classified using random forest algorithm. We have achieved 100% accuracy in fault detection along with avoiding false alarms based on new extracted deep features, which outperforms results using existing features. This research will help various predictive maintenance systems to detect false alarms, which will in turn reduce unnecessary visits of service technicians to installation sites.
Original languageEnglish
Publication statusPublished - 2021
MoE publication typeO2 Other


Dive into the research topics of 'Condition monitoring of elevator using deep learning and frequency analysis approach'. Together they form a unique fingerprint.

Cite this