Doctoral dissertation

Krishna Mohan Mishra: Novel data extraction, feature extraction and fault detection techniques for elevator fault detection

Krishna Mohan Mishra.
In his doctoral dissertation, MSc Krishna Mohan Mishra presents novel data extraction, feature extraction and fault detection techniques for elevator fault detection in real-world environments. Aim of the Mishra’s research is to develop systems that can automatically detect the elevator faults commonly present in the systems. In addition, Mishra’s dissertation will help various predictive maintenance systems to detect false alarms, which will in turn reduce unnecessary visits of service technicians to installation sites.

Krishna Mohan Mishra’s dissertation focuses on presenting deep neural networks-based methods for the automatic detection of elevator faults in real-world environments. Condition monitoring is an essential part of every machine maintenance system. Elevators are frequently used by people nowadays, which requires proper maintenance and safety of elevators. Fault detection and diagnosis is very important in smooth functioning of elevator systems. Traditional methods are not very efficient in detecting faults. In this research, Mishra focused on developing deep learning models for efficient fault detection and diagnosis.

State of the art includes fault diagnosis methods having feature extraction methodologies based on deep neural networks and convolutional neural networks for rotatory machines similar to elevator systems. Fault detection methods for rotatory machines are also using support vector machines and extreme learning machines. However, to improve the performance of traditional fault diagnosis methods, Mishra developed an intelligent deep autoencoder model for feature extraction from the data and random forest performs the fault detection in elevator systems based on extracted features.

Mishra’s research also addressed the challenges of dimensionality reduction and robustness against overfitting characteristics. Mishra’s research includes calculation of highly informative deep features from raw sensor data along with existing features. All of the methods aimed at filling a gap.

The research was part of the Doctoral School of Faculty of Engineering and Natural Sciences, Tampere University and Novel Predictive Analytics Technologies for Future Maintenance Business (OPENS) project funded by Business Finland. Other collaboration partners included Åbo Akademi University (ÅAU). Krishna Mohan Mishra is originally from India and graduated as Master of Science from National College of Ireland.

The doctoral dissertation of MSc (Tech) Krishna Mohan Mishra in the field of Automation Technology and Mechanical Engineering titled Deep Neural Networks for Elevator Fault Detection will be publicly examined in the Faculty of Engineering and Natural Sciences at Tampere University at 12.00 on Friday 17th September 2021 in the Pieni Sali 1, of the Festia Building (Korkeakoulunkatu 8, Tampere). The Opponents will be Prof. Leif Kari from KTH Royal Institute of Technology, Sweden, and Dr. Jari Vepsäläinen from Aalto University, Finland. The Custos will be Prof. Kalevi Huhtala from the Faculty of Engineering and Natural Sciences, Tampere University, Finland.

The dissertation is available online at https://trepo.tuni.fi/handle/10024/133718

Photo by TTITO day

Upcoming events

Past events