Krishna Mohan Mishra

Mr. Krishna Mohan Mishra

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 July 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KMKrishna Mohan Mishra
Krishna Mohan Mishra
KHKalevi Huhtala
Kalevi Huhtala
In this paper, we propose a new algorithm for data extraction from time-series data, and furthermore automatic calculation of highly informative deep features to be used in fault detection. In data extraction, elevator start and stop events are extracted from sensor data including both acceleration and magnetic signals. In addition, a generic deep autoencoder model is also developed for automated feature extraction from the extracted profiles. After this, extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The remaining healthy data are used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved above 90% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperforms results using existing features. Existing features are also classified with random forest to compare results. Our developed algorithm provides better results due to the new deep features extracted from the dataset when compared to 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.

1 September 2019
Verified
Conference Paper
Closed access
KMKrishna Mohan Mishra
Krishna Mohan Mishra
KHKalevi J. Huhtala
Kalevi J. Huhtala
In this research, we propose a generic multilayer perceptron (MLP) neural network model based on deep learning algorithm for automatic calculation of highly informative deep features from the elevator time series data and based on extracted deep features faults are detected. Sensor data are labelled as healthy or faulty based on the maintenance actions recorded. The remaining healthy data are used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved nearly 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features. Existing features are also classified with random forest (RF) to compare results. Multilayer perceptron neural network model based on deep learning approach provides better results due to the new deep features extracted from the dataset compared to existing features. Cross-validation method used with multilayer perceptron plays a significant role in improving accuracy of fault detection. Our model provides good classification and is robust against overfitting characteristics. This research will help various predictive maintenance systems to detect false alarms, which will reduce unnecessary visits of service technicians to installation sites.

1 May 2019
Verified
Conference Paper
Closed access
KMKrishna Mohan Mishra
Krishna Mohan Mishra
TKTomi R. Krogerus
Tomi R. Krogerus
KHKalevi J. Huhtala
Kalevi J. Huhtala
In this research, we propose a generic deep autoencoder model for automated feature extraction from the raw sensor data. Extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The remaining healthy data is used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features. Existing features are also classified with random forest to compare results. Deep autoencoder random forest provides better results due to the new deep features extracted from the dataset when compared to existing features. Our model provides good classification and is robust against overfitting characteristics. This research will help various predictive maintenance systems to detect false alarms, which will reduce unnecessary visits of service technicians to installation sites.

1 January 2020
Verified
Conference Paper
Open access
KMKrishna Mohan Mishra
Krishna Mohan Mishra
KHKalevi Huhtala
Kalevi Huhtala

1 July 2019
Verified
Conference Paper
Closed access
KMKrishna Mohan Mishra
Krishna Mohan Mishra
TKTomi R. Krogerus
Tomi R. Krogerus
KHKalevi J. Huhtala
Kalevi J. Huhtala
In this paper, we propose a new algorithm for data extraction from time series data, and furthermore automatic calculation of highly informative deep features to be used in fault detection. In data extraction elevator start and stop events are extracted from sensor data including both acceleration and magnetic signals. In addition, a generic deep autoencoder model is also developed for automated feature extraction from the extracted profiles. After this, extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The remaining healthy data are used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved nearly 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperforms results using existing features. Existing features are also classified with random forest to compare results. Our developed algorithm provides better results due to the new deep features extracted from the dataset when compared to 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.

1 January 2019
Verified
Conference Paper
Open access
KMKrishna Mohan Mishra
Krishna Mohan Mishra
TKTomi Krogerus
Tomi Krogerus
KHKalevi Huhtala
Kalevi Huhtala