Lokukaluge Prasad Perera

Postdoc WP2/WP3 (2015–2017)

LinkedIn

Publications (SFI Smart Maritime)

Scientific Journal Papers

Perera, Lokukaluge Prasad; Mo, Brage Machine Learning based Data Handling Framework for Ship Energy Efficiency. IEEE Transactions on Vehicular Technology 2017 (0018–9545) Vol. 66 (10), s. 8659–8666.

Pascoal, R; Perera, Lokukaluge Prasad; Guedes Soares, Carlos Estimation of Directional Sea Spectra from Ship Motions in Sea Trials. Ocean Engineering 2017 (0029–8018).

Perera, Lokukaluge Prasad; Mo, Brage Marine Engine-Centered Data Analytics for Ship Performance Monitoring. Journal of Offshore Mechanics and Arctic Engineering 2017 (0892–7219) Vol. 139 (2).

Perera, L.P. Marine Engine Centered Localized Models for Sensor Fault Detection under Ship Performance Monitoring, In Proceedings of the 3rd IFAC Workshop on Advanced Maintenance Engineering, Service and Technology (AMEST’16), Biarritz, France, October, 2016.

Perera, L.P. Statistical Filter based Sensor and DAQ Fault Detection for Onboard Ship Performance and Navigation Monitoring Systems, In Proceedings of the 8th IFAC Conference on Control Applications in Marine Systems (CAMS 2016), Trondheim, Norway, September 2016. IFAC-PapersOnLine 2016 (2405-8963) Vol. 49 (23), pp. 323-328

Perera, L.P. and Mo, B. Data analysis on marine engine operating regions in relation to ship navigation. Ocean Engineering 2016 (0029-8018) Vol. 128, pp. 163-172

Perera, L.P. and Mo, B. Emission Control based Energy Efficiency Measures in Ship Operations, Journal of Applied Ocean Research, vol. 60, 2016, pp. 29-46.

Perera, L.P. and Mo, B. Marine Engine Operating Regions under Principal Component Analysis to evaluate Ship Performance and Navigation Behavior, In Proceedings of the 8th IFAC Conference on Control Applications in Marine Systems (CAMS 2016), Trondheim, Norway, September 2016. IFAC-PapersOnLine 2016 (2405-8963) Vol. 49 (23), pp. 512-517


Conference papers

Perera, Lokukaluge Prasad; Mo, Brage Development of Data Analytics in Shipping.
Privacy and Security Policies in Big Data. IGI Global 2017, s. 239–258.

Perera, Lokukaluge Prasad Handling Big Data in Ship Performance and Navigation Monitoring.
Proceedings of Smart Ship Technology. Royal Institution of Naval Architects 2017 s. 89–97.

Perera, L.P. and Mo, B. Data Analytics for Capturing Marine Engine Operating Regions for Ship Performance Monitoring, In Proceedings of the 35th International Conference on Ocean, Offshore and Arctic Engineering (OMAE 2016), Busan, Korea, June, 2016, (OMAE2016-54168).

Perera, L.P. and Mo, B. Data Compression of Ship Performance and Navigation Information under Deep Learning, In Proceedings of the 35th International Conference on Ocean, Offshore and Arctic Engineering (OMAE 2016), Busan, Korea, June, 2016, (OMAE2016-54093).

Perera, L.P. and Mo, B. Machine Intelligence for Energy Efficient Ships: A Big Data Solution, in Proceedings of the 3rd International Conference on Maritime Technology and Engineering (MARTECH 2016), Lis-bon, Portugal, July, 2016. ISBN 978-1-138-03000-8, pp. 143-150.

Perera, L.P. and Mo, B. Ship Speed Power Performance under Relative Wind Profiles, in Proceedings of the 3rd International Conference on Maritime Technology and Engineering (MARTECH 2016), Lisbon, Portugal, July, 2016. ISBN 978-1-138-03000-8, pp. 133-141. 

Perera, L. P., Machado, M. M., Manguinho, D. A., & Valland, A. System Failures of Offshore Gas Turbine Engines in Maintenance Perspective. IFAC-PapersOnLine, 49(28), 280-285.

Conference presentation

Perera, Lokukaluge Prasad; Mo, Brage; Nowak, Matthias P. Visualization of Relative Wind Profiles in Relation to Actual Weather Conditions of Ship Routes. OMAE 2017 06. 25–2017-06. 30.

Perera, Lokukaluge Prasad; Mo, Brage Visual Analytics in Ship Performance and Navigation Information for Sensor Specific Fault Detection. OMAE 2017 06. 25-2017 06. 30.

Perera, Lokukaluge Prasad; Mo, Brage Digitalization of Seagoing Vessels Under High Dimensional Data Driven Models. OMAE 2017 06. 25–2017 06. 30.

 

View all publications on Cristin

Postdoc - Data handling framework for ship performance and navigation monitoring

Research topic

L.P. Perera has developed a machine learning based data handling framework with various data analytics to overcome the respective challenges in ship performance and navigation monitoring. There are various industrial challenges encountered in large-scale data handling situations among vessels and shore based data centers.
The proposed data handling framework consists of pre and post-process sections as onboard and onshore applications, respectively. The pre-process as a part of ship IoT consists of the data analytics with data anomaly detection and parameter reduction/data anomaly compression facilitated by data driven models, i.e. digital models.

The pre-processed data communicate through onboard data transmitters in much smaller improved data sets and that are obtained by shore based data centers through data receivers.
The post-process as a part of onshore data centers consists of the data analytics with parameter expansion/data anomaly recovery, integrity verification & regression and data visualization & decision support facilitated by the same digital models.
These data analytics has special features of self-learning (i.e. data clusters and the structure of each data cluster), self-cleaning (i.e. sensor and DAQ fault removal and compression, data
recovery, data regression & integrity verification), selfcompression & expansion (i.e. parameter reduction and expansion).
Furthermore, that has a multi-purpose structure that can be used for both ship energy efficiency and system reliability applications.