SlideShare a Scribd company logo

Handling Big Data in Ship Performance & Navigation Monitoring.

•
•
Lokukaluge Prasad Perera
Lokukaluge Prasad Perera

The document discusses handling big data in ship performance and navigation monitoring. It presents a data handling framework that includes developing digital models from data clusters, using principal component analysis to analyze the clusters, and extracting information to reduce parameters while preserving information. The framework allows for data projection, sensor fault detection, integrity verification from other sources, and data visualization to support decision making. The talk outlines developing these techniques to better handle large scale data from ships.

Related slideshows

Ship Motion and Stresses
Ship Motion and StressesShip Motion and Stresses
Ship Motion and Stresses
 
Ship’s types
Ship’s typesShip’s types
Ship’s types
 
Ships powerpoint
Ships powerpointShips powerpoint
Ships powerpoint
 
1 of 34
Download to read offline
Lokukaluge Prasad Perera SINTEF Ocean, Trondheim, Norway. The Smart Ship Technology conference The Royal Institution of Naval Architects, UK January 2017, London, UK. Handling Big Data in Ship Performance & Navigation Monitoring.
•Introduction •Objectives •Data Analytics & Internet of Things •Data Handling Framework & Big Data Challenges •Industrial Digitalization •Conclusion & Future Activities Outline Data Analytics Data Management
Introduction •Big Data Solutions play an important role in Future Research and Industrial Applications. •Strategic Priority Area for the MARINTEK. •Research and Industrial Applications: − Data Management: Appropriate actions to develop a bunch of data in a structured collection. − Data Analytics: The science of examining these data with the purpose of drawing meanings about the information. •The size of these data sets may not make a big difference in these applications. •The outcome of the Data set, the meaning, is the most important aspect of these research and industrial applications. •Many Fundamental Challenges.
Objectives •To address the Fundamental Challenges in Big Data Applications in Shipping. − Large Scale Data Sources Data Management − Sensor Related Issues − Quality/Quantity of the data − Data Communication − Data Interpretation Data Analytics − Energy Efficiency − System Reliability " The data has a structure and the structure has a meaning" A Journey towards a Meaningful Data Structure… Social Analytics
Data Analytics & Internet of Things •Conventional Models − Various Conventional Models have been developed in shipping. − Some challenges in handling Big Data : data modelling uncertainty, erroneous data conditions, data visualization challenges and high computational power. •Machine Intelligence & Statistical Analysis − Machine Intelligence (MI) will play an important role in the outcome of Big Data applications. − Statistical Techniques will guide MI Applications. − Such tools and techniques and their applicability as Data Driven Models. •Domain Knowledge − Ship Dynamics/Hydrodynamics − Automation and Navigation Systems − Engine Propeller Combinator Diagram
Data Handling Framework
Digital Models/Data Driven Models
Eigenvalues & Eigenvectors Principal Component Analysis (PCA)
Information Extraction •Data Driven Approach − Self learning − Self cleaning − Self compression-expansion − Multi-purpose structure − Efficiency & Reliability
Engine Centered Approach Digital Models Engine Propeller Combinator Diagram
Engine Propeller Combinator Diagram Possible Region of Engine-Propeller Operations Basis for Digital Models
Vessel Information •A set ship performance and navigation parameters is collected from a selected vessel. •Bulk Carrier with following particulars: − ship length: 225 (m), − beam: 32.29 (m), − Gross tonnage: 38.889 (tons), − deadweight at max draft: 72.562 (tons). − Powered by 2 stroke Main Engine with maximum continuous rating (MCR) of 7564 (kW) at the shaft rotational speed of 105 (rpm). − Fixed pitch propeller diameter 6.20 (m) with 4 blades
Ship Performance and Navigation Parameters Considering a 10 Parameter Data Set Parameter Mini. Max. 1. Avg. draft (m) 0 15 2. STW (Knots) 3 20 3. ME power (kW) 1000 8000 4. Shaft speed (rpm) 20 120 5. ME fuel cons. (Tons/day) 1 40 6. SOG (Knots) 0 20 7. Trim (m) -2 6 8. Rel. wind speed (m/s) 0 25 9. Rel. wind direction (deg) 2 360 10. Aux. fuel cons. (Tons/day) 0 8
Histograms of Engine Parameters
Engine Propeller Combinator Diagram
Digital Models Data Cluster 1 Data Cluster 2 Data Cluster 3
Ship Performance & Navigation Parameters
Digital Model
Localized Models Principal Component Analysis (PCA) Data Cluster 3 Data Cluster 1 Data Cluster 2
Information Extraction
PCs on Data Cluster 3
PCA on Model 3
Digital Models Data Cluster 1 Data Cluster 2 Data Cluster 3
Data Projection into PC Axes
Sensor & DAQ Fault Detection
Parameter Selection •Top 7 PCs Selected. •10 Parameters => 7 Parameters. •Preserve approximately 99.5% of the actual information.
Parameter Reduction/Error Compression & Expansion/Data Recovery Data can be Recovered by Regression or Smoothing Data Regression
Integrity Verification Other Data Sources Actual Weather Data
Data Visualization Relative Wind Profile of a Ship
Data Visualization Ship Speeds
Industrial Digitalization
•Some advanced tools & Techniques are developed in this stage. •Still a logway to go.. − Digital Models − Sensor & DAQ Fault Identification − Parameter Reduction/Error compression − Parameter Expansion/Data Recovery Data Structure − Integrity Verification − Data Regression − Data Visualization − Decision Supporting •High sampling rate data. •Research projects/topics. Conclusion & Future Activities
Thank You Questions ? This work has been conducted under the project of "SFI Smart Maritime - Norwegian Centre for improved energy-efficiency and reduced emissions from the maritime sector" that is partly funded by the Research Council of Norway. smartmaritime.no Publications and high resolution color images: http://bit.do/perera.
Data Classification: Engine Propeller Combinator Diagram

More Related Content

Handling Big Data in Ship Performance & Navigation Monitoring.

  • 1. Lokukaluge Prasad Perera SINTEF Ocean, Trondheim, Norway. The Smart Ship Technology conference The Royal Institution of Naval Architects, UK January 2017, London, UK. Handling Big Data in Ship Performance & Navigation Monitoring.
  • 2. •Introduction •Objectives •Data Analytics & Internet of Things •Data Handling Framework & Big Data Challenges •Industrial Digitalization •Conclusion & Future Activities Outline Data Analytics Data Management
  • 3. Introduction •Big Data Solutions play an important role in Future Research and Industrial Applications. •Strategic Priority Area for the MARINTEK. •Research and Industrial Applications: − Data Management: Appropriate actions to develop a bunch of data in a structured collection. − Data Analytics: The science of examining these data with the purpose of drawing meanings about the information. •The size of these data sets may not make a big difference in these applications. •The outcome of the Data set, the meaning, is the most important aspect of these research and industrial applications. •Many Fundamental Challenges.
  • 4. Objectives •To address the Fundamental Challenges in Big Data Applications in Shipping. − Large Scale Data Sources Data Management − Sensor Related Issues − Quality/Quantity of the data − Data Communication − Data Interpretation Data Analytics − Energy Efficiency − System Reliability " The data has a structure and the structure has a meaning" A Journey towards a Meaningful Data Structure… Social Analytics
  • 5. Data Analytics & Internet of Things •Conventional Models − Various Conventional Models have been developed in shipping. − Some challenges in handling Big Data : data modelling uncertainty, erroneous data conditions, data visualization challenges and high computational power. •Machine Intelligence & Statistical Analysis − Machine Intelligence (MI) will play an important role in the outcome of Big Data applications. − Statistical Techniques will guide MI Applications. − Such tools and techniques and their applicability as Data Driven Models. •Domain Knowledge − Ship Dynamics/Hydrodynamics − Automation and Navigation Systems − Engine Propeller Combinator Diagram
  • 8. Eigenvalues & Eigenvectors Principal Component Analysis (PCA)
  • 9. Information Extraction •Data Driven Approach − Self learning − Self cleaning − Self compression-expansion − Multi-purpose structure − Efficiency & Reliability
  • 10. Engine Centered Approach Digital Models Engine Propeller Combinator Diagram
  • 11. Engine Propeller Combinator Diagram Possible Region of Engine-Propeller Operations Basis for Digital Models
  • 12. Vessel Information •A set ship performance and navigation parameters is collected from a selected vessel. •Bulk Carrier with following particulars: − ship length: 225 (m), − beam: 32.29 (m), − Gross tonnage: 38.889 (tons), − deadweight at max draft: 72.562 (tons). − Powered by 2 stroke Main Engine with maximum continuous rating (MCR) of 7564 (kW) at the shaft rotational speed of 105 (rpm). − Fixed pitch propeller diameter 6.20 (m) with 4 blades
  • 13. Ship Performance and Navigation Parameters Considering a 10 Parameter Data Set Parameter Mini. Max. 1. Avg. draft (m) 0 15 2. STW (Knots) 3 20 3. ME power (kW) 1000 8000 4. Shaft speed (rpm) 20 120 5. ME fuel cons. (Tons/day) 1 40 6. SOG (Knots) 0 20 7. Trim (m) -2 6 8. Rel. wind speed (m/s) 0 25 9. Rel. wind direction (deg) 2 360 10. Aux. fuel cons. (Tons/day) 0 8
  • 14. Histograms of Engine Parameters
  • 16. Digital Models Data Cluster 1 Data Cluster 2 Data Cluster 3
  • 17. Ship Performance & Navigation Parameters
  • 23. Digital Models Data Cluster 1 Data Cluster 2 Data Cluster 3
  • 25. Sensor & DAQ Fault Detection
  • 26. Parameter Selection •Top 7 PCs Selected. •10 Parameters => 7 Parameters. •Preserve approximately 99.5% of the actual information.
  • 27. Parameter Reduction/Error Compression & Expansion/Data Recovery Data can be Recovered by Regression or Smoothing Data Regression
  • 28. Integrity Verification Other Data Sources Actual Weather Data
  • 29. Data Visualization Relative Wind Profile of a Ship
  • 32. •Some advanced tools & Techniques are developed in this stage. •Still a logway to go.. − Digital Models − Sensor & DAQ Fault Identification − Parameter Reduction/Error compression − Parameter Expansion/Data Recovery Data Structure − Integrity Verification − Data Regression − Data Visualization − Decision Supporting •High sampling rate data. •Research projects/topics. Conclusion & Future Activities
  • 33. Thank You Questions ? This work has been conducted under the project of "SFI Smart Maritime - Norwegian Centre for improved energy-efficiency and reduced emissions from the maritime sector" that is partly funded by the Research Council of Norway. smartmaritime.no Publications and high resolution color images: http://bit.do/perera.
  • 34. Data Classification: Engine Propeller Combinator Diagram