Full Scale Data Handling in Shipping: A Big Data Solution
4 likes1,072 views
The document discusses the role of big data solutions in shipping, highlighting objectives, challenges, and data management techniques. It emphasizes the importance of data analytics for improving energy efficiency and the operation of marine engines through empirical models and machine intelligence. Additionally, it outlines future activities aimed at enhancing data handling and collaboration within the maritime sector, particularly in addressing sensor faults and data classification.
![Data Classification
•Engine Centered Data Flow Path
•Localized Models in Ship Performance Monitoring
•Algorithm
− Multivariate Gaussian distribution
− Gaussian Mixture Models (GMMs)
− Expectation Maximization (EM) algorithm
[Source: Matlab.com]](https://image.slidesharecdn.com/lpcbigdata-march-2016v1-160322113610/85/Full-Scale-Data-Handling-in-Shipping-A-Big-Data-Solution-19-320.jpg)
Full Scale Data Handling in Shipping: A Big Data Solution
- 1. Norsk Marinteknisk Forskningsinstitutt Lokukaluge Prasad Perera Norwegian Marine Technology Research Institute (MARINTEK), Trondheim, Norway. March 2016. Trondheim, Norway. Full Scale Data Handling in Shipping: A Big Data Solution.
- 2. •Introduction •Objectives •Data Analytics & Sensors •Energy Flow Path: Marine Engine Centered Approach •Data Flow Path: Big Data Challenges − Sensor Fault Identification − Data Classification − Data Compression − Data Expansion − Data Integrity − Data Regression •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 Big Data, 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 of the data − Data communication − Data Interpretation => Data Analytics − Energy Efficiency − Reliability " The data has a structure and the structure has a meaning"
- 5. Data Analytics & Sensors •The main focus point •Empirical/Stochastic Models − Various Empirical/Stochastic Models have been developed in shipping. − Some challenges in handling Big Data. •Machine Intelligence − Machine Intelligence (MI) can play an important role in the outcome of Big Data applications. − MI Techniques are extensively implemented on current Big Data applications. − These tools and techniques and their applicability in shipping should be investigated. •Knowledge on the Vessel: − Ship Dynamics/Hydrodynamics − Automation and Navigation Systems − Localized Models in Ship Performance Monitoring
- 6. Energy Flow Path •The possible situations of energy conservation: − Marine power plant. − Engine propeller interaction. − Ship resistance.
- 7. Marine Engine Centered Approach Localized Models in Ship Performance Monitoring Engine Propeller Combinator Diagram
- 8. Engine Propeller Combinator Diagram
- 9. Engine Propeller Combinator Diagram Possible Region of Engine-Propeller Operations Basis for Localized Models in Ship Performance Monitoring
- 10. Vessel Information •The respective data set of ship performance and navigation information is collected from: •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 ME 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
- 11. Statistical distributions of Engine Speed, Power & Fuel Consumption
- 12. Statistical distributions of Engine Speed, Power & Fuel Consumption
- 13. Engine Operating Regions: Engine Power vs. Shaft Speed
- 14. Engine Operating Region vs. Rel. Wind Speed, Avg. Draft, Trim and STW
- 15. Engine Propeller Combinator Diagram Operating Patterns
- 16. Engine propeller combinator diagram with STW High to Low STW
- 17. Data Flow Path
- 18. Data Flow Path
- 19. Data Classification •Engine Centered Data Flow Path •Localized Models in Ship Performance Monitoring •Algorithm − Multivariate Gaussian distribution − Gaussian Mixture Models (GMMs) − Expectation Maximization (EM) algorithm [Source: Matlab.com]
- 20. Data Classification: Engine Propeller Combinator Diagram
- 22. Sensor Fault Detection Considering a Two Sensor Situation
- 23. Fault Level 1 Considering 10 Parameter Situation 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
- 24. Fault Level 1 Considering a Two Sensor Situation e3 e1
- 25. Fault Level 2Principal Component Analysis (PCA) Data Standardization. Mean = 0 Variance = 1
- 26. Least Principal Components Projected Data into PCs e1, e2, e3, & e4
- 27. Data Distributions in PC Axes
- 31. Data Flow Path
- 32. Autoencoder : Deep Learning Approach •Encoder Side: Data Compression •Communication Network •Decoder Side: Data Expansion •Top Principal Components
- 33. Autoencoder : A Deep Learning Approach
- 34. Autoencoder : A Deep Learning Approach
- 35. Autoencoder : A Deep Learning Approach
- 36. Autoencoder : A Deep Learning Approach
- 37. Autoencoder : A Deep Learning Approach
- 38. Autoencoder : A Deep Learning Approach
- 39. Autoencoder : A Deep Learning Approach
- 40. Singular ValuesData Compression Information •Top 10, 9, 8 and 7 principal components can preserve 100 %, 99.92%, 99.48%, 97.86% 94.03% of the actual ship performance and navigation information. •The respective 99% and 95% lines are also presented in the same figure. •Top 7 PCs Selected •10 Parameters => 7 Parameters •Preserve approximately 94% of the actual information.
- 41. PCA of Ship Performance and Navigation Information. PCs for Ship Performance Evaluation ?
- 42. PCA of Ship Performance and Navigation Information.
- 43. Actual and estimated parameters of ship performance and navigation information.
- 44. Actual and estimated parameters of ship performance and navigation information. Data can be Recovered by Regression or Smoothing
- 45. Data Flow Path Data can be Recovered by Regression or Smoothing AIS Data
- 46. Data Analysis
- 47. Relative Wind Profile of a Ship
- 48. Relative Wind Profile with STW and SOG Gaussian Type Distributions
- 50. One Sided Relative Wind Profile (Cleaned Data)
- 51. One Sided Relative Wind Profile with STW (> 3 Knots)
- 52. One Sided Relative Wind Profile (Further Cleaned Data)
- 53. Ship Speeds: STW, SOG and STW-SOG
- 54. Ship Speed Power Profile with Relative Wind Speed |STW –SOG| < 5.5 (Knots)
- 55. Speed Power Profile with Rel. Wind Speed and Angle
- 56. STW-SOG vs. Rel. Wind Speed and Direction
- 57. Modified Speed Power Profile
- 58. SWT vs. SOG Unique to the Vessel ?
- 60. Conclusion & Future Activities •Some advanced tools are developed in this stage. •Still a Logway to go.. − Sensor Fault Identification − Data Classification − Data Compression − Data Expansion − Data Integrity − Data Regression •Models should be further developed. •High sampling rate data •Further collaboration with appropriate partners. •Research projects.
- 61. 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.