Use of tree based methods in ship performance monitoring under operating conditions

Abstract Monitoring of operational efficiency in ship fleets is a complex maritime problem which requires an analytical approach in order to provide satisfactory solutions. Since the problem involves high-dimensional data, this paper develops tree-based modelling on bagging, random forest and bootstrap approach to analyse the ship performance under operational condition. To demonstrate the proposed model, the publicly accessible dataset for 254 trips derived from a particular designed acquisition system on-board ferry ship is utilised. In operational variable analysis on speed through water and fuel consumption, the bootstrap approach yields more accurate prediction rate than random forest and bagging. The proposed model is superior to the others such as ANN and GP applications in ship performance monitoring. Consequently, the tree based model adopting bagging, random forest, and boosting environment is capable of increasing the predictive performance during monitoring of ship performance in maritime industry. Beside its theoretical insight, the findings of the paper contribute ship management companies to monitor ship operational performance.

[1]  E. Hadavandi,et al.  Decision tree-based modelling for identification of potential interactions between type 2 diabetes risk factors: a decade follow-up in a Middle East prospective cohort study , 2016, BMJ Open.

[2]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[3]  Hong Han,et al.  Variable selection using Mean Decrease Accuracy and Mean Decrease Gini based on Random Forest , 2016, 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS).

[4]  Lokukaluge P. Perera,et al.  Data Analytics for Capturing Marine Engine Operating Regions for Ship Performance Monitoring , 2016 .

[5]  Christoph Steinbeck,et al.  Building blocks for automated elucidation of metabolites: Machine learning methods for NMR prediction , 2008, BMC Bioinformatics.

[6]  Lg Aldous,et al.  Ship operational efficiency : performance models and uncertainty analysis , 2016 .

[7]  Biagio Palumbo,et al.  A Procedure for Predicting and Controlling the Ship Fuel Consumption: Its Implementation and Test , 2015, Qual. Reliab. Eng. Int..

[8]  Ole Winther,et al.  Statistical modelling for ship propulsion efficiency , 2012 .

[9]  E. Davies,et al.  Field data analysis of active chlorine-containing stormwater samples. , 2018, Journal of environmental management.

[10]  Yacine Rezgui,et al.  Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption , 2017 .

[11]  S. Dalsøren,et al.  Future cost scenarios for reduction of ship CO2 emissions , 2011 .

[12]  Biagio Palumbo,et al.  A comparison of advanced regression techniques for predicting ship CO2 emissions , 2017, Qual. Reliab. Eng. Int..

[13]  Charlotte Banks,et al.  Integrated approach to vessel energy efficiency , 2015 .

[14]  Masaru Tsujimoto,et al.  Performance prediction of full-scale ship and analysis by means of on-board monitoring. Part 2: Validation of full-scale performance predictions in actual seas , 2018 .

[15]  Lokukaluge P. Perera,et al.  Marine Engine Centered Localized Models for Sensor Fault Detection under Ship Performance Monitoring , 2016 .

[16]  Leifur Þ. Leifsson,et al.  Grey-box modeling of an ocean vessel for operational optimization , 2008, Simul. Model. Pract. Theory.

[17]  Wei Liu,et al.  Predicting ship fuel consumption based on LASSO regression , 2017, Transportation Research Part D: Transport and Environment.

[18]  Richard Bucknall,et al.  Uncertainty analysis in ship performance monitoring , 2015 .

[19]  Ole Winther,et al.  A Machine-Learning Approach to Predict Main Energy Consumption under Realistic Operational Conditions , 2012 .

[20]  Rosa G. González-Ramírez,et al.  The impact of lanes segmentation and booking levels on a container terminal gate congestion , 2017 .

[21]  Lawrence Mak,et al.  Ship performance monitoring and analysis to improve fuel efficiency , 2014, 2014 Oceans - St. John's.

[22]  Davide Anguita,et al.  Ship efficiency forecast based on sensors data collection: Improving numerical models through data analytics , 2015, OCEANS 2015 - Genova.

[23]  Ying LU,et al.  Decision tree methods: applications for classification and prediction , 2015, Shanghai archives of psychiatry.

[24]  Kenji Sasa,et al.  Evaluation of ship performance in international maritime transportation using an onboard measurement system - in case of a bulk carrier in international voyages , 2015 .

[25]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[26]  Marielle Christiansen,et al.  Analyzing complex service structures in liner shipping network design , 2017 .

[27]  Benjamin Pjedsted Pedersen,et al.  Modeling of Ship Propulsion Performance , 2009 .

[28]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[29]  Mads Aas-Hansen.  Monitoring of hull condition of ships , 2010 .

[30]  Thijs Willem Frederik Hasselaar.  An investigation into the development of an advanced ship performance monitoring and analysis system , 2011 .

[31]  John H. Maindonald,et al.  Data Analysis and Graphics Using R: An Example-Based Approach , 2010 .

[32]  Baozhen Yao,et al.  Sailing speed optimization for tramp ships with fuzzy time window , 2019 .