A Study on Data Cleaning for Energy Efficiency of Ships

Data cleaning for energy efficiency of ships is of great importance to develop an accurate energy efficiency modeling as well as to improve the accuracy of its calculation and analysis, which can be used to guide energy-saving navigations of ships.Fault features of the data are analyzed and recognized by threshold theory and co-relation analysis.The abnormal data of water depth, ship speed, and fuel consumption are modified by interpolation and grey relational theory.Based on this, a process for data cleaning of energy efficiency is developed.The data collected by the relevant systems on ships are chosen as a case study and cleaning results are analyzed.The results show that the mean error between the modified and measured values of water depth, ship speed, and fuel consumption is 1.58%, 2.8%, 1.5%, respectively.They are satisfactory to meet the requirements of further modeling and data mining.