Font Size: a A A

Research And Application Of Marine Engine Room Data Mining Technology

Posted on:2019-04-23Degree:MasterType:Thesis
Country:ChinaCandidate:H M YanFull Text:PDF
GTID:2322330542989150Subject:Marine Engineering
Abstract/Summary:PDF Full Text Request
In order to improve the efficiency of ship operations,the mechanical equipment of the ship's engine room is becoming more and more automated and intelligent.At the same time,the mechanical and mechanical fault mechanisms of the engine room are complex and changeable.The marine host is the most important core equipment of the ship.Once a failure occurs to the ship,In terms of terms,it is extremely influential.With the rapid development of data mining technology,it has been widely used in various fields,especially the huge advantage of extracting hidden knowledge in massive data.Therefore,the combination of data mining technology and fault diagnosis technology is applied to the nacelle of the ship,and corresponding diagnostic knowledge is extracted from the massive historical operating data to realize intelligent fault diagnosis of the marine host in the nacelle.In this paper,the decision tree algorithm in data mining is introduced into the ship host for fault diagnosis.The general process of data mining and the common components of data mining system are summarized.Then through a laboratory VLCC tanker simulator simulation in the 7th cylinder injector normal operation,nozzle wear,nozzle clogging,injection timing advance,fuel injection timing delayed operation.Each experiment was performed 30 times in each state.A total of 150 experimental sample data were collected and the sample data was discretized.Twenty groups were randomly selected as training sets among the 30 groups,and the rest were used as test sets.The decision tree algorithm program is written in python language.The training set is input to the decision tree fault diagnosis model.Then the decision tree diagnosis model is tested with the test set.The diagnostic accuracy of the diagnostic model is verified by the test set,and the decision tree is used to validate the ship.The feasibility of host fault diagnosis.In the end,the paper builds a framework for marine engine fault diagnosis system based on decision tree,elaborates some of the functions,designs the hardware and software of the system,and uses python to implement a marine host diagnostic module based on decision tree.
Keywords/Search Tags:Marine Engine, Decision Tree, Data Mining, Fault Diagnosis
PDF Full Text Request
Related items