Font Size: a A A

Research On Fault Diagnosis For Low-speed Marine Diesel Engine And Its Applications Using RBF Neural Network

Posted on:2001-04-23Degree:MasterType:Thesis
Country:ChinaCandidate:J L HuangFull Text:PDF
GTID:2132360062480071Subject:Marine Engineering
Abstract/Summary:PDF Full Text Request
In this paper, special emphasis has been placed on the application of fault diagnosis for large-scale low-speed marine diesel engine by an artificial neural network model, which based on radial basis function (RBF). At the first time, a RBF network model has been established, and then taking following two sub-system as examples, the turbo-charging system as well as the cylinder assembly and combustion system in marine diesel engine, which made in Hudong Heavy Industry Co., China. Their sample sets of the symptoms and troubles have been designed. Simultaneously, using a practical Neural Network Toolbox in MATLAB environment, the simulation calculations for fault diagnosis of marine low-speed heavy-duty diesel engine have been performed. In order to verify the accurate and the degree of fault mode, a large number of test calculations have been done through computerization. The simulation experimental results demonstrate that this diagnosis method for these two sub-systems is feasible and successful.The acquirement of the sample sets of the symptoms and troubles is the key to diagnose accurately the faults. Under several typical load conditions and several different ambient temperature, using a computer program for predicting the running performance of heavy-duty marine turbocharged two-stroke diesel engines to set some symptoms quantitatively with different degree through computer simulation, and combining with the experts' experiences in the field, the sample sets can be obtained.In addition, the mathematical model, structure and its main functions of a fault diagnosis simulating system for marine diesel engine are presented. And the trouble diagnosis approach, which based on RBF neural network, is introduced. The system is simple in construction and perfect in function. It is of a practical importance to develop the marine diesel engine performance fault analysis system in ocean ship and extend the functions for marine engine room simulater, and it is also able to train marine engineers to deal with troubles and to make out repairing strategies accordingly for the purpose of enhancing the utility and working life of a diesel engine.
Keywords/Search Tags:Marine diesel engine, Fault diagnosis, RBF neural network, MATLAB language, Simulation system
PDF Full Text Request
Related items