Application And Prospect Of Intelligent Fault Diagnosis Technology For Ship Shafting Vibration

In recent years,intelligent ship has become a global shipping trend.Ship intelligence is mainly reflected in intelligent hull,intelligent engine room,intelligent navigation,intelligent cargo management,intelligent energy efficiency management and intelligent integrated platform.Marine propulsion shafting is an important part of marine power system.How to intelligently identify and diagnose various faults of ship shafting is the key to intelligent condition monitoring and intelligent fault diagnosis of ship shafting.In recent years,with the rise of the concept of smart ships and the development of Internet and information technologies such as big data,cloud computing and the Internet of Things,ship intelligence has become the general trend of global shipping.At present,research on smart ships has been carried out on a global scale.In this paper,the fault diagnosis method based on support vector machine theory is studied.Aiming at the difficulty in selecting penalty factor C and kernel function parametersσ,an improved artificial bee colony algorithm(IABC)is proposed to optimize the penalty factor C and kernel function parameters σ of support vector machine.Moreover,in order to solve the problems of slow convergence speed and falling into local optimal solution in the late iteration stage of artificial bee colony algorithm,the global search factor is introduced into the original artificial bee colony algorithm search formula.In order to verify the effectiveness of the improved artificial bee colony optimization(IABC)algorithm,a simulation experimental platform was designed to simulate the propulsion system structure of the "ShenHan line" passenger ship as an example,aiming at three kinds of common vibration faults(shafting misalignment,slipping,rotor eccentricity),fault diagnosis monitoring points were set up to collect fault data.The improved artificial bee colony(IABC)optimization algorithm and artificial bee colony ABC optimization algorithm are applied to shaft fault diagnosis at the same timeIn the process of model training,because of the introduction of global search factor,IABC-SVM has faster convergence speed in parameter optimization,can jump out of local optimal solution and obtain global optimal parameters,which can achieve global optimization faster than ABC-SVM.According to the trend of average accuracy,IABC-SVM can help training start from a better initial nectar source.The average accuracy of IABC-SVM is 85.41%,which is significantly higher than 72.91%of traditional ABC.Moreover,the training time and the best average accuracy of IABC-SVM are better than ABC-SVM.According to the model test results,the classification accuracy of IABC-SVM is significantly higher than that of ABC-SVM,and IABC-SVM has more advantages in the test process.In this paper,aiming at the vibration characteristics of ship shafting and the problems in fault diagnosis,the iabc-svm fault diagnosis method is proposed.This method can effectively detect and identify the fault of shafting vibration,and has high accuracy and diagnosis efficiency.