Modelling and predictive investigation on the vibration response of a propeller shaft based on a convolutional neural network

It is crucial to detect the working state of a propeller shaft in real time, as its vibration affects the safety of the marine propulsion system directly. With the difficulty of obtaining an accurate signal due to the particularity of propeller shaft, a suitable method for estimating the vibration response of propeller shaft is proposed in this paper. The nonlinear relationship of vibration signals between the bearing and propeller shaft is obtained by fitting the existing data sets with various neural networks. The feasibility of the proposed method is demonstrated through a prediction of shaft vibration on the basis of a shaft experimental platform. Moreover, the optimal model of the neural network is obtained by comparing the influence of different hyper parameters and network models. The results indicate a prediction accuracy of over 95 % of the shaft vibration in the lower frequency band for a convolutional neural network. Therefore, the research provides an easier maintenance method for predicting the real-time monitoring for the vibration response of the propeller shaft.

Automated summary

This study proposes a method for estimating the vibration response of a propeller shaft and demonstrates its feasibility and accuracy through experiments. The research provides an easier maintenance method for predicting the real-time monitoring of propeller shaft vibration response.