When a propeller is under a state of cavitation, it will experience negative effects, including strong noise, vibration, and even damage to the blades. Accordingly, the detection of propeller cavitation has attracted the attention of researchers. Propeller noise signal contains a wealth of cavitation information, which is a powerful method to identify the cavitation state. Considering the nonlinear characteristics of propeller noise, a feature describing the complexity of nonlinear signals, which is called refined composite multiscale fluctuation-based dispersion entropy (RCMFDE), is adopted as the indicator of propeller cavitation, and a framework for the identification of propeller cavitation state is established in this paper. Firstly, the propeller noise signal is decomposed by the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method, and the intrinsic mode function (IMF) components with cavitation characteristics are extracted. Secondly, the RCMFDE of the IMF components is computed. Finally, a hybrid optimization support vector machine (SVM) is established to classify the features, in which a Relief-F filter is utilized to reduce the feature dimension, and a particle swarm optimization (PSO) wrapper is utilized to optimize the parameters of the SVM. The experimental results demonstrate encouraging accuracy to apply this approach to identify the propeller cavitation states, with an identification accuracy of 91.11%.

Tip vortex cavitation is typically the first type of cavitation in real ship propellers due to the scale effect. To lessen or eliminate propeller cavitation noise, it is necessary to effectively identify and predict the tip vortex cavitation initiation of the propeller and run the propeller as far as possible in the “non-cavitation area.” However, for the current numerical computation, it is impossible to determine the minimum pressure at the vortex core directly and correctly, making it difficult to anticipate the cavitation initiation of the propeller tip vortex. In this paper, based on computational fluid dynamics (CFD) numerical calculations and the tip vortex model proposed by Xin [Proceedings of 2013 Ship Hydrodynamics Conference (2013), pp. 211–218], we propose a new prediction method for propeller tip vortex cavitation initiation—“the tip vortex model method.” The propeller tip vortex is solved by CFD calculation in this model, and the minimum pressure at the downstream vortex core is examined based on the tip vortex model to determine the initiation of propeller cavitation. We examine the cavitation inception using the tip vortex model method and compare it to the results obtained using the minimum pressure coefficient method and the minimum vapor volume method. It is discovered that the cavitation inception number obtained by the tip vortex model method is closer to the experimental results. Furthermore, the effects of different turbulence models and grid settings on the prediction of tip vortex cavitation initiation are investigated, providing an effective reference for the prediction of propeller tip vortex cavitation initiation.

Due to the scale effect, tip vortex cavitation (TVC) is the earliest type of cavitation that occurs on real ship propellers. As a result, experts in the ship field have been paying close attention to the accurate prediction of propeller TVC inception for a long time. The motion and growth of the microscopic nuclei in the water have a significant influence on TVC inception. However, the minimum pressure coefficient method—a common method at present—based on the traditional Eulerian framework, neglects the influence of microscopic nuclei and therefore cannot accurately predict the cavitation inception. Moreover, the numerical prediction method for cavitation inception, which is based on bubble dynamics models and considers the influence of nuclei, has not established a set of unified and specific discrimination criteria applicable to propeller cavitation inception. In order to make up for the shortcomings of traditional prediction models and the existing methods based on bubble dynamics in the prediction of TVC inception, we propose a new discrimination method for propeller TVC inception based on bubble dynamics in this paper. The comparison with experimental results demonstrates that our proposed method allows us to predict propeller TVC inception more accurately. In addition, the effect mechanism of tip vortex flow characteristics on nuclei evolution is further investigated, and it is found that when approaching the low-pressure region at a vortex core under the influence of tip vortex suction, nuclei grow explosively under the continuous action of the low pressure at the vortex core until they reach their maximum sizes and then collapse rapidly.

The radiation impedance is an essential parameter in analyzing the vibroacoustic response of the planar source. In order to calculate the acoustic radiation impedance of the rectangular plate with arbitrary boundary conditions, a unified approximate approach is proposed in this study. The displacement function of the plate is expressed in the form of a supplemented two-dimensional Fourier cosine series, which can be solved by the Rayleigh–Ritz method. The radiated acoustic field from the plate is further determined by the Rayleigh integrals. The coordinate transformation is performed twice to convert the quadruple integrals into simple integrals, significantly reducing the computational effort of the acoustic calculation. Regardless of the wavenumber or frequency, the proposed approach is theoretically accurate because no assumptions or approximations are involved in the mathematical process. Furthermore, the correctness of the formulas is validated by the results obtained from previous studies. Several numerical examples are performed using this approach, and the effects of boundary conditions on the modal radiation impedance are discussed.

The versatility of the existing A-optimal-based CNN for solving multiple types of signals classification problems has not been verified by different signals datasets. Moreover, the existing A-optimal-based CNN uses a simplified approximate function as the optimization objective function instead of precise analytical function, which affects the signals classification accuracy to a certain extent. In this paper, a classification method called IA-optimal CNN is proposed. To improve the stability of the classifier, the trace of the covariance matrix of the weights of the fully connected layer is used as the optimization objective function, and the parameter optimization model is established without any simplification of the optimization objective function. In addition, to avoid the difficulty of not being able to obtain the analytical expression formula of the partial derivative of the inverse matrix with regard to the networks parameters, a novel dual function is introduced to transform the optimization problem into an equivalent binary function optimization problem. Furthermore, based on the above analytical solution results, the parameters are updated using the alternate iterative optimization method and the accurate weight update formula is deduced in detail. Five signals datasets are used to test the universality of the IA-optimal CNN in signals classification fields. The performance of IA-optimal CNN is showed, and the experimental results are compared with the existing A-optimal-based classification algorithm. Lastly, the following conclusion is proved theoretically: For the A-optimal-based CNN, the trace of the covariance matrix will continue to decrease and approach a convergence value in the iterative process, but it is impossible for the networks to strictly reach the A-optimal state.

Transductive Confidence Machine(TCM) is an effective machine- learning algorithm. But its classification results are not satisfying under high confidence level. Therefor an improved algorithm, named TCM-IKNN, is put forward by means of improving strangeness measure method on the basis of traditional TCM-KNN. The results of the experiment on parts of UCI dataset show that the TCM-IKNN algorithm using the improved strangeness measure can increase the correct rate of predictions, reduce the number of uncertain predictions in both online and offline learning settings, be superior to traditional TCM-KNN.