Multi-sensor data fusion is a feasible technique to achieve accurate and robust results in fault diagnosis of rotating machinery under complex conditions. However, the problem of information losses is always ignored during the fusion process. To solve above problem, an ensemble convolutional neural network model is proposed for bearing fault diagnosis. The framework of the proposed model contains three convolutional neural network branches: one multi-channel fusion convolutional neural network branch and two 1-D convolutional neural network branches. The former branch extracts the coupling features based on multi-sensor data and the latter two branches extract the inherent features based on single-sensor data, which can collect comprehensive fault information and reduce information losses. Furthermore, the support vector machine ensemble strategy is employed to fuse the results of multiple branches, which can improve the generalization and robustness of the proposed model. The experiments show that the proposed can obtain more effective and robust results than other methods.

A highly efficient local-piston theory is presented for the prediction of inviscid unsteady pressure loads at supersonic and hypersonic speeds. A steady mean flow solution is first obtained by an Euler method. The classical piston theory is modified to apply locally at each point on the airfoil surface on top of the local mean flow to obtain the unsteady pressure perturbations caused by the deviation of the airfoil surface from its mean location without the need of performing unsteady Euler computations. Results of two-and three-dimensional unsteady air loads and flutter predictions are compared with those obtained by the classical piston theory and an unsteady Euler method to assess the accuracy and validity range in airfoil thickness, flight Mach number, and angle of attack and with the presence of blunt leading edges. The local-piston theory is found to offer superior accuracy and much wider validity range compared with the classical piston theory, with the cost of only a fraction of the computational time needed by an unsteady Euler method.

No abstract