Zhe Cheng

TL;DR: A deep convolutional neural network (DCNN) based data fusion method for health state identification that fuses the raw data from the horizontal and the vertical vibration signals and extracts features automatically and could obtain better identification results than the other methods.

TL;DR: Simulation and experimental signal verification results of bearing fault degradation under the condition of variable speed show that the HI extracted based on the IPSW method can reduce the influence ofVariable speed and track the bearing damage degradation trend effectively.

TL;DR: A feature based on statistical parameters of the analog tachometer signal is extracted to detect incipient faults of a planetary gearbox and the results show that the proposed feature has better classification ability in fault detection compared with the traditional features based on vibration signals.

TL;DR: An improved tooth tip chipping model is proposed, and analytical equations of time-varying mesh stiffness (TVMS) for a chipped tooth is derived and a new term called “torsional stiffness” is introduced into the overall TVMS due to the chipping defect.

TL;DR: In this article, a method for monitoring health of a rotary machine suitable for a working condition changing condition is proposed. But the method is not suitable for the case of rotating speed changing and load changing conditions.