Explore the vast range of titles available.

Recurrence-plot (RP) analysis is a graphical tool to visualize and analyze the recurrence of nonlinear dynamic systems. By combining the advantages of the RP and a convolutional neural network (CNN), a fault-classification scheme for planetary gear sets is proposed in this paper. In the proposed approach, a vibration is first picked up from the planetary-gear test rig and converted into an angular-domain quasistationary signal through computed order tracking to eliminate the frequency blur caused by speed fluctuations. Then, the signal in the angular domain is divided into several segments, and each segment is processed by the RP to constitute the training sample. Moreover, a two-dimensional CNN model was developed to adaptively extract faulty features. Experiments on a planetary-gear test rig with four conditions under three operating speeds were carried out. The results of measured vibration demonstrated the validity of CNN and recurrence plot analysis for the fault classification of planetary-gear sets.

The vibration control of a construction vehicle must be carried out in order to meet the aims of sustainable environmental development and to avoid the potential human health hazards. In this paper, based on market feedback, the driver seat vibration of a type of wheel loader in the left and right direction, is found to be significant over a certain speed range. In order to find abnormal vibration components, the order tracking technique (OTT) and transmission path analysis (TPA) were used to analyze the vibration sources of the wheel loader. Through this analysis, it can be seen that the abnormal vibration comes from the interaction between the tire tread and the road, and this is because the vibration was amplified by the cab mount, which was eventually transmitted to the cab seat. Finally, the seat vibration amplitudes were decreased by up to 50.8%, after implementing the vibration reduction strategy.

Abstract Vibration monitoring of CNC high-speed machining (HSM) centers under non-stationary conditions, characterized by varying operating parameters and uncertainties affected by the change of speed and load during operation currently presents a particular challenge. Therefore, bearing condition monitoring is important. Indeed, this variation has a considerable impact on the vibratory response delivered by the accelerometers and therefore can mask any fault. The change in speed causes considerable changes in the spectrum of the vibration such that defect signatures become almost undetectable with conventional tools. The order tracking method based on time–frequency representation is regarded as an effective tool for fault detection of bearings with varying rotating speeds. This study aims to propose non-stationary tools based on tachometer order tracking to detect bearing faults in high-speed milling centers during run-up and coast-down conditions. Developed tools are compared to stationary technics in this study, remaining limited to detect faults. Indeed, the speed variation would cause spectrum smearing if classic tools are used in non-stationary conditions. These latter methods are based on constant rotating speed and would fail to detect faults of bearings with variable spindle rotating speeds.