Fracture of blades is usually catastrophic and creates serious damages in the turbomachines. Blades are subjected to high centrifugal force, oscillating stresses, and high temperature which makes their life limited. Therefore, blades should be checked and replaced at specified intervals or utilize a health monitoring method for them. Crack detection by nondestructive tests can only be performed during machine overhaul which is not suitable for monitoring purposes. Blade tip timing (BTT) method as a noncontact monitoring technique is spreading for health monitoring of the turbine blades. One of the main challenges of BTT method is identification of vibration parameters from one per revolution samples which is quite below Nyquist sampling rate. In this study, a new method for derivation of blade asynchronous vibration parameters from BTT data is proposed. The proposed method requires only two BTT sensors and applies least mean square algorithm to identify frequency and amplitude of blade vibration. These parameters can be further used as blade health indicators to predict defect growth in the blades. Robustness of the proposed method against measurement noise which is an important factor has been examined by numerical simulation. An experimental test was conducted on a bladed disk to show efficiency of the proposed method.

Envelope analysis is widely used in fault diagnosis of rolling element bearings (REBs). In envelope analysis, it is necessary to select a frequency band which is related to the resonance of the bearing. Spectral kurtosis (SK) is known as a powerful method to find the resonance band in vibration of a defective REB. SK, calculated by short time Fourier transform, suffers from its dependency on the window length. In this article, a special wavelet transform is used to obtain a SK diagram. It is shown that choice of mother wavelet function has great influence on the resulting SK diagram. The proposed wavelet is based on the impulse response of a damped single degree of freedom system. An optimization algorithm is used to optimize the SK diagram for fault detection. The method is tested for both simulated and experimental vibration data.

Intelligent fault diagnosis (IFD) based on deep learning methods has shown excellent performance, however, the fact that their implementation requires massive amount of data and lack of sufficient labeled data, limits their real-world application. In this paper, we propose a two-step technique to extract fault discriminative features using unlabeled and a limited number of labeled samples for classification. To this end, we first train an Autoencoder (AE) using unlabeled samples to extract a set of potentially useful features for classification purpose and consecutively, a Contrastive Learning-based post-training is applied to make use of limited available labeled samples to improve the feature set discriminability. Our Experiments—on SEU bearing dataset—show that unsupervised feature learning using AEs improves classification performance. In addition, we demonstrate the effectiveness of the employment of contrastive learning to perform the post-training process; this strategy outperforms Cross-Entropy based post-training in limited labeled information cases.

Torsional vibration of the power transmission system is one of the main factors which affects ride comfort and fatigue of the driveline components. These vibrations are caused by periodic changes in the gas pressure and inertial forces. To reduce these vibrations, dual mass flywheels (DMF) are used in some vehicles. DMFs are usually modelled as two disks connected with linear springs. However large rotation angle in DMFs can invalidate linear assumption. In this research, torsional vibration of a three-cylinder engine with nonlinear DMF is investigated and an analytical solution is obtained for the governing nonlinear equations of torsional vibrations under real engine torsional excitation for the first time. It should be noted that in the previous works, the torsional vibration equations of the DMF had been solved numerically. Analytical solution helps to study the effect of design parameters of DMF more easily. It is shown that the analytical and numerical solutions are well matched in steady-state conditions. Finally, a parametric study is performed and the effects of design parameters on the oscillation amplitude of the engine speed and flywheel output speed are presented.