A New Deep Learning Framework for Imbalance Detection of a Rotating Shaft.

Rotor unbalance is the most common cause of vibration in industrial machines. The unbalance can result in efficiency losses and decreased lifetime of bearings and other components, leading to system failure and significant safety risk. Many complex analytical techniques and specific classifiers algorithms have been developed to study rotor imbalance. The classifier algorithms, though simple to use, lack the flexibility to be used efficiently for both low and high numbers of classes. Therefore, a robust multiclass prediction algorithm is needed to efficiently classify the rotor imbalance problem during runtime and avoid the problem's escalation to failure. In this work, a new deep learning (DL) algorithm was developed for detecting the unbalance of a rotating shaft for both binary and multiclass identification. The model was developed by utilizing the depth and efficacy of ResNet and the feature extraction property of Convolutional Neural Network (CNN). The new algorithm outperforms both ResNet and CNN. Accelerometer data collected by a vibration sensor were used to train the algorithm. This time series data were preprocessed to extract important vibration signatures such as Fast Fourier Transform (FFT) and Short-Time Fourier Transform (STFT). STFT, being a feature-rich characteristic, performs better on our model. Two types of analyses were carried out: (i) balanced vs. unbalanced case detection (two output classes) and (ii) the level of unbalance detection (five output classes). The developed model gave a testing accuracy of 99.23% for the two-class classification and 95.15% for the multilevel unbalance classification. The results suggest that the proposed deep learning framework is robust for both binary and multiclass classification problems. This study provides a robust framework for detecting shaft unbalance of rotating machinery and can serve as a real-time fault detection mechanism in industrial applications.

A Novel GBSM for Non-Stationary V2V Channels Allowing 3D Velocity Variations.

A new non-stationary (NS) geometry-based stochastic model (GBSM) is presented for developing and testing the communication systems of vehicle-to-vehicle (V2V) applications, which considers the three-dimensional (3D) scattering environments and allows 3D velocity as well. In this paper, the proposed GBSM for NS V2V channels allowed 3D velocity variations and was more suitable for actual V2V communications because it provided smoother transitions between the consecutive channel segments. The time-variant channel coefficient and the channel parameters, i.e., Doppler frequencies, path delay and power, angle of arrival (AoA), and angle of departure (AoD), were analyzed and derived. Likewise, the theoretical statistical properties as the probability density function (PDF), the auto-correlation function (ACF), and Doppler power spectral density (DPSD) were also analyzed and derived under the von Mises-Fisher (VMF) distribution. Finally, the theoretical and measured results were well coordinated alongside the implemented results, which confirmed the feasibility of the introduced model along with the theoretical expressions.