Effective Prediction of Bearing Fault Degradation under Different Crack Sizes Using a Deep Neural Network

Abstract

Exact evaluation of the degradation levels in bearing defects is one of the most essential works in bearing condition monitoring. This paper proposed an efficient evaluation method using a deep neural network (DNN) for correct prediction of degradation levels of bearings under different crack size conditions. An envelope technique was first used to capture the characteristic fault frequencies from acoustic emission (AE) signals of bearing defects. Accordingly, a health-related indicator (HI) calculation was performed on the collected envelope power spectrum (EPS) signals using a Gaussian window method to estimate the fault severities of bearings that served as an appropriate dataset for DNN training. The proposed DNN was then trained for effective prediction of bearing degradation using the Adam optimization-based backpropagation algorithm, in which the synaptic weights were optimally initialized by the Xavier initialization method. The effectiveness of the proposed degradation prediction approach was evaluated through different crack size experiments (3, 6, and 12 mm) of bearing faults.

Defect Size Evaluation of Cylindrical Roller Bearings with Compound Faults on the Inner and Outer Races

“…A Levenberg-Marquardt backpropagation neural network (BPNN) has also been used to predict inner race, outer race, and roller defect sizes [24]. A high-efficient assessment method using a deep neural network (DNN) was presented to correctly predict bearing degradation levels with a range of crack sizes [25]. Lu et al [26] proposed an innovative diagnosis model based on a deep convolutional network with the Bayesian optimization to recognize bearing defect severity.…”

Novel Bearing Fault Diagnosis Using Gaussian Mixture Model-Based Fault Band Selection

“…In that work, signal processing using Gaussian mixture model (GMM)-based windows is performed to select the fault frequency components from the envelope spectrum and later substitute them into the full envelope spectrum to get the residual signals, which are then used for the Health index calculation and fault classification. Later, Nguyen et al used the same GMM-windows with health index calculation technique for bearing fault diagnosis using a Deep Neural Network [ 38 ].…”

Reliable Method to Detect Alloy Soldering Fractures under Accelerated Life Test

“…ALT can take the form of "Acceleration of the rate of use" or "Overload and acceleration". The ALT methods due to the acceleration of the usage rate and the test data can be analyzed with typical life data and methods of analysis, the acceleration of excessive stresses [32,[34][35][36][37][38].…”

“…The purpose of the known components and the reliability of the systems is a fundamental issue. The reliability assessment is normally based on the collection of field data during the daily work of the assets [34][35][36][37]. If the data collection is not automated, it is a laborious activity due to a very long period required.…”

“…Consequently, the reported data come from a truncated distribution and the number of uninformed premature failures is unknown. Inferences are developed for a Weibull ALT model in which transformed scale and shape parameters are expressed as linear combinations of environmental functions (stress) [11][12][13][15][16][17][18]32,[36][37][38].…”