FEM Simulation-Based Generative Adversarial Networks to Detect Bearing Faults

Gao, Yun; Liu, Xiaoyang; Xiang, Jiawei

doi:10.1109/tii.2020.2968370

Cited by 138 publications

(45 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past few decades, a lot of novelty approaches have been proposed [6][7][8]. Time-frequency (TF) method techniques have been developed to allow access to the timefrequency energy behavior of nonstationary signals.…”

Section: Introductionmentioning

confidence: 99%

Kernel Regression Residual Decomposition Method to Detect Rolling Element Bearing Faults

Wang

Sheng

Deng

et al. 2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

The raw vibration signal carries a great deal of information representing the mechanical equipment's health conditions. However, in the working condition, the vibration response signals of faulty components are often characterized by the presence of different kinds of impulses, and the corresponding fault features are always immersed in heavy noises. Therefore, signal denoising is one of the most important tasks in the fault detection of mechanical components. As a time-frequency signal processing technique without the support of the strictly mathematical theory, empirical mode decomposition (EMD) has been widely applied to detect faults in mechanical systems. Kernel regression (KR) is a well-known nonparametric mathematical tool to construct a prediction model with good performance. Inspired by the basic idea of EMD, a new kernel regression residual decomposition (KRRD) method is proposed. Nonparametric Nadaraya–Watson KR and a standard deviation (SD) criterion are employed to generate a deep cascading framework including a series of high-frequency terms denoted by residual signals and a final low-frequency term represented by kernel regression signal. The soft thresholding technique is then applied to each residual signal to suppress noises. To illustrate the feasibility and the performance of the KRRD method, a numerical simulation and the faulty rolling element bearings of well-known open access data as well as the experimental investigations of the machinery simulator are performed. The fault detection results show that the proposed method enables the recognition of faults in mechanical systems. It is expected that the KRRD method might have a similar application prospect of EMD.

show abstract

Section: Introductionmentioning

confidence: 99%

Kernel Regression Residual Decomposition Method to Detect Rolling Element Bearing Faults

Wang

Sheng

Deng

et al. 2021

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liu X et al 5 used extreme learning machine method in gear fault diagnosis. Gao Y et al 6 employed generative adversarial networks to detect bearing fault. Hence, for head sheaves, it is of great feasibility and significance to build an online fault diagnosis system.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of head sheaves based on vibration measurement and data mining method

Yao

Xiao

et al. 2020

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Head sheaves are critical components in a mine hoisting system. It is inconvenient for workers to climb up to the high platform for overhaul and maintenance, and there is an urgent need for condition monitoring and fault diagnosis of head sheaves. In this article, Fault Tree Analysis is employed to investigate the faults of head sheaves, and headframe inclination, bearing faults, and head sheave swing are the three focal faults discussed. A test rig is built to simulate these three faults and collect vibration signals at bearing blocks. Based on vibration signals, some characteristic parameters are calculated, and together with the fault labels, a sample set is established. Before the selection of an excellent data mining method, these features are screened according to their significance, and then, gain–percentile chart, response–percentile chart, and prediction accuracy are used as the criteria to make a comparison between data mining algorithms. The result shows the boosted tree algorithm outperforms others and presents excellent performance on the evaluation of head sheave faults. Finally, this method is verified on a data set of 20 samples, and each case is identified correctly, which illustrates its high applicability.

show abstract

“…Figure 1 shows the framework of calculating the loss rate of linings bearing capacity scheme. MLLBC summarizes four steps by referring to logic of the usage on the existing toolbox [9], [57]: 1) building a physical model of tunnel lining to obtain the loss rate of the lining under different conditions (such as void ratio, stratum stiffness and the angle of load); 2) augmenting simulation data with finite element analysis tool; 3) training the machine learning models in the toolbox with the simulation data of different conditions and the corresponding bearing capacity loss rate; 4) calculating the bearing capacity loss rate under various conditions by one of the pre-trained machine learning models.…”

Section: Introductionmentioning

confidence: 99%

MLLBC: A Machine Learning Toolbox for Modeling the Loss Rate of the Lining Bearing Capacity

Zhang

Wu²,

Zhao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Testing the health of tunnels, as a branch of highway operation, has an extremely important application in public property and even life safety. Among them, there are many factors that cause the tunnel to deform or collapse. The conventional methods use the finite element method (FEM) which are to simulate the bearing capacity loss rate of the lining by using the mechanical method. However, it takes a long time to calculate the stress-strain-situation of the lining model under each condition. This paper explores the machine learning to calculate the loss rate of the lining bearing capacity under more conditions based on FEM simulation data. Here, we establish a machine learning toolbox for modeling the loss rate of the lining bearing capacity named ''MLLBC'', which contains three main components: 1) data loading; 2) machine learning model deployment; 3) performance evaluation. To ensure the fairness of model evaluation, ten machine learning models use a unified code library. We also conduct experiments on our new dataset which is the loss rate of the lining bearing capacity with different data amounts, as well as experiments on the goodness of model fitting under different ranges of various variables. INDEX TERMS Toolbox, the loss rate of the lining bearing capacity, machine learning, tunnel health.

show abstract

FEM Simulation-Based Generative Adversarial Networks to Detect Bearing Faults

Cited by 138 publications

References 41 publications

Kernel Regression Residual Decomposition Method to Detect Rolling Element Bearing Faults

Kernel Regression Residual Decomposition Method to Detect Rolling Element Bearing Faults

Fault diagnosis of head sheaves based on vibration measurement and data mining method

MLLBC: A Machine Learning Toolbox for Modeling the Loss Rate of the Lining Bearing Capacity

Contact Info

Product

Resources

About