Fault diagnosis of rolling bearing of wind turbines based on the Variational Mode Decomposition and Deep Convolutional Neural Networks

Variational mode decomposition provides a feasible method for non-stationary signal analysis, but the method is still not adaptive, which greatly limits the wide application of the method. Therefor...

A new fault diagnosis method based on adaptive spectrum mode extraction

Remaining useful life estimation using deep metric transfer learning for kernel regression

A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing

Intelligent fault diagnosis techniques play an important role in improving the abilities of automated monitoring, inference, and decision making for the repair and maintenance of machinery and processes. In this article, a modified stacked autoencoder (MSAE) that uses adaptive Morlet wavelet is proposed to automatically diagnose various fault types and severities of rotating machinery. First, the Morlet wavelet activation function is utilized to construct an MSAE to establish an accurate nonlinear mapping between the raw nonstationary vibration data and different fault states. Then, the nonnegative constraint is applied to enhance the cost function to improve sparsity performance and reconstruction quality. Finally, the fruit fly optimization algorithm is used to determine the adjustable parameters of the Morlet wavelet to flexibly match the characteristics of the analyzed data. The proposed method is used to analyze the raw vibration data collected from a sun gear unit and a roller bearing unit. Experimental results show that the proposed method is superior to other state-of-the-art methods. 

/pdf/modified-stacked-autoencoder-using-adaptive-morlet-wavelet-2juyyzt7.pdf

Modified Stacked Autoencoder Using Adaptive Morlet Wavelet for Intelligent Fault Diagnosis of Rotating Machinery

Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator

A hybrid DBN-SOM-PF-based prognostic approach of remaining useful life for wind turbine gearbox

Gearboxes are critical transmission components in the drivetrain of wind turbine, which have a dominant failure rate and the highest downtime loss in all wind turbine subsystems. However, load vari...

Performance degradation assessment of wind turbine gearbox based on maximum mean discrepancy and multi-sensor transfer learning:

With the development of error compensation technology, reliability and stability of error identification deserve much attention. And rotary axis errors of five-axis machine tool are the main error sources which result in machining inaccuracy. Hence, a new method for position-dependent geometric error (PDGE) identification of a rotary table using double ball bar was proposed in this paper. Especially, only the targeted rotary table was driven during the ball bar test, which can reduce the impact of interference error sources. During the measurement, the ball on the spindle holds still, and the ball on the rotary table rotates around the rotation axis. There are three mounting positions of magnetic socket on the rotary table. Total six measurement procedures of cone test are executed to obtain enough measuring results by setting different positions of magnetic socket ball. These measuring results are used to construct the identification model based on homogeneous transformation matrix (HTM). The impact of installation errors of the double ball bar on identified results was analyzed. The uncertainty of identified errors could be reduced with the single-axis driven and the installation parameter optimization. At last, testing experiments on a five-axis machine tool were conducted to verify the proposed method. The results confirm that the method is an effective way to identify PDGEs of a rotary axis, and the accuracy of identified results is improved.

Single-axis driven measurement method to identify position-dependent geometric errors of a rotary table using double ball bar

As one kind of the most important non-Newtonian fluids, Herschel-Bulkley fluids have been applied in practical engineering widely. In order to improve the stability and accuracy in the simulation of Herschel-Bulkley fluids with lattice Boltzmann method (LBM), a modified lattice Boltzmann method was proposed. With Poiseuille flow as the example, the shear-thinning fluids and the shear-thickening fluids were used, respectively, to introduce the method in detail. The comparison between the velocity distributions and the analytical solutions demonstrated the feasibility of the modified method. Also the effect of the power law index, lattice nodes, and the region of the shear rate on the relative error was discussed. Then, the method was applied into the simulation of the cement paste flow in the 3D printing extruder. The streamline figure was obtained and then conducted the flow simulation by the modified method and multiple-relaxation-time lattice Boltzmann method (MRT-LBM), respectively; the comparison further proved the modified method was feasible for Herschel-Bulkley fluids.

Weiwei Wu

Papers

Incipient fault diagnosis of rolling bearings based on adaptive variational mode decomposition and Teager energy operator

A hybrid DBN-SOM-PF-based prognostic approach of remaining useful life for wind turbine gearbox

Performance degradation assessment of wind turbine gearbox based on maximum mean discrepancy and multi-sensor transfer learning:

Single-axis driven measurement method to identify position-dependent geometric errors of a rotary table using double ball bar

A modified lattice boltzmann method for herschel-bulkley fluids