Wyniki wyszukiwania - BazTech

1

Wasserstein Distance-EEMD Enhanced Multi-Head Graph Attention Network for Rolling Bearing Fault Diagnosis Under Different Working Conditions

Wang Xingbing, Yao Yunfeng, Gao Chen

Eksploatacja i Niezawodność

|

2024

|

Vol. 26, no. 2

art. no. 184037

EN

Traditional fault diagnosis models often overlook the interconnections between segments of vibration data, resulting in the loss of critical feature information. Additionally, the vibration signals of rolling bearings exhibit non-linear behaviors during operation. Therefore, an efficient fault diagnosis model tailored for rolling bearings is proposed in this paper. In the proposed model, the 1D vibration signals are first preprocessed using ensemble empirical mode decomposition (EEMD). This technique generates multiple intrinsic mode functions (IMF) as individual nodes. The percentage distance between each node is calculated using the Wasserstein distance (WD) to capture the relationships between nodes and use it as the edge weights to construct a node graph. This unique approach enhances the transformation of 1D vibration signals into a node graph representation, preserving important information. An improved multi-head graph attention network (MGAT) model is established to extract features and perform classification on the node graph. This MGAT model effectively utilizes the relationships between nodes and enhances the accuracy of fault diagnosis. The experimental results demonstrate that the proposed method achieves higher accuracy compared to similar modelswhile requiring less processing time. The proposed approach contributes significantly to the field of fault diagnosis for rolling bearings and provides a valuable tool for practical applications.

2

Limit behavior of the invariant measure for Langevin~dynamics

Barrera Gerardo

Probability and Mathematical Statistics

|

2022

|

Vol. 42, Fasc. 1

143--162

EN

We consider the Langevin dynamics on Rd with an overdamped vector field and driven by multiplicative Brownian noise of small amplitude √ϵ, ϵ>0. Under suitable assumptions on the vector field and the diffusion coefficient, it is well-known that it has a unique invariant probability measure μ ϵ . We prove that as ε tends to zero, the probability measure ϵd/2μ ϵ(√ϵdx) converges in the p--Wasserstein distance for p∈[1,2] to a Gaussian measure with zero-mean vector and non-degenerate covariance matrix which solves a Lyapunov matrix equation. Moreover, the error term is estimated. We emphasize that generically no explicit formula for μϵ can be found.

3

Finiteness of entropy for granular media equations

Tugaut Julian

Probability and Mathematical Statistics

|

2019

|

Vol. 39, Fasc. 1

75--84

EN

The current work deals with the granular media equation whose probabilistic interpretation is the McKean-Vlasov diffusion. It is well known that the Laplacian provides a regularization of the solution. Indeed, for any t > 0, the solution is absolutely continuous with respect to the Lebesgue measure. It has also been proved that all the moments are bounded for positive t. However, the finiteness of the entropy of the solution is a new result which will be presented here.

4

Sliced Generative Models

Knop Szymon, Mazur Marcin, Tabor Jacek, Podolak Igor T., Spurek Przemysław

Schedae Informaticae

|

2018

|

Vol. 27

69--79

EN

In this paper we discuss a class of AutoEncoder based generative models based on one dimensional sliced approach. The idea is based on the reduction of the discrimination between samples to one-dimensional case. Our experiments show that methods can be divided into two groups. First consists of methods which are a modification of standard normality tests, while the second is based on classical distances between samples. It turns out that both groups are correct generative models, but the second one gives a slightly faster decrease rate of Fréchet Inception Distance (FID).

5

On Some Goodness of Fit Tests for Normality Based on the Optimal Transport Distance

Mazur Marcin, Kościelniak Piotr

Schedae Informaticae

|

2018

|

Vol. 27

59--68

EN

We apply the optimal transport distance to construct two goodness of t tests for (univariate) normality. The derived statistics are then compared with those used by the Shapiro-Wilk, the Anderson-Darling and the Cramervon Mises tests. In particular, we preform Monte Carlo experiments, involving computations of the test power against some selected alternatives and wide range of sample sizes, which show eciency of the obtained test procedures.