Search results

With the development of deep learning-based analytical techniques, increased research has focused on fatigue data analysis methods based on deep learning, which are gaining in popularity. However, the application of deep neural networks in the material science domain is mainly inhibited by data availability. In this paper, to overcome the difficulty of multifactor fatigue life prediction with small data sets,

A multiple neural network ensemble (MNNE) is used, and an MNNE with a general and flexible explicit function is developed to accurately quantify the complicated relationships hidden in multivariable data sets. Moreover, a variational autoencoder-based data generator is trained with small sample sets to expand the size of the training data set. A comparative study involving the proposed method and traditional models is performed. In addition, a filtering rule based on the R2 score is proposed and applied in the training process of the MNNE, and this approach has a beneficial effect on the prediction accuracy and generalization ability.

A comparative study involving the proposed method and traditional models is performed. The comparative experiment confirms that the use of hybrid data can improve the accuracy and generalization ability of the deep neural network and that the MNNE outperforms support vector machines, multilayer perceptron and deep neural network models based on the goodness of fit and robustness in the small sample case.

The experimental results imply that the proposed algorithm is a sophisticated and promising multivariate method for predicting the contact fatigue life of a coating when data availability is limited.

A data generated model based on variational autoencoder was used to make up lack of data. An MNNE method was proposed to apply in the small data case of fatigue life prediction.

This paper aims to investigate the effect of aluminum addition on the microstructure and mechanical properties of Mg-8Gd-4Y-1Zn alloy.

Mg-8Gd-4Y-1Zn-xAl (x = 0, 0.5, 1.0, 1.5, 2.0 Wt.%) alloys were prepared by the conventional gravity casting technology, and then microstructures, phase composition and mechanical properties were investigated by material characterization method, systematically.

Results show that the as-cast microstructure of Mg-8Gd-4Y-1Zn alloy mainly consists of a-Mg matrix as well as Mg₁₂REZn (18 R LPSO structure), and island-like Mg₃(RE, Zn) phase is distributed at the grain boundary. The addition of a small amount of Al (0.5 Wt.%) can decrease the content of island-like Mg₃(RE, Zn) phase, but significantly increase the content of long-period stacking ordered (LPSO) structure, resulting in the improvement of both tensile strength and elongation of Mg-8Gd-4Y-1Zn alloy. However, the addition of excessive Al will consume Re element and decrease the amount of LPSO structure, leading to the decrease of tensile properties. When the content of Al is 0.5 Wt.%, the tensile strength and elongation are 225 MPa and 9.0% of Mg-8Gd-4Y-1Zn alloy, which are 14% and 29% higher than that of Mg-8Gd-4Y-1Zn alloy, respectively.

Adding aluminum to Mg-8Gd-4Y-1Zn alloy strengthens its mechanical properties. And the effect of Al content on the alloy strengthening. The formation mechanism of LPSO structure with different aluminum content was revealed.

Under the trend of global economic integration and the new context of stagflation, frequent fluctuations in international interest rates are exerting far-reaching impacts on the world economy. In this paper, the transmission mechanism of the impact of fluctuations in international interest rates (specifically, the American interest rate) on the bankruptcy risk in China's pillar industry, the construction industry (which is also sensitive to interest rates), is examined.

Using an improved contingent claims analysis, the bankruptcy risk of enterprises is calculated in this paper. Additionally, an individual fixed-effects model is developed to investigate the mediating effects of international interest rates on the bankruptcy risk in the Chinese construction industry. The heterogeneity of subindustries in the industrial chain and the impact of China's energy consumption structure are also analysed in this paper.

The findings show that fluctuations in international interest rates, which affect the bankruptcy risk of China's construction industry, are mainly transmitted through two major pathways, namely, commodity price effects and exchange rate effects. In addition, the authors examine the important impact of China's energy consumption structure on risk transmission and assess the transmission and sharing of risks within the industrial chain.

First, in the research field, the study of international interest rate risk is extended to domestic-oriented industries. Second, in terms of the research content, this paper is focused on China-specific issues, including the significant influence of China's energy consumption structure characteristics and the risk contagion (and risk sharing) as determined by the current development of the Chinese construction industry. Third, in terms of research methods a modified contingent claim analysis approach to bankruptcy risk indicators is adopted for this study, thus overcoming the problems of data frequency, market sentiment and financial data fraud, which are issues that are ignored by most relevant studies.