Search

In this study, we propose an innovative approach that enhances the performance of the backpropagation (BP) neural network in predicting the low‐cycle fatigue life of Ti‐6Al‐4V alloy by improving the dung beetle optimization (DBO) algorithm with the maximin Latin hypercube design (MLHD) strategy. To address the challenges posed by complex geometric components under different temperature conditions, this research employs finite element simulation to expand the limited experimental dataset and utilizes these data to further guide and optimize the MLHD_DBO_BP model. Test results indicate that the proposed MLHD_DBO_BP model significantly outperforms the traditional finite element method (FEM) and other neural network models in terms of fatigue life prediction performance. This research demonstrates the effectiveness of machine learning models that combine experimental and simulation data in predicting the low‐cycle fatigue life of Ti‐6Al‐4V alloy. [ABSTRACT FROM AUTHOR]

Aiming at the vibration displacement signals of cracked rotors is unstable and non-linear,and the fault features are extracted difficultly,and the sample collection is lacking in the initial stage of fault,the crack fault diagnosis method based on Variational Mode Decomposition and AR model is proposed. A number of Intrinsic Mode Function are obtained by VMD as the preprocessing of the AR model. The AR model for each IMF component is established. The variance of the model parameters and residuals is calculated by the least square method. The model parameters and the variance of the residual are used as the characteristic vector of the system state. From the Mahalanobis distance and setting the corresponding weighted parameters,the synthetic distance is used to diagnose crack fault of rotor. Through the analysis of the experimental data,the feasibility of the fault diagnosis method based on the variational mode decomposition and the AR model are successfully verified,which provides a method for the fault diagnosis of the rotor,and the shortcomings of AR model in the diagnosis of rotor crack fault are overcome.

With the implementation of the green development strategy and the "double carbon goal", as an important energy for sustainable development, wind power has been widely researched and vigorously developed across the world. Wind speed prediction has a major impact on the grid dispatching of wind power connection. Most current studies only focus on the deterministic prediction of wind speed. However, the traditional deterministic forecast only provides the single wind speed prediction results and cannot meet the diverse demands of dispatchers. To bridge the gap, a wind speed point-interval forecasting method is proposed that utilizes empirical wavelet transform, an improved wild horse optimization algorithm, a multi-predictor, and improved kernel density estimation. This method decomposes the wind speed sequence into stationary subsequences through empirical wavelet transform, and then optimizes three basic learners with completely different learning mechanisms to form an ensemble model using the modified wild horse optimization algorithm. Finally, the uncertainty is analysed using an improved kernel density estimation. The datasets of three sites from America's national renewable energy laboratory are used for comparison experiments with other models, and the predictions are discussed from different angles. The simulation results demonstrate that the model can produce high-precision deterministic results and high-quality probabilistic results. The reference information the model provides can be extremely valuable for scheduling operators. [ABSTRACT FROM AUTHOR]

Phase-field model was employed to quantitatively study the effect of convection on pattern selection and growth rate of 2D and 3D dendrite tip, as well as the effect of the different convection velocity on the dendritic growth. The calculated results show that crystal is asymmetric in the priority direction of growth under flow. The dentritic growth is promoted in the upstream region and suppressed in the downstream region. Convection can cause deviation in the dendrite growth direction and the preferred direction of the columnar crystals. It has been found that both primary dendrite stem and secondary dendrite arm deflect significantly towards upstream direction, secondary dendrite arm in upstream direction is more developed than the primary dendrite in downstream direction.

On the basis of the linearized fluid forces acting on the rotor obtained directly by using the two-dimensional Navier-Stokes equations, the stability of symmetrical rotors with a cylindrical chamber partially filled with a viscous incompressible fluid is investigated in this paper. The effects of the parameters of rotor system, such as external damping ratio, fluid fill ratio, Reynolds number and mass ratio, on the unstable regions are analyzed. It is shown that for the stability analysis of fluid filled rotor systems with external damping, the effect of the fluid viscosity on the stability should be considered. When the fluid viscosity is included, the adding external damping will make the system more stable and two unstable regions may exist even if rotors are isotropic in some casIs.