In materials science,data-driven methods accelerate material discovery and optimization while reducing costs and improving success *** regression is a key to extracting material descriptors from large datasets,in part...
详细信息
In materials science,data-driven methods accelerate material discovery and optimization while reducing costs and improving success *** regression is a key to extracting material descriptors from large datasets,in particular the Sure Independence Screening and Sparsifying Operator(SISSO)*** SISSO needs to store the entire expression space to impose heavy memory demands,it limits the performance in complex *** address this issue,we propose a RF-SISSO algorithm by combining Random Forests(RF)with *** this algorithm,the Random Forests algorithm is used for prescreening,capturing non-linear relationships and improving feature selection,which may enhance the quality of the input data and boost the accuracy and efficiency on regression and classification *** a testing on the SISSO’s verification problem for 299 materials,RF-SISSO demonstrates its robust performance and high ***-SISSO can maintain the testing accuracy above 0.9 across all four training sample sizes and significantly enhancing regression efficiency,especially in training subsets with smaller sample *** the training subset with 45 samples,the efficiency of RF-SISSO was 265 times higher than that of original *** collecting large datasets would be both costly and time-consuming in the practical experiments,it is thus believed that RF-SISSO may benefit scientific researches by offering a high predicting accuracy with limited data efficiently.
Modal mass is the important dynamic parameter in weak component research of machine tool structure and also for its control design and load design. Modal mass matrix is defined as the multiplication of mass matrix of ...
详细信息
Modal mass is the important dynamic parameter in weak component research of machine tool structure and also for its control design and load design. Modal mass matrix is defined as the multiplication of mass matrix of a machine tool and its corresponding modal shape matrix. Currently, the big problem is that the mass matrix is hard to get for the calculation of modal mass matrix. Traditional method such as the finite element method cannot acquire the mass matrix well because the overall mass matrix of complex systems cannot be given by experience and the mass matrix in finite element analysis is so large that the computer hard disk will be blasted. In addition to finite element method, the UMM method is used commonly but the noise contained in the mode of the data processing is mixed into the mass matrix, resulting in the inaccurate result and even failure in severe cases. So, there is an urgent need for a method of directly obtaining the mass matrix based on a general equation of multi-degree-of-freedom vibration system from a data source, and then used to calculate the modal mass. In this paper, Genetic programming algorithm (GP) in symbolicregression as an evolution computation method is used to search out the equation expression structure and its coefficients among a group of variances including displacement, velocity, acceleration and external excitation force. And the mass matrix is contained in the equations' coefficients. In addition, its performance is compared with LRA method and PSO method.
To investigate the effect of various factors on bearing stress response, Huber-Hencky-von Mises stress serves as a bridge, the equivalent interrelation between radial loading, axial loading, and temperature of bearing...
详细信息
To investigate the effect of various factors on bearing stress response, Huber-Hencky-von Mises stress serves as a bridge, the equivalent interrelation between radial loading, axial loading, and temperature of bearing is studied using finite element method (FEM). symbolicregression (SR) algorithm is employed to analyze simulation results, establishing a functional expression between independent and dependent variables by optimizing combinations of variables, constants, and functional forms. The results showed that within the specified force and temperature values, the curved surface of the equivalent correlation function, trained using the SR algorithm, demonstrates smoothness. Both training and validation data exhibit a strong correlation with this curved surface. Among the three factors, temperature exerts the greatest influence on bearing stress values, followed by radial loading, and axial loading components had the smallest impact.
The paper presents a numerical investigation on the retrofitting of Hot-Rolled Steel (HRS) beams using ColdFormed Steel (CFS) encasing channels. The open cross-section HRS channel is transformed into a closed crosssec...
详细信息
The paper presents a numerical investigation on the retrofitting of Hot-Rolled Steel (HRS) beams using ColdFormed Steel (CFS) encasing channels. The open cross-section HRS channel is transformed into a closed crosssection by encasing the CFS channel. This transformation increases the torsional rigidity of the structural member and helps in reducing the vulnerability of Lateral-Torsional Buckling (LTB). Parametric studies were carried out using numerical analysis. The existing experimental results were used for validation of the numerical model. A total of 600 numerical simulations including design parameters such as thickness of the CFS channel, intermediate spacing between the spot welds (connecting HRS and CFS channels), slenderness ratio, and the cross-sectional dimensions of the HRS beam were considered. The analyses indicated that the effectiveness of the retrofitting increases with an increase in the slenderness ratio of the HRS channel. Machine Learning (ML) method called symbolicregression (SR) was used to formulate an equation predicting the increment in the moment capacity as a function of parameters investigated. Finally, a simple design concept is suggested to determine the required CFS channel thickness and intermediate spot weld spacing to achieve the required increment in the moment capacity after retrofitting.
暂无评论