scholarly journals SVR Prediction Algorithm for Crack Propagation of Aviation Aluminum Alloy

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jincai Chang ◽  
Zhihang Wang ◽  
Qingyu Zhu ◽  
Zhao Wang

Aluminum alloy material is an important component material in the safe flight of aircraft. It is very important and necessary to predict the fatigue crack growth between holes of aviation aluminum alloy materials. At present, the investigation on the prediction of the cracks between two holes and multiholes is a key problem to be solved. Due to the fact that the fatigue crack growth test of aluminum alloy plate with two or three holes was carried out by the MTS fatigue testing machine, the crack length growth data under different test conditions were obtained. In this paper, support vector regression (SVR) was used to fit the crack data, and the parameters of SVR are optimized by the grid search algorithm at the same time. And then the model of SVR to predict the crack length was established. Discussion on the results shows that the prediction model is effective. Furthermore, the crack growth between three holes was predicted accurately through the model of the crack law between two holes under the same load form.

2012 ◽  
Vol 06 ◽  
pp. 318-323
Author(s):  
A. KUSABA ◽  
S. OKAZAKI ◽  
M. ENDO ◽  
K. YANASE

As recognized, flaking-type failure is one of the serious problems for railroad tracks and bearings. In essence, flaking-type failure is closely related to the growth of the shear-mode (Mode-II and Mode-III) fatigue crack. In our research group, it is demonstrated that a shear-mode fatigue crack can be reproduced for cylindrical specimens by applying the cyclic torsion in the presence of the static axial compressive stress. However, a biaxial servo-hydraulic fatigue testing machine is quite expensive to purchase and costly to maintain. The low testing speed (about 10Hz) of the testing machine further aggravates the situation. As a result, study on shear-mode fatigue crack growth is still in the nascent stage. To overcome the difficulties mentioned above, in this research activity, we developed a high-performance and cost-effective testing machine to reproduce the shear-mode fatigue crack growth by improving the available resonance-type torsion fatigue testing machine. The primary advantage of using the resonance-type torsion fatigue testing machine is cost-efficiency. In addition, the testing speed effectively can be improved, in comparison with that of a biaxial servo-hydraulic fatigue testing machine. By utilizing the newly-designed testing machine, we have demonstrated that we can successfully reproduce the shear-mode fatigue crack.


2012 ◽  
Vol 476-478 ◽  
pp. 2435-2439 ◽  
Author(s):  
Chih Chung Ni

Compact tension specimens cut from 2024-T351 aluminum-alloy plate were used for Vickers hardness tests under low-force scale and then for fatigue crack growth tests under sinusoidal loads, and the scattered data sets obtained including Vickers hardness, initiation cycle and specimen life, exponent m and intercept C of Paris-Erdogan law were collected as a factor set with five factor series for analysis of grey relational grade. Nominal value method was adopted for the preprocess referred to as grey relational generation to obtained new factor series, and then Hsia’s method was used to calculate the grey relational grades among new factor series. The analyzed result named global grey relational grade in matrix form with dimension of shows three main findings: (1) Vickers hardness has the largest influence on specimen life, and vice versa. (2) Vickers hardness, specimen life, and m have a large influence on each other. (3) C has the least influence on any other factors, and vice versa.


2013 ◽  
Vol 690-693 ◽  
pp. 1779-1783 ◽  
Author(s):  
Chih Chung Ni

The study is focused on the investigations into applying the grey model with rolling check to the prediction of fatigue crack growth. Fatigue crack growth data of compact tension specimens made of 2024-T351 aluminum-alloy plate tested under constant-amplitude loads were carried out for verifications. The optimal values of parameter affecting the accuracy of prediction were found by variational analysis. Using four experimental crack lengths as the source series and the optimal value of parameter for modelling with rolling check, it was found almost entire fatigue crack growth curve of the specimen can be predicted accurately. Besides, the analyzed results including number of rolling check performed, loading cycle corresponding to the maximum predicted crack length, fractured cycle of specimen, cycle ratio of loading cycle and fractured cycle, and percentage of error between maximum predicted and experimental crack length for all specimens were tabulated.


2019 ◽  
Vol 2019 ◽  
pp. 1-11
Author(s):  
Xu Du ◽  
Yuting He ◽  
Tianyu Zhang ◽  
Chao Gao ◽  
Teng Zhang ◽  
...  

Fatigue crack growth test for 2A12-T4 aluminum alloy was conducted under constant amplitude loading, and the scatter of fatigue crack growth was analyzed by using experimental data based on mathematical statistics. A probabilistic modeling method was introduced to describe the crack growth behavior of 2A12-T4 aluminum alloy. The posterior distribution of model parameter is obtained based on diffuse prior distribution and fatigue crack test data, which is through Bayesian updating. Based on posterior samples of model parameter, the simulation steps and approach give us the crack length exceedance probability, the cumulative distribution function of loading cycle number, and scatter of crack length and loading cycle number, of which simulation results were used to verify the veracity and superiority of the proposed model versus the experimental results. In the present study, it can be used for the reliability assessment of aircraft cracked structures.


2011 ◽  
Vol 291-294 ◽  
pp. 941-944
Author(s):  
Zheng Lun Wang ◽  
Zhi Xiang Wang

The fatigue crack growth behavior of weld metal (WM), heat affected zone(HAZ) and base metal(BM) of Duplex Stainless Steel 2205(DSS) has been determined at high-frequency fatigue testing machine. The results show that the fatigue crack growth rate of WM is slowest and the ability to resist fatigue crack growth is highest in the three parts. Secondly, the sensitivity caused by the stress change of WM is the highest, followed by HAZ, and the BM is the weakest.


2012 ◽  
Vol 503-504 ◽  
pp. 991-994
Author(s):  
Zhi Xiang Wang ◽  
Zheng Lun Wang ◽  
Xin Zhang

The fatigue crack growth behavior of weld metal (WM), heat affected zone (HAZ) and base metal(BM) of Duplex Stainless Steel (DSS) 2205 standard sample was tested in different stress ratios at HF fatigue testing machine. ANSYS analysis software was used to simulate the fatigue crack growth rate of the steel under different stress ratio. Regression equations and da / dK-ΔK curves of experiment and simulation are compared and analyzed. The results show that the fatigue crack growth rate of WM is slowest and the ability to resist fatigue crack growth is highest among the three parts, the lowest is BM. Secondly, the sensitivity of the rate caused by the stress change of WM is the highest, and the lowest is BM. The simulation of fatigue crack growth rate of DSS 2205 is completely correct and feasible by the experiment.


1977 ◽  
Vol 99 (4) ◽  
pp. 306-312 ◽  
Author(s):  
R. L. Tobler ◽  
R. P. Reed

The fatigue crack growth and fracture resistance of a 5083-0 aluminum alloy plate were investigated at four temperatures in the ambient-to-cryogenic range—295, 111, 76, and 4 K. J-integral test methods were applied using compact specimens 3.17 cm thick, and the value of J required to initiate crack extension (JIc) is reported as an index of fracture toughness. The fracture toughness was orientation dependent, with anisotropy accounting for JIc variations of up to a factor of 2. For specimens having fracture planes parallel to the rolling direction, JIc increases progressively from 9 to 25 kJm−2 as temperature decreases between 295 and 4 K. In contrast, the fatigue crack growth rates (da/dN) are insensitive to specimen orientation. The fatigue crack growth rates at cryogenic temperatures are up to 10 times lower than in air at room temperature, but are virtually constant between 111 and 4 K.


Sign in / Sign up

Export Citation Format

Share Document