Buckling optimization of variable stiffness cylindrical shells through artificial intelligence techniques

Pitton, Stefano Francesco; Ricci, Sergio; Bisagni, Chiara

doi:10.1016/j.compstruct.2019.111513

Cited by 35 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed ANN model has been compared with selected experiments and has shown an extremely high utilization rate. In addition, other studies [21][22][23][24][25][26] have also confirmed the strong predictability of different ML models for the behavior of structural elements and different materials in the field of mechanics under different solicitations [8,9,[27][28][29][30].…”

Section: Introductionmentioning

confidence: 57%

Development of Hybrid Machine Learning Models for Predicting the Critical Buckling Load of I-Shaped Cellular Beams

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

The principal purpose of this work is to develop three hybrid machine learning (ML) algorithms, namely ANFIS-RCSA, ANFIS-CA, and ANFIS-SFLA which are a combination of adaptive neuro-fuzzy inference system (ANFIS) with metaheuristic optimization techniques such as real-coded simulated annealing (RCSA), cultural algorithm (CA) and shuffled frog leaping algorithm (SFLA), respectively, to predict the critical buckling load of I-shaped cellular steel beams with circular openings. For this purpose, the existing database of buckling tests on I-shaped steel beams were extracted from the available literature and used to generate the datasets for modeling. Eight inputs, considered as independent variables, including the beam length, beam end-opening distance, opening diameter, inter-opening distance, section height, web thickness, flange width, and flange thickness, as well as one output of the critical buckling load of cellular steel beams considered as a dependent variable, were used in the datasets. Three quality assessment criteria, namely correlation coefficient (R), root mean squared error (RMSE) and mean absolute error (MAE) were employed for assessment of three developed hybrid ML models. The obtained results indicate that all three hybrid ML models have a strong ability to predict the buckling load of steel beams with circular openings, but ANFIS-SFLA (R = 0.960, RMSE = 0.040 and MAE = 0.017) exhibits the best effectiveness as compared with other hybrid models. In addition, sensitivity analysis was investigated and compared with linear statistical correlation between inputs and output to validate the importance of input variables in the models. The sensitivity results show that the most influenced variable affecting beam buckling capacity is the beam length, following by the flange width, the flange thickness, and the web thickness, respectively. This study shows that the hybrid ML techniques could help in establishing a robust numerical tool for beam buckling analysis. The proposed methodology is also promising to predict other types of failure, as well as other types of perforated beams.

show abstract

Section: Introductionmentioning

confidence: 57%

Development of Hybrid Machine Learning Models for Predicting the Critical Buckling Load of I-Shaped Cellular Beams

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…However, improved tailoring opportunities are available by exploiting the concept of stiffness variability, using tow-steering and curvilinear stringers, separately or in combination. Potential gains offered by tow-steered panels are well-documented in the literature [1][2][3][4][5], and several studies clearly illustrated the possibility of improving buckling and postbuckling responses with respect to corresponding quasi-isotropic configurations. Recent works addressed also the effects of different kinematic theories when applied to the analysis of tow-steered panels [3,6,7].…”

Section: Introductionmentioning

confidence: 88%

Pre-buckling and Buckling Analysis of Variable-Stiffness, Curvilinearly Stiffened Panels

Vescovini

Oliveri

Pizzi

et al. 2019

Aerotec. Missili Spaz.

View full text Add to dashboard Cite

This work illustrates a fast numerical approach for analyzing the pre-buckling and buckling response of innovative panel configurations for aerospace structures. Specifically, the approach allows composite panels with variable-stiffness skins and stiffened by curvilinear stringers to be studied in a fast yet accurate manner. The method of Ritz is applied in conjunction with first-order theories for modeling the skin and the stiffeners, the former described referring to Mindlin plate theory, the latter to Timoshenko beam model. Due to the excellent convergence properties of the approach, pre-buckling stress distributions can be captured with reduced effort. Similarly, accurate buckling predictions can be obtained with relatively few degrees of freedom, much less with respect to typical models relying upon the use of finite elements. Results are presented for a number of test-cases from the literature, illustrating the potential of the proposed approach as a mean for performing preliminary studies with reduced computational effort.

show abstract

“…Optimization studies of fibre angles for variable-stiffness plates have demonstrated significant weight-savings due to enhanced mechanical properties in pre-and post-buckling [19][20][21]; reducing stress concentrations around cutouts [22]; and improving buckling of sandwich panels [23]. Variable-stiffness cylinders have been optimized for bending [24,25], buckling [26,27] and fundamental vibration frequency [28] using linear analyses. However, limited work has investigated the optimization of fibre angle of variable-stiffness cylinders to maximize the nonlinear buckling load in the presence of geometric imperfections.…”

Section: Introductionmentioning

confidence: 99%

Increasing reliability of axially compressed cylinders through stiffness tailoring and optimization

Lincoln

Pirrera

Groh

2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

The capabilities of the rapid tow shearing (RTS) process are explored to reduce the well-known imperfection sensitivity of axially compressed cylindrical shells. RTS deposits curvilinear carbon fibre tapes with a fibre-angle-thickness coupling that enables the in situ manufacturing of embedded rings and stringers. By blending the material’s elastic modulus and wall thickness smoothly across the cylindrical surface, the load paths can be redistributed favourably with a minimal-design approach that contains part count and weight while ameliorating imperfection sensitivity. A genetic algorithm that incorporates realistic manufacturing imperfections and axial stiffness penalty is used to maximize the 99.9% reliability load of straight fibre (SF) and RTS cylinders. The axial stiffness penalty ensures that reliability does not come at the expense of stiffness. The first-order second-moment method is used to calculate statistical moments that enable an estimate of the 99.9% reliability load. Due to the fibre-angle-thickness coupling of RTS, buckling data are normalized by mass and thickness. Compared to a quasi-isotropic laminate, which corresponds to the optimal eight-layer design for a perfect cylinder, the optimized SF and RTS laminates have a 6% and 8% greater 99.9% normalized reliability load. By relaxing the axial stiffness penalty, the performance benefit can be increased such that SF and RTS cylinders exceed the 99.9% normalized reliability load of an eight-layer quasi-isotropic laminate by 23% and 37%, respectively. Both improvements (with and without penalty functions) stem largely from a reduction in the variance of the buckling-load distribution, thereby demonstrating the potential of fibre-steered cylinders in reducing the imperfection sensitivity of cylindrical shells. This article is part of the theme issue ‘Probing and dynamics of shock sensitive shells’.

show abstract

Buckling optimization of variable stiffness cylindrical shells through artificial intelligence techniques

Cited by 35 publications

References 20 publications

Development of Hybrid Machine Learning Models for Predicting the Critical Buckling Load of I-Shaped Cellular Beams

Development of Hybrid Machine Learning Models for Predicting the Critical Buckling Load of I-Shaped Cellular Beams

Pre-buckling and Buckling Analysis of Variable-Stiffness, Curvilinearly Stiffened Panels

Increasing reliability of axially compressed cylinders through stiffness tailoring and optimization

Contact Info

Product

Resources

About