Balancing Composite Motion Optimization and Artificial Neural Network for the Prediction of Critical Load of Concrete-Filled Steel Tubes Under Axial Compression

Duong, Huan Thanh; Le, Tien-Thinh; Nguyen, X.; Le, Minh Vuong; Phan, Hieu Chi; Le, Lu Minh; Nguyen, Van-Hai

doi:10.1007/978-3-031-22200-9_31

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, the weights and bias of each neuron are adjusted to identify the optimal set of parameters for the model. Mathematically, the function f in equation (9) is expressed below for the problem in question 42 :…”

Section: Methodsmentioning

confidence: 99%

Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded material plate

Duong

Phan

2023

Advances in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

Functionally Graded Material (FGM) plate is a complicated structure with complex allocation of spatially changing proportions of ceramic and metal within the matter. Various analytical and numerical methods have been applied with a view to evaluating the critical load of FGM plate. However, these conventional methods struggle when the computational complexity is significant, which represents an obstacle to incorporation with other advanced techniques where computational power is required (e.g. optimization or random simulations). The Neural Network (NNet) model has been successfully applied to resolve this issue. However, the conventional NNet requires proper configuration to take advantage of the model, and thus, careful parameter tuning is required. Furthermore, the NNet is typically a “black box,” where the prediction mechanism is hidden. This paper establishes an optimized architecture for NNet, with parametric study of the model’s hyperparameters. Variance propagation is also applied to observe the variation of the model’s performance on random sub-databases splintered from the database. To this end, the explicit expression of the trained NNet model is provided after mathematically deploying the hidden algebra behind an NNet prediction. The developed model has very promising evaluation metrics: R2, MAE, and RMSE on the test set are 0.999925, 0.067516, and 0.146438, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded material plate

Duong

Phan

2023

Advances in Mechanical Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Phan-Chi et al [30] amalgamated BCMO and ANN to optimize the model of rectangular concretefilled steel tube short columns. Le-Tien et al [31] employed BCMO to forecast the critical load of concrete-filled steel tubes under axial compression. The fundamental concept underlying the BCMO algorithm revolves around harmonizing the exploratory and exploitative movements of potential solutions within the solution space, which is assumed to be Cartesian.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Stiffened Composite Plate Using Balancing Composite Motion Optimization

Nguyen,

Lam,

Trieu

et al. 2023

tvujs

View full text Add to dashboard Cite

Recently, metaheuristic optimization algorithms have been studied and applied in many fields of engineering, especially in solving structural optimization problems. For structures with complex behaviors, the selection of a suitable optimization algorithm significantly increases the computational efficiency and the accuracy of the solution. In this paper, we investigate the optimization problem of stiffened composite plates using Balancing Composite Motion Optimization. The core idea of the Balancing Composite Motion Optimization algorithm is that the searching movements of candidate solutions are compositely equalized in both global and local ones in the solution space of solving the fiber optimization problem of stiffened composite plates. A candidate solution can move closer to better ones to exploit the local regions and move further to explore the search space also. The method does not require algorithm parameters. The calculation results are compared with many other metaheuristic optimization methods to prove the accuracy and efficiency of the method.

show abstract

Balancing Composite Motion Optimization and Artificial Neural Network for the Prediction of Critical Load of Concrete-Filled Steel Tubes Under Axial Compression

Cited by 2 publications

References 11 publications

Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded material plate

Optimization of Neural Network architecture and derivation of closed-form equation to predict ultimate load of functionally graded material plate

Optimization of Stiffened Composite Plate Using Balancing Composite Motion Optimization

Contact Info

Product

Resources

About