Search for accurate RSM metamodels for structural engineering

Kalita, Kanak; Dey, Partha Pratim; Haldar, Salil

doi:10.1177/0731684419862346

Cited by 25 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, sometimes the R 2 value can be misleading, as adding more terms to a polynomial regression model will in general increase the R 2 . Hence, as emphasized by Kalita et al [26] in a recent study, all researchers should rely more on the adjusted R 2 values.…”

Section: Building the Regression Modelmentioning

confidence: 93%

Memetic Cuckoo-Search-Based Optimization in Machining Galvanized Iron

et al. 2020

Self Cite

View full text Add to dashboard Cite

In this article, an improved variant of the cuckoo search (CS) algorithm named Coevolutionary Host-Parasite (CHP) is used for maximizing the metal removal rate in a turning process. The spindle speed, feed rate and depth of cut are considered as the independent parameters that describe the metal removal rate during the turning operation. A data-driven second-order polynomial regression approach is used for this purpose. The training dataset is designed using an L16 orthogonal array. The CHP algorithm is effective in quickly locating the global optima. Furthermore, CHP is seen to be sufficiently robust in the sense that it is able to identify the optima on independent reruns. The CHP predicted optimal solution presents ±10% deviations in the optimal process parameters, which shows the robustness of the optimal solution.

show abstract

Section: Building the Regression Modelmentioning

confidence: 93%

Memetic Cuckoo-Search-Based Optimization in Machining Galvanized Iron

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the experiment, cutting speed, feed rate and axial cutting depth were selected for the test design of three factors and three levels. 32 This design requires 20 sets of tests, which include 8 sets of factor designs, 6 sets of centre point designs, and 6 sets of axial point designs. The experiment’s design and results are shown in Table 3.…”

Section: Experiments Of Tool Wearmentioning

confidence: 99%

Prediction of tool wear based on GA-BP neural network

Wei

Cong

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

The anisotropy and nonuniformity of wood-plastic composites (WPCs) affect the milling tool, which rapidly wears during high-speed milling of WPCs. Thus, the evolution mechanism of tool failure becomes complicated, and the prediction of tool wear cannot be precisely described mathematically. A neural network based on tool wear test was proposed to predict the tool wear condition during high-speed milling of WPCs. The traditional backpropagation (BP) neural network easily falls into the local optimal solution. A genetic algorithm (GA-BP) neural network prediction model was established by using the GA to optimise its initial weight and threshold. The BP model and the GA-BP model were evaluated in terms of mean square error and training times, and the generalisation verification was applied to the prediction model. After analysing and comparing the results of the two models, the GA-BP neural network model has better training speed and accuracy under the test conditions. The relative error between the predicted value and the actual value is controlled within 5%.

show abstract

“…It was also used to evaluate the regression line between y a and ŷp values. The closer to one is the coefficient of determination for these two values, the better has worked the regression model for predicting the stress concentration factor [45].…”

Section: Model Assessmentmentioning

confidence: 99%

A novel method for estimation of stress concentration factor of central cutouts located in orthotropic plate

Abbasnia

Jafari

Rohani

2021

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

The purpose of this paper is to present a new method based on the regression analysis for estimating stress concentration factor of different cutouts in orthotropic plates. The existence of an explicit relation in terms of mechanical properties can be an approach for analyzing the stress of viscoelastic plates. Little research has been conducted to provide explicit relationships to calculate the theoretical stress concentration. In the present study first, using different values of the mechanical properties of the composites, stress concentration factor was calculated by employing an analytical solution based on the complex variable method. Then, using multiple linear regression, an explicit mathematical relation for different cutouts was presented with the purpose of estimating stress concentration factor in terms of mechanical properties. The results showed that the regression model is able to predict circumferential stress with a maximum error of 1% for circular, elliptical, triangular and square cutouts. Also, the evaluation of the model with k-fold cross validation method and also comparison with other studies showed that it is possible to rely on the present estimation. Working with the regression models, which are presented in this article, is very simple and can be practical.

show abstract

Search for accurate RSM metamodels for structural engineering

Cited by 25 publications

References 45 publications

Memetic Cuckoo-Search-Based Optimization in Machining Galvanized Iron

Memetic Cuckoo-Search-Based Optimization in Machining Galvanized Iron

Prediction of tool wear based on GA-BP neural network

A novel method for estimation of stress concentration factor of central cutouts located in orthotropic plate

Contact Info

Product

Resources

About