Genetic algorithm based optimization for multi-physical properties of HSLA steel through hybridization of neural network and desirability function

Das, Prasun; Mukherjee, Shibani; Ganguly, Subhas; Bhattacharyay, B. K.; Datta, Someswar

doi:10.1016/j.commatsci.2008.03.050

Cited by 38 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In another study, Kros and Mastrangello [23] study the relationship between response types when they are mixed (the larger the better, the smaller the better, and nominal the best). On the other hand, Das et al [24] employ a genetic algorithm-based optimization to determine the tensile properties of a high-strength low-alloy steel, where multi-layer perceptron ANNs are developed for the output responses and then a desirability function based on employing a sigmoidal function is obtained [24] and Zong et al [25] combine variations due to noise factors and controllable factors. In another study developed by He et al [26], a robust desirability function approach to simultaneously optimize multiple responses is proposed.…”

Section: State Of the Artmentioning

confidence: 99%

On the Application of a Design of Experiments along with an ANFIS and a Desirability Function to Model Response Variables

Pérez

2021

Symmetry

View full text Add to dashboard Cite

In manufacturing engineering, it is common to use both symmetrical and asymmetrical factorial designs along with regression techniques to model technological response variables, since the in-advance prediction of their behavior is of great importance to determine the levels of variation that lead to optimal response values to be obtained. For this purpose, regression techniques based on the response surface method combined with a desirability function for multi-objective optimization are commonly employed, since it is usual to find manufacturing processes that require simultaneous optimization of several variables, which exhibit in many cases an opposite behavior. However, these regression models are sometimes not accurate enough to predict the behavior of these response variables, especially when they have significant non-linearities. To deal with this drawback, soft computing techniques are very effective in overcoming the limitations of conventional regression models. This present study is focused on the employment of a symmetrical design of experiments along with a new desirability function, which is proposed in this study, and with soft computing techniques based on fuzzy logic. It will be shown that more accurate results than those obtained from regression techniques are obtained. Moreover, this new desirability function is analyzed in this study.

show abstract

Section: State Of the Artmentioning

confidence: 99%

On the Application of a Design of Experiments along with an ANFIS and a Desirability Function to Model Response Variables

Pérez

2021

Symmetry

View full text Add to dashboard Cite

show abstract

“…As discussed in [20,21], hybrid intelligent systems based on different integration schemes of neural networks, fuzzy logic and genetic algorithms have recently received much attention. Artificial neural networks (ANNs) and genetic algorithms (GA) have proved to be very effective in substitution of direct simulation and optimization in several contests, including manufacturing processes [22][23][24][25][26][27], composite material performance [28,29], mechanical and/or microstructural properties [30], and assisted process planning [31,32]. As far as the application of ANNs to curing simulation and optimization is concerned, early contributions can be individuated in [33,34], discussing the development of a static neural network to simulate the curing process, recalled by a nonlinear programming scheme.…”

Section: Introductionmentioning

confidence: 99%

Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites

2016

View full text Add to dashboard Cite

An intelligent optimization model aiming at off-line or pre-series optimization of the thermal curing cycle of polymer matrix composites is proposed and discussed. The computational procedure is based on the coupling of a finite element thermochemical process model, dynamic artificial neural networks and genetic algorithms. Objective of the optimization routine is the maximization of the composite degree of cure by the definition of the autoclave temperature. Obtained outcomes evidenced the capability of the method as well as its efficiency with respect to hard computing or experimental procedures

show abstract

“…To overcome the difficulty of implementing the optimization of the process machine, several types of researches are recently dedicated for seeking Another method known as Artificial Neural Network (ANN) [18][19][20][21] to implement the mathematical computing and design the relationships between the input and output parameters.…”

Section: Introductionmentioning

confidence: 99%

Comparative Prediction and Modelling of Surface Roughness in Milling of AL-7075 Using Regression Analysis and Neural Network

Hussein¹,

Shareef²,

Zayer³

2022

MMEP

View full text Add to dashboard Cite

The surface roughness (Ra) of machine parts effects significantly the fatigue strength, corrosion resistance and aesthetic appeal of them. Therefore, Ra is an important parameter in manufacturing process. In this research, Ra of Aluminum Al-7075 in milling process is predicted and minimized. Ra minimization has to be in standard mathematical model formula. In order to predict minimum Ra value, developing a model is taken to deal with real Ra experimental data of the milling process. Two model approaches which are Regression and Artificial Neural Network (ANN) are proposed for minimum Ra value prediction. The studied process parameters were: speed of cut, feed rate and depth of cut. Regression and ANN were used to investigate the effect of these parameters on Ra through 27 cases of study, where full Analysis of Ra besides to determining regression equation and optimum process parameters are achieved. This study results show that each of Regression & ANN models had reduced minimum Ra in very similar value by 0.987. This similarity reflects the promise approach of this study in predicting Ra in AL-7075 milling, unlike previous studies that either the regression or the Artificial intelligence method was the dominant in results.

show abstract

Genetic algorithm based optimization for multi-physical properties of HSLA steel through hybridization of neural network and desirability function

Cited by 38 publications

References 15 publications

On the Application of a Design of Experiments along with an ANFIS and a Desirability Function to Model Response Variables

On the Application of a Design of Experiments along with an ANFIS and a Desirability Function to Model Response Variables

Optimization of the Temperature-Time Curve for the Curing Process of Thermoset Matrix Composites

Comparative Prediction and Modelling of Surface Roughness in Milling of AL-7075 Using Regression Analysis and Neural Network

Contact Info

Product

Resources

About