Genetic programming-assisted multi-scale optimization for multi-objective dynamic performance of laminated composites: the advantage of more elementary-level analyses

Kalita, Kanak; Mukhopadhyay, T.; Dey, Partha Pratim; Haldar, Salil

doi:10.1007/s00521-019-04280-z

Cited by 38 publications

(15 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Genetic algorithm is one of the most effective tools in the optimization and evaluation of engineering problems. Multi-objective genetic algorithm (MOGA) metamodel can be used to develop a relation between the input performance parameters considering multiple objectives for performance evaluation and prediction, used in various engineering applications (Yusup et al , 2012; Kalita et al , 2019; Han et al , 2018).…”

Section: Multi-objective Optimizationmentioning

confidence: 99%

Tribological performance evaluation on brake friction material by using multi-objective optimization methods

Öktem

Shinde

2021

ILT

View full text Add to dashboard Cite

Purpose The purpose of this study is to present a novel approach for the evaluation of tribological properties of brake friction materials (BFM). Design/methodology/approach In this study, a BFM was newly formulated with 16 different ingredients and produced using an industrial hot compression molding process. Experimentation was carried out on the brake tester, which was developed for this purpose according to SAE J661 standards. The braking applications, sliding speed and braking pressure were considered as performance parameters, whereas coefficient of friction (CoF) and wear rate as output parameters. The influence of the performance parameters on the output was studied using response surface plots. Analysis of variance and regression analysis was accomplished for post-experimental evaluation of results. Multi-criteria decision-making (MCDM) and multi-objective genetic algorithm (MOGA) were applied for estimating the most critical performance parameter combination to evaluate the BFM. Findings The present experimental model was significant and effectively used to predict the performance. MCDM generates the optimal values for the parameters braking applications, braking pressure (Bar) and sliding speed (rpm) as 1000, 30 and 915, whereas MOGA as 1008, 10.503 and 462.8202, respectively. Originality/value An efficient model for performance evaluation of the BFM considering maximum CoF and minimum wear rate was experimentally presented and statistically verified. Also, the two multi-objective optimization methodologies were implemented and compared. A comparison between the results of MCDM and MOGA reveals that MOGA yields 30% better results than MCDM.

show abstract

Section: Multi-objective Optimizationmentioning

confidence: 99%

Tribological performance evaluation on brake friction material by using multi-objective optimization methods

Öktem

Shinde

2021

ILT

View full text Add to dashboard Cite

show abstract

“…Figure 9 shows the classification of optimization algorithms based on the design variables, objective function and constraints. Optimization methods can be significantly improved in terms of efficacy and efficiency by involving machine learning algorithms [88,89]. Salah et al [90] predicted the absorption index of CNT reinforced polycarbonate composites using a ML approach of multilayer perceptron network approach.…”

Section: Prediction Optimization and Uncertainty Quantificationmentioning

confidence: 99%

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Sharma

Mukhopadhyay

Rangappa

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The superior multi-functional properties of polymer composites have made them an ideal choice for aerospace, automobile, marine, civil, and many other technologically demanding industries. The increasing demand of these composites calls for an extensive investigation of their physical, chemical and mechanical behavior under different exposure conditions. Machine learning (ML) has been recognized as a powerful predictive tool for data-driven multi-physical modeling, leading to unprecedented insights and exploration of the system properties beyond the capability of traditional computational and experimental analyses. Here we aim to abridge the findings of the large volume of relevant literature and highlight the broad spectrum potential of ML in applications like prediction, optimization, feature identification, uncertainty quantification, reliability and sensitivity analysis along with the framework of different ML algorithms concerning polymer composites. Challenges like the curse of dimensionality, overfitting, noise and mixed variable problems are discussed, including the latest advancements in ML that have the potential to be integrated in the field of polymer composites. Based on the extensive literature survey, a few recommendations on the exploitation of various ML algorithms for addressing different critical problems concerning polymer composites are provided along with insightful perspectives on the potential directions of future research.

show abstract

“…Several researchers have already adopted various metamodeling algorithms ranging from polynomial regression (PR) [1,2] to genetic programming (GP) [3] to the artificial neural network (ANN) for estimation of static and dynamic behaviors of laminated composite structures. Applications of the metamodels in laminated structures have also varied from prediction [4,5] to uncertainty quantification [6,7] to single-objective [8,9] and multiobjective optimization [10,11].…”

Section: Introductionmentioning

confidence: 99%

“…Further, it was observed that lack of exclusive tests on dedicated test data could lead to ignorance and mistrust on PR metamodels, although many of them had shown excellent prediction on training data but failed miserably on test data. Kalita et al [3] also carried out a multi-scale optimization of laminated structures using GP metamodels and noticed that GP metamodels could be deployed to efficiently and inexpensively switch between micro to macroscale and vice versa. It was also postulated that as much as 99% of the optimization algorithm running time could be saved by replacing an FE model with a metamodel in a metaheuristic-based global optimization problem of laminated composites.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Analysis of Radial Basis Function Metamodels for Predictive Modelling of Laminated Composites

et al. 2021

Self Cite

View full text Add to dashboard Cite

High-fidelity structural analysis using numerical techniques, such as finite element method (FEM), has become an essential step in design of laminated composite structures. Despite its high accuracy, the computational intensiveness of FEM is its serious drawback. Once trained properly, the metamodels developed with even a small training set of FEM data can be employed to replace the original FEM model. In this paper, an attempt is put forward to investigate the utility of radial basis function (RBF) metamodels in the predictive modelling of laminated composites. The effectiveness of various RBF basis functions is assessed. The role of problem dimensionality on the RBF metamodels is studied while considering a low-dimensional (2-variable) and a high-dimensional (16-variable) problem. The effect of uniformity of training sample points on the performance of RBF metamodels is also explored while considering three different sampling methods, i.e., random sampling, Latin hypercube sampling and Hammersley sampling. It is observed that relying only on the performance metrics, such as cross-validation error that essentially reuses training samples to assess the performance of the metamodels, may lead to ill-informed decisions. The performance of metamodels should also be assessed based on independent test data. It is further revealed that uniformity in training samples would lead towards better trained metamodels.

show abstract

Genetic programming-assisted multi-scale optimization for multi-objective dynamic performance of laminated composites: the advantage of more elementary-level analyses

Cited by 38 publications

References 75 publications

Tribological performance evaluation on brake friction material by using multi-objective optimization methods

Tribological performance evaluation on brake friction material by using multi-objective optimization methods

Advances in Computational Intelligence of Polymer Composite Materials: Machine Learning Assisted Modeling, Analysis and Design

Performance Analysis of Radial Basis Function Metamodels for Predictive Modelling of Laminated Composites

Contact Info

Product

Resources

About