Multiresponse optimization of friction stir welding by an integrated ANN-PSO approach

Quarto, Mariangela; Bocchi, Sara; D’Urso, Gianluca Danilo; Giardini, Claudio

doi:10.1177/09544054221138143

Cited by 7 publications

(1 citation statement)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN models. Inspired by the behavior of the human nervous system, 34 the ANN modeling approach involves a large number of highly connected elements called neurons to form a network. In the present study, a multi-layer feed-forward ANN with an error backpropagation training algorithm has been developed for each response.…”

Section: Modeling and Multi-objective Optimization Methodsmentioning

confidence: 99%

Modeling and multi-objective optimization of abrasive water jet machining process of composite laminates using a hybrid approach based on neural networks and metaheuristic algorithm

Chaouch,

Ben Khalifa,

Zitoune

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Although the abrasive water jet (AWJ) has proven to be a suitable process for machining composite materials, it has some limitations related to dimensional inaccuracy and surface defects. As the performance of the AWJ process mainly depends on the machining parameters, an optimal selection of them is crucial to achieving an improved quality of cut. In this context, the present study reports an experimental investigation to assess the influence of AWJ machining parameters on kerf taper angle (θ) and surface roughness ( Ra) of E glass/Vinylester 411 resin laminates. The experiments are carried out using a full factorial design by varying the water pressure, traverse speed, abrasive flow rate, and standoff distance. A first-ever attempt is made in this paper to optimize the AWJ process using a hybrid approach combining artificial neural networks (ANNs) with a recently proposed metaheuristic algorithm known as multi-objective bonobo optimizer (MOBO). The results show that standoff distance and abrasive flow rate were the most significant control factors in influencing θ and Ra, respectively. The developed ANN models are capable to predict the output responses with high accuracy and the solutions from the Pareto front provide a sufficient performance with a trade-off between θ and Ra. The corresponding levels of the optimal process parameters are 430 g/min for the abrasive flow rate, the range of 140–180 mm/min for the traverse speed, 280 MPa for the pressure, and 1.5 mm for the standoff distance.

show abstract

Section: Modeling and Multi-objective Optimization Methodsmentioning

confidence: 99%

Modeling and multi-objective optimization of abrasive water jet machining process of composite laminates using a hybrid approach based on neural networks and metaheuristic algorithm

Chaouch,

Ben Khalifa,

Zitoune

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

show abstract

A technical perspective on integrating artificial intelligence to solid-state welding

Yaknesh,

Rajamurugu,

Babu

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The implementation of artificial intelligence (AI) techniques in industrial applications, especially solid-state welding (SSW), has transformed modeling, optimization, forecasting, and controlling sophisticated systems. SSW is a better method for joining due to the least melting of material thus maintaining Nugget region integrity. This study investigates thoroughly how AI-based predictions have impacted SSW by looking at methods like Artificial Neural Networks (ANN), Fuzzy Logic (FL), Machine Learning (ML), Meta-Heuristic Algorithms, and Hybrid Methods (HM) as applied to Friction Stir Welding (FSW), Ultrasonic Welding (UW), and Diffusion Bonding (DB). Studies on Diffusion Bonding reveal that ANN and Generic Algorithms can predict outcomes with an accuracy range of 85 – 99%, while Response Surface Methodology such as Optimization Strategy can achieve up to 95 percent confidence levels in improving bonding strength and optimizing process parameters. Using ANNs for FSW gives an average percentage error of about 95%, but using metaheuristics refined it at an incrementally improved accuracy rate of about 2%. In UW, ANN, Hybrid ANN, and ML models predict output parameters with accuracy levels ranging from 85 to 96%. Integrating AI techniques with optimization algorithms, for instance, GA and Particle Swarm Optimization (PSO) significantly improves accuracy, enhancing parameter prediction and optimizing UW processes. ANN’s high accuracy of nearly 95% compared to other techniques like FL and ML in predicting welding parameters. HM exhibits superior precision, showcasing their potential to enhance weld quality, minimize trial welds, and reduce costs and time. Various emerging hybrid methods offer better prediction accuracy.

show abstract

A comparative analysis of forecasting surface hardness in various aluminum friction stir welded joints: FEM-ANN hybrid versus ANN-PSO-integrated approaches

Bocchi,

Quarto,

D’Urso

et al. 2024

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Multiresponse optimization of friction stir welding by an integrated ANN-PSO approach

Cited by 7 publications

References 50 publications

Modeling and multi-objective optimization of abrasive water jet machining process of composite laminates using a hybrid approach based on neural networks and metaheuristic algorithm

Modeling and multi-objective optimization of abrasive water jet machining process of composite laminates using a hybrid approach based on neural networks and metaheuristic algorithm

A technical perspective on integrating artificial intelligence to solid-state welding

A comparative analysis of forecasting surface hardness in various aluminum friction stir welded joints: FEM-ANN hybrid versus ANN-PSO-integrated approaches

Contact Info

Product

Resources

About