Optimisation of Ultrasonically Welded Joints through Machine Learning

Mongan, Patrick G.; Hinchy, Eoin P.; O’Dowd, Noel P.; McCarthy, Conor T.

doi:10.1016/j.procir.2020.04.060

Cited by 17 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the complex and non-linear nature of the process, the authors considered multiple machine learning methods such as ANNs, gaussian process regression (GPR), random forest (RF), and support vector machines (SVM). However, published studies have demonstrated the excellent capabilities of ANNs in accurately capturing the non-linearity in the USW process (Mongan et al, 2020 , 2021 ; Pradeep Kumar & Divyenth, 2020 ; Zhao et al, 2017 ). Therefore, this study adopts an ANN modelling approach.…”

Section: Machine Learningmentioning

confidence: 99%

“…However, the model was not assessed on test data. Mongan et al (2020) developed an ANN to predict the weld quality for USW aluminium 5754, achieving a correlation coefficient of 0.98 between predicted and actual values for lap shear strength (LSS). Zhao et al (2017) developed an ANN on twenty-seven training samples to predict the strength of aluminium 6061 joined to A36 steel, producing a correlation coefficient of 0.998 between predicted and measured results.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning

et al. 2022

View full text Add to dashboard Cite

The use of composite materials is increasing in industry sectors such as renewable energy generation and storage, transport (including automotive, aerospace and agri-machinery) and construction. This is a result of the various advantages of composite materials over their monolithic counterparts, such as high strength-to-weight ratio, corrosion resistance, and superior fatigue performance. However, there is a lack of detailed knowledge in relation to fusion joining techniques for composite materials. In this work, ultrasonic welding is carried out on a carbon fibre/PEKK composite material bonded to carbon fibre/epoxy composite to investigate the influence of weld process parameters on the joint’s lap shear strength (LSS), the process repeatability, and the process induced defects. A 33 parametric study is carried out and a robust machine learning model is developed using a hybrid genetic algorithm–artificial neural network (GA–ANN) trained on the experimental data. Bayesian optimisation is employed to determine the most suitable GA–ANN hyperparameters and the resulting GA–ANN surrogate model is exploited to optimise the welding process, where the process performance metrics are LSS, repeatability and joint visual quality. The prediction for the optimal LSS was subsequently validated through a further set of experiments, which resulted in a prediction error of just 3%.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Mongan P.G. et al [14] used the ANN with GA and further used Lavenberg-Marquardt algorithm to train the model for a data set of 37 trials and demonstrated high accuracy with mean relative error of 6.79%.…”

Section: Introductionmentioning

confidence: 99%

Parametric Study and Optimization for Welding Processes Using Machine Learning

Chaturvedi

Vendan

2021

AWET

View full text Add to dashboard Cite

Optimization facilitates in attainment of maximum strength, efficiency, reliability, productivity and longevity. In this work, data from three material joining processes - Ultrasonic welding of polymers, arc welding as Metal Inert Gas and Tungsten Inert Gas are analysed for establishing quantitative relationship between the process parameters and for prediction of weld features using Multivariate Linear Regression algorithm. The various dependency coefficients and characteristics generated with the ML algorithms are in agreement with the inherent dependency as obtained from experimental data and simulation results. This investigation is a preliminary attempt with a limited set of data to manifest the suitability of machine learning techniques; nevertheless, the results are far from conclusive owing to small data set and hence may be extended to precisely model joining processes with higher number of process parameters, degree of freedom and responses.

show abstract

“…Aimiyeakagbon et al [6 ] used machine learning time series forecasting approach for prediction of crack length in the riveted aluminium plates. Mongan et al [7] combined genetic algorithm (GA) with Artificial Neural Network (ANN) for predicting the strength of ultrasonically welded joints. The model resulted high accuracy with 0.9827 as a correlation coefficient.…”

Section: Introductionmentioning

confidence: 99%

Discrete Wavelet Transformation Approach for Surface Defects Detection in Friction Stir Welded Joints

Mishra

2020

Fatigue of Aircraft Structures

View full text Add to dashboard Cite

Friction Stir Welding joint quality depends on input parameters such as tool rotational speed, tool traverse speed, tool tilt angle and an axial force. Surface defects formation occurs when these input parameters are not selected properly. The main objective of the recent paper is to develop Discrete Wavelet Transform algorithm by using Python programming and further subject it to the Friction Stir Welded samples for the identification of various external surface defects present.

show abstract

Optimisation of Ultrasonically Welded Joints through Machine Learning

Cited by 17 publications

References 13 publications

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning

Multi-objective optimisation of ultrasonically welded dissimilar joints through machine learning

Parametric Study and Optimization for Welding Processes Using Machine Learning

Discrete Wavelet Transformation Approach for Surface Defects Detection in Friction Stir Welded Joints

Contact Info

Product

Resources

About