Quality prediction of ultrasonically welded joints using a hybrid machine learning model

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

doi:10.1016/j.jmapro.2021.09.044

Cited by 27 publications

(7 citation statements)

References 31 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, degradation of the matrix and fibre re-orientation, resulting in low-performing components are drawbacks when joining fibre composite materials. It has been shown that joint quality shows a strong dependence on weld input parameters and the relationships are extremely non-linear (Mongan et al, 2021 ). Therefore, it is important to identify the appropriate weld input parameters during the process development stage.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

Self Cite

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%

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

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Liang et al [20] used GBDT, XGBoost, and LightGBM algorithms to predict the stability of hard rock columns. Mongan et al [21] used particle swarm optimization artificial neural network to predict the quality of ultrasonic welded joints.…”

Section: Introductionmentioning

confidence: 99%

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

Yang

Lin

Zhang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained.

show abstract

“…In recent decades, there has been a steady rise toward the research and development of alternative joining techniques in response to the growing demand for metal–polymer hybrid structures in industry and the limitations of conventional joining methods. For instance, ultrasonic welding (USW) is a process by which high-frequency, low-amplitude waves, typically in the range of 10–250 µm, are applied to the joint area while in the solid state to break the oxide layer and create the joint [ 13 , 14 , 15 ]. USW stands out for its low cost and short process time.…”

Section: Introductionmentioning

confidence: 99%

“…USW stands out for its low cost and short process time. However, for metal–polymer bonding, the difference in material performance is the main cause of USW formed joint high sensitivity to the applied waves vibrations amplitude which deteriorates joint strength [ 15 ]. Another metal–polymer welding process is laser welding, in which the joint is subjected to a laser beam, initiating bubbles of the plastic part to spread and diffuse in the molten solid interface forming the bond between the metal and the polymer.…”

Section: Introductionmentioning

confidence: 99%

A Comprehensive Technical Review of the Friction Stir Welding of Metal-to-Polymer Hybrid Structures

et al. 2022

View full text Add to dashboard Cite

Metal–polymer hybrid structures are becoming desirable due to their wide range of applications in the automotive, aerospace, biomedical and construction industries. Properties such as a light weight, high specific strength, and design flexibility along with the low manufacturing costs of metal–polymer hybrid structures make them widely attractive in several applications. One of the main challenges that hinders the widespread utilization of metal–polymer hybrid structures is the challenging dissimilar joining of metals to polymers. Friction stir welding (FSW) shows a promising potential in overcoming most of the issues and limitations faced in the conventional joining methods of such structures. Several works in the literature have explored the FSW of different metal-to-polymer combinations. In some of the works, the joints are examined based on processing parameter optimization, microstructural characteristics, and mechanical performances. It is, therefore, important to summarize the findings of these works as a means of providing a reference to researchers to facilitate further research on the utilization of FSW in joining metals to polymers. Thus, this work aims to present a comprehensive technical review on the FSW technique for joining metals to polymers by reviewing the reported literature findings on the impact of materials, tools, process parameters, and defects on the strength and microstructure of the produced joints. In addition, this work reviews and presents the latest practices aiming to enhance the metal–polymer joint quality that have been reported in the literature.

show abstract

Quality prediction of ultrasonically welded joints using a hybrid machine learning model

Cited by 27 publications

References 31 publications

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

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

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

A Comprehensive Technical Review of the Friction Stir Welding of Metal-to-Polymer Hybrid Structures

Contact Info

Product

Resources

About