Automated visual inspection of friction stir welds: a deep learning approach

Hartl, Roman; Landgraf, Johannes; Spahl, Julian; Bachmann, Andreas; Zaeh, Michael F.

doi:10.1117/12.2525947

Cited by 13 publications

(20 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hartl et al 19 have shown that an automated visual inspection of friction stir welds using CNNs is possible. Zuo et al 20 investigated the influence of process parameters on the surface topography of friction stir welds.…”

Section: Related Work -Automated Detection Of Surface Defects In the mentioning

confidence: 99%

“…81 to 96) with welding speeds v s from 500 mm/min to 1500 mm/min and tool rotational speeds n from 1500 min À1 to 3500 min À1 (see Figure 20 in Appendix 1). The tool used in Studies 5 and 6 in Hartl et al 19 had a probe diameter of 6 mm, a shoulder geometry with concentric rings, and a shoulder diameter d s of 14 mm. During the welding experiments, the forces F x , F y , F z in the x, y, and z-direction, the accelerations a x , a y , a z in the x, y, and z-direction, the temperatures at the welding probe T p and the welding shoulder T s as well as the spindle torque M z were recorded.…”

Section: Welding Experimentsmentioning

confidence: 99%

“…113 to experiment no. 128 in continuation of the experiments described in Hartl et al 19 The sequence of the given experiment numbers was analogous to the sequence of the experiment numbers for Studies 5 and 6 (see Figure 20 in Appendix 1). The execution of the tests and the evaluation of the weld surfaces were identical to the procedure for experiments 65 to 96, with the exception that instead of the aluminum alloy EN AW-6082 T6, the aluminum alloy EN AW-5754 H111 was selected.…”

Section: En Aw-6082 T6mentioning

confidence: 99%

See 2 more Smart Citations

Prediction of the surface quality of friction stir welds by the analysis of process data using Artificial Neural Networks

Hartl

Praehofer

Zaeh

2020

Proceedings of the Institution of Mechanical Engineers, Part L:

View full text Add to dashboard Cite

Friction stir welding is an advanced joining technology that is particularly suitable for aluminum alloys. Various studies have shown that welding quality depends significantly on the welding speed and the rotational speed of the tool. It is frequently possible to detect an unsuitable setting of these parameters by examining the resulting surface defects, such as increased flash formation or surface galling. In this work, Artificial Neural Networks were used to analyze process data in friction stir welding and predict the resulting quality of the weld surface. For this purpose, nine different variables were recorded during friction stir welding of EN AW-6082 T6 sheets: the forces and accelerations in three spatial directions, the spindle torque, and temperatures at the tool shoulder and tool probe. In Case 1, the welds were assigned to the classes good and defective on the basis of a human visual inspection of the weld surface. In Case 2, the welds were categorized into the two classes on the basis of a surface topography analysis. Subsequently, three different major Artificial Neural Network architectures were tested for their ability to predict the surface quality: Feed Forward Fully Connected Neural Networks, Recurrent Neural Networks and Convolutional Neural Networks. The highest classification accuracy was achieved when Convolutional Neural Networks were used. Thus, the evaluation of the force signal transverse to the welding direction yielded the highest accuracy of 99.1% for the prediction of the result of the human visual inspection. The result achieved for the prediction of the topography analysis was an accuracy of 87.4% when the spindle torque was evaluated. Using all nine different process variables to predict the topography analysis, the accuracy could be improved slightly to 88.0%. The sampling rate of the spindle torque was varied between 40 Hz and 9600 Hz and no significant influence was determined. The findings show that Convolutional Neural Networks are well suited for the interpretation of friction stir welding process data and can be used to predict the resulting surface quality. In future work, the results are to be used to develop a parameter optimization method for friction stir welding.

show abstract

Section: Related Work -Automated Detection Of Surface Defects In the mentioning

confidence: 99%

Section: Welding Experimentsmentioning

confidence: 99%

Section: En Aw-6082 T6mentioning

confidence: 99%

See 1 more Smart Citation

Prediction of the surface quality of friction stir welds by the analysis of process data using Artificial Neural Networks

Hartl

Praehofer

Zaeh

2020

Proceedings of the Institution of Mechanical Engineers, Part L:

View full text Add to dashboard Cite

show abstract

“…If the distortion correction was carried out without the down-sampling operation, we can see that a large amount of processing time was lost, while the accuracy and SSIM exponential increase was not high. By comparing the two models with the same parameters of the patch traversal mechanism without the ground truth and with the ground truth, it can be seen that the accuracy and speed were significantly improved [30,31]. After adding the confidence guiding mechanism, the recognition speed of the model was further improved.…”

Section: Resultsmentioning

confidence: 95%

An End-To-End Model for Pipe Crack Three-Dimensional Visualization Based on a Cascade Neural Network

Xia

Wang

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

With the continuous progress of machine vision technology, crack detection in pipelines has been greatly improved. For crack detection in deep holes, inner tubes, and other environments, it is not only necessary to detect the existence of cracks, but also to collect important information regarding the crack detection direction for further analysis. Because shooting with a frontal field of view causes the real side wall images to produce certain distortions, the detection and calibration of cracks requires a certain amount of professional technology and time. It usually takes a long time to collect the image to eliminate the distortion, and then to identify the crack and mark the direction according to the data line. Therefore, a simple and efficient end-to-end neural network model for crack recognition and three-dimensional visualization are proposed by using a cascade network and simple recognition technology in conjunction with inertial navigation equipment. In addition, we screen the crack data via pixel calibration and eliminate the ambiguous data to make the visualization more accurate. Experiments in pipelines and burrows show that the accuracy, performance, and efficiency of the proposed method reached a high level.

show abstract

“…Table 1 provides an overview of the different studies. Some of the studies have already been described in more detail in previous research conducted by Hartl et al [23,26]. The evaluated weld seam length varied in the ten studies, but was always between 70 and 170 mm.…”

Section: Welding Experimentsmentioning

confidence: 96%

Improving the surface quality of friction stir welds using reinforcement learning and Bayesian optimization

Hartl

Hansjakob

Zaeh

2020

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Friction stir welding is an advanced joining technology that is particularly suitable for aluminum alloys. Various studies have shown a significant dependence of the welding quality on the welding speed and the rotational speed of the tool. Frequently, an inappropriate setting of these parameters can be detected through an examination of the resulting surface defects, such as increased flash formation or surface galling. In this work, two different learning-based algorithms were applied to improve the surface topography of friction stir welds. For this purpose, the surface topographies of 262 welds, which were performed as part of ten studies, were evaluated offline. The aim was to use reinforcement learning and Bayesian optimization approaches to determine the most appropriate settings for the welding speed and the rotational speed of the tool. The optimization problem was solved using reinforcement learning, specifically value iteration. However, the value iteration algorithm was not efficient, since all actions and states had to be iterated over, i.e., each possible parameter combination had to be evaluated, to find the best policy. Instead, it was better to solve the optimization problem directly using the Bayesian optimization. Two approaches were applied: both an approach in which the information from the other studies was not used and an approach in which the information from the other studies was used. On average, both the Bayesian optimization approaches found suitable welding parameters significantly faster than a random search algorithm, and the latter approach improved the result even further compared with the former approach. Future research will aim to show that optimization of the surface topography also leads to an increase in the ultimate tensile strength.

show abstract

Automated visual inspection of friction stir welds: a deep learning approach

Cited by 13 publications

References 21 publications

Prediction of the surface quality of friction stir welds by the analysis of process data using Artificial Neural Networks

Prediction of the surface quality of friction stir welds by the analysis of process data using Artificial Neural Networks

An End-To-End Model for Pipe Crack Three-Dimensional Visualization Based on a Cascade Neural Network

Improving the surface quality of friction stir welds using reinforcement learning and Bayesian optimization

Contact Info

Product

Resources

About