Using Data Mining Techniques to Investigate the Correlation between Surface Cracks and Flange Lengths in Deep Drawn Sheet Metals

Heger, Jens; Abdine, Mazhar Zein El

doi:10.1016/j.ifacol.2019.11.236

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have compared the performance of kNN, SVM and ANN using the same descriptor, and concluded tha,t on average, ANN outperformed than other methods. Furthermore, due to cost and time constraints of getting more data, Jens et al, have used eight traditional ML techniques-which are SVM, Decision Trees (DT), kNN, Logistic Regression, RF, ANN, Adaboost, and Discriminant Analyzer-for predicting cracks on inline images (camera images) of sheet metals to improve the monitoring in automotive industry [12]. The authors of this study concluded that DT has achieved the best accuracy to detect the cracks for quality inspection compared to other methods.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Melt-Pool Defects Classification for Additive Manufactured Components in Aerospace Use-Case

Dasari

Cheddad

Palmquist

2020

2020 7th International Conference on Soft Computing &Amp; Machine Intelligence (ISCMI)

View full text Add to dashboard Cite

One of the crucial aspects of additive manufacturing is the monitoring of the welding process for quality assurance of components. A common way to analyse the welding process is through visual inspection of melt-pool images to identify possible defects in manufacturing. Recent literature studies showed the potential use of prediction models for defects classification to speed up the manual verification criteria since a huge data is generated from the additive manufacturing. Although a huge image data is available, the data needs to be labelled manually by experts which results in small sample datasets. Hence, to model small sample sizes and also to acquire the importance of parameters, we opted a traditional machine learning method, Random Forests (RF). For feature extraction, we opted for the Polar Transformation to explore its applicability using the meltpool image dataset and a publicly available shape image dataset. The results show that RF models with Polar Transformation performed the best on our case study datasets and the second-best for the public dataset when compared to the Histogram of Oriented Gradients, HARALICK, XY-projections of an image, and Local Binary Patterns methods. As such, the Polar Transformation can be considered as a suitable compact shape descriptor.

show abstract

Section: Related Workmentioning

confidence: 99%

“…They have shown that their proposed model can be applied for adaptive SLM process control and part quality assurance in AM. Although DL techniques can extract features automatically, they require huge amount of training data [12]. This is not always feasible due to cost and time constraints of data labeling.…”

Section: Related Workmentioning

confidence: 99%

Melt-Pool Defects Classification for Additive Manufactured Components in Aerospace Use-Case

Dasari

Cheddad

Palmquist

2020

2020 7th International Conference on Soft Computing &Amp; Machine Intelligence (ISCMI)

View full text Add to dashboard Cite

show abstract

“…The former, in combination with the advancements in computational capabilities, has resulted in machine learning approaches based on ANNs gaining a lot of popularity within the manufacturing community as a whole, both in industry and academia. They are used for a wide range of applications, including tool wear monitoring and forecasting [16,17], decision support systems [18], process parameter predictions [19], quality control [20,21], etc. They are also gaining more traction within incremental sheet forming; specifically, Khan et al [22] used ANNs to predict local springback errors in an SPIF process and adjusted the tool path accordingly.…”

Section: Introductionmentioning

confidence: 99%

Closed-loop control of product geometry by using an artificial neural network in incremental sheet forming with active medium

et al. 2020

View full text Add to dashboard Cite

A strategy to adjust the product geometry autonomously through an online control of the manufacturing process in incremental sheet forming with active medium is presented. An axial force sensor and a laser distance sensor are integrated into the process setup to measure the forming force and the product height, respectively. Experiments are conducted to estimate the bulging behavior for different pre-determined tool paths. An artificial neural network is consequently trained based on the experimental data to continuously predict the pressure levels required to control the final product height. The predicted pressure is part of a closed-loop control to improve the geometrical accuracy of formed parts. Finally, experiments were conducted to verify the results, where truncated cones with different dimensions were formed with and without the closed-loop control. The results indicate that this strategy enhances the geometrical accuracy of the parts and can potentially be expanded to be implemented for different types of material and geometries.

show abstract

Responsible manufacturing toward Industry 5.0

Tian,

Liu

2024

Manufacturing From Industry 4.0 to Industry 5.0

View full text Add to dashboard Cite

Using Data Mining Techniques to Investigate the Correlation between Surface Cracks and Flange Lengths in Deep Drawn Sheet Metals

Cited by 7 publications

References 9 publications

Melt-Pool Defects Classification for Additive Manufactured Components in Aerospace Use-Case

Melt-Pool Defects Classification for Additive Manufactured Components in Aerospace Use-Case

Closed-loop control of product geometry by using an artificial neural network in incremental sheet forming with active medium

Responsible manufacturing toward Industry 5.0

Contact Info

Product

Resources

About