Quality Control of Semi-Solid Die Casting by Filling Pressure Based on Machine Learning Method

Abstract:

In the actual semi-solid die-casting production, the existence of several uncertain factors can impose an effect on the final product quality, which poses a challenge to semi-solid production. However, data analysis such as machine learning (ML) can help producers eliminate this problem. In order to quickly identify defective castings, a new model of predicting quality by real-time injection pressure data will be generated in terms of ML in this research. Quality assessment will be based on non-filling defect, density and tensile properties. The result of cross-validation shows that the classifier can achieve a confidence level of 0.95 for the quality classification. In addition, this research will find key intervals by the importance given by the model and analyze the effects of process on filling pressure. According to the result of feature screening, the surface quality problems are related to speed-pressure conversion and feeding displacement of plunger, the flowing state of slurry in filling affects the formation of defects and tensile properties. This work will make semi-solid die casting more automatically and efficiently, and thus provides support for semi-solid sustainable development.

• Periodical: Solid State Phenomena (Volume 347)
• Pages: 191-196
• DOI: https://doi.org/10.4028/p-N1qeat
• Online since: August 2023
• Authors: Zhi Yuan Wang, Xiao Gang Hu, Hong Xing Lu, Qiang Zhu*
• Keywords: Die Casting, Intelligent Manufacturing, Machine Learning, Semi-Solid Processing

References

[1] S. Midson, Industrial Applications for Aluminum Semi-Solid Castings, Solid State Phenom. 217- 218 (2015) 487-495.

DOI: 10.4028/www.scientific.net/ssp.217-218.487

[2] KAPRANOS P. Current state of semi-solid net-shape die casting, Metals, 9 (12) (2019), 1301.

DOI: 10.3390/met9121301

[3] Jun Kim, Ju Yeon Lee, Data-analytics-based factory operation strategies for die-casting quality enhancement, The International Journal of Advanced Manufacturing Technology. 119 (2022) 3865-3890.

DOI: 10.1007/s00170-021-08625-8

[4] Morgado, João, Knowledge elicitation by merging heterogeneous data sources in a die-casting process, (2015).

[5] K.D.V. Yarlagadda, Eric Cheng Wei Chiang, A neural network system for the prediction of process parameters in pressure die casting, Journal of Materials Processing Technology. 89-90 (1999) 583-590.

DOI: 10.1016/s0924-0136(99)00071-0

[6] A tutorial on support vector machines for pattern recognition, Data Min. Knowl. Disc. 2 (2) (1998) 121-167.

[7] V.N. Vapnik, An overview of statistical learning theory, IEEE Trans Neural Net. 10 (5) (1998) 988-999.

[8] F. Rosenblatt, Perceptron simulation experiments, Proc IRE. 48 (3) (1960) 301-309.

DOI: 10.1109/jrproc.1960.287598

[9] Breiman. L, Random forests, Machine learning. 45 (1) (2001a) 5-32.

[10] F. Sigrist, Gradient and Newton boosting for classification and regression, Expert Syst. Appl. 167 (2021) 114080.

DOI: 10.1016/j.eswa.2020.114080