Next Article in Journal
Performance of CRTS-II Ballastless Track–Bridge Structural System Rebars under Fatigue Loading Test
Previous Article in Journal
Electromagnetic Field Analysis and Design of a Hermetic Interior Permanent Magnet Synchronous Motor with Helical-Grooved Self-Cooling Case for Unmanned Aerial Vehicles
Previous Article in Special Issue
Smart Manufacturing Real-Time Analysis Based on Blockchain and Machine Learning Approaches
Article

The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm

1
Department of Biomedical Engineering, Da-Yeh University, No.168, University Road, Dacun, Changhua 515, Taiwan
2
Department of Computer Science and Information Engineering, National Pingtung University, 51 Min Sheng E. Road, Pingtung 900, Taiwan
3
Green Energy & System Integration Research & Development Department, China Steel Corporation, 1, Chung Kang Rd., Hsiao Kang, Kaohsiung 806, Taiwan
4
Department of Intelligent Robotics, National Pingtung University, 51 Min Sheng E. Road, Pingtung 900, Taiwan
5
Department of Computer Science and Information Engineering, National Cheng Kung University, No 1, University-Road, Tainan 701, Taiwan
*
Author to whom correspondence should be addressed.
Academic Editor: Antonella Petrillo
Appl. Sci. 2021, 11(11), 4857; https://doi.org/10.3390/app11114857
Received: 8 April 2021 / Revised: 28 April 2021 / Accepted: 14 May 2021 / Published: 25 May 2021
High-strength low-alloy steels (HSLAs) are widely used in the structural body components of many domestic motor vehicles owing to their better mechanical properties and greater resistance. The real production process of HSLA steelmaking can be regarded as a model that builds on the relationship between process parameters and product quality attributes. A surrogate modeling method is used, and the resulting production process model can be applied to predict the optimal manufacturing process parameters. We used different methods in this paper, including linear regression, random forests, support vector regression, multilayer perception, and a simplified VGG model to build such a surrogate model. We then applied three bio-inspired search algorithms, namely particle swarm optimization, the artificial bee colony algorithm, and the firefly algorithm, to search for the optimal controllable manufacturing process parameters. Through experiments on 9000 test samples used for building the surrogate model and 299 test samples for making the optimal process parameter selection, we found that the combination of a simplified VGG model and the firefly algorithm was the most successful at reaching a success rate of 100%—in other words, when the product quality attributes of all test samples satisfy the mechanical requirements of the end products. View Full-Text
Keywords: high-strength low-alloy steel; manufacturing process optimization; surrogate model; firefly algorithm; VGG model high-strength low-alloy steel; manufacturing process optimization; surrogate model; firefly algorithm; VGG model
Show Figures

Figure 1

MDPI and ACS Style

Liu, Y.-C.; Horng, M.-H.; Yang, Y.-Y.; Hsu, J.-H.; Chen, Y.-T.; Hung, Y.-C.; Sun, Y.-N.; Tsai, Y.-H. The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm. Appl. Sci. 2021, 11, 4857. https://doi.org/10.3390/app11114857

AMA Style

Liu Y-C, Horng M-H, Yang Y-Y, Hsu J-H, Chen Y-T, Hung Y-C, Sun Y-N, Tsai Y-H. The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm. Applied Sciences. 2021; 11(11):4857. https://doi.org/10.3390/app11114857

Chicago/Turabian Style

Liu, Yung-Chun, Ming-Huwi Horng, Yung-Yi Yang, Jian-Han Hsu, Yen-Ting Chen, Yu-Chen Hung, Yung-Nien Sun, and Yu-Hsuan Tsai. 2021. "The Steelmaking Process Parameter Optimization with a Surrogate Model Based on Convolutional Neural Networks and the Firefly Algorithm" Applied Sciences 11, no. 11: 4857. https://doi.org/10.3390/app11114857

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop