ABSTRACT
A multi-channel parallel convolutional neural network model is proposed to predict the mechanical properties of hot-rolled steel by chemical content and process parameters. The innovative contribution of this paper is to propose an improved Gramian Angular field method in the field of steel performance prediction, which converts the original data into a two-dimensional image matrix and introduces new features. Compared with the traditional convolutional neural network model, the multi-channel parallel convolutional neural network uses private blocks to decouple data and public blocks to integrate key data, which effectively improves the prediction accuracy of the model. Experiments in this paper show that the optimal hyperparameter structure model proposed in this paper has higher prediction accuracy than similar models proposed in other literatures.
- Wang, Z. H., Gong, D. Y., Li, X., Li, G. T., & Zhang, D. H. 2017. Prediction of bending force in the hot strip rolling process using artificial neural network and genetic algorithm (ANN-GA). The International Journal of Advanced Manufacturing Technology, 93, 3325-3338.Google ScholarCross Ref
- Wu, Y., & Ren, Y. 2011, September. Prediction of mechanical properties of hot rolled strips by BP artificial neural network. In 2011 International Conference of Information Technology, Computer Engineering and Management Sciences (Vol. 1, pp. 15-17). IEEE.Google Scholar
- Chou, P. Y., Tsai, J. T., & Chou, J. H. 2016. Modeling and optimizing tensile strength and yield point on a steel bar using an artificial neural network with taguchi particle swarm optimizer. IEEE access, 4, 585-593.Google Scholar
- Mohanty, I., Sarkar, S., Jha, B., Das, S., & Kumar, R. 2014. Online mechanical property prediction system for hot rolled IF steel. Ironmaking & Steelmaking, 41(8), 618-627.Google ScholarCross Ref
- Beghini, M., Bertini, L., Monelli, B. D., Santus, C., & Bandini, M. 2014. Experimental parameter sensitivity analysis of residual stresses induced by deep rolling on 7075-T6 aluminium alloy. Surface and Coatings Technology, 254, 175-186.Google ScholarCross Ref
- Cheng, C. K., Tsai, J. T., Lee, T. T., Chou, J. H., & Hwang, K. S. 2015, August. Modeling and optimizing tensile strength and yield point on steel bar by artificial neural network with evolutionary algorithm. In 2015 IEEE International Conference on Automation Science and Engineering (CASE) (pp. 1562-1563). IEEE.Google ScholarCross Ref
- Yun, X., Gardner, L., & Boissonnade, N. 2018. The continuous strength method for the design of hot-rolled steel cross-sections. Engineering Structures, 157, 179-191.Google ScholarCross Ref
- Lee, H., Yang, K., Kim, N., & Ahn, C. R. 2020. Detecting excessive load-carrying tasks using a deep learning network with a Gramian Angular Field. Automation in Construction, 120, 103390.Google ScholarCross Ref
- Heo, J., Song, K., Han, S., & Lee, D. E. 2021. Multi-channel convolutional neural network for integration of meteorological and geographical features in solar power forecasting. Applied Energy, 295, 117083.Google ScholarCross Ref
- Wang, Z., & Oates, T. 2015. Imaging time-series to improve classification and imputation. arXiv preprint arXiv:1506.00327.Google Scholar
- Wang, Y., Li, C., Peng, L., An, R., & Jin, X. 2021. Application of convolutional neural networks for prediction of strip flatness in tandem cold rolling process. Journal of Manufacturing Processes, 68, 512-522.Google ScholarCross Ref
Index Terms
- Prediction of mechanical properties of hot-rolled steel based on multi-channel convolutional neural network
Recommendations
Prediction of Mechanical Properties of Hot Rolled Strips by BP Artificial Neural Network
ICM '11: Proceedings of the 2011 International Conference of Information Technology, Computer Engineering and Management Sciences - Volume 01Based on analysis of artificial neural network model theory and modeling methods, combining with parameters of a certain factory strip research unit and mechanical performance inspection data, Through choosing Traingdm to train network, then, the ...
Prediction of creep curve of HP40Nb steel using artificial neural network
Simulation of creep curves using data obtained from a limited number of short-time creep tests is helpful for predicting the long-time creep life of materials by extrapolation techniques. The present paper demonstrates the application of artificial ...
KPCA-ELM Based Mechanical Properties Prediction of Hot Rolled Strip
DSIT 2020: Proceedings of the 3rd International Conference on Data Science and Information TechnologyPrediction of steel mechanical properties is significant in both industrial and academia area. For the modelling problem of mechanical properties prediction of hot-rolled strip, a data-driven method based on KPCA-ELM was proposed in this paper. KPCA is ...
Comments