Data-driven composition design and property optimization of solid solution and precipitation simultaneously strengthened non-oriented silicon steel

• Published in: Materials & design Vol. 242; p. 113011
• Main Authors: Liu, Yameng, Wang, Zhilei, Wang, Yutang, Li, Yanguo, Zhao, Fan, Zhang, Zhihao, Liu, Xinhua
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.06.2024; Elsevier
• Subjects: Machine learning; Magnetic properties; Non-oriented silicon steel; Strength; Non-oriented silicon steel; Strength; Machine learning; Magnetic properties
• ISSN: 0264-1275; 1873-4197
• DOI: 10.1016/j.matdes.2024.113011

[Display omitted] •Strength and magnetic properties of silicon steel were optimized simultaneously.•Adversarial model was applied in silicon steel composition design.•The effect of alloying elements on properties was analyzed based on Association rule mining. Limitations on data volume and quality are key bottlenecks in using machine learning for property prediction and property-oriented composition design of non-oriented silicon steel. In response, this study employed a Gaussian Mixture Model (GMM) to generate virtual samples for enhancing the in-house experimental data, by which the generated virtual data well captured the distribution of the raw experimental data. As a result, compared with the model without data augmentation, the enhanced prediction model (composition → property) fitted by virtual samples improved its R2 value from 0.52 to 0.86. Based on this model, a multi-properties-oriented (yield strength σs, magnetic induction B50, and iron loss P10/400) composition prediction model (property → composition) was established to rapidly discover high-performance non-oriented silicon steel. Experimental characterization and theory calculation of the explored candidate alloys exhibited that their yield strength was above 750 MPa, which primarily results from solid solution strengthening (50 %) and precipitation strengthening (36 %). Moreover, the alloys possessed magnetic induction B50 of over 1.72 T and low core losses with P10/400 of 12.1 W/kg (0.2 mm) and 17.0 W/kg (0.35 mm). Further microstructural characterization exhibited that such satisfactory performance is associated with copper (Cu)-rich nanoprecipitates that dramatically improved the yield strength without deteriorating the magnetic properties.