Part I Foundations of Alloy Yield 1 Ferroalloys: Properties, Applications, and Dissolution Behavior 1.1 Background 1.1.1 Steel industry's importance in national economy 1.1.2 The role of ferroalloys in the steel industry 1.2 Overview of ferroalloy foundation 1.2.1 Definition and classification of ferroalloys 1.2.2 Fundamental principles of ferroalloy smelting 1.3 Applications of ferroalloys in steelmaking 1.3.1 Deoxidation effects of ferroalloys in steelmaking 1.3.2 Alloying effects of ferroalloys in steelmaking 1.3.3 The modifying effect of ferroalloys on inclusions 1.3.4 Impact of ferroalloy composition and impurity management on steel melt cleanliness 1.3.5 Effect of ferroalloy addition practices on molten steel cleanliness 1.4 Frontier technologies in ferroalloy production 1.4.1 Steelmaking ferroalloy functionalization customization 1.4.2 Digitalization and intelligentization 1.4.3 Green and low-carbon ferroalloys 1.4.4 Resource circulation and regenerative utilization References 2 Research on Alloy Reduction Technology in Steelmaking Process 2.1 Introduction 2.2 Current research status of alloy reduction in the steelmaking process 2.2.1 The influence of the fundamental characteristics of alloys 2.2.2 The influence of alloy addition process 2.2.3 The impact of steelmaking process 2.3 Application of alloy reduction technology in steelmaking process 2.3.1 Alloy powdering control technology 2.3.2 Loss control technology of alloys under vacuum conditions 2.3.3 Motion and melting control technology of alloys added to molten steel 2.3.4 Alloy substitution technology 2.4 The main content and features of this book References Part II Data-Driven Modeling for Process Prediction 3 Complex Raw Material Conditions Alloy Yield 3.1 Background 3.2 Methodology of multi-model PSO-LSTM 3.2.1 Classification of working conditions based on raw material conditions for ferroalloys 3.2.2 Long short-term memory network 3.2.3 Ferroalloy yield estimator based on PSO-LSTM 3.3 Data preprocessing 3.4 Parameter optimization 3.5 Comparison of model capabilities 3.5.1 Analysis of model simulation results
4.2.1 Overview of the studied integrated steel mill 4.2.2 Data acquisition 4.2.3 Data analytical method 4.3 Results and discussion 4.3.1 Consumption statistics of various ferroalloys 4.3.2 K-means clustering algorithm analysis of data 4.3.3 Path analysis of silicon and manganese yield 4.4 Conclusions References 5 Steel Composition 5.1 Background 5.2 Methodology of PSO-BP 5.3 Data preprocessing 5.4 Parameter optimization 5.4.1 The effect of the learning rate on the prediction results 5.4.2 The effect of the training times on the prediction results 5.4.3 The effect of the number of hidden layer nodes on the prediction results 5.5 Comparison of model capabilities 5.5.1 PSO-BP and other neural network prediction model comparison 5.5.2 Application effect evaluation 5.6 Some aspects on carbon content at the endpoint of converter prediction References 6 Converter Tapping Weight 6.1 Background 6.2 Analysis of the BOF refining process 6.2.1 Description of converter smelting and data acquisition process 6.2.2 Scrap classification 6.3 Data processing and research methods 6.3.1 BP neural network based on PCA-WOA optimization 6.3.2 Data preprocessing 6.3.3 Extraction by principal component analysis (PCA) 6.3.4 Evaluation criteria 6.4 Establishment and discussion of model 6.4.1 Structural optimization of the model 6.4.2 Verification and comparison of PCA-WOA-BP model effect 6.4.3 Practical application 6.5 Conclusion References 7 Converter Endpoint Temperature 7.1 Background 7.2 Methodology of SOA-BP 7.3 Data preprocessing 7.4 Parameter optimization 7.5 Comparison of model capabilities 7.6 Some aspects of predicting the endpoint temperature of a converter References Part III Industrial Application and Optimization 8 Real-Time Alloy Yield Prediction for Dynamic Process Control 8.1 Background 8.2 Methodology of t-SNE-WOA-LSTM
8.3 Data preprocessing 8.4 Parameter optimization 8.5 Comparison of model capabilities 8.5.1 t-SNE-WOA-LSTM and other neural network prediction model comparison 8.5.2 Application effect evaluation 8.6 Some aspects on prediction of alloying element yield References 9 Cost Optimization in Steelmaking Through Enhanced Yield Models 9.1 Background 9.2 Methodology of real-time alloy yield prediction model 9.2.1 Mathematical model for general linear programming problem 9.2.2 Solutions to linear programming problems 9.2.3 Development of the SVM-based revised CBR model 9.2.4 Evaluation metrics 9.3 Data preprocessing 9.4 Parameter optimization 9.5 Comparison of model capabilities 9.5.1 Experimental results of ferroalloy batching research based on linear programming 9.5.2 Development of human-machine interface 9.5.3 Effects of industrial applications 9.6 Some aspects on intelligent model and application of ferroalloy reduction in steelmaking References
[