Development and Application of Integrated Learning System for Hot-Rolled Steel
1 Research Background
The comprehensive quality level of hot-rolled steel is an important indicator for measuring the overall technological development of the steel industry. With the support of the country's continuous and huge investment in scientific research and technological development, China has made significant progress in the fields of mechanical property regulation, size and shape control, and surface quality optimization of hot-rolled steel. We have successfully developed the hot-rolling production technology represented by the "New Generation TMCP", which has improved the strength and toughness of steel. We have introduced, absorbed and innovated the automatic thickness and width control technology, ensuring the dimensional accuracy of the products. The developed hot-rolling oxidation control technology has improved the surface quality of steel. However, the above-mentioned progress is the crystallization of technological advancements in the industrial age, featuring distinct independent control characteristics that operate independently. While enhancing a single performance indicator, it is bound to sacrifice other quality indicators. Therefore, how to further improve the comprehensive quality of hot-rolled steel determines whether our country can further enhance the competitiveness of its products, achieve efficient production, and thus remain invincible in the global competition for basic raw materials.
The hot rolling process is a typical multi-field coupled steel forming and formative process. The combined effect of temperature and deformation causes a series of complex physical and metallurgical processes within the rolled piece, including solid solution of elements, precipitation of microalloy elements, recovery and recrystallization softening. These organizational evolution behaviors not only determine the internal organizational structure and mechanical properties of the product, but also determine the deformation resistance of the rolled piece and affect the changes in force-energy parameters during the rolling process. They are the core factors in controlling the shape and dimensional accuracy of the product. On the other hand, during the rolling process, the rolled piece is constantly exposed to high temperatures and air environments, and severe surface high-temperature oxidation is inevitable. As the interface medium between the roll and the rolled piece, the variation of the thickness of the iron oxide scale can change the interface friction coefficient, thereby affecting the rolling force energy parameters. Meanwhile, the statistics of industrial production show that over 70% of the surface quality defects of products are caused by improper control of high-temperature oxidation behavior.
In conclusion, the microstructure evolution, surface oxidation behavior and force and energy parameter changes of hot-rolled products present the characteristics of strong coupling and black box state. Only by solving this problem can the coordinated optimization of surface quality, mechanical properties and dimensional accuracy be achieved, and the overall quality of the product be improved. However, the traditional hot-rolling production control technology is no longer capable of solving the strong coupling black box problem of such complex nonlinear systems.
2. Technical routes and solutions
The project team, through the big data mining of the hot rolling industry, integrated the process mechanism of steel rolling and the physical metallurgical mechanism, and developed an integrated learning system for hot-rolled steel that comprehensively considers the evolution of microstructure, the evolution of iron oxide scale thickness, interfacial friction and changes in rolling force, as shown in Figure 1. On this basis, by applying the multi-objective optimization theory and methods, the comprehensive quality control of hot-rolled products was achieved.
Picture
During the hot rolling process, the evolution of the microstructure inside the rolled piece determines its macroscopic rheological stress. Rolling force, as a key parameter that can be detected in real time and precisely in industrial production, can accurately reflect the changes in microstructure. By taking rheological stress as a bridge and conducting machine learning on industrial big data of hot-rolling force energy parameters, the process of austenite recrystallization and grain morphology evolution during the rolling process can be revealed. In addition, during the hot rolling production process, iron oxide scale is constantly formed on the surface of the steel, acting as a lubricating medium at the interface between the rolls and the rolled piece, thereby affecting their contact state and further influencing the changes in the rolling load of the rolled piece. The project team has cracked the strong coupling relationship among microstructure, force-energy load and friction coefficient. Based on the precise prediction of the softening behavior and friction state of the rolled piece, they can accurately predict the changes in rolling force during the hot rolling process, thereby effectively improving the control accuracy of thickness and plate shape.
After the rolling process is completed, hot-rolled steel needs to undergo an accelerated cooling process to control its phase transformation behavior. During this period, the deformed austenite undergoes continuous cooling phase transitions such as ferrite, pearlite, bainite and martensite. The main factors influencing the phase transformation behavior of rolled pieces include: the austenite microstructure state after rolling and the cooling path of the rolled piece. Their combined effect determines the phase transformation products, the proportion of each phase and the degree of grain refinement. Under the premise that the rolling process parameters remain basically unchanged, the cooling path will directly determine the phase composition of the steel and thereby its final mechanical properties. Rapid and accurate acquisition of the continuous cooling transition curve (CCT) helps to formulate the correct cooling path and achieve precise regulation of the performance of hot-rolled steel. For this purpose, the project team, based on the establishment of CCT databases for different steel grades, developed a hereditary machine learning modeling method for dynamic phase transformation in combination with the principles of physical metallurgy, achieving the rapid generation of continuous cooling phase transformation curves for different steel grades.
High-strength steel undergoes complex phase transformation behavior during the cooling stage and is highly sensitive to the influence of the cooling path. The traditional modeling method that solely relies on static digital data cannot fully reflect the impact of cooling path fluctuations on the microstructure and performance of the product, resulting in a significant deviation between the predicted results and the actual performance. To this end, the project team developed a dynamic deep learning model. By introducing convolutional neural networks, it not only effectively overcame the feature loss problem of traditional data-driven machine learning models when dealing with unstructured data, but also significantly enhanced the multi-modal information integration ability for complex physical phenomena, thereby being able to perceive various complex factors that affect the final microstructure and mechanical properties of steel. This modeling method can automatically learn and extract the influence law of the cooling path on the evolution of microstructure, and thereby accurately perceive the fluctuation of mechanical properties with the change of process parameters.
3. Implement the production line and the implementation effect
3.1 Promotion and application of 1580mm hot continuous rolling and continuous stripping production lines
For a certain 1580mm hot continuous rolling and continuous annealing production line, taking a series of steel grades such as low-alloy high-strength steel and IF steel, which are widely used in large quantities, as the research object, based on industrial big data, an integrated machine learning system was developed and the autonomous optimization of key influencing factors of the system was achieved. For the produced Nb, NB-Ti microalloy steel and IF steel, the full-process temperature field calculation of microstructure evolution during rolling and continuous annealing is realized, as well as the precise calculation of austenite recrystallization behavior, phase transformation behavior and precipitation behavior. And by taking SAPH440, QstE380TM, S420MC, QstE460TM, S500MC, M3A45 and M3A21 as examples, the precise prediction of the organizational evolution process was achieved. For grades such as SAPH440, S420MC, QStE420TM, DC04, DC06, and St13, online prediction of mechanical properties is achieved. Regarding yield strength and tensile strength, over 90% of the predicted strength values of the steel coils have an error of within ±20MPa compared to the actual values. For elongation, the predicted elongation value of over 90% of steel coils has an error of within ±3% compared to the actual value.
The promotion and application of the 2250mm hot continuous rolling production line
Relying on a certain 2250mm hot continuous rolling production line, by integrating steel rolling technology, big data mining, and artificial intelligence technology, and driven by industrial big data, an integrated learning system for hot-rolled steel was developed through physical mechanisms and knowledge learning. This system deconstructed the complex relationships between key parameters such as processes, techniques, and equipment and their organizational structures, achieving intelligent process design for hot-rolled products. Through the learning strategy of "initial learning - reinforcement learning - optimization learning", and by integrating industrial big data-driven and machine learning algorithms, precise analysis of physical processes such as recrystallization, precipitation, and surface oxidation in the hot rolling process has been achieved. Online performance prediction of over 20 steel grades including Q235B, Q420B, 600XL, and 700XL has been realized. The strength prediction accuracy reaches ±6%, and the elongation prediction accuracy is within ±4%, significantly reducing the amount of mechanical property inspection and enhancing the market response capability. In addition, dynamic soft measurement of hot-rolled oxidation behavior was achieved, and the prediction accuracy of the oxide scale thickness and structure of the product reached ±2μm and ±10% respectively. Based on this, the flexible control technology for iron oxide scale structure was developed, and new varieties of steel series represented by 700MPa grade acid-free steel and SPHC, which are easy to acid wash, were developed.
3. Promotion and application of the 5500mm wide and thick plate production line
In the face of the changes in production and consumption structure brought about by the new industrialization, the characteristics of the wide and thick plate production process, such as complex variety structure and a large number of small-batch orders, have become more prominent. The large amount of billets generated has caused huge economic losses to enterprises. Moreover, the excessive number of steel grades has complicated the steelmaking process, seriously affecting the continuous improvement of production efficiency and product quality. In response to the above-mentioned challenges, the project team, relying on the 5500mm wide and thick plate production line, has developed an integrated learning system for hot-rolled steel for typical wide and thick plate production lines. This system can conduct self-learning of the model based on actual production conditions, process and environmental changes, and automatically optimize the model parameters. We have successfully achieved high-precision prediction of the mechanical properties of multiple grades of products, including A, AH32, AH36, DH36, and Q355MD. On this basis, a flexible design object library for the billet process was established, an evaluation function for the optimal organizational structure and performance indicators of billet production was proposed, an intelligent matching optimization algorithm was developed, and a prediction model of "composition - process - structure - performance" for the billet was established. Based on the comprehensive consideration of the combined effects of strengthening mechanisms such as fine grains, precipitation, dislocations and phase transformation, a flexible design method for the rolling process was proposed to achieve flexible design of the process across thickness and strength for three major series of steel grades, namely C-Mn, pipeline and low alloy.
4. Promotion and application of 5000mm wide and thick plate production lines
In recent years, steel for offshore wind power has emerged as a powerful force, with a sharp increase in demand. According to authoritative research, each megawatt of offshore wind power uses approximately 200 tons of medium and heavy plates. During the "14th Five-Year Plan" period, the newly installed capacity of offshore wind power will exceed 44GW, and it is estimated that the demand for medium and heavy plates will be no less than 8.8 million tons. Among them, there is a huge demand for large-thickness (60-150mm) steel plates used in offshore wind power towers and pipe piles. In terms of composition design, conventional extra-thick plates generally adopt high C, high Mn, +Cr, Ni, Cu and other precious metals, as well as a small amount of Nb, V, Ti grain refinement elements. The mechanical properties of extra-thick steel plates are mainly guaranteed through the solid solution strengthening of alloy elements and grain refinement. The original design not only had a high cost, but also due to the severe central segregation of alloying elements in the extra-thick continuous casting slab, the core performance of the extra-thick plate decreased significantly, especially the low-temperature impact toughness of the core was difficult to meet the performance requirements of the extra-thick plate. The project team, in response to the 355-460MPa grade wind power steel, combined with the characteristics of the 5000mm wide and thick plate production line, adopted an ultra-low C and N composition route to redesign the composition system of the extra-thick steel plate, increase the niobium content in the steel, reduce the content of carbon, manganese and other precious metal alloys, and improve the central segregation of the extra-thick plate billet. Based on this, in combination with the integrated machine learning system for hot-rolled steel, the rolling process design for 60-150mm thick wind power steel is achieved by calculating the temperature and microstructure distribution in the thickness gradient direction of the thick plate. The results of batch production show that the qualified rate of mechanical properties of 355MPa strength grade steel plates is 100%, and the qualified rate of one-time core impact performance reaches over 98%.
4 Conclusion
The project team comprehensively utilized the principles of machine learning, deep learning, and physical metallurgy, and integrated data with multi-modal structures to innovatively propose an integrated machine learning system for steel, which has been successfully applied to multiple production lines in China. This system enables high-precision prediction of the microstructure evolution, surface oxidation behavior and rolling force of rolled pieces. At the same time, it also provides strong support for the optimization of process parameters, the development of new steel grades and new processes, thereby enhancing the overall production efficiency.
15358968703