Search

In the field of hot rolling big data, the presence of different steel types, specifications, and data heterogeneity poses significant challenges to the accuracy and stability of using single machine learning regression technology for prediction. Therefore, this study proposes a hot‐rolled strip crown prediction method that combines data clustering and fusion modeling. First, this article introduces a relevant mechanism for designing cluster strategies. The optimal clustering strategy is determined through comparative experiments using rolling process parameters, strip size, and main material components as the clustering features. Subsequently, the K‐Means++ algorithm is used to effectively cluster the training and testing datasets based on this strategy, generating multiple clusters for both datasets. Finally, this study establishes seven different training models to match the most suitable regression prediction model for each cluster, and matching between each cluster and the model is determined through rigorous testing. The evaluation of the fusion model shows an R2 value of 0.829 and a root mean square error value of 3.974. The experimental results show that the proposed method outperforms traditional methods in solving the challenges of multiclass classification and data heterogeneity, providing strong data support for the intelligent control of the hot‐rolled strip crown in the future. [ABSTRACT FROM AUTHOR]

During the slab sizing press (SP) process, the pressing force corresponds to the slab profile, which guides the production schedule design and the final profile control. To accomplish the prediction of pressing force for SP, an improved ensemble method based on chaotic Harris hawks optimizer (CHHO) and stacking is proposed. A mechanistic knowledge is introduced for feature selection that enhances the rationality of input features. Subsequently, 11 machine learning models are compared and 5 of them are selected as candidate learners for the stacking method. Based on the candidates learners, 8 stacking strategies are constructed, which the stacked model with extratree regressor, gradient boosted decision trees, and kernel ridge regression (KRR) as base‐learners and KRR as meta‐learner performs the best. The R2, MAE, mean square error, mean squared log error, and mean absolute percentage error for the test dataset are 0.9912, 0.0856, 0.0167, 0.0005, and 2.00%, respectively, and 95% of the prediction errors are less than 0.15 MN. Then, sensitivity analysis and predictive analysis based on Shapley Additive Explanations are performed to demonstrate the good alignment of the proposed model with physical reality. Furthermore, to cope with the complexity and uncertainty of the production process, the proposed CHHO‐stacking model and the kernel density estimation method are integrated to model the prediction interval. [ABSTRACT FROM AUTHOR]

As an emerging technology in the production of electrical steel, edge‐drop control (EDC) caters to the increasing requirements for the overall shape quality of strips. Herein this review, the development of EDC theory, method, and control system used in the cold‐rolling process is summarized. Also, in this review, research on EDC theory is found to be based on the 3D plastic deformation model of the strip, considering the lateral metal flow. Further, an analytical model and a numerical calculation method are employed to establish an edge‐drop calculation model with high accuracy and speed. Next, taper‐work‐roll shifting (T‐WRS), a conventional EDC technology, is found to have been greatly improved in actual production. However, T‐WRS technology involves coupling problems in terms of edge drop and crown and flatness control. Finally, the closed‐loop EDC is found to depend on the online WRS of multiple stands. Particularly, the genetic law of strip thickness in the continuous rolling process and the edge‐drop regulation characteristics of each stand in the continuous rolling mill are significant aspects; thus, a reasonable roll‐shifting control strategy must be formulated. Based on the reviewed research, the development prospect of EDC is characterized. [ABSTRACT FROM AUTHOR]

To obtain the transverse temperature distribution of running strips under C‐type edge induction heaters during the hot‐rolling process, a coupled electromagnetic–thermal finite‐element model is established using COMSOL, in which the electromagnetic and temperature distributions regularity with various process parameters are systematically obtained. It is shown in the results that the temperature increase is directly proportional to the frequency and current and inversely proportional to the thickness. Meanwhile, the edge temperature drop can be rapidly compensated for using an edge heater, but it also leads to the appearance of a "cat‐ear" high‐temperature zone at the edge; thus, the transverse temperature uniformity cannot be guaranteed. To improve the temperature uniformity of the running strip, a magnetic shield plate is designed to weaken the effect of the cat ear, and the effects of the size and installation position of the shielding plate on the temperature distribution are analyzed. The standard deviation and uniformity of the temperature are used to determine the uniformity of the transverse temperature, and the optimal parameter combination mode of the magnetic shielding amounts is obtained, which can provide a reference for optimizing the heating process at the edge of the strip under moving conditions. [ABSTRACT FROM AUTHOR]

In the hot strip process, the prediction of strip shape is a key factor to improve the quality of products. However, strip‐shape prediction models based on traditional machine learning algorithms with relatively simple network structures often rely on data preprocessing and feature selection. Herein, five strip‐shape prediction models are proposed by combining sparrow search algorithm (SSA), particle swarm optimization algorithm (PSO), extreme learning machine (ELM), and deep multilayer extreme learning machine (DELM). The prediction experiments show that the SSA‐DELM model has highest accuracy, and the determination coefficient (R2) of crown prediction and flatness prediction of SSA‐DELM model is 0.971 and 0.979. 100% of the samples have a prediction error of less than ±7 μm and ±7 IU. Furthermore, to solve the problem of concept drift affecting prediction accuracy in industrial processes, online optimization method is proposed. Especially, online sequential deep ELM model (OS‐DELM) optimized by SSA and guided by double window drift detection is proposed to fill the gap. Compared with other online optimization methods, the update time with this method can be reduced by up to 83.05% averagely, which is more suitable for online strip‐shape prediction in hot rolling process. [ABSTRACT FROM AUTHOR]