Application of SVM and PCA-CS algorithms for prediction of strip crown in hot strip rolling

Self Cite

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.

MSE = \frac{1}{n} {\sum_{i = 1}^{n} (y_{i} - {\overset{y}{true}}_{i})}^{2}

MAPE = \frac{1}{n} \sum_{i = 1}^{n} | \frac{y_{i} - {\overset{y}{true}}_{i}}{y_{i}} |

MSLE = \frac{1}{n} \sum_{i = 1}^{n} {false(\log_{e} false(1 + y_{i} false) - \log_{e} false(1 + {\overset{false^}{y}}_{i} false) false)}^{2}

R^{2} = \frac{\sum_{i = 1}^{n} {({\overset{false^}{y}}_{i} - \overset{y}{true})}^{2}}{\sum_{i = 1}^{n} {(y_{i} - \overset{y}{true})}^{2}}

As for prediction interval, the prediction interval coverage probability (PICP) is determined to evaluate the accuracy of the model, and the formula of PICP is expressed as follows

PICP = \frac{1}{n} i \sum_{i = 1}^{n} ε_{...}

…”

Section: Proposed Modelmentioning

confidence: 99%

Section: Model Evaluation Indicatorsmentioning

confidence: 99%

A Combination of Chaotic Harris Hawks Optimizer‐Stacking Model and Kernel Density Estimation Method for Pressing Force Prediction During Slab Sizing Press Process

Wen

Wang

et al. 2023

Self Cite

“…To solve the limitation of weak generalization ability of ANN, Wang et al [ 8 ] developed strip crown prediction model based on support vector machine (SVM), and an improved PSO algorithm is used to optimize parameters ( C , σ ) of SVM. Ji et al [ 9 ] applied the SVM and principal component analysis combined with cuckoo search algorithms (PCA‐CS) to predict strip crown in hot strip rolling, and the proposed PCA‐CS‐SVM model has better performance than the traditional SVM model. Although these strip‐shape prediction methods based on machine learning algorithms extract various features and predict the strip shape parameters such as crown and flatness, the following problems still exist.…”

Section: Introductionmentioning

confidence: 99%

Prediction and Online Optimization of Strip Shape in Hot Strip Rolling Process Using Sparrow Search Algorithm‐Online Sequential‐Deep Multilayer Extreme Learning Machine Algorithm

Zhang

Ding

Sun

et al. 2023

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.

“…Methods that combine intelligent algorithms and machine learning are widely used in the field of metal processing. Ji et al [ 19 ] established an SVM prediction model for strip crowns based on principal component analysis combined with cuckoo optimization strategies. Dong et al [ 20 ] proposed a prediction model for head deformation of medium‐thick plates based on neural networks with an improved sparrow search algorithm.…”

Section: Introductionmentioning

confidence: 99%

Crown Prediction of Hot‐Rolled Silicon Steel Using Transfer Learning Network Fused with Whale Optimization Algorithm

Meng

Ding

Dong

et al. 2023

Massive amounts of data are generated during hot strip production in the hot‐rolling metal forming process; the resultant dataset is sufficient for model learning in strip steel crown prediction. However, the data of high‐grade nonoriented silicon steel are limited, and the rolling process parameters differ, resulting in poor crown prediction. Herein, a model based on the whale optimization algorithm and transfer learning to predict the crowns of hot‐rolled high‐grade nonoriented silicon strip steel is presented. The model is composed of convolutional and linear layers. The whale optimization algorithm is used to optimize the hyperparameters and obtain an optimal model during pretraining. The model is then fine tuned based on insufficient silicon steel data to achieve model migration. The application results show that the correlation coefficient reaches 0.993, which is the highest prediction accuracy among the comparison models. Furthermore, the root mean square error is 1.14 μm, and the hit rate within 4.0 μm of the crown deviation reaches 99.502%. In addition, the influences of four parameters on the crown of the silicon steel strip are studied based on the response surfaces. The results indicate that the proposed model can efficiently predict silicon steel strip crowns.