Abstract
In the hot rolling process, the prediction of strip crown is the key factor to improve the flatness quality of the strip. However, the traditional prediction method can only provide prediction values, but does not quantitatively evaluate the prediction error and stability. While Gaussian process regression (GPR) provides full probability prediction and estimates the uncertainty in the prediction. Therefore, for the first time, GPR is applied to predict strip crown. Furthermore, considering the negative influence of unavoidable outliers in measurement data, this article proposes an improved local outlier factor (LOF) algorithm to calculate the weights. And a novel Weight-GPR based on improved LOF prediction model is established. The proposed model not only retains the effective information of outlier values, but also avoids the negative influence brought by outlier values. The prediction experiments based on the real world production line data show that the proposed model can be successfully applied to the prediction of the strip crown in hot rolling process. Also, the performance of the proposed model is compared with typical GPR, ANN and SVM, and the results demonstrate that the Weight-GPR based on the improved LOF model provides better prediction accuracy and stability.
Highlights
Hot rolling process is to use a series of rolls to progressively thin a cast or semi-finished steels to a desired thickness products such as the strip and sheet steel [1]
In the view of mean prediction interval width (MPIW) value, it is lower than the typical Gaussian process regression (GPR) model, which indicates that the stability of the proposed model is better than that of typical GPR
Considering the existence of outlier values in the ture data of the factory, this article proposes a novel Weight-GPR based on improved local outlier factor (LOF) prediction model by combining feature-weighting technology with LOF algorithm
Summary
Hot rolling process is to use a series of rolls to progressively thin a cast or semi-finished steels to a desired thickness products such as the strip and sheet steel [1]. Y. Wu et al.: Novel GPR-Based Prediction Model for Strip Crown in Hot Rolling by Using the Improved LOF speed and high computational complexity. The actual experimental data are affected by some negative factors, such as the measurement deviation caused by the machine and the inherent uncertainty of the working environment caused by changes in temperature and humidity [22], inevitably generating outliers. Due to their high heteroscedasticity and other side effects, outliers are partially responsible for irregularities in the model, deviations in parameter settings and incorrect results [23], [24]. Where C40 stands for the strip crown at the edge 40mm, hc is the thickness at the center of the strip, h and h respectively means the thickness at 40mm on the left and right sides
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
