Data-Driven Intelligent Recognition of Flatness Control Efficiency for Cold Rolling Mills

In the production process of strip tandem cold rolling mills, flatness control system is important for improving quality. The efficiency actuators a pivotal factor affecting accuracy. At present, data-driven methods to intelligently identify have become research hotspot. this paper, wavelet transform longitudinal denoising method, combined with genetic algorithm (GA-WT), proposed handle big noise measured data from each signal channel meter, and Legendre orthogonal polynomial fitting employed extract effective features. Based on preprocessed actual data, adaptive moment estimation (Adam) optimization applied, efficiency. This paper takes 1420 mm mill as an example, verify performance new method. Compared determined by empirical residual MSE 0.035 5.4% lower. test results indicate that GA-WT-Legendre-Adam method can effectively reduce noise, features, achieve intelligent determination