On-line cold-rolled flatness signal pattern recognition system

Abstract

The invention provides an on-line cold-rolled flatness signal pattern recognition system. The on-line cold-rolled flatness signal pattern recognition system comprises a flatness gauge measurement signal receiving module, a flatness gauge measurement signal preprocessing module, a flatness signal pattern recognition module based on a radial basis function neural network and an on-line flatness signal pattern recognition output module. The flatness gauge measurement signal receiving module is used for receiving flatness gauge measurement signals through the industrial Gigabit Ethernet; the flatness gauge measurement signal preprocessing module is used for performing normalization and filtering processing on the flatness gauge measurement signals; the flatness signal pattern recognition module based on the radial basis function neural network is used for converting the preprocessed flatness gauge measurement signal into input signals of the radial basis function neural network and computing to obtain network output values of flatness pattern recognition; the on-line flatness signal pattern recognition output module is used for obtaining flatness pattern recognition results according to the network output values and transmitting the flatness pattern recognition results to a control system to provide control bases to the control system. By the on-line cold-rolled flatness signal pattern recognition system, the technical problems of dissatisfactory system recognition accuracy and real-time performance, complicated recognition model structures, long network training time and poor stability and robustness of traditional flatness pattern recognition systems are solved effectively, and the reliable control bases are provided for the control system.

Description

technical field [0001] The invention belongs to the field of cold-rolled steel strips, in particular to an online pattern recognition system for cold-rolled strip shape signals. Background technique [0002] In the cold-rolled strip production process, cold-rolled flatness pattern recognition is an important part of the cold-rolled flatness control system. Shape pattern recognition is to identify and classify the measured shape signal output by the shape meter, so as to accurately judge the shape defect type of the strip, provide control basis for the control system, and finally produce high-quality cold-rolled strip material products. [0003] The traditional plate shape signal pattern recognition method is based on the polynomial decomposition method of the least square method and the improved orthogonal polynomial regression decomposition method. These methods have poor anti-interference ability and have theoretical defects. High-precision shape control requirements. T...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide an online pattern recognition system for cold-rolled flatness signals, which can effectively solve the problems that traditional flatness pattern recognition systems often encounter, such as unsatisfactory system recognition accuracy and real-time performance, complex identification model structure and network training problems. The technical problems of too long time, poor stability and robustness can provide a reliable control basis for the control system, and provide a strong guarantee for improving the quality of cold-rolled strip shape control

Images