Research On Remote Evaluation And Judgment System For Shape Quality Of Hot Rolled Strip

With drastic development of home appliances, automobile and electronic industry etc, not only the requirement of quantity but also the requirement of quality of steel strip product are more and more in market. Shape quality is a key index of hot rolled strip and an important factor for its competition in market. But recently postmortem is applied by most enterprises for evaluating shape quality of hot rolled strip. The accuracy of this method is so low that it leads the increase of cost for uncoiling strip and compensation for goods inferior to sample, which therefore increases the cost of production greatly. How to evaluate and judge shape quality of hot rolled strip effectively becomes an urgent problem to solve, so it is very necessary to do some research on it.First of all, background, resource and significance of this project are elaborated, and domestic and oversea research status of remote evaluation and judgment for steel strip shape quality are introduced in detail, and outline of research is confirmed integrating with the fact of Zhujiang Steel in this dissertation. Then, according to definition of strip shape, multiple indexes of its two aspects including strip profile and flatness are analyzed. Consequently, required data and project for evaluating strip shape quality are confirmed. And then, principle of flatness measurement, acquirement of flatness parameter and survey of data collection system are introduced briefly. Project of remote data transmission is put forward under circumstance of taking full use of the software and hardware of original system. And then, Method of reconstruction and evaluation for two-dimensional strip shape quality are discussed by long pieces of paper, three methods of flatness defects pattern recognition are compared including pattern recognition of flatness defect by least square approximation method, pattern recognition of flatness defect by fuzzy classification method and pattern recognition of flatness defect by neural network method. Because the known parameters of strip shape can not be preferably used by these methods to distinguish flatness defects, pattern recognition of flatness defect by reasoning method...