Analysis of the cause of crack in cold rolling of QSn6.5-0.1 strip

In order to know the cause of cracks in cold rolling of QSn6.5 0.1 copper alloy strip, a lot of experiments and analysis were done. The microstructure changes of QSn6.5 0.1 were investigated by means of metallurgical microscope. The morphology of cracks and surface defects were examined using scanning electron microscope. Macroscopic residual stresses produced in every process during manufacturing in the QSn6.5 0.1 strip were measured by X ray diffraction method and hole drilling method. The results show that the cracks in the QSn6.5 0.1 cold rolling strip were caused due to the derivation of metallurgical defects, such as SnO 2, S, fine looses,the inverse segregation unable to clear up when milling, and the accumulation of all kinds of resi dual stresses. When the accumulation of the residual stress reaches the material′s breaking strength, the cracks will be generated. Several measures to avoid the development of these kinds of cracks were put forward, such as: controlling the casting technology, improving homogenization annealing procedure (680 ℃/7 h) and milling quality(using the second milling when necessary), working out a more reasonable rolling technology to ensure intermediate annealing in time.

Study on the Asymmetrical Cold Rolling of Strip under Large Width to Thickness Ratio

On the condition of the width to thickness ratio 625 of rolled strip, the asymmetrical cold strip rolling process about the width center is studied by using computer numerical simulation method and experimental method. The simulated results of the transverse distributions of the rolling pressure. the 2-directional frictions and the front and back.tensions agree with the experimental reuslts well. It is an important discovery that the rolling pressure has three peak values across the strip width on the condition of large width to thickness ratio.

Effect of Width-to-Thickness Ratio and Thickness Profile Changing on the Critical Instable Shape During Cold Strip Rolling

Based on the volume constancy with equal flow-per-second and elastic sheet stability theory, a coupling relationship among lateral thickness difference, width-to-thickness ratio of cold rolling strip steel under ideal and actual working conditions, and shape is concluded according to the comprehensive influence principle of various factors on the critical instable shape analyzed in-depth. Firstly, the influence model under actual working condition is developed by referring to the basic relationship between lateral thickness difference and shape under ideal condition. The test results prove that for thin strips with thickness below 0.3 mm, their lateral thickness differences have significant effect on the shape. After then, the combined influence of lateral thickness difference and width-to-thickness ratio on the critical instable shape is concluded according to the elastic sheet stability model, with the synthetic effect of these three factors analyzed. Test data indicate that for cold rolling strip steel with width-to-thickness ratio above 3 000, the critical instability stress difference decreases significantly. Actual measurements are conducted on the lateral thickness differences of two rolls of typical strip manufactured by a sixhigh cold mill, with the influence law of lateral thickness variation and width-to-thickness ratio comprehensively investigated. It is demonstrated that during the production of ultrathin strip steel with different width-to-thickness ratios, the loading roll shapes should be fine adjusted according to the lateral thickness difference of input strips.Therefore, the variation of lateral thickness difference of output strips can meet the requirement of shape stability,so as to obtain fine shape.

Prediction of mechanical properties of cold rolled strip based on improved extreme random tree

Taking the 2130 cold rolling production line of a steel mill as the research object,feature dimensionality reduction and decoupling processing were realized by fusing random forest and factor analysis,which reduced the generation of weak decision trees while ensured its diversity.The base learner used a weighted voting mechanism to replace the traditional average method,which improved the prediction accuracy.Finally,the analysis method of the correlation between steel grades was proposed to solve the problem of unstable prediction accuracy of multiple steel grades.The experimental results show that the improved prediction model of mechanical properties has high accuracy:the prediction accuracy of yield strength and tensile strength within the error of±20 MPa reaches 93.20%and 97.62%,respectively,and that of the elongation rate under the error of±5%has reached 96.60%.

Intelligent representation method of image flatness for cold rolled strip

Real flatness images are the bases for flatness detection based on machine vision of cold rolled strip.The characteristics of a real flatness image are analyzed,and a lightweight strip location detection(SLD)model with deep semantic segmentation networks is established.The interference areas in the real flatness image can be eliminated by the SLD model,and valid information can be retained.On this basis,the concept of image flatness is proposed for the first time.An image flatness representation(IFAR)model is established on the basis of an autoencoder with a new structure.The optimal structure of the bottleneck layer is 16×16×4,and the IFAR model exhibits a good representation effect.Moreover,interpretability analysis of the representation factors is carried out,and the difference and physical meaning of the representation factors for image flatness with different categories are analyzed.Image flatness with new defect morphologies(bilateral quarter waves and large middle waves)that are not present in the original dataset are generated by modifying the representation factors of the no wave image.Lastly,the SLD and IFAR models are used to detect and represent all the real flatness images on the test set.The average processing time for a single image is 11.42 ms,which is suitable for industrial applications.The research results provide effective methods and ideas for intelligent flatness detection technology based on machine vision.