The edge of a hot rolling strip corresponds to the area where surface defects often occur. morphologies several common are similar one another, thereby leading easy error detection. To improve detection accuracy defects, authors this paper first classified and then made dataset defect images on basis. Subsequently, recognition models were established basis LeNet-5, AlexNet, VggNet-16 by using c...

The cold metal rolling industry needs reliable and accurate models to improve predictions of surface finish and friction and thus increase productivity and improve quality. These models are used in setup programs for schedule optimisation, for on-line control algorithms and to help determine process improvements. In most cold rolling operations, lubricant is used to reduce frictional forces, to...

in this work, effects of homogenization time of 3 to 13 h at 1200 °c on the grain refinement of as-cast aisi 301 stainless steel after different hot rolling conditions were investigated. the results showed that the minimum grain size of 16±7 mm was achieved when homogenization took place at 1200 °c for 9 h followed by hot rolling at temperature range of 1000–1200 °c with strain of 0.8 and strai...

There is a complicated relation between cold flat rolling parameters such as effective input parameters of cold rolling, output cold rolling force and exit thickness of strips. In many mathematical models, the effect of some cold rolling parameters has been ignored and the outputs have not a desirable accuracy. In the other hand, there is a special relation among input thickness of strips, the ...

It has great significance to research the dynamical reliability probability of rolling mill rolls system for improving its stochastic dynamical reliability and products quality rolled. The fifth-octave vertical vibration stochastic dynamical model of rolls system was established, and the pseudo-excitation method was used to obtain the power spectral density and the variance variation characteri...

The early fault characteristics of rolling element bearings carried by vibration signals are quite weak because the signals are generally masked by heavy background noise. To extract the weak fault characteristics of bearings from the signals, an improved spectral kurtosis (SK) method is proposed based on maximum correlated kurtosis deconvolution (MCKD). The proposed method combines the ability...

Based on the stochastic rolling force data from aluminum hot strip tandem mill, the ARMA time series model and the stochastic excitation power spectral density (PSD) model are established, and the stochastic rolling forces excitation model is established by utilizing Levenberg-Marquardt combined with generalized global planning algorithm. A two dimensional stochastic nonlinear dynamical model o...