Adriano G. Passos, Tiago Cousseau, Marco A. Luersen^*

Computer Systems Science and Engineering, Vol.41, No.2, pp. 583-593, 2022, DOI:10.32604/csse.2022.020020 - 25 October 2021

Abstract A proper detection and classification of defects in steel sheets in real time have become a requirement for manufacturing these products, largely used in many industrial sectors. However, computers used in the production line of small to medium size companies, in general, lack performance to attend real-time inspection with high processing demands. In this paper, a smart deep convolutional neural network for using in real-time surface inspection of steel rolling sheets is proposed. The architecture is based on the state-of-the-art SqueezeNet approach, which was originally developed for usage with autonomous vehicles. The main features of More >

S.K. Pal¹, D.A. Linkens²

CMC-Computers, Materials & Continua, Vol.2, No.2, pp. 113-118, 2005, DOI:10.3970/cmc.2005.002.113

Abstract In hot rolling, the final thickness of the strip is achieved through plastic deformation of the original stock by a series of counter-rotating rollers. In this work, static recrystallization kinetics in between two stages of steel rolling has been modelled, and simulation studies have also been performed to find out the effect of entry temperature on the recrystallization kinetics. A viable bond graph model has been developed to study the kinetics of the process. Low-carbon steel has been considered for this purpose. More >