A neural network model to determine the plate width set-up value in a hot plate mill

Performance of the process reducing the slab width in hot plate mill called edging is critical to produce rolled products with a desired dimension, wh ich otherwise increase the yield loss caused by trimming. This process, the refore, requires a stringent width control performance. In this paper, an e dger set-up model generating the desired slab width required for the contro l is proposed based upon the neural network approach. This neural network m odel accounts for variation of the dimension of incoming slabs to predict t he preset value of the width as accurately as possible. A series of simulat ions were conducted to evaluate the performance of the neural network estim ator for a variety of operating conditions needed for producing rolled prod ucts of various dimensions. The results show that the proposed model can es timate the preset value of the slab width with good accuracy, thereby enhan cing the dimensional accuracy of rolled products. The estimation performanc e is discussed in detail for various process operation conditions.