Abstract: The present invention provides a learning method of rolling load prediction which uses a prediction error of a rolling load at an actual pass of a stock in hot rolling to correct a predicted value of rolling load at a subsequent rolling pass. The method comprises changing a gain for multiplying with the prediction error of the rolling load at the actual pass in accordance with a thickness of the stock to thereby set the learning coefficient of the rolling load prediction and improve the precision of the prediction.

Abstract: In the learning method of rolling load prediction in hot rolling, in the past the prediction error of the rolling load was corrected based on envisioned error factors, but in the complicated rolling phenomenon, there are many influential factors and therefore logical extraction and estimation had been difficult. Therefore, the learning method of rolling load prediction according to the present invention refers to prediction error of a rolling load at an actual pass of a stock in hot rolling to correct a predicted value of rolling load at a rolling pass to be performed from then on, at which time changing a gain multiplied with the prediction error of the rolling load at said actual pass in accordance with a thickness of said stock to thereby set the learning coefficient of the rolling load prediction and improve the precision of the prediction.