In this paper, a hybrid intelligent parameter estimation algorithm is proposed for predicting the striptemperature during laminar cooling process. The algorithm combines a hybrid genetic algorithm (HGA) withgrey case-based reasoning (GCBR) in order to improve the precision of the strip temperature prediction. Inthis context, the hybrid genetic algorithm is formed by combining the genetic algorithm with an annealingand a local multidimensional search algorithm based on deterministic inverse parabolic interpolation. Firstly,the weight vectors of retrieval features in case-based reasoning are optimised using hybrid genetic algorithmin of�ine mode, and then they are used in grey case-based reasoning to accurately estimate the modelparameters online. The hybrid intelligent parameter estimation algorithm is validated using a set ofoperational data gathered from a hot-rolled strip laminar cooling process in a steel plant. Experiment resultsshow the effectiveness of the proposed method in improving the precision of the strip temperatureprediction. The proposed method can be used in real-time temperature control of hot-rolled strip and haspotential for parameter estimation ofdifferenttypesofcoolingprocess.
展开▼