Prediction of finishing rolling temperature of hot strip mill based on data driving
The finishing rolling temperature is the main control process parameter in the hot continuous rolling process,and is an important prerequisite to ensure the quality of strip steel.The strip steel has experienced a complex heat exchange process in the finishing rolling stage,and it is difficult to improve the prediction accuracy of the semi mechanism model adopted in the field.In view of this problem,from the perspective of data-driven,a prediction model of finishing rolling temperature based on the combination of multi strategy improved whale optimization algorithm(IWOA)and extreme learning machine(ELM)is established.Incorporating cauchy variation improves the ability of whale algorithm to jump out of local optimization;Balance the global search and local development capabilities of whale algorithm with cosine control factors;The turning over for food is introduced to reduce the probability of the whale algorithm falling into the local optimum and improve the convergence speed of the algorithm.The experimental results show that the IWOA-ELM finishing rolling temperature prediction model has obvious advantages in prediction accuracy,and the hit rate of predicting the finishing rolling temperature within±6℃is 94%,which has broad application prospects.
prediction of finishing rolling temperaturewhale optimization algorithmCauchy variationturn over for foodcosine control factor
NETL
NSTL
万方数据
