YANG Jing-ming
,
ZHANG Qing
,
CHE Hai-jun
,
et al
钢铁研究学报(英文版)
Based on rolling feature of continuous tandem cold rolling mill, such as multi-variable, strong coupling, non-linear, analyze and set the equal relative load, preventing slippage and profile well as the multi-objective optimization goal, BP neural network with self-learning function is adopted to replace traditional rolling force models and then Levenberg-Marquardt algorithm is adopted to predict the rolling force. Then use multi-objective fuzzy theory to solve the problem of multi-objective optimization of tandem cold rolling schedule. With the example of 1370mm tandem cold rolling, the rolling schedule of the common rolling, the single-object optimization design and the multi-objective fuzzy optimization design are compared with each other, optimization result shows the proposed optimization method decreases the value of three objective functions simultaneous. The performance of the optimal rolling schedule is satisfying and it is promising.
关键词:
rolling schedule;tandem cold rolling;neural network;multi-objective fuzzy optimization
