基于案例推理的冷轧负荷分配模型研究

Case-based Reasoning Model for Cold Rolling Schedule

针对冷轧负荷分配的特点,提出了一种基于案例推理的冷轧负荷建模方法,着重研究了基于粗糙集和神经网络的快速案例检索以及利用数据库中的知识发现技术进行案例修改,经现场数据对比实验表明所建模型更符合实际轧制情况。

To develop a cold roUing schedule model that complies with the practical operations in cold strip rolling, the techniques of case-based reasoning were introduced in the modeling process, in which rough set and neural networks were used for rapidly retrieving the cases; while the knowledge discovery in database was introduced to find the rules from the operational data records to modify the initial schedule if there was difference between the ongoing rolling practice and the case applied, The experimental results show that the schedule generated by the new model is more reasonable and conformable to the actual cold rolling practice than that generated by traditional method, which indicates that the method proposed is a promising method for modeling.