氧化铝苛性比值的在线修正神经网络模型研究

The research of ANN after on-line amending for caustic ratio in the production of alumina

苛性比值是氧化铝生产过程中一个重要的生产指标。文章提出了一种在线修正方法,实现了对神经网络苛模型的在线修正,解决了基于历史数据建立的神经网络模型随着时间推移出现一定偏差的问题,提高了预测水平,而且因为执行过程均在计算机中进行,工作效率和可靠程度都得以大幅度提高。

In the production of alumina, the caustic ratio is the main production index in today's alumina industries. This paper raised a way of on-line amending, which be realized for ANN and solved the problem that ANN present some departures as time pass by and advanced its prediction level. Moreover, as the execution proceedings are all included the computer progressing, work efficiency and credibility can be improved greatly.