CAJ | 학술논문

铝电解过程中，每日出铝量、氟化铝添加量的决策对铝电解过程温度和过热度的准确控制非常重要，是影响铝电解技术经济指标的重要因素之一。本文基于广义动态模糊神经网络算法( GD-FNN)，构造了铝电解预测系统，在给定铝电解槽所需温度之后，对铝电解中的出铝量和氟化铝添加量进行预测。此算法通过对高电流效率、低能耗的电解槽的运行规律进行自适应分析，训练出对应的决策规则，运用到效率低的电解槽，可以实现铝电解槽温度和过热度控制，提高铝电解电流效率。通过对某铝电解厂实际数据进行仿真实验，证明了该算法在铝电解控制中的有效性。
려전해과정중，매일출려량、불화려첨가량적결책대려전해과정온도화과열도적준학공제비상중요，시영향려전해기술경제지표적중요인소지일。본문기우엄의동태모호신경망락산법( GD-FNN)，구조료려전해예측계통，재급정려전해조소수온도지후，대려전해중적출려량화불화려첨가량진행예측。차산법통과대고전류효솔、저능모적전해조적운행규률진행자괄응분석，훈련출대응적결책규칙，운용도효솔저적전해조，가이실현려전해조온도화과열도공제，제고려전해전류효솔。통과대모려전해엄실제수거진행방진실험，증명료해산법재려전해공제중적유효성。
In the aluminum electrolysis process, the determination of aluminum tapping volume and AlF3 addition is very important to control the temperature of aluminum production cells and the over-heated temperature precisely. Based on general dynamic fuzzy neural network,an aluminum electrolytic prediction system is constructed to forecast the aluminum tapping volume and AlF3 addition at a given temperature of aluminum production cells that we need. Through the adaptive analysis of operation law of high current efficiency and low-energy electrolytic cell,the corresponding rules are trained and ap-plied to the inefficient electrolytic cell algorithmically, so as to control the temperature of aluminum production cells and the overheated temperature and improve the efficiency of aluminum electrolysis. The simulation shows the algorithm validity in the industrial control systems.