摘要
设计了预焙铝电解生产过程先进控制系统的总体结构,建立了基于神经网络的电解槽参数及阳极效应预测模型,设计了基于支持向量机的槽况解析与槽况诊断专家系统,提出了极距NN—PID控制策略、电解质温度基于混沌优化的模糊控制策略及氧化铝浓度的模糊专家控制策略;同时,针对有关参数的优化控制和产量质量能耗优化控制问题,提出了基于模糊专家控制技术的智能协调策略,以满足全局优化的控制目标;实验结果表明,系统能有效地实现预焙铝电解槽的优化控制,实现槽状态在线解析,并能达到优良的生产控制指标,为企业带来了巨大的经济效益和社会效益。
The collectivity structure of pre--baked aluminium electrolysis process advanced control system is designed. Prediction model of cell parameters based on neural network is constituted; the neural network expert system of cell state diagnosis based on support vector machine （SVM） is designed. The NN--PID control strategy of anode distance, the fuzzy control strategy based on chaos optimal of electrolyte temperature and the fuzzy--expert control strategy of alumina concentration are proposed. At the same time, considering the optimal control of important parameters, output, quality and energy consumption, the intelligent coordination strategy based on fuzzy--expert control technology is proposed, which can satisfy global optimal control target. The experiment results showed that the system could realize optimal control of aluminium electrolysis effectively; realize the cell state diagnosis on--line, and gain good control effect. The proposed system can bring large economic and social profits for the corporations.
出处
《计算机测量与控制》
CSCD
2008年第5期637-639,656,共4页
Computer Measurement &Control
关键词
先进控制
预焙铝电解槽
混沌神经网络
支持向量机
专家模糊控制
advanced process control （APC）
pre--baked aluminium electrolysis cell
chaos neural network
support vector machine（SVM）
expert fuzzy control
