摘要
提出一种基于改进的FasBack神经模糊系统的新型对羧基苯甲醛(4-CBA)软测量模型,用Leven-berg-M arquardt算法训练模型中的部分参数,经实际过程数据验证表明,提出的模型学习速度快、预测精度高、鲁棒性强,为实现精对苯二甲酸(PTA)生产过程中4-CBA含量的实时、精确控制提供了一条有效的途径。
A new carboxybenzaldehyde (4-CBA) soft-sensor model based on improved FasBack neuro-fuzzy system is developed. Levenberg-Marquardt algorithm is used to train some parameters in the model. Based on practical process data, the proposed improved FasBack is applied to build 4-CBA soft-sensor model. Simulation results indicate that the proposed model is precise and efficient, and it is possible to realize the quality control of purified terephthalic acid (PTA) product promptly.
出处
《化工自动化及仪表》
EI
CAS
2005年第6期44-47,共4页
Control and Instruments in Chemical Industry
基金
国家自然科学创新研究群体项目(60421002)
国家十.五科技攻关项目(2004BA204B08)