摘要
以焦化厂德士古煤气化炉为对象,根据煤气化流程的工艺分析,针对德士古气化炉膛温度软测量的需要,研究了辅助变量选择,数据采集与处理,以及利用模糊神经网络和RBF网络建立炉温软测量模型等问题,建立了炉温软测量系统。该系统在不增加设备投资的条件下,通过工厂信息集成处理和先进的监控技术,提高生产装置的工艺操作水平和管理水平为目的。现场调试运行结果表明应用本文方法建模精度较高,系统效果良好。该系统能够充分发挥DCS系统和网络计算机的功能优点,完全克服了在测温元件损坏时对生产的不利影响。
In light of the technical flow of coal gasification and demand of Texaco gasifier temperature soft measurement, many questions about modeling, such as selections of auxihary variable, collection and disposal of fields data, are discussed. And the modeling of gasifier soft measurement is composed by two methods, which are fuzzy neural network and radial basic function network. Without increase of equipment, the technical operation and management level can be improved, through factory integrated information and advanced supervisal technology. The application results show that the modeling method is excellent and the precision is high. The disadvantage of produce process caused by the thermocouple burned out is eliminated.
出处
《化工自动化及仪表》
EI
CAS
2006年第3期59-63,共5页
Control and Instruments in Chemical Industry
基金
上海市曙光计划资助项目(03SG26)
