论文部分内容阅读
针对超临界锅炉燃料量不易准确测量和燃料发热量难以在线检测的问题,通过分析某厂直流锅炉燃料量控制系统缺点,设计了基于径向基函数神经网络(RBFNN)-信息融合方法的燃料量优化控制方案.该优化控制综合了RBFNN的强自学习、并行计算能力和信息融合方法的互补性、冗余性等特点,重构燃料发热量系数,在燃烧内扰时用来在线精确修正实际燃料量,外扰时作为燃料量需求的前馈控制,以保证燃料量实时符合机组负荷变化或锅炉内扰下各工况的实际需求.通过磨煤机切换内扰下燃料量控制实验和负荷变换外扰下燃料量控制实验表明:在内外扰动工况下,此控制系统可保证燃料量控制的准确性、快速性和稳定性.
Aiming at the problem that the quantity of fuel in supercritical boiler is not easy to measure accurately and the heating value of fuel is difficult to measure online, the fuel quantity based on radial basis function neural network (RBFNN) - information fusion method is designed by analyzing the defect of the fuel quantity control system of a boiler. Optimization control scheme.The optimization control combines the strong self-learning RBFNN self-learning, parallel computing capabilities and information fusion method of complementarity, redundancy and other characteristics of the reconstructed fuel calorific coefficient in the combustion of internal disturbances used to accurately correct the actual online Fuel quantity and external disturbance are used as feedforward control of fuel quantity demand to ensure that the fuel quantity can meet real demand of each load in real time or fluctuate in boiler under real conditions.Metal control experiment and load The experimental results show that the control system can ensure the accuracy, speed and stability of the fuel quantity control under the condition of internal and external disturbances.