基于改进FCM的超超临界机组过热器T—S神经网络模型辨识

作者: 方彦军, 胡龙珍, 胡文凯
成果类型: 期刊论文
发表日期: 2012
年卷期页: 2012,43,(4 ),4-8
期刊名: 《锅炉技术》
中图法分类号: TK223.3
关键词: 超超临界机组 过热器 T—S神经网络 模型辨识
英文关键词: Ultra-supercritical units; superheater; T-S neural network; model identifi-cation
摘要: 构建了过热器多输入单输出的T-s神经网络模型,并针对输入变量空间划分问题提出了一种改进FCM算法。通过确定高斯型隶属函数参数,实现模型结构参数辨识,利用递推最小二乘法完成模型后件参数辨识。对华能海门电厂百万机组过热器模型辨识进行仿真,结果表明此方法具有较好的辨识效果,辨识出的过热器模型具有较好的精度和泛化能力。
英文摘要: The paper constructs of the TS neural network model for the superheater with multiple inputs and single output, and presents an improved FCM algorithm aiming to solve the inputs' space division problem. The function parameters of the Gaussian membership are obtained to identify the model structure and the recursive least squares method is adopted to identify model parameters. Simulations are implemented for the superheater of Haimen ultrasupercritical units. Results show that the improved method has good performance in model i dentification, and the identified models have preferable accuracy and generalization ability.
语言: chi
相关文献
作者其它文献
My JSP 'reqreturndiv.jsp' starting page