Indexed by:
Abstract:
针对污水处理过程氨氮实时测量难的问题,提出了一种基于尖峰自组织径向基神经网络(spiking self-organizing RBF neural network,SSORBF)的氨氮软测量方法.首先,该方法通过选取对氨氮预测影响较大的辅助变量,利用SSORBF神经网络建立主元变量和预测变量的非线性关系;其次,采用尖峰机制和梯度下降算法调整网络结构和参数;最后,将SSORBF神经网络应用于污水处理实际运行过程.仿真结果表明,该方法有效地实现了氨氮浓度的在线预测,提高了网络的预测精度和自适应能力.
Keyword:
Reprint Author's Address:
Email:
Source :
信息与控制
Year: 2017
Issue: 06
Volume: 46
Page: 752-758
Cited Count:
WoS CC Cited Count: 0
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 10
Affiliated Colleges: