摘要
通过对跨越—侧抑制神经网络(S-LINN)的权值连接分析,设计一种跨越输出权值——隐含层前馈连接权值分别训练的序列学习(SFSL)方法,并结合S-LINN的BOD(biochemical oxygen demand)特征建模方法,实现其在线预测.权值序列学习方法能够实现网络权值的快速收敛,进一步提高网络的学习性能.实验研究表明,S-LINN的特征建模能够实现BOD的准确预测,并且SFSL对网络的学习精度和泛化能力均有明显提升.
Based on the analysis of the weight connection of the span-lateral inhibition neural network （S-LINN）, a sequence learning approach （SFSL） is proposed on the basis of separate training of the span-output weights and the hidden-layer-feedforward weights during the learning process. By combining the intelligent character- istic biochemical oxygen demand （BOD） modeling of the S-LINN, the method can real_ize forecasting values online. The new learning strategy not only accelerates the convergence of weights but also improves the performance of the S-LINN. Experiment results show that the proposed S-LINN sequential learning characteristic modeling approach can achieve high-accuracy BOD prediction mad that the SFSL improves the approximation and generalization abilities of the S-LINN.
出处
《信息与控制》
CSCD
北大核心
2015年第5期577-584,591,共9页
Information and Control
基金
国家自然科学基金资助项目(61034008
61164013
51174091)
"973"计划前期研究专项资助项目(2014CB360502)
江西省教育厅科技研究项目(GJJ14402)
关键词
污水处理
生化需氧量
跨越—侧抑制神经网络
序列学习
特征建模
wastewater treatment
biochemical oxygen demand（BOD）
span-lateral inhibition neural network （S-LINN）
sequential learning
characteristic modelling
