Indexed by:
Abstract:
分解炉出口温度是水泥生产过程中的关键指标。针对传统预测方法只考虑风、煤、料影响的问题,提出一种弹性网(ElasticNet)结合长短时记忆(Long Short-Term Memory,LSTM)神经网络的温度预测模型。利用弹性网方法对不同变量进行参数估计,充分考虑影响因素并实现变量筛选,同时分析隐含层和节点数对神经网络精确度的影响,构建ElasticNet-LSTM出口温度预测模型。仿真结果表明:所提出的方法优于LSTM, LASSO(Least Absolute Shrinkage and Selection Operator)-LSTM,BP神经网络和RBF神经网络方法,具有较高的预测精...
Keyword:
Reprint 's Address:
Email:
Source :
系统仿真学报
ISSN: 1004-731X
CN: 11-3092/V
Year: 2021
Issue: 05
Volume: 33
Page: 1078-1085
Cited Count:
SCOPUS Cited Count:
ESI Highly Cited Papers on the List: 0 Unfold All
WanFang Cited Count:
Chinese Cited Count:
30 Days PV: 4
Affiliated Colleges: