摘要
针对非线性动态系统分阶段指标预测问题,提出了一种基于级联过程神经元网络和相空间重构技术的动态预测模型和方法。考虑实际系统各个变量在运行过程中不同阶段可能具有不同的作用关系和信息变换机制,以及各阶段系统状态的连续性,采用若干过程神经元子网络构成级联结构建立系统动态预测模型;同时,为弥补实际采样数据的不足和提高数据信息的利用率,利用相空间重构理论构造训练样本集。给出了预测模型的信息处理机制和学习算法,以油田开发三次采油过程仿真为例,实验结果验证了模型和方法的有效性。
Aiming at the problem of nonlinear time-varying system dynamic indicators forecast in different stages,a dynamic forecast model and algorithm based on a cascade process neural network and phase space reconstruction technology are proposed in this paper.Taking into account the actual system variables have different roles and information transformation mechanism as well as the succession of system state in different stage,a cascade process neural network with some sub-networks is presented to establish the dynamic forecast model of actual system.At the same time,the theory of phase space reconstruction is applied to construct sample set so as to make up for the lack of training sample data and improve the utilization of actual sample data.The information processing mechanisms and learning algorithm of prediction model are also proposed in this paper.Taking tertiary oil recovery process of oil field development for example,the experimental result shows the effectiveness of the proposed model and method.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第11期145-148,共4页
Computer Engineering and Applications
基金
黑龙江省教育厅科技项目(No.11521013)
黑龙江省自然科学基金(No.ZA2006-11)
黑龙江省科技攻关项目(No.GZ07A103)
关键词
动态预测
级联过程神经元网络
相空间重构
模型
应用
dynamic forecast
cascade process neural networks
phase space reconstruction
model
application
