摘要
针对复杂系统的在线态势评估问题,依据信息融合理论,提出了一种新的网络在线态势评估模型。它采用定性与定量、局部与综合相结合的评估策略,即首先进行快速定性评估,一旦系统异常,立即启动集成神经网络组对来自系统多侧面的故障特征信息进行定量分析和分类,最后两级D-S证据推理模型在各自的融合中心实现对各子网络的融合,提高了评估的精度和可靠性。基于本体论成功地实现了该模型,在丰满水电数字仿真系统的成功应用验证了模型的有效性和实际应用价值。
In order to solve effectively the issue of online situation assessment to complex system, a kind of new intelligent assessment model of network on-line is proposed based on information fusion theories on network environment. The integrated project combined qualitative and quantitative assessment strategy with local and synthetic strategy. First of all, qualitative assessment is performed. In case system is abnormal, the integrated neural networks group will perform immediately quantitative analysis and classification to multi-sources character information from multi-sensors. At last, two level D-S evidence reasoning model will assess synthetically to outputs of ANNs and local D-S models in their fusion center respectively, and the precision and reliability of assessment conclusion are improved evidently. The model has been implemented based on ontology and had been tested and run in Fengman Hydroelectricity Digital Simulation System that we developed. The implementation shows that the proposed model is effective and has practical application value.
出处
《系统仿真学报》
EI
CAS
CSCD
北大核心
2005年第5期1200-1202,1251,共4页
Journal of System Simulation
基金
国家自然科学基金项目(69873007)
关键词
信息融合
态势评估
集成神经网络
专家系统
本体论
丰满水电数字仿真系统
information fusion
situation assessment
integrated neural networks
expert system
ontology
Fengman Hydroelectricity Digital Simulation System