摘要
为了提高现有分布式电力网络的故障诊断能力,加强故障元器件的实时判断能力,保证线路保护设备的正确动作,减少继电保护设备的拒动、误动次数,本文基于贝叶斯网络理论,针对现有的网络结构,建立了基于贝叶斯网络方法的元件、联合故障诊断模型,并用接收到的实时保护动作信号作为诊断的证据,运用GeNIe软件进行仿真;其次,在贝叶斯网络故障诊断的基础上引入粗糙集理论,提出基于粗糙集-贝叶斯网的故障诊断方法,基于ROSETTA软件将历史数据进行属性约简,根据约简决策表,简化并建立新的拓扑结构.两种实验均表明本文所提出方法与模型对于现有网络故障的诊断有效可行,在一定程度上降低了推理计算的复杂性,但未能良好体现出该方法的容错优势.通过两种仿真算例的验证与比较,证实了粗糙集-贝叶斯网诊断模型在准确性并未降低的情况下有效提高了计算速度,具有一定的适用性.
In order to improve the fault diagnosis capability of the existing distributed power network,strengthen the ability to judge faulty components in real time,ensure the correct operation of line protection equipment,and reduce the number of refusal and disoperation of relay protection equipment,a component and joint fault diagnosis model based on the Bayesian network method is established in this paper.For the existing network structure,and the real-time protection action signal received is used as the diagnosis evidence for simulation calculation by GeNIe software.Secondly,on the basis of Bayesian network fault diagnosis,rough set theory is introduced,and a fault diagnosis method based on rough set-Bayesian network is proposed.Based on ROSETTA software,historical data is attribute reduced,and the reduction is simplified to establish a new topology according to the obtained reduction decision table.Both experiments show that the method and model proposed in this paper are feasible and effective for the diagnosis of existing network faults,reducing the complexity of inference calculation to a certain extent,but failing to reflect the fault tolerance advantages of this method.Through the verification and comparison of two simulation examples,it is confirmed that the rough set-Bayesian network diagnosis model effectively improves the calculation speed without reducing the accuracy,and has certain applicability.
作者
夏昌浩
胡爽
李伶俐
刘艳芳
程杉
XIA Changhao;HU Shuang;LI Lingli;LIU Yanfang;CHENG Shan(College of Electrical Engineering&New Energy,China Three Gorges Univ.,Yichang 443002,China;Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station,China Three Gorges Univ.,Yichang 443002,China)
出处
《三峡大学学报（自然科学版）》
CAS
北大核心
2020年第5期82-87,共6页
Journal of China Three Gorges University：Natural Sciences
基金
国家自然科学基金项目(51607105)。
