基于模糊Petri网和马尔科夫链理论的水电厂设备故障应急响应模型  被引量:2

Emergency response model of hydropower plant equipment failure based on fuzzy Petri net and Markov chain theory

在线阅读下载全文

作  者:尤渺 YOU Miao(Gongzui Hydropower Station,CHN Energy Dadu River Co.,Ltd.,Leshan 614900,China)

机构地区:[1]国能大渡河公司龚嘴水力发电总厂,四川乐山614900

出  处:《电子设计工程》2024年第10期59-63,共5页Electronic Design Engineering

摘  要:为保证水电厂设备安全,避免因故障导致意外事故,基于模糊Petri网和马尔科夫链理论设计水电厂设备故障应急响应模型。确定加权因子命题阈值,结合传感器收集的初始信号,在滤波器的作用下还原信号特征,基于模糊Petri网提取水电厂设备故障特征。设计故障分类器,建立概率转移矩阵,设置概率转移矩阵的条件,面对动态解码,给定模型参数,计算马尔可夫模型下的连续变量密度函数,修正比例因子的状态系数,得到设备故障分类结果。建立设备故障应急响应模型,输出设备故障状态下的应急响应结果。实验结果显示,该模型在四种故障类型中的分类精度分别为98.8%、98.6%、98.7%、98.8%,可见该模型分类精度较好。In order to ensure the safety of hydropower plant equipment and avoid accidents caused by failures,an emergency response model for hydropower plant equipment failures is designed based on fuzzy Petri nets and Markov chain theory.Determine the threshold value of the weighting factor proposition,combine the initial signal collected by the sensor,restore the signal characteristics under the action of the filter,and extract the fault characteristics of the hydropower plant equipment.The fault classifier is designed,the probability transfer matrix is established,and the conditions of the probability transfer matrix are set.In the face of dynamic decoding,given the model parameters,the continuous variable density function under the Markov model is calculated,and the state coefficient of the scale factor is modified to obtain the equipment fault classification results.Establish equipment failure emergency response model and output the emergency response results under equipment failure state.The experimental results show that the classification accuracy of the model in the four fault types is 98.8%,98.6%,98.7%and 98.8%respectively,which shows that the classification accuracy of the model is good.

关 键 词:模糊PETRI网 马尔科夫链理论 水电厂设备 设备故障 应急响应模型 

分 类 号:TN06[电子电信—物理电子学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象