Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However a...Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However almost all existing probing-based techniques face the following problems: 1) performing inaccurately in noisy networks; 2) generating additional traffic to the network; 3) high cost computation. To address these problems, we propose an efficient probe selection algorithm for fault diagnosis based on Bayesian network. Moreover, two approaches which could significantly reduce the computational complexity of the probe selection process are provided. Finally, we implement the new proposed algorithm and a former representative probing-based algorithm (BPEA algorithm) on different settings of networks. The results show that, the new algorithm performs much faster than BPEA does without sacrificing the diagnostic quality, especially in large, noisy and multiple-fault networks.展开更多
A novel fault detection and identification(FDI)scheme for HVDC(High Voltage Direct Current Transmission)system was presented.It was based on the unique active disturbance rejection concept,where the HVDC system faults...A novel fault detection and identification(FDI)scheme for HVDC(High Voltage Direct Current Transmission)system was presented.It was based on the unique active disturbance rejection concept,where the HVDC system faults were estimated using an extended states observer(ESO).Firstly,the mathematical model of HVDC system was constructed,where the system states and disturbance were treated as an extended state.An augment HVDC system was established by using the extended state in rectify side and converter side,respectively.Then,a fault diagnosis filter was established to diagnose the HVDC system faults via the ESO theory.The evolution of the extended state in the augment HVDC system can reflect the actual system faults and disturbances,which can be used for the fault diagnosis purpose.A novel feature of this approach is that it can simultaneously detect and identify the shape and magnitude of the HVDC faults and disturbance.Finally,different kinds of HVDC faults were simulated to illustrate the feasibility and effectiveness of the proposed ESO based FDI approach.Compared with the neural network based or support vector machine based FDI approach,the ESO based FDI scheme can reduce the fault detection time dramatically and track the actual system fault accurately.What's more important,it needs not do complex online calculations and the training of neural network so that it can be applied into practice.展开更多
针对有源电力滤波器APF(Active Power Filter)的IGBT功率管易发生故障的问题,提出了基于故障特征提取的有源电力滤波器故障诊断方法。构建了APF故障仿真模型和基于小波包分析的故障特征提取方法,仿真分析了APF网侧电流波形,并运用小波...针对有源电力滤波器APF(Active Power Filter)的IGBT功率管易发生故障的问题,提出了基于故障特征提取的有源电力滤波器故障诊断方法。构建了APF故障仿真模型和基于小波包分析的故障特征提取方法,仿真分析了APF网侧电流波形,并运用小波包分析对IGBT故障时的网侧电流波形进行处理,提取了IGBT故障特征向量,最后运用神经网络对特征向量的分类来实现对APF的故障诊断。在APF故障诊断系统上进行测试,验证了该诊断方法的有效性和可行性。展开更多
基金supported by National Key Basic Research Program of China (973 program) under Grant No.2007CB310703Funds for Creative Research Groups of China under Grant No.60821001+1 种基金National Natural Science Foundation of China under Grant No. 60973108National S&T Major Project under Grant No.2011ZX03005-004-02
文摘Fault diagnosis on large-scale and complex networks is a challenging task, as it requires efficient and accurate inference from huge data volumes. Active probing is a cost-efficient tool for fault diagnosis. However almost all existing probing-based techniques face the following problems: 1) performing inaccurately in noisy networks; 2) generating additional traffic to the network; 3) high cost computation. To address these problems, we propose an efficient probe selection algorithm for fault diagnosis based on Bayesian network. Moreover, two approaches which could significantly reduce the computational complexity of the probe selection process are provided. Finally, we implement the new proposed algorithm and a former representative probing-based algorithm (BPEA algorithm) on different settings of networks. The results show that, the new algorithm performs much faster than BPEA does without sacrificing the diagnostic quality, especially in large, noisy and multiple-fault networks.
基金Project Supported by National Natural Science Foundation of China(60574081).
文摘A novel fault detection and identification(FDI)scheme for HVDC(High Voltage Direct Current Transmission)system was presented.It was based on the unique active disturbance rejection concept,where the HVDC system faults were estimated using an extended states observer(ESO).Firstly,the mathematical model of HVDC system was constructed,where the system states and disturbance were treated as an extended state.An augment HVDC system was established by using the extended state in rectify side and converter side,respectively.Then,a fault diagnosis filter was established to diagnose the HVDC system faults via the ESO theory.The evolution of the extended state in the augment HVDC system can reflect the actual system faults and disturbances,which can be used for the fault diagnosis purpose.A novel feature of this approach is that it can simultaneously detect and identify the shape and magnitude of the HVDC faults and disturbance.Finally,different kinds of HVDC faults were simulated to illustrate the feasibility and effectiveness of the proposed ESO based FDI approach.Compared with the neural network based or support vector machine based FDI approach,the ESO based FDI scheme can reduce the fault detection time dramatically and track the actual system fault accurately.What's more important,it needs not do complex online calculations and the training of neural network so that it can be applied into practice.
文摘针对有源电力滤波器APF(Active Power Filter)的IGBT功率管易发生故障的问题,提出了基于故障特征提取的有源电力滤波器故障诊断方法。构建了APF故障仿真模型和基于小波包分析的故障特征提取方法,仿真分析了APF网侧电流波形,并运用小波包分析对IGBT故障时的网侧电流波形进行处理,提取了IGBT故障特征向量,最后运用神经网络对特征向量的分类来实现对APF的故障诊断。在APF故障诊断系统上进行测试,验证了该诊断方法的有效性和可行性。
