为处理好变电站故障诊断问题中故障源和故障征兆间因果关系的不确定性,提出了基于故障群组合优化的故障诊断方法。依据变电站运行方式和保护配置建立保护配合的 Petri 网模型,用该模型的状态转移方程获取所有的故障群-征兆群对子,创建...为处理好变电站故障诊断问题中故障源和故障征兆间因果关系的不确定性,提出了基于故障群组合优化的故障诊断方法。依据变电站运行方式和保护配置建立保护配合的 Petri 网模型,用该模型的状态转移方程获取所有的故障群-征兆群对子,创建故障群组合作为已知故障征兆诊断解的适应度函数,并用遗传算法搜索出最优诊断解。实验证明:该方法不仅能有效地辨识出故障源,而且能提供保护装置拒动、断路器拒动、信号传输错误等信息,对现场人员迅速确认故障设备非常有利。展开更多
Utilising dissolved gases analysis, a new insulation fault diagnosis methodfor power transformers is proposed. This method is based on the group grey relational grade analysismethod. First, according to the fault type...Utilising dissolved gases analysis, a new insulation fault diagnosis methodfor power transformers is proposed. This method is based on the group grey relational grade analysismethod. First, according to the fault type and grey reference sequence structure, some typicalfault samples are divided into several sets of grey reference sequences. These sets are structuredas one grey reference sequence group. Secondly, according to a new calculation method of the greyrelational coefficient, the individual relational coefficient and grade are computed. Then accordingto the given calculation method for the group grey relation grade, the group grey relational gradeis computed and the group grey relational grade matrix is structured. Finally, according to therelational sequence, the insulation fault is identified for power transformers. The results of alarge quantity of instant analyses show that the proposed method has higher diagnosis accuracy andreliability than the three-ratio method and the traditional grey relational method. It has goodclassified diagnosis ability and reliability.展开更多
MANET routing is critical and routing decision should be made sooner before the node leaves the network.Fast decisions always compensate network performance.In addition,most MANET routing protocols assume a friendly a...MANET routing is critical and routing decision should be made sooner before the node leaves the network.Fast decisions always compensate network performance.In addition,most MANET routing protocols assume a friendly and cooperative environment,and hence are vulnerable to various attacks.Trust and Reputation would serve as a major solution to these problems.Learning the network characteristics and choosing right routing decisions at right times would be a significant solution.In this work,we have done an extensive survey of fault tolerant protocols and ant colony algorithms applied to routing in MANETs.We propose a QoS constrained fault tolerant ant lookahead routing algorithm which attempts to identify valid route and look-ahead route pairs which might help in choosing the alternate path in case of valid route failure.The results prove that the proposed algorithm takes better routing decisions with 20-30 percent improvement compared with existing ant colony algorithms.展开更多
A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessi...A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessing technique based on the kurtosis and entropy of signals were used. Firstly, sinusoidal inputs with different frequencies were applied to the circuit under test (CUT). Then, the resulting frequency responses were sampled to generate features. The frequency response was sampled to compute its kurtosis and entropy, which can show the information capacity of signal. By analyzing the output signals, the proposed method can detect and identify faulty components in circuits. The results indicate that the fault classes can be classified correctly for at least 99% of the test data in example circuit. And the proposed method can diagnose hard and soft faults.展开更多
文摘为处理好变电站故障诊断问题中故障源和故障征兆间因果关系的不确定性,提出了基于故障群组合优化的故障诊断方法。依据变电站运行方式和保护配置建立保护配合的 Petri 网模型,用该模型的状态转移方程获取所有的故障群-征兆群对子,创建故障群组合作为已知故障征兆诊断解的适应度函数,并用遗传算法搜索出最优诊断解。实验证明:该方法不仅能有效地辨识出故障源,而且能提供保护装置拒动、断路器拒动、信号传输错误等信息,对现场人员迅速确认故障设备非常有利。
文摘Utilising dissolved gases analysis, a new insulation fault diagnosis methodfor power transformers is proposed. This method is based on the group grey relational grade analysismethod. First, according to the fault type and grey reference sequence structure, some typicalfault samples are divided into several sets of grey reference sequences. These sets are structuredas one grey reference sequence group. Secondly, according to a new calculation method of the greyrelational coefficient, the individual relational coefficient and grade are computed. Then accordingto the given calculation method for the group grey relation grade, the group grey relational gradeis computed and the group grey relational grade matrix is structured. Finally, according to therelational sequence, the insulation fault is identified for power transformers. The results of alarge quantity of instant analyses show that the proposed method has higher diagnosis accuracy andreliability than the three-ratio method and the traditional grey relational method. It has goodclassified diagnosis ability and reliability.
文摘MANET routing is critical and routing decision should be made sooner before the node leaves the network.Fast decisions always compensate network performance.In addition,most MANET routing protocols assume a friendly and cooperative environment,and hence are vulnerable to various attacks.Trust and Reputation would serve as a major solution to these problems.Learning the network characteristics and choosing right routing decisions at right times would be a significant solution.In this work,we have done an extensive survey of fault tolerant protocols and ant colony algorithms applied to routing in MANETs.We propose a QoS constrained fault tolerant ant lookahead routing algorithm which attempts to identify valid route and look-ahead route pairs which might help in choosing the alternate path in case of valid route failure.The results prove that the proposed algorithm takes better routing decisions with 20-30 percent improvement compared with existing ant colony algorithms.
基金Project(Z132012)supported by the Second Five Technology-based in Science and Industry Bureau of ChinaProject(YWF1103Q062)supported by the Fundemental Research Funds for the Central Universities in China
文摘A relevance vector machine (RVM) based fault diagnosis method was presented for non-linear circuits. In order to simplify RVM classifier, parameters selection based on particle swarm optimization (PSO) and preprocessing technique based on the kurtosis and entropy of signals were used. Firstly, sinusoidal inputs with different frequencies were applied to the circuit under test (CUT). Then, the resulting frequency responses were sampled to generate features. The frequency response was sampled to compute its kurtosis and entropy, which can show the information capacity of signal. By analyzing the output signals, the proposed method can detect and identify faulty components in circuits. The results indicate that the fault classes can be classified correctly for at least 99% of the test data in example circuit. And the proposed method can diagnose hard and soft faults.
