提出了机舱式激光雷达测风仪传动齿轮机械故障诊断方法。利用最小熵反褶积(MED)对齿轮的振动信号去噪处理,利用集成经验模态分解(EEMD)得到齿轮信号的内涵模态(IMF)分量,并根据IMF能量和齿轮峭度建立齿轮故障特征向量,将特征向量输入到...提出了机舱式激光雷达测风仪传动齿轮机械故障诊断方法。利用最小熵反褶积(MED)对齿轮的振动信号去噪处理,利用集成经验模态分解(EEMD)得到齿轮信号的内涵模态(IMF)分量,并根据IMF能量和齿轮峭度建立齿轮故障特征向量,将特征向量输入到最小二乘支持向量机(least squares support vector machine,LSSVM)中,完成传动齿轮机械故障的诊断。实验结果表明,该方法的齿轮故障诊断时间短,根据迭代次数的增加,误差率可控制在3%以下。展开更多
针对变分模态分解(Variational mode decomposition,VMD)检测微电网中多类电能质量扰动信号时,其实时性差及多类信号难以统一处理的问题,提出一种参数优化的VMD与Teager能量算子(Teager energy operator,TEO)融合的微电网电能质量扰动...针对变分模态分解(Variational mode decomposition,VMD)检测微电网中多类电能质量扰动信号时,其实时性差及多类信号难以统一处理的问题,提出一种参数优化的VMD与Teager能量算子(Teager energy operator,TEO)融合的微电网电能质量扰动检测方法。针对VMD方法参数难确定的问题,利用天牛须搜索(Beetleantennaesearch,BAS)对VMD方法的最佳参数进行优化搜索。搜索过程以VMD分解后各本征模函数的包络熵极小值与VMD迭代次数的结合作为适应度函数。根据搜索结果设定VMD方法的最佳分解层数K和惩罚因子α,并运用参数优化VMD对扰动信号进行分解。针对扰动信号经分解后本征模函数的筛选问题,以包络熵为指标,选取包络熵较小值的本征模函数进行TEO解调分析,提取扰动信号的特征信息。仿真结果表明,融合算法能实现对微电网电能质量扰动的准确检测,并具有良好的抗噪性。展开更多
针对水电机组振动信号存在非平稳和非线性,提出一种结合IMF能量矩和双向长短期记忆神经网络(bidirection long short term memory neural network,BiLSTMNN)的故障诊断方法。首先采用互补集合经验模态分解(complementary ensemble empir...针对水电机组振动信号存在非平稳和非线性,提出一种结合IMF能量矩和双向长短期记忆神经网络(bidirection long short term memory neural network,BiLSTMNN)的故障诊断方法。首先采用互补集合经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)方法对正常和故障振动信号样本进行处理,得到频率各异的本征模态函数(intrinsic mode functions,IMF)和剩余分量。然后计算IMF能量矩,并将其作为故障特征。进一步,将故障特征作为输入、故障类别作为输出,训练BiLSTMNN得到水电机组故障识别器。结合故障识别器和实时振动信号IMF能量矩特征,即可识别水电机组运行状态为正常或具体故障类型。最后,结合转子实验台数据和实际电站机组样本数据,设计对比实验,验证了所提方法在挖掘信号特征方面的有效性及较高的故障诊断准确率。展开更多
The integration of distributed energy resources(DERs) into distribution networks is becoming increasingly important, as it supports the continued adoption of renewable power generation, combined heat and power plants,...The integration of distributed energy resources(DERs) into distribution networks is becoming increasingly important, as it supports the continued adoption of renewable power generation, combined heat and power plants, and storage systems. Nevertheless, inadvertent islanding operation is one of the major protection issues in distribution networks connected to DERs. This study proposes an intelligent islanding detection method(IIDM) using an intrinsic mode function(IMF)feature-based grey wolf optimized artificial neural network(GWO-ANN). In the proposed IIDM, the modal voltage signal is pre-processed by variational mode decomposition followed by Hilbert transform on each IMF to derive highly involved features. Then, the energy and standard deviation of IMFs are employed to train/test the GWO-ANN model for identifying the islanding operations from other non-islanding events. To evaluate the performance of the proposed IIDM, various islanding and non-islanding conditions such as faults, voltage sag, linear and nonlinear load and switching, are considered as the training and testing datasets. Moreover, the proposed IIDM is evaluated under noise conditions for the measured voltage signal. The simulation results demonstrate that the proposed IIDM is capable of differentiating between islanding and non-islanding events without any sensitivity under noise conditions in the test signal.展开更多
文摘提出了机舱式激光雷达测风仪传动齿轮机械故障诊断方法。利用最小熵反褶积(MED)对齿轮的振动信号去噪处理,利用集成经验模态分解(EEMD)得到齿轮信号的内涵模态(IMF)分量,并根据IMF能量和齿轮峭度建立齿轮故障特征向量,将特征向量输入到最小二乘支持向量机(least squares support vector machine,LSSVM)中,完成传动齿轮机械故障的诊断。实验结果表明,该方法的齿轮故障诊断时间短,根据迭代次数的增加,误差率可控制在3%以下。
文摘针对变分模态分解(Variational mode decomposition,VMD)检测微电网中多类电能质量扰动信号时,其实时性差及多类信号难以统一处理的问题,提出一种参数优化的VMD与Teager能量算子(Teager energy operator,TEO)融合的微电网电能质量扰动检测方法。针对VMD方法参数难确定的问题,利用天牛须搜索(Beetleantennaesearch,BAS)对VMD方法的最佳参数进行优化搜索。搜索过程以VMD分解后各本征模函数的包络熵极小值与VMD迭代次数的结合作为适应度函数。根据搜索结果设定VMD方法的最佳分解层数K和惩罚因子α,并运用参数优化VMD对扰动信号进行分解。针对扰动信号经分解后本征模函数的筛选问题,以包络熵为指标,选取包络熵较小值的本征模函数进行TEO解调分析,提取扰动信号的特征信息。仿真结果表明,融合算法能实现对微电网电能质量扰动的准确检测,并具有良好的抗噪性。
文摘针对水电机组振动信号存在非平稳和非线性,提出一种结合IMF能量矩和双向长短期记忆神经网络(bidirection long short term memory neural network,BiLSTMNN)的故障诊断方法。首先采用互补集合经验模态分解(complementary ensemble empirical mode decomposition,CEEMD)方法对正常和故障振动信号样本进行处理,得到频率各异的本征模态函数(intrinsic mode functions,IMF)和剩余分量。然后计算IMF能量矩,并将其作为故障特征。进一步,将故障特征作为输入、故障类别作为输出,训练BiLSTMNN得到水电机组故障识别器。结合故障识别器和实时振动信号IMF能量矩特征,即可识别水电机组运行状态为正常或具体故障类型。最后,结合转子实验台数据和实际电站机组样本数据,设计对比实验,验证了所提方法在挖掘信号特征方面的有效性及较高的故障诊断准确率。
基金supported by the National Research Foundation (NRF) of South Korea funded by the Ministry of Science, ICT & Future Planning (MSIP) of the Korean government (No.2018R1A2A1A05078680)。
文摘The integration of distributed energy resources(DERs) into distribution networks is becoming increasingly important, as it supports the continued adoption of renewable power generation, combined heat and power plants, and storage systems. Nevertheless, inadvertent islanding operation is one of the major protection issues in distribution networks connected to DERs. This study proposes an intelligent islanding detection method(IIDM) using an intrinsic mode function(IMF)feature-based grey wolf optimized artificial neural network(GWO-ANN). In the proposed IIDM, the modal voltage signal is pre-processed by variational mode decomposition followed by Hilbert transform on each IMF to derive highly involved features. Then, the energy and standard deviation of IMFs are employed to train/test the GWO-ANN model for identifying the islanding operations from other non-islanding events. To evaluate the performance of the proposed IIDM, various islanding and non-islanding conditions such as faults, voltage sag, linear and nonlinear load and switching, are considered as the training and testing datasets. Moreover, the proposed IIDM is evaluated under noise conditions for the measured voltage signal. The simulation results demonstrate that the proposed IIDM is capable of differentiating between islanding and non-islanding events without any sensitivity under noise conditions in the test signal.
