Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold l...Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold learning and particle swarm optimization support vector machine(PSO-SVM) is studied. This fault diagnosis model is used for a rolling bearing experimental of three kinds faults. The results are verified that this model based on multi-manifold learning and PSO-SVM is good at the fault sensitive features acquisition with effective accuracy.展开更多
针对齿轮箱多类故障信号非线性、不确定性难以进行有效识别的问题,提出了一种混合灰狼优化算法(Hybrid Grey Wolf Optimizer,HGWO)优化多分类支持向量机(Multi-class Support Vector Machine,MSVM)的齿轮箱故障诊断方法。首先利用小波...针对齿轮箱多类故障信号非线性、不确定性难以进行有效识别的问题,提出了一种混合灰狼优化算法(Hybrid Grey Wolf Optimizer,HGWO)优化多分类支持向量机(Multi-class Support Vector Machine,MSVM)的齿轮箱故障诊断方法。首先利用小波包对齿轮箱故障信号进行降噪处理,并通过信号中各频带的能量,提取能量特征值,再将获取的特征值输入优化后的MSVM模型进行故障模式的识别。实验结果表明,相对于传统的诊断模型,基于HGWO-MSVM的齿轮箱故障诊断模型能够更有效地诊断齿轮箱的实际运行状态,提高识别效率和精度。展开更多
随着电网中新能源渗透率的增加,传统火电机组调频已无法满足电能质量需求。针对多源场景中传统自动发电控制系统区域控制误差较大的问题,提出一种基于Stackelberg博弈与改进深度神经网络(Stackelberg game and improved deep neural net...随着电网中新能源渗透率的增加,传统火电机组调频已无法满足电能质量需求。针对多源场景中传统自动发电控制系统区域控制误差较大的问题,提出一种基于Stackelberg博弈与改进深度神经网络(Stackelberg game and improved deep neural network,S-DNN)的多源调频协调策略。首先,设计一种改进多层次深度神经网络(deep neural network,DNN),由DNN层、自然梯度提升层、最小二乘支持向量机层顺序递进完成预测、评价、执行动作,输出总调频功率指令。该多层次总调频功率输出模型考虑新能源渗透率对调频系统的动态影响,充分学习历史信息与实时状态中更多的特征,提高了时序调频指令精度。然后基于Stackelberg博弈理论,考虑多源调频特征与协同作用,优化各调频源间的功率分配,提高系统二次调频的经济性。最后,通过算例分析验证了提出的多源调频协调策略的有效性。与传统调频方法相比,所提出的S-DNN多源调频协调策略可有效降低区域控制误差与频率偏差,并降低调频成本。展开更多
基金Beijing Natural Science Foundation(KZ201211232039)National Natural Science Foundation of China(51275052)+1 种基金Funding Project for Academic Human Resources Development in Institutions of Higher Learning under the Jurisdiction of Beijing Municipalipality(PHR201106132)PXM2014_014224_000080
文摘Fault diagnosis technology plays an important role in the industries due to the emergency fault of a machine could bring the heavy lost for the people and the company. A fault diagnosis model based on multi-manifold learning and particle swarm optimization support vector machine(PSO-SVM) is studied. This fault diagnosis model is used for a rolling bearing experimental of three kinds faults. The results are verified that this model based on multi-manifold learning and PSO-SVM is good at the fault sensitive features acquisition with effective accuracy.
文摘针对齿轮箱多类故障信号非线性、不确定性难以进行有效识别的问题,提出了一种混合灰狼优化算法(Hybrid Grey Wolf Optimizer,HGWO)优化多分类支持向量机(Multi-class Support Vector Machine,MSVM)的齿轮箱故障诊断方法。首先利用小波包对齿轮箱故障信号进行降噪处理,并通过信号中各频带的能量,提取能量特征值,再将获取的特征值输入优化后的MSVM模型进行故障模式的识别。实验结果表明,相对于传统的诊断模型,基于HGWO-MSVM的齿轮箱故障诊断模型能够更有效地诊断齿轮箱的实际运行状态,提高识别效率和精度。
文摘随着电网中新能源渗透率的增加,传统火电机组调频已无法满足电能质量需求。针对多源场景中传统自动发电控制系统区域控制误差较大的问题,提出一种基于Stackelberg博弈与改进深度神经网络(Stackelberg game and improved deep neural network,S-DNN)的多源调频协调策略。首先,设计一种改进多层次深度神经网络(deep neural network,DNN),由DNN层、自然梯度提升层、最小二乘支持向量机层顺序递进完成预测、评价、执行动作,输出总调频功率指令。该多层次总调频功率输出模型考虑新能源渗透率对调频系统的动态影响,充分学习历史信息与实时状态中更多的特征,提高了时序调频指令精度。然后基于Stackelberg博弈理论,考虑多源调频特征与协同作用,优化各调频源间的功率分配,提高系统二次调频的经济性。最后,通过算例分析验证了提出的多源调频协调策略的有效性。与传统调频方法相比,所提出的S-DNN多源调频协调策略可有效降低区域控制误差与频率偏差,并降低调频成本。
