提出一种优化相关向量机的寿命预测方法,并用于对辅助动力系统(Auxiliary power unit,APU)涡轮的剩余寿命预测。首先,提出了改进的核函数,兼顾效率和精度,用天牛须搜索(Beetle antennae search,BAS)算法对相关向量机的核参数进行优化,...提出一种优化相关向量机的寿命预测方法,并用于对辅助动力系统(Auxiliary power unit,APU)涡轮的剩余寿命预测。首先,提出了改进的核函数,兼顾效率和精度,用天牛须搜索(Beetle antennae search,BAS)算法对相关向量机的核参数进行优化,建立寿命预测模型;然后,对历史数据进行分析,提取排气温度(Exhaust gas temperature,EGT)并进行修正、降噪,用多项式回归建立了EGT的涡轮性能退化模式库;最后,实例验证表明,文中算法在APU涡轮剩余寿命预测上与传统相关向量机相比效率提高40%,精度提高20%,通过敏感性分析确定了最佳的初始步长和输入维度。展开更多
针对飞控系统安全性分析问题,提出一种基于系统拓展模型(extended system model,ESM)的安全性分析方法。首先,运用Simulink建立系统名义模型。然后,对名义模型进行故障注入,得到系统扩展模型,观察故障情况下的系统响应并对系统进行安全...针对飞控系统安全性分析问题,提出一种基于系统拓展模型(extended system model,ESM)的安全性分析方法。首先,运用Simulink建立系统名义模型。然后,对名义模型进行故障注入,得到系统扩展模型,观察故障情况下的系统响应并对系统进行安全性分析。最后,选取操纵舵面系统(副翼/方向舵)为例。结果表明,系统故障拓展模型使得模型保持完整性和一致性,能够模拟系统故障多状态模式,保证了安全性分析结果的准确性和完整性。展开更多
Performance parameter prediction technology is the core research content of aeroengine health management,and more and more machine learning algorithms have been applied in the field.Regularized extreme learning machin...Performance parameter prediction technology is the core research content of aeroengine health management,and more and more machine learning algorithms have been applied in the field.Regularized extreme learning machine(RELM)is one of them.However,the regularization parameter determination of RELM consumes computational resources,which makes it unsuitable in the field of aeroengine performance parameter prediction with a large amount of data.This paper uses the forward and backward segmentation(FBS)algorithms to improve the RELM performance,and introduces an adaptive step size determination method and an improved solution mechanism to obtain a new machine learning algorithm.While maintaining good generalization,the new algorithm is not sensitive to regularization parameters,which greatly saves computing resources.The experimental results on the public data sets prove the above conclusions.Finally,the new algorithm is applied to the prediction of aero-engine performance parameters,and the excellent prediction performance is achieved.展开更多
By taking a 2.3 MW double-fed asynchronous generator as an example,a new method for fast simulation analysis of ventilation cooling system inside generator is proposed based on the one-dimensional simulation software ...By taking a 2.3 MW double-fed asynchronous generator as an example,a new method for fast simulation analysis of ventilation cooling system inside generator is proposed based on the one-dimensional simulation software FLOWMASTER.The thermal-fluid coupling simulation model of ventilation cooling system inside generator is established.Under the stable running state of the generator,the flow velocity distribution and temperature rise of the key parts of the generator are analyzed.The results prove that the ventilation structure design of the generator meets the temperature rise limit.The simulation results are compared with the theoretical calculation results and the experimental results,which verify the correctness of the thermal-fluid coupling simulation method proposed in this paper.展开更多
文摘提出一种优化相关向量机的寿命预测方法,并用于对辅助动力系统(Auxiliary power unit,APU)涡轮的剩余寿命预测。首先,提出了改进的核函数,兼顾效率和精度,用天牛须搜索(Beetle antennae search,BAS)算法对相关向量机的核参数进行优化,建立寿命预测模型;然后,对历史数据进行分析,提取排气温度(Exhaust gas temperature,EGT)并进行修正、降噪,用多项式回归建立了EGT的涡轮性能退化模式库;最后,实例验证表明,文中算法在APU涡轮剩余寿命预测上与传统相关向量机相比效率提高40%,精度提高20%,通过敏感性分析确定了最佳的初始步长和输入维度。
文摘针对飞控系统安全性分析问题,提出一种基于系统拓展模型(extended system model,ESM)的安全性分析方法。首先,运用Simulink建立系统名义模型。然后,对名义模型进行故障注入,得到系统扩展模型,观察故障情况下的系统响应并对系统进行安全性分析。最后,选取操纵舵面系统(副翼/方向舵)为例。结果表明,系统故障拓展模型使得模型保持完整性和一致性,能够模拟系统故障多状态模式,保证了安全性分析结果的准确性和完整性。
文摘Performance parameter prediction technology is the core research content of aeroengine health management,and more and more machine learning algorithms have been applied in the field.Regularized extreme learning machine(RELM)is one of them.However,the regularization parameter determination of RELM consumes computational resources,which makes it unsuitable in the field of aeroengine performance parameter prediction with a large amount of data.This paper uses the forward and backward segmentation(FBS)algorithms to improve the RELM performance,and introduces an adaptive step size determination method and an improved solution mechanism to obtain a new machine learning algorithm.While maintaining good generalization,the new algorithm is not sensitive to regularization parameters,which greatly saves computing resources.The experimental results on the public data sets prove the above conclusions.Finally,the new algorithm is applied to the prediction of aero-engine performance parameters,and the excellent prediction performance is achieved.
文摘By taking a 2.3 MW double-fed asynchronous generator as an example,a new method for fast simulation analysis of ventilation cooling system inside generator is proposed based on the one-dimensional simulation software FLOWMASTER.The thermal-fluid coupling simulation model of ventilation cooling system inside generator is established.Under the stable running state of the generator,the flow velocity distribution and temperature rise of the key parts of the generator are analyzed.The results prove that the ventilation structure design of the generator meets the temperature rise limit.The simulation results are compared with the theoretical calculation results and the experimental results,which verify the correctness of the thermal-fluid coupling simulation method proposed in this paper.
