This paper focuses on the reachable set estimation for Markovian jump neural networks with time delay.By allowing uncertainty in the transition probabilities,a framework unifies and enhances the generality and realism...This paper focuses on the reachable set estimation for Markovian jump neural networks with time delay.By allowing uncertainty in the transition probabilities,a framework unifies and enhances the generality and realism of these systems.To fully exploit the unified uncertain transition probabilities,an equivalent transformation technique is introduced as an alternative to traditional estimation methods,effectively utilizing the information of transition probabilities.Furthermore,a vector Wirtinger-based summation inequality is proposed,which captures more system information compared to existing ones.Building upon these components,a novel condition that guarantees a reachable set estimation is presented for Markovian jump neural networks with unified uncertain transition probabilities.A numerical example is illustrated to demonstrate the superiority of the approaches.展开更多
航空发动机结构与系统的复杂性导致轴承的故障诊断方法通常面临特征提取与模式识别的困难。针对以上不足,考虑实际工程诊断的实时性与准确性,提出了一种新的基于转子位移概率密度信息(probability density information of rotor displac...航空发动机结构与系统的复杂性导致轴承的故障诊断方法通常面临特征提取与模式识别的困难。针对以上不足,考虑实际工程诊断的实时性与准确性,提出了一种新的基于转子位移概率密度信息(probability density information of rotor displacement,PIRD)的航空发动机轴承智能故障诊断方法。其主要对一维卷积神经网络(1-dimensional convolutional neural network,1DCNN)模型进行改进,在传统的卷积层前面增加了PIRD的提取层,可以提取转子振动位移信号的概率密度信息,有效地降低了数据的冗余度,同时保留了故障监测的重要指标。提出的PIRD-CNN诊断模型保留了1DCNN端到端的故障诊断优势,将该模型在航空发动机试验台产生的轴承故障数据进行测试,其对轴承故障诊断精度可达96.58%,与基准研究相对比表明,PIRD-CNN能够快速且更加精准地诊断航空发动机轴承的故障。展开更多
基金funded by National Key Research and Development Program of China under Grant 2022YFE0107300the Chongqing Technology Innovation and Application Development Special Key Project under Grant CSTB2022TIAD-KPX0162+3 种基金the National Natural Science Foundation of China under Grant U22A20101the Chongqing Technology Innovation and Application Development Special Key Project under Grant CSTB2022TIAD-CUX0015the Chongqing postdoctoral innovativetalents support program under Grant CQBX202205the China Postdoctoral Science Foundation under Grant 2023M730411.
文摘This paper focuses on the reachable set estimation for Markovian jump neural networks with time delay.By allowing uncertainty in the transition probabilities,a framework unifies and enhances the generality and realism of these systems.To fully exploit the unified uncertain transition probabilities,an equivalent transformation technique is introduced as an alternative to traditional estimation methods,effectively utilizing the information of transition probabilities.Furthermore,a vector Wirtinger-based summation inequality is proposed,which captures more system information compared to existing ones.Building upon these components,a novel condition that guarantees a reachable set estimation is presented for Markovian jump neural networks with unified uncertain transition probabilities.A numerical example is illustrated to demonstrate the superiority of the approaches.
文摘航空发动机结构与系统的复杂性导致轴承的故障诊断方法通常面临特征提取与模式识别的困难。针对以上不足,考虑实际工程诊断的实时性与准确性,提出了一种新的基于转子位移概率密度信息(probability density information of rotor displacement,PIRD)的航空发动机轴承智能故障诊断方法。其主要对一维卷积神经网络(1-dimensional convolutional neural network,1DCNN)模型进行改进,在传统的卷积层前面增加了PIRD的提取层,可以提取转子振动位移信号的概率密度信息,有效地降低了数据的冗余度,同时保留了故障监测的重要指标。提出的PIRD-CNN诊断模型保留了1DCNN端到端的故障诊断优势,将该模型在航空发动机试验台产生的轴承故障数据进行测试,其对轴承故障诊断精度可达96.58%,与基准研究相对比表明,PIRD-CNN能够快速且更加精准地诊断航空发动机轴承的故障。
