Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis,while the noise mixed in measured signals harms the prediction accuracy of networks.Existing denoising methods ...Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis,while the noise mixed in measured signals harms the prediction accuracy of networks.Existing denoising methods in neural networks,such as using complex network architectures and introducing sparse techniques,always suffer from the difficulty of estimating hyperparameters and the lack of physical interpretability.To address this issue,this paper proposes a novel interpretable denoising layer based on reproducing kernel Hilbert space(RKHS)as the first layer for standard neural networks,with the aim to combine the advantages of both traditional signal processing technology with physical interpretation and network modeling strategy with parameter adaption.By investigating the influencing mechanism of parameters on the regularization procedure in RKHS,the key parameter that dynamically controls the signal smoothness with low computational cost is selected as the only trainable parameter of the proposed layer.Besides,the forward and backward propagation algorithms of the designed layer are formulated to ensure that the selected parameter can be automatically updated together with other parameters in the neural network.Moreover,exponential and piecewise functions are introduced in the weight updating process to keep the trainable weight within a reasonable range and avoid the ill-conditioned problem.Experiment studies verify the effectiveness and compatibility of the proposed layer design method in intelligent fault diagnosis of machinery in noisy environments.展开更多
This study develops an optimal performance monitoring metric for a hybrid free space optical and radio wireless network, the Outage Capacity Objective Function. The objective function—the dependence of hybrid channel...This study develops an optimal performance monitoring metric for a hybrid free space optical and radio wireless network, the Outage Capacity Objective Function. The objective function—the dependence of hybrid channel outage capacity upon the error rate, jointly quantifies the effects of atmospheric optical impairments on the performance of the free space optical segment as well as the effect of RF channel impairments on the radio frequency segment. The objective function is developed from the basic information-theoretic capacity of the optical and radio channels using the gamma-gamma model for optical fading and Ricean statistics for the radio channel fading. A simulation is performed by using the hybrid network. The objective function is shown to provide significantly improved sensitivity to degrading performance trends and supports of proactive link failure prediction and mitigation when compared to current thresholding techniques for signal quality metrics.展开更多
为研究空间故障网络(Space Fault Network,SFN)中故障模式的最终事件故障概率分布(Fault Probability Distribution of Target Event,TEFPD),在不同情况下确定分布特征,提出不同情况下的TEFPD确定方法。研究对象为单元故障演化过程和全...为研究空间故障网络(Space Fault Network,SFN)中故障模式的最终事件故障概率分布(Fault Probability Distribution of Target Event,TEFPD),在不同情况下确定分布特征,提出不同情况下的TEFPD确定方法。研究对象为单元故障演化过程和全事件诱发+最终事件过程两种。根据原因事件和结果事件的关系,分析方法分为比较形式方法和继承形式方法。根据故障模式中事件存在性,故障概率分布处理方式分为最大值方法和平均值方法。考虑多因素影响,将事件故障概率分布引入到分析中,得到各种情况下的TEFPD.通过一个简单故障模式得到TEFPD,最终总结各种方式得到的TEFPD的特征显著程度。展开更多
基金Supported by National Natural Science Foundation of China(Grant Nos.12072188,11632011,11702171,11572189,51121063)Shanghai Municipal Natural Science Foundation of China(Grant No.20ZR1425200).
文摘Deep learning algorithms based on neural networks make remarkable achievements in machine fault diagnosis,while the noise mixed in measured signals harms the prediction accuracy of networks.Existing denoising methods in neural networks,such as using complex network architectures and introducing sparse techniques,always suffer from the difficulty of estimating hyperparameters and the lack of physical interpretability.To address this issue,this paper proposes a novel interpretable denoising layer based on reproducing kernel Hilbert space(RKHS)as the first layer for standard neural networks,with the aim to combine the advantages of both traditional signal processing technology with physical interpretation and network modeling strategy with parameter adaption.By investigating the influencing mechanism of parameters on the regularization procedure in RKHS,the key parameter that dynamically controls the signal smoothness with low computational cost is selected as the only trainable parameter of the proposed layer.Besides,the forward and backward propagation algorithms of the designed layer are formulated to ensure that the selected parameter can be automatically updated together with other parameters in the neural network.Moreover,exponential and piecewise functions are introduced in the weight updating process to keep the trainable weight within a reasonable range and avoid the ill-conditioned problem.Experiment studies verify the effectiveness and compatibility of the proposed layer design method in intelligent fault diagnosis of machinery in noisy environments.
文摘This study develops an optimal performance monitoring metric for a hybrid free space optical and radio wireless network, the Outage Capacity Objective Function. The objective function—the dependence of hybrid channel outage capacity upon the error rate, jointly quantifies the effects of atmospheric optical impairments on the performance of the free space optical segment as well as the effect of RF channel impairments on the radio frequency segment. The objective function is developed from the basic information-theoretic capacity of the optical and radio channels using the gamma-gamma model for optical fading and Ricean statistics for the radio channel fading. A simulation is performed by using the hybrid network. The objective function is shown to provide significantly improved sensitivity to degrading performance trends and supports of proactive link failure prediction and mitigation when compared to current thresholding techniques for signal quality metrics.
文摘为研究空间故障网络(Space Fault Network,SFN)中故障模式的最终事件故障概率分布(Fault Probability Distribution of Target Event,TEFPD),在不同情况下确定分布特征,提出不同情况下的TEFPD确定方法。研究对象为单元故障演化过程和全事件诱发+最终事件过程两种。根据原因事件和结果事件的关系,分析方法分为比较形式方法和继承形式方法。根据故障模式中事件存在性,故障概率分布处理方式分为最大值方法和平均值方法。考虑多因素影响,将事件故障概率分布引入到分析中,得到各种情况下的TEFPD.通过一个简单故障模式得到TEFPD,最终总结各种方式得到的TEFPD的特征显著程度。
