The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension.Currently,nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddi...The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension.Currently,nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddings,such as manifold learning.However,these methods are all based on manual intervention,which have some shortages in stability,and suppressing the disturbance noise.To extract features automatically,a manifold learning method with self-organization mapping is introduced for the first time.Under the non-uniform sample distribution reconstructed by the phase space,the expectation maximization(EM) iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention.After that,the local tangent space alignment(LTSA) algorithm is adopted to compress the high-dimensional phase space into a more truthful low-dimensional representation.Finally,the signal is reconstructed by the kernel regression.Several typical states include the Lorenz system,engine fault with piston pin defect,and bearing fault with outer-race defect are analyzed.Compared with the LTSA and continuous wavelet transform,the results show that the background noise can be fully restrained and the entire periodic repetition of impact components is well separated and identified.A new way to automatically and precisely extract the impulsive components from mechanical signals is proposed.展开更多
Using the method of localization, the authors obtain the permutation formula of singular integrals with Bochner-Martinelli kernel for a relative compact domain with C^（1） smooth boundary on a Stein manifold. As an a...Using the method of localization, the authors obtain the permutation formula of singular integrals with Bochner-Martinelli kernel for a relative compact domain with C^（1） smooth boundary on a Stein manifold. As an application the authors discuss the regularization problem for linear singular integral equations with Bochner-Martinelli kernel and variable coefficients; using permutation formula, the singular integral equation can be reduced to a fredholm equation.展开更多
经数据分析途径实现机器智能的故障决策引发出了关于故障数据集的降维问题。通过将等距映射算法(Isometric Mapping,ISOMAP)、局部线性嵌入(Locally Linear Embedding,LLE)算法的优缺点进行互补,提出一种适用于非线性数据集降维的核框...经数据分析途径实现机器智能的故障决策引发出了关于故障数据集的降维问题。通过将等距映射算法(Isometric Mapping,ISOMAP)、局部线性嵌入(Locally Linear Embedding,LLE)算法的优缺点进行互补,提出一种适用于非线性数据集降维的核框架下等距映射与局部线性嵌入相结合的KISOMAPLLE算法。该算法能够同时满足全局距离保持性和局部结构保持能力的数据降维基本要求。用典型的人工数据集和转子故障数据集进行的降维验证结果表明,该算法能够继承ISOMAP、LLE两种算法的各自优良性能,具有能够显著提高典型非线性数据集分类精度的性能。展开更多
基金supported by National Natural Science Foundation of China(Grant No.51075323)
文摘The feature space extracted from vibration signals with various faults is often nonlinear and of high dimension.Currently,nonlinear dimensionality reduction methods are available for extracting low-dimensional embeddings,such as manifold learning.However,these methods are all based on manual intervention,which have some shortages in stability,and suppressing the disturbance noise.To extract features automatically,a manifold learning method with self-organization mapping is introduced for the first time.Under the non-uniform sample distribution reconstructed by the phase space,the expectation maximization(EM) iteration algorithm is used to divide the local neighborhoods adaptively without manual intervention.After that,the local tangent space alignment(LTSA) algorithm is adopted to compress the high-dimensional phase space into a more truthful low-dimensional representation.Finally,the signal is reconstructed by the kernel regression.Several typical states include the Lorenz system,engine fault with piston pin defect,and bearing fault with outer-race defect are analyzed.Compared with the LTSA and continuous wavelet transform,the results show that the background noise can be fully restrained and the entire periodic repetition of impact components is well separated and identified.A new way to automatically and precisely extract the impulsive components from mechanical signals is proposed.
基金The project was supported by the Natural Science Foundation of Fujian Province of China (Z0511002)the National Science Foundation of China (10271097,10571144)+1 种基金Foundation of Tianyuan (10526033)Chen L P, the Corresponding author
文摘Using the method of localization, the authors obtain the permutation formula of singular integrals with Bochner-Martinelli kernel for a relative compact domain with C^（1） smooth boundary on a Stein manifold. As an application the authors discuss the regularization problem for linear singular integral equations with Bochner-Martinelli kernel and variable coefficients; using permutation formula, the singular integral equation can be reduced to a fredholm equation.
文摘经数据分析途径实现机器智能的故障决策引发出了关于故障数据集的降维问题。通过将等距映射算法(Isometric Mapping,ISOMAP)、局部线性嵌入(Locally Linear Embedding,LLE)算法的优缺点进行互补,提出一种适用于非线性数据集降维的核框架下等距映射与局部线性嵌入相结合的KISOMAPLLE算法。该算法能够同时满足全局距离保持性和局部结构保持能力的数据降维基本要求。用典型的人工数据集和转子故障数据集进行的降维验证结果表明,该算法能够继承ISOMAP、LLE两种算法的各自优良性能,具有能够显著提高典型非线性数据集分类精度的性能。
