In actual engineering scenarios, multichannel datasets that contain complete information contribute to better accuracy of bearing fault diagnosis. Multivariate variational mode decomposition (MVMD), as an extension (VMD), can deal with multivariate signals. However, the performance MVMD is affected by initial parameters, i.e., number modes, bandwidth balance parameter, and center frequencies (ICFs). To overcome difficulty parameter selection, a self-adaptive proposed, where modes ICFs are...

Unknown domain shift caused by the unavailability of target during training phase degrades performance intelligent fault diagnosis models in practical applications. Domain generalization (DG)-based methods have recently emerged to alleviate influence and improve ability toward invisible working conditions. However, most existing studies are conducted on multiple fully labeled source domains. Meanwhile, domain-specific information related variations conditions is often neglected model...

Swarm decomposition (SWD) is an emerging signal method and has been applied in the fault diagnosis of rotating machinery. However, performance SWD highly dependent on user-defined parameter. In this article, adaptive swarm (ASWD) guided by spectral characteristic information scanner (SCIS) proposed to automatically decompose vibration into a set subcomponents. The can not only adaptively extract weak fault-related component from contaminated strong noise but also avoid problem parameter...

Summary To realize a high‐accuracy tracking control of an electromechanical actuator in which only position signal is available, new robust adaptive output feedback strategy based on dual CMAC neural networks proposed this article. A high‐gain observer and network are combined to estimate the unmeasured system states, designed compensate parameter estimation error other uncertain nonlinearity improve performance traditional observer. controller another decrease impact perturbation external...

Variational mode extraction (VME), a novel signal decomposition method based on frequency-domain filter in essence, has recently become potential tool fault diagnosis. However, the original VME algorithm is not provided with full self-adaptation, and its performance of features subject to predefining initial parameters, including center frequency (ICF) balance parameter. To address these issues, spectral feature informed variational model (SFIVM) constructed overcome defects parameters...

Abstract Central frequency mode decomposition (CFMD) is a promising tool for complex mechanical signal processing. Some characteristics of CFMD are disclosed by performing detailed discussion on its decomposing theory in this study. As result, three deficiencies found through the characteristic analysis, including low accuracies detected central frequencies (CFs), filters with too wide bandwidth, and excessive number decomposed modes. To address these issues, modified (MCFMD) method proposed...

As the basis of condition-based maintenance, machine health monitoring aims timely to detect incipient faults and quantitatively assess performance degradation. This study proposes a multiscale sparsity measure (SM) fusion framework enhance bearing degradation assessment with SMs. The consists following three steps. First, SMs are constructed by combining analysis adaptive weighted signal preprocessing technique (AWSPT) for enriching status features. Second, scheme including offline training...

Abstract Sparse filtering (SF) has received considerable attentions in the machinery fault diagnosis thanks to its ability extract fault-related features using their sparsity. However, existing SF methods have dilemmas with empirical selection of model parameters, loss information caused by a screening way for target mode, and singularity results induced some large-amplitude random impulses (LARIs). Hence, manifold learning-assisted method is proposed feature enhancement this study. First,...

The bearing failure diagnosis methods based upon variational mode decomposition (VMD) have been researched extensively in recent years. However, these are only capable of dealing with single channel data, which the amount information is limited and anti-interference ability needs to be further enhanced. Recently, as one extensions VMD, multivariate (MVMD) was put forward deal signal. For sake monitoring operation state equipment more comprehensively diagnose mechanical accurately, we propose...

Sparse filtering and its variants have been used in the field of weak feature extraction bearing. However, fault features extracted by current sparse methods are still subject to contamination strong noises. Therefore, an enhanced fusion method is proposed for bearing diagnosis this study. Specifically, conducted through following steps. First, extract under background noise filtering. Second, Gini index select sparser constructing a multi-dimensional source. Third, obtain intrinsic...

Various failures are prone to occur in rotating machinery due the harsh working conditions, thereby making it a vital work perform accurate fault diagnosis prevent performance degradation and safety hazards. The presence of multivariate variational mode decomposition (MVMD) provides good knowledge how cope with multichannel data which contains more comprehensive information. In this work, an innovative diagnostic approach based on optimized MVMD is proposed for machinery. Corner-stone method...