An adaptive spectrum segmentation-based optimized VMD method and its application in rolling bearing fault diagnosis

DC/DC converters are widely used as power supplies in various power supply systems. Their faults can lead to improper system operation. Building intelligent fault diagnosis models for ``highly reliable and long-life” DC/DC converters is challenging due to the high data acquisition costs and insufficient fault data. In this paper, the digital twin (DT) technique is utilized to provide extensive and reliable data to address the issue of insufficient data for diagnosing DC/DC converter faults. However, establishing multidisciplinary, multi-physical quantity, multi-scale, and multi-probability virtual models can be challenging. Thus, a cloud model-based Interpretable transfer model is designed to overcome the limitations of virtual models in fully deducing the full-state output properties. The proposed method effectively diagnoses DC/DC converters based on digital twin technology by providing a more comprehensive and uniformly distributed source domain data to suit the samples in the target domain. Comparison with other algorithms shows the effectiveness of the proposed method. It has the potential to provide accurate and real-time diagnosis for DC/DC converter faults and enable timely maintenance strategies for power monitoring in equipment, such as submarine observation networks and space power supply systems.

Section: Vmdmentioning

confidence: 99%

Early fault diagnosis for DC/DC converters based on digital twins and transfer learning

Xia

Yue

Chen

et al. 2023

“…applications [6]. Specifically, methods such as empirical mode decomposition (EMD) [7], variational mode decomposition (VMD) [8], wavelet analysis [9], and Hilbert-Huang transform (HHT) [10] are commonly utilized within the timefrequency domain for fault diagnosis purposes.…”

Section: Introductionmentioning

confidence: 99%

A novel algorithm for complex transfer conditions in bearing fault diagnosis

Dong,

Su,

Jiang

et al. 2024

Transfer learning in bearing fault diagnosis can effectively improve model generalization and accelerate the practical application of fault diagnosis algorithms. However, previous algorithms primarily focused on simple transfer conditions like known target domain data or the same device. In industrial practice, the conditions for algorithm transfer are more complex. Therefore, cross-domain fault diagnosis under complex transfer conditions is a challenging task with significant practical value. This paper proposes a new bearing fault diagnosis algorithm based on attention mechanism and feature enhancement, which provides better feature extraction capabilities. The main approach involves performing deep aliasing on deep features and training the model to identify domain-invariant classification features under extreme conditions for effective fault diagnosis. Additionally, our network performs well in handling low signal-to-noise ratio problems. Extensive experiments were conducted on three different bearing case studies to validate the effectiveness of the proposed method, showing superior performance compared to other deep transfer learning methods.

“…Li et al [14] utilized VMD to decompose the voltage signals with the aim of eliminating the impact of noise, more precisely positioning series DC arc faults. However, VMD results are limited by the decomposition number k and quadratic penalty factor α, which is an important shortcoming [15].…”

Section: Introductionmentioning

confidence: 99%

High accuracy key feature extraction approach for the non-stationary signals measurement based on NGO-VMD noise reduction and CNN-LSTM

Xu,

Jing,

Zhang

et al. 2023

The effective extraction of key features in non-stationary signals measurement is crucial in numerous engineering fields, including fault diagnosis, geological exploration, and state detection. To accomplish a more accurate and efficient extraction of key feature information from non-stationary signals, we design a novel approach based on variational mode decomposition (VMD) optimization by northern goshawk optimization (NGO) algorithm, convolutional neural network (CNN), and long short-term memory network (LSTM). First, NGO is used to optimize multiple intrinsic mode functions of VMD and reconstruct the signal according to the linear correlation method. Subsequently, the features of moving root mean square, moving kurtosis, and upper envelope are calculated, thereby constructing the feature matrix. Finally, the CNN-LSTM model is established with the chosen optimal hyperparameters prior to the training phase. The experimental results demonstrate that the proposed NGO-VMD-CNN-LSTM method, with a high accuracy reaching 98.22%, can more accurately extract the key information of typical non-stationary signals.