Adaptive feature mode decomposition: a fault-oriented vibration signal decomposition method for identification of multiple localized faults in rotating machinery

He, Xiuzhi; Zhou, Xiaoqin; Li, Jieli; Mechefske, Chris K.; Wang, Rongqi; Yao, Guofeng; Liu, Qiang

doi:10.1007/s11071-023-08703-4

Cited by 13 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While deep learning models have demonstrated promising results in wind power prediction, the inherent unpredictability and volatility of wind signals pose significant challenges to accurate forecasting. Signal decomposition, a technique that involves the dissection of complex signals into their constituent modal components, offers a strategy for mitigating these signals' inherent randomness and instability [12]. The application of signal decomposition algorithms for mitigating the nonlinearity in high-and lowfrequency signals has garnered growing interest among researchers in time-series signal processing.…”

Section: Introductionmentioning

confidence: 99%

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

Chen,

Zhang,

Tong

et al. 2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

To augment the accuracy, stability, and qualification rate of wind power prediction, thereby fostering the secure and economical operation of wind farms, a method predicated on quadratic decomposition and multi-objective optimization for ultra-short-term wind power prediction is proposed. Initially, the original wind power signal is decomposed using a quadratic decomposition method constituted by the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Fuzzy Entropy (FE), and Symplectic Geometry Mode Decomposition (SGMD), thereby mitigating the randomness and volatility of the original signal. Subsequently, the decomposed signal components are introduced into the Deep Bidirectional Long Short-Term Memory (DBiLSTM) neural network for time series modeling, and the Sand Cat Swarm Optimization Algorithm (SCSO) is employed to optimize the network hyperparameters, thereby enhancing the network’s predictive performance. Ultimately, a multi-objective optimization loss that accommodates accuracy, stability, and grid compliance is proposed to guide network training. Experimental results reveal that the employed quadratic decomposition method and the proposed multi-objective optimization loss can effectively bolster the model’s predictive performance. Compared to other classical methods, the proposed method achieves optimal results across different seasons, thereby demonstrating robust practicality.

show abstract

Section: Introductionmentioning

confidence: 99%

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

Chen,

Zhang,

Tong

et al. 2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

show abstract

“…Therefore, it is of great significance to adaptively select these two important parameters. In the previous study, the AFMD proposed by Zhou et al [39] was based on autoregressive model and weighted square envelope harmonic noise ratio. Yan and Jia [40] employed the PSO algorithm to optimize the parameters of FMD and realized parameter self-adaptation of FMD.…”

Section: Introductionmentioning

confidence: 99%

Iterative feature mode decomposition: a novel adaptive denoising method for mechanical fault diagnosis

Ruan,

Yuan,

Dang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Remaining useful life prediction of rolling bearings highly relies on feature extraction of signals. The use of denoising algorithms helps to better eliminate noise and extract features, thereby constructing health indicators to predict remaining useful life. This paper proposes a novel adaptive denoising method based on iterative feature mode decomposition ( FMD) toI accurately and efficiently extract fault features. The feature mode decomposition (FMD) employs correlation kurtosis (CK) as the objective function for iterative filter bank updates, enabling rapid identification of fault features. To achieve IFMD, the sparrow search algorithm combines sine-cosine algorithm and cauchy variation (SCSSA) to optimize two key parameters in FMD. During the continuous iteration process of the SCSSA algorithm, filter length and number of modes were determined. IFMD does not require empirical setting of initial parameters. During iterative process, the signal is accurately decomposed and the noise is eliminated. Compared with other optimization algorithms, SCSSA has obvious advantages in iterative rate and global optimization. The envelope spectrum feature energy ratio (ES-FER) is used to select decomposed modes, and the mode with the largest ES-FER is chosen as the optimal mode. Bearing fault diagnosis is realized by envelope spectrum analysis of the optimal mode. The numerical simulations and experimental verifications both validate the effectiveness and superiority of the proposed IFMD in mechanical fault diagnosis.

show abstract

On modeling and damage detection methodologies in rotor systems

Abdul Nasar,

Alzarooni,

AL-Shudeifat

2024

Nonlinear Dyn

View full text Add to dashboard Cite

Damages in rotor systems have severe impact on their functionality, safety, running durability and their industrial productivity, which usually leads to unavoidable economical and human losses. Rotor systems are employed in extensive industrial applications such as jet engines, gas and steam turbines, heavy-duty pumps and compressors, drilling tools, and in other machineries. One of the major damages in such systems is the propagation of fatigue cracks. The heavy-duty and recurrent cyclic fatigue loading in rotor systems is one of the main factors leading to fatigue crack propagation. For the past few decades, numerous research have been conducted to study crack related damages and various methodologies were proposed or employed for damage detection in rotor systems. Therefore, the purpose of the present review article is to provide a thorough analysis and evaluation regarding the associated research related to the modeling aspects of rotor systems that are associated with various kinds of (rotor related) damages. Based on this review, it is observed that the crack modeling, especially with the breathing crack type in rotor systems, is still based on few primary models. Several researchers, based on different assumptions, have extended and modified such models to be more reliable for analysis. Moreover, the arising demand for early crack detection has led to utilization of various tools such as Fast Fourier transform, Hilbert Huang transform, wavelet transform, whirling analysis, energy methods, and the correlation between backward whirling and rotor faults etc. In addition, the significant impact of nonsynchronous whirl within resonance zones of rotor systems on post-resonance backward whirl, under various rotor related faults, is also highlighted in the present review. Therefore, the review provides an evaluation and comparison between several crack models and detection methodologies in rotor systems. Moreover, this review could help in identifying the gaps in modeling, simulation, and dynamical analysis of cracked rotor systems to establish robust research platform on cracked rotor systems.

show abstract

Adaptive feature mode decomposition: a fault-oriented vibration signal decomposition method for identification of multiple localized faults in rotating machinery

Cited by 13 publications

References 36 publications

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

An Ultra-Short-Term Wind Power Prediction Method Based on Quadratic Decomposition and Multi-Objective Optimization

Iterative feature mode decomposition: a novel adaptive denoising method for mechanical fault diagnosis

On modeling and damage detection methodologies in rotor systems

Contact Info

Product

Resources

About