Online blind source separation method with adaptive step size in both time-invariant and time-varying cases

Lu, Jiming; Cheng, Wei; Ye, Zi

doi:10.1088/1361-6501/ab5c75

Cited by 6 publications

(7 citation statements)

References 31 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the method proposed by Chua and Klejin reduced the calculation delay while also retaining good separation properties [6]. In 2020, Lu et al proposed an online BSS method with an adaptive step size based on an isometric adaptive separation method to find a valid equilibrium between the convergence rate and the steady-state error of online BSS; this method demonstrated high estimation precision [18]. In 2021, because the vibration signal of the composite fault of a rotary mechanical machine acquired in the field had a complex noise source, Feng et al addressed this problem by proposing a wavelet package analysis and fast independent component analysis extraction method for the source fault signal [9].…”

Section: Related Workmentioning

confidence: 99%

Variational Mode Decomposition-based Synchronous Multi-Frequency Electrical Impedance Tomography

Pan¹,

Li²,

Wang³

et al. 2022

ITC

View full text Add to dashboard Cite

Electrical Impedance Tomography (EIT) can perform non-invasive, low-cost, safe, fast, and simple system structure and functional imaging to map the distribution and changes of root zone. Multi frequency EIT solves the problem that single-frequency EIT can only carry more impedance information than a given single excitation frequency. It still remains challenges to simultaneously obtain multi-frequency electrical impedance tomography. To address the problem, a mixed signal superimposed by multiple frequencies is injected to the object. Essentially, separating the measured mixed voltage signals, which can be used to obtain electrical impedance information at different frequencies at the same time quickly. Since the measurement signal is a multi-frequency signal, the effect of decomposing the multi-frequency signal directly affects the accuracy of imaging. In order to obtain more accurate data, this article used the variational mode decomposition (VMD) method to decompose the measured multi-frequency signal. Accurate amplitude and phase information could be obtained simultaneously at the same time in multi-frequency excitation, and these data could be used to reconstruct electrical impedance distribution The results showed that the proposed method can achieve the expected imaging effect. It was concluded that using the variational modal decomposition method to process the data of multi-frequency signals is more accurate and the imaging effect is better, and it can be applied to multi-frequency electrical impedance imaging in practice.

show abstract

Section: Related Workmentioning

confidence: 99%

Variational Mode Decomposition-based Synchronous Multi-Frequency Electrical Impedance Tomography

Pan¹,

Li²,

Wang³

et al. 2022

ITC

View full text Add to dashboard Cite

show abstract

“…e proposed method is compared with the EASI method with fixed step size (FS-EASI) [24], the exponential-decay-step size method (EDS) [29], the adaptive step size method with weighted orthogonalization (AS-WO) [28] and variable step size algorithm with separation indicator (VS-SI) [15]. e initial parameters are set as follows: the step size of FS-EASI μ � 0.005. e parameters of EDS are set as μ(0) � 0.005, K 0 � 1000, L 0 � 0.0012, which are widely used in [19,23].…”

Section: Compare With Othermentioning

confidence: 99%

“…It cannot only obtain the target signal but also obtain every interference noise source, which is convenient for deeper noise source location and feature extraction. It is widely used in acoustic signal processing [12], wireless sensor signal transmission [13], biomedical engineering [14], and fault diagnosis [15]. BSS can be divided into online methods and offline methods [16].…”

Section: Introductionmentioning

confidence: 99%

A Novel Improved Threshold Adaptive Forgetting Variable Step Size Blind Separation Model for Weak Signal Detection

Wang

et al. 2022

Shock and Vibration

Self Cite

View full text Add to dashboard Cite

The online blind source separation (BSS) is seriously disturbed by strong noise when extracting weak signals and has the defects that it cannot both give consideration to convergence speed and steady-state error. In order to solve the abovementioned problems, a novel improved threshold adaptive forgetting variable step size blind separation model (ITAFBS) for weak signal detection is proposed. Firstly, an improved lifting wavelet transform (ILWT) is proposed to reduce the noise of weak signals. In ILWT, a threshold function containing an adjustment factor is proposed to reduce the constant deviation so as to ensure a high signal-to-noise ratio and low distortion after denoising. Then, the separation index (SI) is constructed according to the convergence conditions of the BSS model. An adaptive variable step size blind separation model based on the SI is studied. At the initial stage of separation, the step size is increased to obtain a fast convergence rate, and at the end of separation and the step size is shortened to obtain a small steady-state error. Finally, the forgetting factor is introduced into the model to reduce the error accumulation in the early stage of the algorithm, and the Fourier norm is introduced to improve the convergence speed and separation accuracy of the model. The simulation and experimental results show that ITAFBS has a good performance in multi-frequency weak signal detection. Compared with other methods, the ITAFBS has a faster convergence speed and minimum steady-state error.

show abstract

“…Blind source separation (BSS) is widely used in the separation of noise sources in mechanical systems [4][5][6][7], and can separate the source signals when the source signals and transmission channel are unknown [8][9][10]. Independent component analysis (ICA) is a kind of BSS, which is based on the assumption of source signal independence [11,12].…”

Section: Introductionmentioning

confidence: 99%

Convolutive blind source separation in the frequency domain of mechanical noise for gas turbines based on bounded component analysis

Cheng¹,

Chen²,

Song³

et al. 2022

Meas. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Noise source identification of gas turbines can provide basis and guidance for vibration and noise reduction of gas turbines. Independent component analysis (ICA) which is one of the most popular techniques of blind source separation (BSS) widely used in vibration and noise sources of mechanical systems. However, ICA is suitable for independent source signals. In order to identify dependent mechanical noise sources of gas turbines, a convolutive blind source separation in frequency domain based on bounded component analysis (BCA) is proposed. First, the basic theory of BSS and BCA is introduced in detail. The convolutive mixing in time domain is transformed into an instantaneous mixing in frequency domain by STFT, and complex BCA is performed at each frequency bin. Then a permutation alignment method based on local and global optimization is proposed to solve the problem of the fuzziness of permutation. Finally, the accuracy and robustness of the proposed method are studied and compared through typical numerical studies and experimental studies on a three-rotor experimental bench. The results show that the proposed method can effectively separate and identify independent and dependent source signals.

show abstract

Online blind source separation method with adaptive step size in both time-invariant and time-varying cases

Cited by 6 publications

References 31 publications

Variational Mode Decomposition-based Synchronous Multi-Frequency Electrical Impedance Tomography

Variational Mode Decomposition-based Synchronous Multi-Frequency Electrical Impedance Tomography

A Novel Improved Threshold Adaptive Forgetting Variable Step Size Blind Separation Model for Weak Signal Detection

Convolutive blind source separation in the frequency domain of mechanical noise for gas turbines based on bounded component analysis

Contact Info

Product

Resources

About