Multiscale noise tuning of stochastic resonance for enhanced fault diagnosis in rotating machines

He, Qingbo; Zhu, Zhongkui; Liu, Yongbin; Dai, Daoyi; Kong, Fanrang

doi:10.1016/j.ymssp.2011.11.021

Cited by 137 publications

(56 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the MSTSR and the SMSTSR methods are conducted to deal with the same offline signals, it can be found that both of the two methods outperform the EMD-based and the LPSR-based spectral analysis methods in processing three kinds of defective signals. The obtained experimental results show that the weak periodic signals have been enhanced successfully by the 1/ f -type noise [17]- [19]. From the running duration aspect, it can be found that the EMD method spends a large computation time but has poorer efficiency.…”

Section: B Effectiveness Of the Proposed Algorithmmentioning

confidence: 86%

“…Literature [18], [19] proposed a set of detailed steps to realize the MSTSR for the fault diagnosis of rotating machine: 1) demodulate the original signal based on the Hilbert transform (HT); 2) the multiscale noise of the demodulated signal is transformed to be an approximate 1/ f -type distribution based on the discrete WT (DWT); and 3) the modified signal is being sent to the bistable SR system, calculating the result of differential equation based on the fourth Runge-Kkutta method. For more details, please refer to [19].…”

Section: B Mstsr Principlementioning

confidence: 99%

“…The above MSTSR algorithm gives good results when it runs on the computer based on the x64 framework in processing the offline signal [18], [19]. If this algorithm is, however, transplanted to the embedded system for processing the online signal, it may not be the most suitable choice.…”

Section: Sequential Mstsrmentioning

confidence: 99%

“…In [17]- [19], the multiscale noise tuning SR (MSTSR) has been proposed as a new kind of large parameter SR (LPSR). The MSTSR method has been verified to outperform traditional SR method and some other signal processing methods for enhancing weak signals being submerged in heavy noise in bearing fault diagnosis [18], [19]. In this paper, a sequential algorithm of MSTSR (denoted by SMSTSR) is further proposed to satisfy the online data processing requirement for the TADS.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Sequential Multiscale Noise Tuning Stochastic Resonance for Train Bearing Fault Diagnosis in an Embedded System

et al. 2014

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

Multiscale noise tuning stochastic resonance (MSTSR) has been proved to be an effective method for enhanced fault diagnosis by taking advantage of noise to detect the incipient faults of the bearings and gearbox. This paper addresses a sequential algorithm for the MSTSR method to detect the train bearing faults in an embedded system through the acoustic signal analysis. Specifically, the energy operator, digital filter array, and fourth rank Runge-Kutta equation methods are designed to realize the signal demodulation, multiscale noise tuning, and bistable stochastic resonance in sequence. The merit of the sequential algorithm is that it reduces the memory consumption and decreases the computation complexity, so that it can be efficiently implemented in the embedded system based on a low-cost, low-power hardware platform. After the sequential algorithm, the real-valued fast Fourier transform is used to calculate the power spectrum of the analyzed signal. The proposed method has been verified in algorithm performance and hardware implementation by three kinds of practical acoustic signals from defective train bearings. An enhanced performance of the proposed fault diagnosis method is confirmed as compared with several traditional methods, and the hardware performance is also validated.Index Terms-Embedded system, fault diagnosis, multiscale noise tuning, sequential algorithm, stochastic resonance (SR), train bearing.

show abstract

Section: B Effectiveness Of the Proposed Algorithmmentioning

confidence: 86%

Section: B Mstsr Principlementioning

confidence: 99%

Section: Sequential Mstsrmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sequential Multiscale Noise Tuning Stochastic Resonance for Train Bearing Fault Diagnosis in an Embedded System

et al. 2014

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Detecting and diagnosing fault to enhance the safety and reliability of machinery, as well as reduce operation and maintenance costs, are essential and have practical significant because of the effect of unexpected accidents [2]. Vibration signals can accurately indicate the health conditions of mechanical equipment; hence, these signals are extensively used in fault diagnosis based on artificial methods, such as multinomial logistic regression, wavelet packet transforms (WPT), and support vector machines (SVMs) [3][4][5][6].…”

Section: Introductionmentioning

confidence: 99%

Deep Fault Recognizer: An Integrated Model to Denoise and Extract Features for Fault Diagnosis in Rotating Machinery

2016

View full text Add to dashboard Cite

Fault diagnosis in rotating machinery is significant to avoid serious accidents; thus, an accurate and timely diagnosis method is necessary. With the breakthrough in deep learning algorithm, some intelligent methods, such as deep belief network (DBN) and deep convolution neural network (DCNN), have been developed with satisfactory performances to conduct machinery fault diagnosis. However, only a few of these methods consider properly dealing with noises that exist in practical situations and the denoising methods are in need of extensive professional experiences. Accordingly, rethinking the fault diagnosis method based on deep architectures is essential. Hence, this study proposes an automatic denoising and feature extraction method that inherently considers spatial and temporal correlations. In this study, an integrated deep fault recognizer model based on the stacked denoising autoencoder (SDAE) is applied to both denoise random noises in the raw signals and represent fault features in fault pattern diagnosis for both bearing rolling fault and gearbox fault, and trained in a greedy layer-wise fashion. Finally, the experimental validation demonstrates that the proposed method has better diagnosis accuracy than DBN, particularly in the existing situation of noises with superiority of approximately 7% in fault diagnosis accuracy.

show abstract

On the Use of Stochastic Resonance in Mechanical Fault Signal Detection

Zhang

et al. 2017

Smart Sensors, Measurement and Instrumentation

View full text Add to dashboard Cite

Multiscale noise tuning of stochastic resonance for enhanced fault diagnosis in rotating machines

Cited by 137 publications

References 22 publications

Sequential Multiscale Noise Tuning Stochastic Resonance for Train Bearing Fault Diagnosis in an Embedded System

Sequential Multiscale Noise Tuning Stochastic Resonance for Train Bearing Fault Diagnosis in an Embedded System

Deep Fault Recognizer: An Integrated Model to Denoise and Extract Features for Fault Diagnosis in Rotating Machinery

On the Use of Stochastic Resonance in Mechanical Fault Signal Detection

Contact Info

Product

Resources

About