A novel sensor fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition and Probabilistic Neural Network

Yu, Yunluo; Li, Wei; De-ren, Sheng; Chen, Jianhong

doi:10.1016/j.measurement.2015.03.003

Cited by 71 publications

(33 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wu et al [19] integrated wavelet decomposition with PNN to diagnose the fault of machinery vibration in Aero-Engine. To solve the mode mixing problem in traditional EMD, Yu et al [20] proposed a novel fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition (MEEMD) and PNN. However, most papers focus on the technologies of feature extraction or pattern recognition, ignoring the significance of de-noising in fault diagnosis and using general de-noising methods without consideration of those signal characteristics.…”

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of rotor using EMD thresholding-based de-noising combined with probabilistic neural network

Liu¹,

Zeng²,

Zhang³

et al. 2017

J. vibroeng.

View full text Add to dashboard Cite

De-noising of signal processing is crucial for fault diagnosis in order to successfully conduct feature extraction and is an efficient method for accurate determination of cause. In this paper, the empirical mode decomposition (EMD) thresholding-based de-noising method and probabilistic neural network (PNN) are respectively used in the de-noising of the vibration signal and rotor fault diagnosis and compared with wavelet thresholding-based de-noising technology and back propagation neural network (BPNN). The results show that the clear iterative EMD interval thresholding performs better than wavelet thresholding in the de-noising of the vibration signal, and avoids the determination of wavelet basis and decomposition level. In addition, the PNN created by feature samples does not require training and has a higher accuracy than BPNN. on the fault diagnosis of hydropower units, application of artificial intelligence in electric power system, and modeling, analysis, design and control of hydropower equipment. Peng Lihong received B.E degree in thermal and power engineering from School of Energy and Electrical Engineering, Hohai University, Nanjing, P.R. China, in 2015. She is currently a Master candidate in hydraulic hydroelectric engineering from School of Power and Mechanical Engineering, Wuhan University. Her research interests include modeling simulation and optimization control of the hydroelectric generating set, condition monitoring and fault diagnosis technology.

show abstract

Section: Introductionmentioning

confidence: 99%

Fault diagnosis of rotor using EMD thresholding-based de-noising combined with probabilistic neural network

Liu¹,

Zeng²,

Zhang³

et al. 2017

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…In this paper, the porcine acoustic signal is firstly decomposed. EMD can decompose the signals into IMFs from high to low frequency self-adaptively [18,19], which is based on the decomposition principle that any signal is composed of IMFs [20]. e IMF must satisfy two conditions: (1) e number of extreme points is equal to the number of zero-crossings.…”

Section: Porcine Acoustic Signal Decomposition Based On Eemdmentioning

confidence: 99%

An Efficient Porcine Acoustic Signal Denoising Technique Based on EEMD‐ICA‐WTD

Zhang

Tian

Banerjee

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Automatic monitoring of group-housed pigs in real time through porcine acoustic signals has played a crucial role in automated farming. In the process of data collection and transmission, acoustic signals are generally interfered with noise. In this paper, an effective porcine acoustic signal denoising technique based on ensemble empirical mode decomposition (EEMD), independent component analysis (ICA), and wavelet threshold denoising (WTD) is proposed. Firstly, the porcine acoustic signal is decomposed into intrinsic mode functions (IMFs) by EEMD. In addition, permutation entropy (PE) is adopted to distinguish noise-dominant IMFs from the IMFs. Secondly, ICA is employed to extract the independent components (ICs) of the noise-dominant IMFs. The correlation coefficients of ICs and the first IMF are calculated to recognize noise ICs. The noise ICs will be removed. Then, WTD is applied to the other ICs. Finally, the porcine acoustic signal is reconstructed by the processed components. Experimental results show that the proposed method can effectively improve the denoising performance of porcine acoustic signal.

show abstract

“…Thus, the errors of sensor measurements exist on different degrees when the sensors malfunction. The fault outputs of a temperature sensor are complicated and can be expressed in several different forms [32][33][34], in a perspective of simulation, its typical faults may be primarily simplified into the following three forms:…”

Section: Description Of Faultsmentioning

confidence: 99%

Model-Based Temperature Sensor Fault Detection and Fault-Tolerant Control of Urea-Selective Catalyst Reduction Control Systems

Wang

Zeng

et al. 2018

Energies

View full text Add to dashboard Cite

This paper aims at investigating the fault diagnosis of the selective catalyst reduction (SCR) outlet temperature sensors and fault-tolerant control methods of the SCR system, and three typical faults of downstream temperature sensors were modeled and analyzed to present influences of different faults on the SCR system performances (such as nitrogen oxides (NO x ) emission and conversion efficiency, NH 3 slip, urea dosage and ammonia coverage estimation). A temperature model was established to estimate the SCR outlet temperature, and diagnostics were developed based on the differences between model estimates and sensor measurements. Once a downstream temperature sensor fault was detected, the fault-tolerant control will be enabled, and the output of the sensor may be substituted with the estimates of the model. Thus, SCR performances shall be maintained within the acceptable ranges. Moreover, a 0-D SCR model was also established to validate the capability of diagnostics and fault-tolerant control strategy over the European transient cycle (ETC).

show abstract

A novel sensor fault diagnosis method based on Modified Ensemble Empirical Mode Decomposition and Probabilistic Neural Network

Cited by 71 publications

References 29 publications

Fault diagnosis of rotor using EMD thresholding-based de-noising combined with probabilistic neural network

Fault diagnosis of rotor using EMD thresholding-based de-noising combined with probabilistic neural network

An Efficient Porcine Acoustic Signal Denoising Technique Based on EEMD‐ICA‐WTD

Model-Based Temperature Sensor Fault Detection and Fault-Tolerant Control of Urea-Selective Catalyst Reduction Control Systems

Contact Info

Product

Resources

About