A Fault Prediction Method of Rotating Machinery Based on an Improved Empirical Mode Decomposition

2012 ◽  
Vol 5 (2) ◽  
pp. 874-877 ◽  
Author(s):  
Keyong Wang ◽  
Jiahao Deng ◽  
Yanli Yang
Keyword(s):  
Empirical Mode Decomposition ◽  
Prediction Method ◽  
Rotating Machinery ◽  
Fault Prediction ◽  
Mode Decomposition

scholarly journals Early Fault Detection Method for Rotating Machinery Based on Harmonic-Assisted Multivariate Empirical Mode Decomposition and Transfer Entropy

Entropy ◽  
2018 ◽  
Vol 20 (11) ◽  
pp. 873 ◽  
Author(s):  
Zhe Wu ◽  
Qiang Zhang ◽  
Lixin Wang ◽  
Lifeng Cheng ◽  
Jingbo Zhou
Keyword(s):  
Fault Detection ◽  
Empirical Mode Decomposition ◽  
High Frequency ◽  
Rotating Machinery ◽  
Transfer Entropy ◽  
Multivariate Empirical Mode Decomposition ◽  
Mode Decomposition ◽  
Coupling Characteristics ◽  
High Frequency Harmonic ◽  
Frequency Harmonic

It is a difficult task to analyze the coupling characteristics of rotating machinery fault signals under the influence of complex and nonlinear interference signals. This difficulty is due to the strong noise background of rotating machinery fault feature extraction and weaknesses, such as modal mixing problems, in the existing Ensemble Empirical Mode Decomposition (EEMD) time–frequency analysis methods. To quantitatively study the nonlinear synchronous coupling characteristics and information transfer characteristics of rotating machinery fault signals between different frequency scales under the influence of complex and nonlinear interference signals, a new nonlinear signal processing method—the harmonic assisted multivariate empirical mode decomposition method (HA-MEMD)—is proposed in this paper. By adding additional high-frequency harmonic-assisted channels and reducing them, the decomposing precision of the Intrinsic Mode Function (IMF) can be effectively improved, and the phenomenon of mode aliasing can be mitigated. Analysis results of the simulated signals prove the effectiveness of this method. By combining HA-MEMD with the transfer entropy algorithm and introducing signal processing of the rotating machinery, a fault detection method of rotating machinery based on high-frequency harmonic-assisted multivariate empirical mode decomposition-transfer entropy (HA-MEMD-TE) was established. The main features of the mechanical transmission system were extracted by the high-frequency harmonic-assisted multivariate empirical mode decomposition method, and the signal, after noise reduction, was used for the transfer entropy calculation. The evaluation index of the rotating machinery state based on HA-MEMD-TE was established to quantitatively describe the degree of nonlinear coupling between signals to effectively evaluate and diagnose the operating state of the mechanical system. By adding noise to different signal-to-noise ratios, the fault detection ability of HA-MEMD-TE method in the background of strong noise is investigated, which proves that the method has strong reliability and robustness. In this paper, transfer entropy is applied to the fault diagnosis field of rotating machinery, which provides a new effective method for early fault diagnosis and performance degradation-state recognition of rotating machinery, and leads to relevant research conclusions.

A New Method for Discharge State Prediction of Micro-EDM Using Empirical Mode Decomposition

2009 ◽  
Vol 132 (1) ◽  
Author(s):  
Zhenyuan Jia ◽  
Lingxuan Zhang ◽  
Fuji Wang ◽  
Wei Liu
Keyword(s):  
Empirical Mode Decomposition ◽  
Linear Prediction ◽  
Electrical Discharge Machining ◽  
Model Identification ◽  
Prediction Method ◽  
Ar Model ◽  
Micro Edm ◽  
Multisensor Data Fusion ◽  
State Prediction ◽  
Mode Decomposition

The property of high frequency in micro-EDM (electrical discharge machining) causes the discharge states to vary much faster than in conventional EDM, and discharge states of micro-EDM have the characteristics of nonstationarity, nonlinearity, and internal coupling, all of this makes it very difficult to carry out stable control. Thus empirical mode decomposition is adopted to conduct the prediction of the discharge states obtained through multisensor data fusion and fuzzy logic in micro-EDM. Combined with the autoregressive (AR) model identification and linear prediction, the mathematical model for EDM discharge state prediction using empirical mode decomposition is established and the corresponding prediction method is presented. Experiments demonstrate that the new prediction method with short identification data is highly accurate and operates quickly. Even using short model identification data, the accuracy of empirical mode decomposition prediction can stably reach a correlation of 74%, which satisfies statistical expectations. Additionally, the new process can also effectively eliminate the lag of conventional prediction methods to improve the efficiency of micro-EDM, and it provides a good basis to enhance the stability of the control system.

scholarly journals Fault Diagnosis for Rotating Machinery Based on Convolutional Neural Network and Empirical Mode Decomposition

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Yuan Xie ◽  
Tao Zhang
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Spatial Information ◽  
Health Management ◽  
Rotating Machinery ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Mode Decomposition

The analysis of vibration signals has been a very important technique for fault diagnosis and health management of rotating machinery. Classic fault diagnosis methods are mainly based on traditional signal features such as mean value, standard derivation, and kurtosis. Signals still contain abundant information which we did not fully take advantage of. In this paper, a new approach is proposed for rotating machinery fault diagnosis with feature extraction algorithm based on empirical mode decomposition (EMD) and convolutional neural network (CNN) techniques. The fundamental purpose of our newly proposed approach is to extract distinguishing features. Frequency spectrum of the signal obtained through fast Fourier transform process is trained in a designed CNN structure to extract compressed features with spatial information. To solve the nonstationary characteristic, we also apply EMD technique to the original vibration signals. EMD energy entropy is calculated using the first few intrinsic mode functions (IMFs) which contain more energy. With features extracted from both methods combined, classification models are trained for diagnosis. We carried out experiments with vibration data of 52 different categories under different machine conditions to test the validity of the approach, and the results indicate it is more accurate and reliable than previous approaches.

scholarly journals Fault Diagnosis of Rotating Machinery Based on Adaptive Stochastic Resonance and AMD-EEMD

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Peiming Shi ◽  
Cuijiao Su ◽  
Dongying Han
Keyword(s):  
Fault Diagnosis ◽  
Stochastic Resonance ◽  
Empirical Mode Decomposition ◽  
Rolling Bearing ◽  
Ensemble Empirical Mode Decomposition ◽  
Rotating Machinery ◽  
Good Effect ◽  
Resonance System ◽  
Mode Decomposition ◽  
Eemd Method

An adaptive stochastic resonance and analytical mode decomposition-ensemble empirical mode decomposition (AMD-EEMD) method is proposed for fault diagnosis of rotating machinery in this paper. Firstly, the stochastic resonance system is optimized by particle swarm optimization (PSO), and the best structure parameters are obtained. Then, the signal with noise is put into the stochastic resonance system and denoising and enhancing the signal. Secondly, the signal output from the stochastic resonance system is extracted by analytical mode decomposition (AMD) method. Finally, the signal is decomposed by ensemble empirical mode decomposition (EEMD) method. The simulation results show that the optimal stochastic resonance system can effectively improve the signal-to-noise ratio, and the number of effective components of EEMD decomposition is significantly reduced after using AMD, thus improving the decomposition results of EEMD and enhancing the amplitude of components frequency. Through the extraction of the rolling bearing fault signal feature proved that the method has a good effect.

Sign in / Sign up

Export Citation Format

Share Document