Research on aero-engine bearing fault using acoustic emission technique based on wavelet packet decomposition and support vector machine

Li, Haibin; Wu, Zhenhuan; Xue, Kaixuan; Yang, Guoan

doi:10.1109/iaeac.2017.8054252

Cited by 10 publications

(6 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different from STFT [ 19 ] and EMD [ 20 ], wavelet packet decomposition retains the effective local frequency analysis of wavelet decomposition, and further decomposes different frequency ranges to achieve multi-resolution analysis of signals. Li [ 21 ] realized the diagnosis and classification of bearing faults based on wavelet packet decomposition and multi-fault classifiers composed of multiple support vector mechanisms. Wu [ 22 ] combined wavelet packet decomposition and high order cumulant to effectively extract fault features and use principal component analysis algorithm for dimensionality reduction, thus achieving effective identification of rolling bearing fault types.…”

Section: Related Workmentioning

confidence: 99%

Power Equipment Fault Diagnosis Method Based on Energy Spectrogram and Deep Learning

Liu

Guan

et al. 2022

Sensors

View full text Add to dashboard Cite

With the development of industrial manufacturing intelligence, the role of rotating machinery in industrial production and life is more and more important. Aiming at the problems of the complex and changeable working environment of rolling bearings and limited computing ability, fault feature information cannot be effectively extracted, and the current deep learning model is difficult to be compatible with lightweight and high efficiency. Therefore, this paper proposes a fault detection method for power equipment based on an energy spectrum diagram and deep learning. Firstly, a novel two-dimensional time-frequency feature representation method and energy spectrum feature map based on wavelet packet transform is proposed, and an energy spectrum feature map dataset is made for subsequent diagnosis. This method can realize multi-resolution analysis, fully extract the feature information contained in the fault signal, and accelerate the convergence of the subsequent diagnosis model. Secondly, a lightweight residual dense convolutional neural network model (LR-DenseNet) is proposed. This model combines the advantages of residual learning and a dense connection, and can not only extract deep features more easily, but can also effectively use shallow features. Then, based on the lightweight residual dense convolutional neural network model, an LR-DenseSENet model is proposed. By introducing the transfer learning strategy and adding the channel domain, an attention mechanism is added to the channel feature fusion layer, with the accuracy of detection up to 99.4%, and the amount of parameter calculation greatly reduced to one-fifth of that of VGG. Finally, through an experimental analysis, it is verified that the fault detection model designed in this paper based on the combination of an energy spectrum feature map and LR-DenseSENet achieves a satisfactory detection effect.

show abstract

Section: Related Workmentioning

confidence: 99%

Power Equipment Fault Diagnosis Method Based on Energy Spectrogram and Deep Learning

Liu

Guan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…For aerospace-engine rolling bearings, once a failure occurs, it will affect the normal use and cause huge economic losses or even lead to machine damage or casualties at worst. Therefore, equipment condition monitoring and fault diagnosis have become more and more important [2]. For example, an aeroengine is a vibrating system with multiple degrees of freedom, and the vibration of the engine is the response of the system under various exciting forces.…”

Section: Introductionmentioning

confidence: 99%

Early fault diagnosis of rolling bearings based on parameter-adaptive multipoint optimal minimum entropy deconvolution adjusted and dynamic mode decomposition

Xiong¹,

Lv²,

Dang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Fault vibration signals of rolling bearings in early stages are affected by complex transmission paths and strong background noise, resulting in weak information about fault characteristics, which is difficult to extract clearly and accurately. To this end, a new diagnosis method for early faults of rolling bearings is proposed. First, the parameter-adaptive multipoint optimal minimum entropy deconvolution adjusted (PA-MOMEDA) algorithm is used to preprocess the fault signals by strengthening their shock components and weakening the influence of noise on their results. Second, the maximum envelope-spectrum characteristic energy ratio is employed as the selection criterion for the optimal truncation order of dynamic mode decomposition (DMD) to decompose and reconstruct the signals. Finally, the processed signals are subjected to the Hilbert envelope spectral transformation to accurately extract early fault characteristic frequencies. An analysis of simulated signals, public database signals, and bearing signals from a wind turbine has shown that the proposed PA-MOMEDA–DMD method can successfully extract the early fault characteristics of rolling bearings. Compared with the traditional pattern decomposition algorithms, the proposed method is much better at extracting fault characteristics and diagnosing early faults of rolling bearings. The facts have proved that the proposed method is promising in engineering applications.

show abstract

“…Condition monitoring and fault diagnosis have become urgent problems. 1 Structural health monitoring (SHM) means that the inspectors can use the non-destructive detection monitoring methods on the premise of not damaging the basic performance of the structure itself and ensuring the structural integrity. During the SHM, the status information inside the structure is first monitored online, real-time, and continuously; then, the system characteristics and monitoring signals are identified and analyzed to automatically reflect whether the monitoring structures have damages or not.…”

Section: Introductionmentioning

confidence: 99%

A method of acoustic emission source location for engine fault based on time difference matrix

Liu

Han

Wang

et al. 2022

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

The structure of a high-performance engine is becoming more and more complex, so it is very important to accurately and quickly locate the faults to ensure its operation safety. The acoustic emission (AE) signal which is caused by the structural damage of engines contains important structural integrity information; however, the accuracy of existing AE location methods is affected by complex structures, such as stiffeners, holes, variable wall thickness, and interface coupling. Therefore, this paper proposes a new AE source location method that combines the two-step Akaike information criterion (AIC) based on the dispersion curve and the time difference matrix (TDM). This method can precisely locate the faults of complex structures without considering the wave velocity. Through theoretical calculation and numerical simulation, this paper intends to show that the proposed method is superior to the traditional AIC and can track the arrival time of the AE signal more accurately. In addition, experiments on different structures illustrate that the proposed method has higher location accuracy in complex structures. This paper also analyzes the location sensitivity to the number and array of sensors in a complex structure and puts forward an optimal scheme of sensor layout on the condition of high location accuracy. The results show that the proposed method can be used as a reliable tool for AE source location and fault monitoring of complex structures. It will have a wide application prospect in the engine and other fields.

show abstract

Research on aero-engine bearing fault using acoustic emission technique based on wavelet packet decomposition and support vector machine

Cited by 10 publications

References 3 publications

Power Equipment Fault Diagnosis Method Based on Energy Spectrogram and Deep Learning

Power Equipment Fault Diagnosis Method Based on Energy Spectrogram and Deep Learning

Early fault diagnosis of rolling bearings based on parameter-adaptive multipoint optimal minimum entropy deconvolution adjusted and dynamic mode decomposition

A method of acoustic emission source location for engine fault based on time difference matrix

Contact Info

Product

Resources

About