scholarly journals Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Xinghua Huang ◽  
Yuanyuan Li ◽  
Yi Chai
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbines ◽  
Feature Fusion ◽  
Positive Role ◽  
Planetary Gearbox ◽  
Time Frequency ◽  
Multi Scale ◽  
Average Accuracy ◽  
Fault Features ◽  
Ablation Study

Due to the powerful capability of feature extraction, convolutional neural network (CNN) is increasingly applied to the fault diagnosis of key components of rotating machineries. Due to the shortcomings of traditional CNN-based fault diagnosis methods, the continuous convolution and pooling operations result in the constant decrease of feature resolution, which may cause the loss of some subtle fault information in the samples. This paper proposes a CNN-based model with improved structure multi-scale dense fusion network (MSDFN) to realize the fault diagnosis of wind turbines planetary gearboxes under complicated working conditions. First, the continuous wavelet transform is applied to preprocess the vibration signals, and the two-dimensional wavelet time-frequency diagrams are used as the network input. Then, the multi-scale feature fusion (MSFF) module and a feature of maximum (FoM) module are used in the extraction and classification stages of fault features, respectively. Next, the multi-scale features of each network layer are fused to enhance the fault features. Finally, the high fault diagnosis accuracy is achieved by extracting the separable fusion result of fault features. The proposed method achieves more than 99% fault diagnosis average accuracy on a planetary gearbox dataset. The comparative experimental results verify the effectiveness of the proposed method and its superiority to some mainstream approaches. The ablation study further confirms that MSFF module and FoM module play the positive role in fault diagnosis.

scholarly journals A New Method of Two-stage Planetary Gearbox Fault Detection Based on Multi-Sensor Information Fusion

2019 ◽  
Vol 9 (24) ◽  
pp. 5443 ◽  
Author(s):  
Zhe Wu ◽  
Qiang Zhang ◽  
Lifeng Cheng ◽  
Shengyue Tan
Keyword(s):  
Fault Diagnosis ◽  
Wind Turbines ◽  
Planetary Gear ◽  
Energy Operator ◽  
New Method ◽  
Signal Spectrum ◽  
Strong Nonlinearity ◽  
Planetary Gearbox ◽  
Time Frequency ◽  
Full Vector

Due to their high transmission ratio, high load carrying capacity and small size, planetary gears are widely used in the transmission systems of wind turbines. The planetary gearbox is the core of the transmission system of a wind turbine, but because of its special structure and complex internal and external excitation, the vibration signal spectrum shows strong nonlinearity, asymmetry and time variation, which brings great trouble to planetary gear fault diagnosis. The traditional time-frequency analysis technology is insufficient in the condition monitoring and fault diagnosis of wind turbines. For this reason, we propose a new method of planetary gearbox fault diagnosis based on Compressive sensing, Two-dimensional variational mode decomposition (2D-VMD) and full-vector spectrum technology. Firstly, the nonlinear reconstruction and noise reduction of the signal is carried out by using compressed sensing, and then the signal with multiple degrees of freedom is adaptively decomposed into multiple sets of characteristic scale components by using 2D-VMD. Then, Rényi entropy is used as the optimization index of 2D-VMD analysis performance to extract the effective target intrinsic mode function (IMF) component, reconstruct the dynamics signal in the planetary gearbox, and improve the signal-to-noise ratio. Then, using the full-vector spectrum technique, the homologous information collected by numerous sensors is data layer fused in the spatial domain and the time domain to increase the comprehensiveness and certainty of the fault information. Finally, the Teager–Kaiser energy operator is used to demodulate the potential low-frequency dynamics frequency characteristics from the high-frequency domain and detect the fault characteristic frequency. Furthermore, the correctness and validity of the method are verified by the fault test signal of the planetary gearbox.

scholarly journals Multi-Scale Demodulation for Fault Diagnosis Based on a Weighted-EMD De-Noising Technique and Time–Frequency Envelope Analysis

2020 ◽  
Vol 10 (21) ◽  
pp. 7796 ◽  
Author(s):  
Wei-tao Du ◽  
Qiang Zeng ◽  
Yi-min Shao ◽  
Li-ming Wang ◽  
Xiao-xi Ding
Keyword(s):  
Fault Diagnosis ◽  
Signal To Noise Ratio ◽  
Fast Fourier Transformation ◽  
Intrinsic Mode Functions ◽  
Envelope Analysis ◽  
Planetary Gearbox ◽  
Time Frequency ◽  
Multi Scale ◽  
Mode Decomposition ◽  
Envelope Signal

Demodulation is one of the most useful techniques for the fault diagnosis of rotating machinery. The commonly used demodulation methods try to select one sensitive sub-band signal that contains the most fault-related components for further analysis. However, a large number of the fault-related components that exist in other sub-bands are ignored in the commonly used envelope demodulation methods. Based on a weighted-empirical mode decomposition (EMD) de-noising technique and time–frequency (TF) impulse envelope analysis, a multi-scale demodulation method is proposed for fault diagnosis. In the proposed method, EMD is first employed to divide the signal into some IMFs (intrinsic mode functions). Then, a new weighted-EMD de-noising technique is presented, and different weights are assigned to IMFs for construction according to their fault-related degrees; thus, the fault-unrelated components are suppressed to improve the signal-to-noise ratio (SNR). After that, continuous wavelet transformation (CWT) is adopted to obtain the time–frequency representation (TFR) of the de-noised signal. Subsequently, the fault-related components in the entire frequency range scale are calculated together, referring to the TF impulse envelope signal. Finally, a fault diagnosis result can be obtained after the fast Fourier transformation of the TF impulse envelope signal. The proposed method and three commonly used methods are applied to the fault diagnosis of a planetary gearbox with a sun gear spalling fault and a fixed shaft gearbox with a crack fault. The results show that the proposed method can effectively detect gear faults and yields better performance than other methods.

Current-Aided Time-Frequency Analysis of Vibration Signals for Gearbox Fault Diagnosis

2018 ◽  
Author(s):  
Xiaotong Tu ◽  
Yue Hu ◽  
Fucai Li
Keyword(s):  
Fault Diagnosis ◽  
Frequency Analysis ◽  
Vibration Signal ◽  
Vibration Monitoring ◽  
Current Signal ◽  
Reliable Technique ◽  
Time Frequency Analysis ◽  
Rotating Speed ◽  
Planetary Gearbox ◽  
Time Frequency

Vibration monitoring is an effective method for mechanical fault diagnosis. Wind turbines usually operated under varying-speed condition. Time-frequency analysis (TFA) is a reliable technique to handle such kind of nonstationary signal. In this paper, a new scheme, called current-aided TFA, is proposed to diagnose the planetary gearbox. This new technique acquires necessary information required by TFA from a current signal. The current signal is firstly used to estimate the rotating speed of the shaft. These parameters are applied to the demodulation transform to obtain a rough time-frequency distribution (TFD). Finally, the synchrosqueezing method further enhances the concentration of the obtained TFD. The validation and application of the proposed method are presented by a simulated signal and a vibration signal captured from a test rig.

scholarly journals Research on Multi-Domain Fault Diagnosis of Gearbox of Wind Turbine Based on Adaptive Variational Mode Decomposition and Extreme Learning Machine Algorithms

Energies ◽  
2020 ◽  
Vol 13 (6) ◽  
pp. 1375 ◽  
Author(s):  
Hui Li ◽  
Bangji Fan ◽  
Rong Jia ◽  
Fang Zhai ◽  
Liang Bai ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Grey Wolf Optimizer ◽  
Mechanical Equipment ◽  
Variational Mode Decomposition ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Fault Features ◽  
Frequency Domains ◽  
Learning Machine

Since variational mode decomposition (VMD) was proposed, it has been widely used in condition monitoring and fault diagnosis of mechanical equipment. However, the parameters K and α in the VMD algorithm need to be set before decomposition, which causes VMD to be unable to decompose adaptively and obtain the best result for signal decomposition. Therefore, this paper optimizes the VMD algorithm. On this basis, this paper also proposes a method of multi-domain feature extraction of signals and combines an extreme learning machine (ELM) to realize comprehensive and accurate fault diagnosis. First, VMD is optimized according to the improved grey wolf optimizer; second, the feature vectors of the time, frequency, and time-frequency domains are calculated, which are synthesized after dimensionality reduction; ultimately, the synthesized vectors are input into the ELM for training and classification. The experimental results show that the proposed method can decompose the signal adaptively, which produces the best decomposition parameters and results. Moreover, this method can extract the fault features of the signal more completely to realize accurate fault identification.

scholarly journals SAR Ship Detection Based on Improved Libra RetinaNet

2021 ◽  
Author(s):  
Haomiao Liu ◽  
Haizhou Xu ◽  
Lei Zhang ◽  
Weigang Lu ◽  
Fei Yang ◽  
...  
Keyword(s):  
Feature Fusion ◽  
Weather Conditions ◽  
Maritime Transportation ◽  
Detection Methods ◽  
Sar Images ◽  
Style Transfer ◽  
Ship Detection ◽  
Multi Scale ◽  
Optical Images ◽  
Average Accuracy

Maritime ship monitoring plays an important role in maritime transportation. Fast and accurate detection of maritime ship is the key to maritime ship monitoring. The main sources of marine ship images are optical images and synthetic aperture radar (SAR) images. Different from natural images, SAR images are independent to daylight and weather conditions. Traditional ship detection methods of SAR images mainly depend on the statistical distribution of sea clutter, which leads to poor robustness. As a deep learning detector, RetinaNet can break this obstacle, and the problem of imbalance on feature level and objective level can be further solved by combining with Libra R-CNN algorithm. In this paper, we modify the feature fusion part of Libra RetinaNet by adding a bottom-up path augmentation structure to better preserve the low-level feature information, and we expand the dataset through style transfer. We evaluate our method on the publicly available SAR dataset of ship detection with complex backgrounds. The experimental results show that the improved Libra RetinaNet can effectively detect multi-scale ships through expansion of the dataset, with an average accuracy of 97.38%.

Sign in / Sign up

Export Citation Format

Share Document