scholarly journals Multi-Stage Feature Selection by Using Genetic Algorithms for Fault Diagnosis in Gearboxes Based on Vibration Signal

Sensors ◽  
2015 ◽  
Vol 15 (9) ◽  
pp. 23903-23926 ◽  
Author(s):  
Mariela Cerrada ◽  
René Sánchez ◽  
Diego Cabrera ◽  
Grover Zurita ◽  
Chuan Li
Keyword(s):  
Genetic Algorithms ◽  
Feature Selection ◽  
Fault Diagnosis ◽  
Vibration Signal ◽  
Multi Stage

scholarly journals A Novel Mechanical Fault Feature Selection and Diagnosis Approach for High-Voltage Circuit Breakers Using Features Extracted without Signal Processing

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 288 ◽  
Author(s):  
Lin Lin ◽  
Bin Wang ◽  
Jiajin Qi ◽  
Lingling Chen ◽  
Nantian Huang
Keyword(s):  
Signal Processing ◽  
Feature Extraction ◽  
Feature Selection ◽  
Fault Diagnosis ◽  
High Voltage ◽  
Vibration Signal ◽  
Circuit Breakers ◽  
Optimal Subset ◽  
Fault Type ◽  
Diagnosis Approach

The reliability and performance of high-voltage circuit breakers (HVCBs) will directly affect the safety and stability of the power system itself, and mechanical failures of HVCBs are one of the important factors affecting the reliability of circuit breakers. Moreover, the existing fault diagnosis methods for circuit breakers are complex and inefficient in feature extraction. To improve the efficiency of feature extraction, a novel mechanical fault feature selection and diagnosis approach for high-voltage circuit breakers, using features extracted without signal processing is proposed. Firstly, the vibration signal of the HVCBs’ operating system, which collects the amplitudes of signals from normal vibration signals, is segmented by a time scale, and obviously changed. Adopting the ensemble learning method, features were extracted from each part of the divided signal, and used for constructing a vector. The Gini importance of features is obtained by random forest (RF), and the feature is ranked by the features’ importance index. After that, sequential forward selection (SFS) is applied to determine the optimal subset, while the regularized Fisher’s criterion (RFC) is used to analyze the classification ability. Then, the optimal subset is input to the hierarchical hybrid classifier, and based on a one-class support vector machine (OCSVM) and RF for fault diagnosis, the state is accurately recognized by OCSVM. The known fault types are identified using RF, and the identification results are calibrated with OCSVM of a particular fault type. The experimental proves that the new method has high feature extraction efficiency and recognition accuracy by the measured HVCBs vibration signal, while the unknown fault type data of the untrained samples is effectively identified.

scholarly journals Extraction of local and global features by a convolutional neural network–long short-term memory network for diagnosing bearing faults

2021 ◽  
pp. 095440622110165
Author(s):  
Zhang Chao ◽  
Wang Wei-zhi ◽  
Zhang Chen ◽  
Fan Bin ◽  
Wang Jian-guo ◽  
...  
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Short Term Memory ◽  
Vibration Signal ◽  
Short Term ◽  
Global Features ◽  
Term Memory ◽  
Long Short Term Memory ◽  
Lstm Network

Accurate and reliable fault diagnosis is one of the key and difficult issues in mechanical condition monitoring. In recent years, Convolutional Neural Network (CNN) has been widely used in mechanical condition monitoring, which is also a great breakthrough in the field of bearing fault diagnosis. However, CNN can only extract local features of signals. The model accuracy and generalization of the original vibration signals are very low in the process of vibration signal processing only by CNN. Based on the above problems, this paper improves the traditional convolution layer of CNN, and builds the learning module (local feature learning block, LFLB) of the local characteristics. At the same time, the Long Short-Term Memory (LSTM) is introduced into the network, which is used to extract the global features. This paper proposes the new neural network—improved CNN-LSTM network. The extracted deep feature is used for fault classification. The improved CNN-LSTM network is applied to the processing of the vibration signal of the faulty bearing collected by the bearing failure laboratory of Inner Mongolia University of science and technology. The results show that the accuracy of the improved CNN-LSTM network on the same batch test set is 98.75%, which is about 24% higher than that of the traditional CNN. The proposed network is applied to the bearing data collection of Western Reserve University under the condition that the network parameters remain unchanged. The experiment shows that the improved CNN-LSTM network has better generalization than the traditional CNN.

scholarly journals Fault Diagnosis of a Helical Gearbox Based on an Adaptive Empirical Wavelet Transform in Combination with a Spectral Subtraction Method

2019 ◽  
Vol 9 (8) ◽  
pp. 1696 ◽  
Author(s):  
Wang ◽  
Lee
Keyword(s):  
Wavelet Transform ◽  
Fault Diagnosis ◽  
Background Noise ◽  
Vibration Signal ◽  
Spectral Subtraction ◽  
Accurate Identification ◽  
Side Band ◽  
Empirical Wavelet Transform ◽  
Gear Fault ◽  
Fault Characteristic

Fault characteristic extraction is attracting a great deal of attention from researchers for the fault diagnosis of rotating machinery. Generally, when a gearbox is damaged, accurate identification of the side-band features can be used to detect the condition of the machinery equipment to reduce financial losses. However, the side-band feature of damaged gears that are constantly disturbed by strong jamming is embedded in the background noise. In this paper, a hybrid signal-processing method is proposed based on a spectral subtraction (SS) denoising algorithm combined with an empirical wavelet transform (EWT) to extract the side-band feature of gear faults. Firstly, SS is used to estimate the real-time noise information, which is used to enhance the fault signal of the helical gearbox from a vibration signal with strong noise disturbance. The empirical wavelet transform can extract amplitude-modulated/frequency-modulated (AM-FM) components of a signal using different filter bands that are designed in accordance with the signal properties. The fault signal is obtained by building a flexible gear for a helical gearbox with ADAMS software. The experiment shows the feasibility and availability of the multi-body dynamics model. The spectral subtraction-based adaptive empirical wavelet transform (SS-AEWT) method was applied to estimate the gear side-band feature for different tooth breakages and the strong background noise. The verification results show that the proposed method gives a clearer indication of gear fault characteristics with different tooth breakages and the different signal-noise ratio (SNR) than the conventional EMD and LMD methods. Finally, the fault characteristic frequency of a damaged gear suggests that the proposed SS-AEWT method can accurately and reliably diagnose faults of a gearbox.

Improved Local Mean Decomposition and its Application to Fault Diagnosis of Train Bearing

2013 ◽  
Vol 819 ◽  
pp. 155-159
Author(s):  
Peng Wang ◽  
Huai Xiang Ma
Keyword(s):  
Fault Diagnosis ◽  
Vibration Signal ◽  
Processing Method ◽  
Nonstationary Signal ◽  
Practical Application ◽  
Local Mean Decomposition ◽  
Signal Processing Method ◽  
Signal Demodulation ◽  
Improvement Method ◽  
Local Mean

Fault diagnosis of train bearing is an important method to ensure the security of railway. The key to the fault diagnosis is the method of vibration signal demodulation. The local mean decomposition (LMD) is a self-adapted signal processing method which has a good performance in nonlinear nonstationary signal demodulation. The improved LMD method based on kurtosis criterion can prevent errors in the process of calculating the product functions. With the verification of simulation and wheel set experiment, the improvement method has been certified usefully in practical application.

Sign in / Sign up

Export Citation Format

Share Document