scholarly journals Bearing Condition Recognition and Degradation Assessment under Varying Running Conditions Using NPE and SOM

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Shaohui Zhang ◽  
Weihua Li
Keyword(s):  
Feature Space ◽  
Vibration Signal ◽  
Fault Classification ◽  
Self Organizing Map ◽  
Performance Simulation ◽  
Rotating Machine ◽  
Time Domain Signal ◽  
Machine Condition Monitoring ◽  
Signal Features ◽  
Simulation And Experiment

Manifold learning methods have been widely used in machine condition monitoring and fault diagnosis. However, the results reported in these studies focus on the machine faults under stable loading and rotational speeds, which cannot interpret the practical machine running. Rotating machine is always running under variable speeds and loading, which makes the vibration signal more complicated. To address such concern, the NPE (neighborhood preserving embedding) is applied for bearing fault classification. Compared with other algorithms (PCA, LPP, LDA, and ISOP), the NPE performs well in feature extraction. Since the traditional time domain signal denoising is time consuming and memory consuming, we denoise the signal features directly in feature space. Furthermore, NPE and SOM (self-organizing map) are combined to assess the bearing degradation performance. Simulation and experiment results validate the effectiveness of the proposed method.

scholarly journals Fault Diagnosis for Rolling Element Bearings Based on Feature Space Reconstruction and Multiscale Permutation Entropy

Entropy ◽  
2019 ◽  
Vol 21 (5) ◽  
pp. 519 ◽  
Author(s):  
Weibo Zhang ◽  
Jianzhong Zhou
Keyword(s):  
Diagnostic Algorithm ◽  
Feature Space ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Ensemble Empirical Mode Decomposition ◽  
Classification Performance ◽  
Fault Classification ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions

Aimed at distinguishing different fault categories of severity of rolling bearings, a novel method based on feature space reconstruction and multiscale permutation entropy is proposed in the study. Firstly, the ensemble empirical mode decomposition algorithm (EEMD) was employed to adaptively decompose the vibration signal into multiple intrinsic mode functions (IMFs), and the representative IMFs which contained rich fault information were selected to reconstruct a feature vector space. Secondly, the multiscale permutation entropy (MPE) was used to calculate the complexity of reconstructed feature space. Finally, the value of multiscale permutation entropy was presented to a support vector machine for fault classification. The proposed diagnostic algorithm was applied to three groups of rolling bearing experiments. The experimental results indicate that the proposed method has better classification performance and robustness than other traditional methods.

scholarly journals Bearing Fault Diagnosis Using a Grad-CAM-Based Convolutional Neuro-Fuzzy Network

Mathematics ◽  
2021 ◽  
Vol 9 (13) ◽  
pp. 1502
Author(s):  
Cheng-Jian Lin ◽  
Jyun-Yu Jhang
Keyword(s):  
Machine Tool ◽  
Vibration Signal ◽  
Fault Classification ◽  
Current Status ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Signal Features ◽  
Neuro Fuzzy ◽  
Long Time ◽  
Fuzzy Network

When a machine tool is used for a long time, its bearing experiences wear and failure due to heat and vibration, resulting in damage to the machine tool. In order to make the machine tool stable for processing, this paper proposes a smart bearing diagnosis system (SBDS), which uses a gradient-weighted class activation mapping (Grad-CAM)-based convolutional neuro-fuzzy network (GC-CNFN) to detect the bearing status of the machine tool. The developed GC-CNFN is composed of a convolutional layer and neuro-fuzzy network. The convolutional layer can automatically extract vibration signal features, which are then classified using the neuro-fuzzy network. Moreover, Grad-CAM is used to analyze the attention of the diagnosis model. To verify the performance of bearing fault classification, the 1D CNN (ODCNN) and improved 1D LeNet-5 (I1DLeNet) were adopted to compare with the proposed GC-CNFN. Experimental results showed that the proposed GC-CNFN required fewer parameters (20K), had a shorter average calculation time (117.7 s), and had a higher prediction accuracy (99.88%) in bearing fault classification. The proposed SBDS can not only accurately classify bearing faults, but also help users understand the current status of the machine tool.

scholarly journals Performance Improvement of Classifier in Fault Diagnosis of Rotating Machines Using Sensor Fusion Techniques

2019 ◽  
Vol 8 (6) ◽  
pp. 1136-1141
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Sensor Fusion ◽  
Feature Fusion ◽  
Learning Algorithm ◽  
Vibration Signal ◽  
Fault Classification ◽  
Rotating Machines ◽  
Rotating Machine ◽  
Vibration Signal Analysis

The shaft, rotor, bearing and gear are the important elements of the rotating machines. Most of the problems in rotating machines are caused due to bearings and shaft. The failure of rotating machine causes production downtime and economic & safety issues. Vibration signal analysis is highly accepted technique in fault diagnosis of rotating machine. For automation of fault diagnosis, machine learning approach has been followed. Machine learning classifies fault based on variation in signatures pattern of the machine. But its effectiveness gets reduced when it is used for multi fault class problem. So in the present work, sound signals are also used along with vibration signals for applying sensor fusion techniques. In sensor fusion, signals from various sensors are fused in three levels such as data fusion, feature fusion and decision level fusion and the fused data sets are used for fault classification using machine learning algorithm. The performance of each technique is studied in detail and compared using classification accuracy. A new method is proposed by combination of fusion techniques to enhance the performance

scholarly journals Fault Detection through Vibration Signal Analysis based on HSM with TRIPPY Classifier

2020 ◽  
Vol 14 ◽  
Keyword(s):  
Fault Detection ◽  
Vibration Signal ◽  
Crest Factor ◽  
Detection Model ◽  
Rotating Machine ◽  
Good Path ◽  
Signal Features ◽  
Vibration Signal Analysis ◽  
Learned Features

A proficient fault detection model has to be sketched for detecting slight variations of the vibrating signal of rotating machine whereas the diagnosis process prominently stuck with the inefficient extraction of effectual features of a signal in reduced time. Existence of above stated hilarious issue results in the confinement of inventive Harmonized Swan Machine (HSM) based on the stochastic characteristics of swan, which could collect the RKC (RMS, Kurtosis, Crest factor) signal features for every instantaneous signal unit which eliminates noise thereby reducing pre-processing task which in turn lessens time consumption and at the end yields learned extracted faulty features. Accurate classification of faulty features can be accomplished by casting inimitable Trippy classifier which is designed based on selective predictive character of trippy fish which provokes a good path to provide accurate classification based on learned features. This responsible classifier collectively organises the RKC features of respective signal units and do accurate classification of faulty occurrences based on the features in less time.

An adaptive multiple time domain synchronous averaging method and its application in vibration signal feature enhancement

2021 ◽  
Author(s):  
Na Yin ◽  
Zong Meng ◽  
Yang Guan ◽  
Fengjie Fan
Keyword(s):  
Time Domain ◽  
Feature Detection ◽  
Vibration Signal ◽  
Rolling Bearing ◽  
Difficult Problem ◽  
Multiple Time ◽  
Denoising Method ◽  
Time Domain Signal ◽  
Signal Features ◽  
The Time Domain

Abstract The time domain synchronous averaging (TSA) method is a typical time domain signal denoising method, which is widely used in the state detection of rotating machinery. In order to solve the difficult problem of extracting vibration signal features from strong interference, an adaptive multiple time domain synchronous averaging(aMTSA) method based on signal period is proposed in this paper. In view of the blindness and randomness of period selection in TSA method, a new evaluation index of periodic impulse characteristics is proposed. In this method, the signal is resampled then the iteration stop threshold is set, and then the calculation period of interest is determined by two cycle screening. Finally, reconstructed signals with enhanced features are obtained by copying and stitching. Experimental results show that the proposed method is robust and superior in the feature detection of rolling bearing vibration signals.

scholarly journals Bearing Fault Classification Using Ensemble Empirical Mode Decomposition and Convolutional Neural Network

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1248
Author(s):  
Rafia Nishat Toma ◽  
Cheol-Hong Kim ◽  
Jong-Myon Kim
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Empirical Mode Decomposition ◽  
Vibration Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Fault Classification ◽  
Original Signal ◽  
Time Frequency ◽  
Mode Decomposition ◽  
Reconstructed Signal

Condition monitoring is used to track the unavoidable phases of rolling element bearings in an induction motor (IM) to ensure reliable operation in domestic and industrial machinery. The convolutional neural network (CNN) has been used as an effective tool to recognize and classify multiple rolling bearing faults in recent times. Due to the nonlinear and nonstationary nature of vibration signals, it is quite difficult to achieve high classification accuracy when directly using the original signal as the input of a convolution neural network. To evaluate the fault characteristics, ensemble empirical mode decomposition (EEMD) is implemented to decompose the signal into multiple intrinsic mode functions (IMFs) in this work. Then, based on the kurtosis value, insignificant IMFs are filtered out and the original signal is reconstructed with the rest of the IMFs so that the reconstructed signal contains the fault characteristics. After that, the 1-D reconstructed vibration signal is converted into a 2-D image using a continuous wavelet transform with information from the damage frequency band. This also transfers the signal into a time-frequency domain and reduces the nonstationary effects of the vibration signal. Finally, the generated images of various fault conditions, which possess a discriminative pattern relative to the types of faults, are used to train an appropriate CNN model. Additionally, with the reconstructed signal, two different methods are used to create an image to compare with our proposed image creation approach. The vibration signal is collected from a self-designed testbed containing multiple bearings of different fault conditions. Two other conventional CNN architectures are compared with our proposed model. Based on the results obtained, it can be concluded that the image generated with fault signatures not only accurately classifies multiple faults with CNN but can also be considered as a reliable and stable method for the diagnosis of fault bearings.

Decoupling Control for Bearingless Synchronous Reluctance Motor Based on Neural Networks Inverse

2012 ◽  
Vol 150 ◽  
pp. 30-35
Author(s):  
Ze Bin Yang ◽  
Huang Qiu Zhu ◽  
Xiao Dong Sun ◽  
Tao Zhang
Keyword(s):  
Neural Networks ◽  
Control Method ◽  
Decoupling Control ◽  
Performance Simulation ◽  
Inverse Control ◽  
Linear Control Theory ◽  
Synchronous Reluctance Motor ◽  
Reluctance Motor ◽  
Static Performance ◽  
Simulation And Experiment

A novel decoupling control method based on neural networks inverse system is presented in this paper for a bearingless synchronous reluctance motor (BSRM) possessing the characteristics of multi-input-multi-output, nonlinearity, and strong coupling. The dynamic mathematical models are built, which are verified to be invertible. A controller based on neural network inverse is designed, which decouples the original nonlinear system to two linear position subsystems and an angular velocity subsystem. Furthermore, the linear control theory is applied to closed-loop synthesis to meet the desired performance. Simulation and experiment results show that the presented neural networks inverse control strategy can realize the dynamic decoupling of BSRM, and that the control system has fine dynamic and static performance.

Parametric Description of Vibration Using the Autocorrelation Function

2009 ◽  
Vol 147-149 ◽  
pp. 606-611
Author(s):  
Adam Kotowski
Keyword(s):  
Autocorrelation Function ◽  
Curve Fitting ◽  
Vibration Signal ◽  
Analytic Form ◽  
Parametric Representation ◽  
Rotating Machine ◽  
Fitting Procedure ◽  
Power Spectral ◽  
Parametric Description ◽  
Harmonic Components

The paper presents the use of the autocorrelation function for the description of vibrations and the problems connected with. The proposed method is based on the analysis of vibration signal recorded for machine during its operations using an analytic form of the autocorrelation function. The parameters are obtained using a curve fitting procedure. To keep a quality of parametric representation of considered vibration, only the curve fitting causes a determination coefficient over 0.90 is taken into consideration. Therefore, the autocorrelation functions are submitted for the fast Fourier transform to be helped, in determination of number of the dominant harmonic components. Also, the analytic form and parameters of power spectral density has been also calculated. Finally, the set of parameters has been collected to describe the selected fragment of vibration of the simple rotating machine. The influence of duration of analyzed vibration on the parameters values is also examined in this work.

Research of the Vertical Vibrations of Tandem Mill Based on Wavelet Analysis

2015 ◽  
Vol 724 ◽  
pp. 279-282
Author(s):  
Chun Hua Ren ◽  
Xu Ma ◽  
Ze Ming Li ◽  
Yan Hong Ding
Keyword(s):  
Wavelet Analysis ◽  
Wavelet Decomposition ◽  
Vibration Signal ◽  
Vertical Vibration ◽  
Rolling Speed ◽  
Vibration Data ◽  
Signal Features ◽  
Operating Side ◽  
Vertical Vibrations ◽  
Vibration Parameters

In this paper, the defect sheet was captured coincidentally. According to the defective product’s characteristics, we suspected to be caused by the vertical vibration of the roll. When the rolling speed reached a certain value, the vibration of the fourth stand can be feel. The experiment of the vibration data collection was taken to compare the vibration parameters of rolling operating side with those of drive side by wavelet analysis. The result states that the abnormal vibration signal features can be extracted in a special frequency segment of wavelet decomposition, and the vibration frequency to the roll is confirmed which appeared product defects.

Sign in / Sign up

Export Citation Format

Share Document