Intelligent Fault Diagnosis Model for Rotating Machinery Based on Fusion of Sound Signals

The failure of rotating machine elements causes unnecessary downtime of the machine. Fault in the rotating machinery can be identified from noises, vibration signals obtained from sensors. Bearing and shaft are the most important basic rotating machine elements. Detection of fault from vibration signals is widely used method in condition monitoring techniques for diagnosis of machine elements. Fault diagnosis from sound signals is cost effective than vibration signals. Sound signal analysis is not well explored in the field of automated fault diagnosis. Under various simulated fault conditions, the sound signals are obtained by placing microphone near the bearing for different speeds. The features are extracted by using statistical and histogram methods. The best features of sound signals are obtained by decision tree algorithm. The extracted features are used as inputs to the classifier-Artificial Neural Network. The classification accuracy results from statistical and histogram features are obtained and compared.

Download Full-text

Fault Diagnosis of Rotating Machinery Based on One-Dimensional Deep Residual Shrinkage Network with a Wide Convolution Layer

Shock and Vibration ◽

10.1155/2020/8880960 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Jingli Yang ◽

Tianyu Gao ◽

Shouda Jiang ◽

Shijie Li ◽

Qing Tang

Keyword(s):

Fault Diagnosis ◽

Noise Immunity ◽

Rotating Machinery ◽

Experimental Results ◽

Vibration Signals ◽

One Dimensional ◽

Noise Interference ◽

Diagnosis Method ◽

Diagnosis Model ◽

Short Time

In actual engineering applications, inevitable noise seriously affects the accuracy of fault diagnosis for rotating machinery. To effectively identify the fault classes of rotating machinery under noise interference, an efficient fault diagnosis method without additional denoising procedures is proposed. First, a one-dimensional deep residual shrinkage network, which directly takes the raw vibration signals contaminated by noise as input, is developed to realize end-to-end fault diagnosis. Then, to further enhance the noise immunity of the diagnosis model, the first layer of the model is set to a wide convolution layer to extract short time features. Moreover, an adaptive batch normalization algorithm (AdaBN) is introduced into the diagnosis model to enhance the adaptability to noise. Experimental results illustrate that the fault diagnosis model for rotating machinery based on one-dimensional deep residual shrinkage network with a wide convolution layer (1D-WDRSN) can accurately identify the fault classes even under noise interference.

Download Full-text

Fault Classification Model of Rotor Based on Support Vector Machine

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.66-68.1982 ◽

2011 ◽

Vol 66-68 ◽

pp. 1982-1987

Author(s):

Wei Niu ◽

Guo Qing Wang ◽

Zheng Jun Zhai ◽

Juan Cheng

Keyword(s):

Support Vector Machine ◽

Fault Diagnosis ◽

Rotating Machinery ◽

Classification Model ◽

Fault Classification ◽

Support Vector ◽

Vibration Signals ◽

Good Classification ◽

Speed Change ◽

Diagnosis Model

The vibration signals of rotating machinery in operation consist of plenty of information about its running condition, and extraction and identification of fault signals in the process of speed change are necessary for the fault diagnosis of rotating machinery. This paper improves DDAG classification method and proposes a new fault diagnosis model based on support vector machine to solve the problem of restricting the rotating machinery fault intelligent diagnosis due to the lack of fault data samples. The testing results demonstrate that the model has good classification precision and can correctly diagnose faults.

Download Full-text

A dual sensor signal fusion approach for detection of faults in rotating machines

Journal of Vibration and Control ◽

10.1177/1077546316689644 ◽

2017 ◽

Vol 24 (12) ◽

pp. 2621-2630 ◽

Cited By ~ 3

Author(s):

M Saimurugan ◽

R Ramprasad

Keyword(s):

Fault Diagnosis ◽

Decision Tree ◽

Signal Analysis ◽

Vibration Signal ◽

Rotating Machinery ◽

Sound Signal ◽

Maintenance Strategy ◽

Decision Tree Algorithm ◽

Tree Algorithm ◽

Signal Fusion

The growing industrial sector utilizes machinery that needs to be monitored continuously by proficient experts and robust software to ensure a proper maintenance strategy. Condition monitoring using vibration signal analysis is one of the chief methods used in predictive maintenance strategy for rotating machinery. Generally, sound signal analysis is considered as secondary as it involves noise. In this paper, the signals for various rotating machinery faults are studied by simulating them in a machine fault simulator at various speeds and the best features are fused to obtain more efficiency in the fault diagnosis of rotating machinery. The vibration signal data obtained from accelerometers and sound signal data from a microphone is extracted for features using wavelet transform. The best features from vibration and sound signals are selected using the decision tree algorithm and are fused. Further, the features are classified using an artificial neural network and the corresponding efficiency at various motor speeds is found. The results of this paper imply that the signal fusion of vibration and sound by the decision tree algorithm is effective in machine fault diagnosis methodologies.

Download Full-text

Application of Deep Learning in Fault Diagnosis of Rotating Machinery

Processes ◽

10.3390/pr9060919 ◽

2021 ◽

Vol 9 (6) ◽

pp. 919

Author(s):

Wanlu Jiang ◽

Chenyang Wang ◽

Jiayun Zou ◽

Shuqing Zhang

Keyword(s):

Neural Network ◽

Feature Extraction ◽

Fault Diagnosis ◽

Rotating Machinery ◽

Generative Adversarial Networks ◽

Extraction Ability ◽

One Dimensional ◽

Adversarial Networks ◽

Diagnosis Model ◽

The One

The field of mechanical fault diagnosis has entered the era of “big data”. However, existing diagnostic algorithms, relying on artificial feature extraction and expert knowledge are of poor extraction ability and lack self-adaptability in the mass data. In the fault diagnosis of rotating machinery, due to the accidental occurrence of equipment faults, the proportion of fault samples is small, the samples are imbalanced, and available data are scarce, which leads to the low accuracy rate of the intelligent diagnosis model trained to identify the equipment state. To solve the above problems, an end-to-end diagnosis model is first proposed, which is an intelligent fault diagnosis method based on one-dimensional convolutional neural network (1D-CNN). That is to say, the original vibration signal is directly input into the model for identification. After that, through combining the convolutional neural network with the generative adversarial networks, a data expansion method based on the one-dimensional deep convolutional generative adversarial networks (1D-DCGAN) is constructed to generate small sample size fault samples and construct the balanced data set. Meanwhile, in order to solve the problem that the network is difficult to optimize, gradient penalty and Wasserstein distance are introduced. Through the test of bearing database and hydraulic pump, it shows that the one-dimensional convolution operation has strong feature extraction ability for vibration signals. The proposed method is very accurate for fault diagnosis of the two kinds of equipment, and high-quality expansion of the original data can be achieved.

Download Full-text

Optimal multi-kernel local fisher discriminant analysis for feature dimensionality reduction and fault diagnosis

Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability ◽

10.1177/1748006x211009335 ◽

2021 ◽

pp. 1748006X2110093

Author(s):

Qing Zhang ◽

Heng Li ◽

Xiaolong Zhang ◽

Haifeng Wang

Keyword(s):

Fault Diagnosis ◽

Discriminant Analysis ◽

Feature Space ◽

High Dimensional ◽

Fisher Discriminant Analysis ◽

Vibration Signals ◽

Fisher Discriminant ◽

Local Fisher Discriminant Analysis ◽

Diagnosis Accuracy ◽

Diagnosis Model

To achieve a more desirable fault diagnosis accuracy by applying multi-domain features of vibration signals, it is significative and challenging to refine the most representative and intrinsic feature components from the original high dimensional feature space. A novel dimensionality reduction method for fault diagnosis is proposed based on local Fisher discriminant analysis (LFDA) which takes both label information and local geometric structure of the high dimensional features into consideration. Multi-kernel trick is introduced into the LFDA to improve its performance in dealing with the nonlinearity of mapping high dimensional feature space into a lower one. To obtain an optimal diagnosis accuracy by the reduced features of low dimensionality, binary particle swarm optimization (BPSO) algorithm is utilized to search for the most appropriate parameters of kernels and K-nearest neighbor (kNN) recognition model. Samples with labels are used to train the optimal multi-kernel LFDA and kNN (OMKLFDA-kNN) fault diagnosis model to obtain the optimal transformation matrix. Consequently, the trained fault diagnosis model implements the recognition of machinery health condition with the most representative feature space of vibration signals. A bearing fault diagnosis experiment is conducted to verify the effectiveness of proposed diagnostic approach. Performance comparison with some other methods are investigated, and the improvement for fault diagnosis of the proposed method are confirmed in different aspects.

Download Full-text

Fault Detection and Discrimination of Rotating Machinery Using Frequency Symptom Parameter and Bayesian Network

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.470.683 ◽

2013 ◽

Vol 470 ◽

pp. 683-688

Author(s):

Hai Yang Jiang ◽

Hua Qing Wang ◽

Peng Chen

Keyword(s):

Fault Diagnosis ◽

Fault Detection ◽

Bayesian Network ◽

Frequency Domain ◽

Evaluation Method ◽

Roller Bearing ◽

Rotating Machinery ◽

Discrimination Index ◽

Vibration Signals ◽

Diagnosis Method

This paper proposes a novel fault diagnosis method for rotating machinery based on symptom parameters and Bayesian Network. Non-dimensional symptom parameters in frequency domain calculated from vibration signals are defined for reflecting the features of vibration signals. In addition, sensitive evaluation method for selecting good non-dimensional symptom parameters using the method of discrimination index is also proposed for detecting and distinguishing faults in rotating machinery. Finally, the application example of diagnosis for a roller bearing by Bayesian Network is given. Diagnosis results show the methods proposed in this paper are effective.

Download Full-text

Identification of Fault Signals in Rotating Machinery Using Higher Order Time Frequency Analysis

Volume 1D: 16th Biennial Conference on Mechanical Vibration and Noise ◽

10.1115/detc97/vib-4137 ◽

1997 ◽

Author(s):

Sang-Kwon Lee ◽

Paul R. White

Keyword(s):

Fault Diagnosis ◽

Wigner Distribution ◽

Higher Order ◽

Rotating Machinery ◽

Data Sets ◽

Higher Order Statistics ◽

Vibration Signals ◽

Time Frequency ◽

Increasing Trend ◽

Monitoring Application

Abstract Impulsive acoustic and vibration signals within rotating machinery are often induced by irregular impacting. Thus the detection of these impulses can be useful for fault diagnosis. Recently there is an increasing trend towards the use of higher order statistics for fault detection within mechanical systems based on the observation that impulsive signals tend to increase the kurtosis values. We show that the fourth order Wigner Moment Spectrum, called the Wigner Trispectrum, has superior detection performance to second order Wigner distribution for typical impulsive signals found in a condition monitoring application. These methods are also applied to data sets measured within a car engine and industrial gearbox.

Download Full-text

Joint Wavelet Transform and Time Synchronous Averaging Source Separation Method and its Application on Aero-Engine

Volume 5: Controls, Diagnostics, and Instrumentation; Cycle Innovations; Cycle Innovations: Energy Storage ◽

10.1115/gt2020-14278 ◽

2020 ◽

Author(s):

Jiqing Cong ◽

Jianping Jing ◽

Changmin Chen ◽

Zezeng Dai ◽

Jianhua Cheng

Keyword(s):

Wavelet Transform ◽

Fault Diagnosis ◽

Fundamental Frequency ◽

Averaging Method ◽

Gaussian White Noise ◽

Rotating Machinery ◽

Vibration Source ◽

Vibration Signals ◽

Aero Engine ◽

Harmonic Components

Abstract The reliability and safety of aero-engine are often the decisive factors for the safe and reliable flight of commercial aircraft. Hence, the vibration source location and fault diagnosis of aero-engine are of prime importance to detect faults and carry out fast and effective maintenance in time. However, the vibration signals collected by the sensors arranged on the casing of the aero-engine are generally the mixed signals of the main vibration sources inside the engine, and the components are extremely complicated. Therefore, the vibration source identification is a big challenge for a fault diagnosis and health management of the engine. In order to separate the key vibration sources of rotating machinery such as aero-engine, a Joint Wavelet Transform and Time Synchronous Averaging based algorithm (JWTS) is proposed in this paper. Based on the fact that the fundamental frequency and its harmonic and sub-harmonic components are generally included in the vibration spectrum of shaft fault signal of rotating machinery, wavelet transform and time synchronous averaging algorithm are combined to extract them. The algorithm completes separating the main vibration sources with three steps. First, the source number and fundamental frequency of each source are estimated using the wavelet transform. Second, every source is extracted from each observed signal by the time synchronous averaging method. Time synchronous averaging method can effectively extract a signal of cycle and harmonic rotor components and can suppress noise. Third, the optimal estimation of each source is determined according to signal’s 2-norm. Since the extracted source with a larger energy is closer to the real source, and signal’s 2-norm is a good indicator of the signal energy. Hence, the key vibration sources related to rotary speeds of the engine are obtained separately. The method is verified by synthetic mixed signals first. Three periodic signals of different frequencies are used to simulate the vibration sources of the aeroengine. The fundamental, harmonic and sub-harmonic components of them, as well as Gaussian white noise, are randomly mixed. The results show that the JWTS algorithm can estimate the number of the main sources and can extract each source effectively. Then the method is demonstrated using vibration signals of a real aero-engine. The results indicate that the proposed JWTS method has extracted and located the main sources within the aero-engine, including sources from the low-pressure rotor, high-pressure rotor, combustion chamber and accessory. Therefore, the proposed method provides a new fault diagnosis technology for rotating machinery, especially for a real aero-engine.

Download Full-text

CvT Fault Diagnosis Method of Manifold Sensitive Modal Matrix Under Variable Speed

10.21203/rs.3.rs-940146/v1 ◽

2021 ◽

Author(s):

Hao DeChen ◽

HuaLing Li ◽

JinYing Huang

Keyword(s):

Feature Extraction ◽

Fault Diagnosis ◽

Working Conditions ◽

Network Structure ◽

Rotating Machinery ◽

Variable Speed ◽

Data Set ◽

Public Data ◽

Diagnosis Method ◽

Diagnosis Model

Abstract Rotating machinery (RM) is one of the most common mechanical equipment in engineering applications and has a broad and vital role. Rotating machinery includes gearboxes, bearing motors, generators, etc. In industrial production, the important position of rotating machinery and its variable speed and complex working conditions lead to unstable vibration characteristics, which have become a research hotspot in mechanical fault diagnosis. Aiming at the multi-classification problem of rotating machinery with variable speed and complex working conditions, this paper proposes a fault diagnosis method based on the construction of improved sensitive mode matrix (ISMM), isometric mapping (ISOMAP) and Convolution-Vision Transformer network (CvT) structure. After overlapping and sampling the variable speed signals, a high-dimensional ISMM is constructed, and the ISMM is mapped into the manifold space through ISOMAP manifold learning. This method can extract the fault transient characteristics of the variable speed signal, and the experiment proves that it can solve the problem that the conventional method cannot effectively extract the characteristics of the variable speed data. CvT combines the advantages of self-attention mechanism and convolution in CNN, so the CvT network structure is used for feature extraction and fault recognition and classification. The CvT network structure takes into account both global feature extraction and local feature extraction, which greatly reduces the number of training iterations and the size of the network model. Two data sets (the HFXZ-I planetary gearbox variable speed data set in the laboratory and the bearing variable speed public data set of the University of Ottawa in Canada) are used to experimentally verify the proposed fault diagnosis model. Experimental results show that the proposed fault diagnosis model has good recognition accuracy and robustness.

Download Full-text