Support vector machine and K-nearest neighbour for unbalanced fault detection

2014 ◽  
Vol 20 (1) ◽  
pp. 65-75 ◽  
Author(s):  
Ashkan Moosavian ◽  
Hojat Ahmadi ◽  
Babak Sakhaei ◽  
Reza Labbafi
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Experimental System ◽  
Performance Comparison ◽  
Fault Classification ◽  
Support Vector ◽  
Rotating Machines ◽  
Vibration Signals ◽  
Content Type ◽  
Intelligent Approach

Purpose – The purpose of this paper is to develop an appropriate approach for detecting unbalanced fault in rotating machines using KNN and SVM classifiers. Design/methodology/approach – To fulfil this goal, a fault diagnosis approach based on signal processing, feature extraction and fault classification, was used. Vibration signals were acquired from a designed experimental system with three conditions, namely, no load, balanced load and unbalanced load. FFT technique was applied to transform the vibration signals from time-domain into frequency-domain. In total, 29 feature parameters were extracted from FFT amplitude of the signals. SVM and KNN were employed to classify the three different conditions. The performances of the two classifiers were obtained under different values of their parameter. Findings – The experimental results show the potential application of SVM for machine fault diagnosis. Practical implications – The results demonstrate that the proposed approach can be used effectively for detecting unbalanced condition in rotating machines. Originality/value – In this paper, an intelligent approach for unbalanced fault detection was proposed based on supervised learning method. Also, a performance comparison was made between KNN and SVM in fault classification. In addition, this approach gave a high level of classification accuracy. The proposed intelligent approach can be used for other mechanical faults.

Wavelet denoising using different mother wavelets for fault diagnosis of engine spark plug

2015 ◽  
Vol 231 (3) ◽  
pp. 359-370 ◽  
Author(s):  
Ashkan Moosavian ◽  
Meghdad Khazaee ◽  
Gholamhassan Najafi ◽  
Majid Khazaee ◽  
Babak Sakhaei ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Combustion Engine ◽  
Wavelet Denoising ◽  
Performance Comparison ◽  
Support Vector ◽  
Vibration Signals ◽  
Spark Plug ◽  
Different Levels ◽  
Mother Wavelets

This paper deals with vibration-fault diagnosis of spark plug of an internal combustion engine using wavelet analysis and support vector machine. In order to reduce the noises of the vibration signals, wavelet denoising technique was used. A performance comparison was made between different mother wavelets as well as different levels of decomposition in order to find the best cases for the system under study. The results showed that the maximum classification accuracies were obtained by 13 different wavelets, namely, db1_4, db1_5, db2_4, db3_4, coif1_4, coif1_5, coif2_4, coif3_3, coif3_4, coif3_5, dmey_2, dmey_4 and bior3.7_6. It was also demonstrated that db1, coif1, coif3 and dmey were valuable mother wavelets for this study. Moreover, the results indicated that the proposed approach can reliably be used for spark plug fault diagnosis.

Fault Classification Model of Rotor Based on Support Vector Machine

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.

scholarly journals Connected Components-based Colour Image Representations of Vibrations for a Two-stage Fault Diagnosis of Roller Bearings Using Convolutional Neural Networks

2021 ◽  
Vol 34 (1) ◽  
Author(s):  
Hosameldin O. A. Ahmed ◽  
Asoke K Nandi
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Roller Bearing ◽  
Fault Classification ◽  
Health Conditions ◽  
Connected Components ◽  
Rotating Machines ◽  
Two Stage ◽  
Vibration Signals ◽  
Roller Bearings

AbstractRoller bearing failure is one of the most common faults in rotating machines. Various techniques for bearing fault diagnosis based on faults feature extraction have been proposed. But feature extraction from fault signals requires expert prior information and human labour. Recently, deep learning algorithms have been applied extensively in the condition monitoring of rotating machines to learn features automatically from the input data. Given its robust performance in image recognition, the convolutional neural network (CNN) architecture has been widely used to learn automatically discriminative features from vibration images and classify health conditions. This paper proposes and evaluates a two-stage method RGBVI-CNN for roller bearings fault diagnosis. The first stage in the proposed method is to generate the RGB vibration images (RGBVIs) from the input vibration signals. To begin this process, first, the 1-D vibration signals were converted to 2-D grayscale vibration Images. Once the conversion was completed, the regions of interest (ROI) were found in the converted 2-D grayscale vibration images. Finally, to produce vibration images with more discriminative characteristics, an algorithm was applied to the 2-D grayscale vibration images to produce connected components-based RGB vibration images (RGBVIs) with sets of colours and texture features. In the second stage, with these RGBVIs a CNN-based architecture was employed to learn automatically features from the RGBVIs and to classify bearing health conditions. Two cases of fault classification of rolling element bearings are used to validate the proposed method. Experimental results of this investigation demonstrate that RGBVI-CNN can generate advantageous health condition features from bearing vibration signals and classify the health conditions under different working loads with high accuracy. Moreover, several classification models trained using RGBVI-CNN offered high performance in the testing results of the overall classification accuracy, precision, recall, and F-score.

scholarly journals Microgrid Fault Detection and Classification: Machine Learning Based Approach, Comparison, and Reviews

Energies ◽  
2020 ◽  
Vol 13 (13) ◽  
pp. 3460 ◽  
Author(s):  
Shahriar Rahman Fahim ◽  
Subrata K. Sarker ◽  
S. M. Muyeen ◽  
Md. Rafiqul Islam Sheikh ◽  
Sajal K. Das
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Classification Model ◽  
Superior Performance ◽  
Fault Classification ◽  
Support Vector ◽  
Discrete Wavelet ◽  
Fault Detection And Classification ◽  
Proposed Model ◽  
The Individual

Accurate fault classification and detection for the microgrid (MG) becomes a concern among the researchers from the state-of-art of fault diagnosis as it increases the chance to increase the transient response. The MG frequently experiences a number of shunt faults during the distribution of power from the generation end to user premises, which affects the system reliability, damages the load, and increases the fault line restoration cost. Therefore, a noise-immune and precise fault diagnosis model is required to perform the fast recovery of the unhealthy phases. This paper presents a review on the MG fault diagnosis techniques with their limitations and proposes a novel discrete-wavelet transform (DWT) based probabilistic generative model to explore the precise solution for fault diagnosis of MG. The proposed model is made of multiple layers with a restricted Boltzmann machine (RBM), which enables the model to make the probability reconstruction over its inputs. The individual RBM layer is trained with an unsupervised learning approach where an artificial neural network (ANN) algorithm tunes the model for minimizing the error between the true and predicted class. The effectiveness of the proposed model is studied by varying the input signal and sampling frequencies. A level of considered noise is added with the sample data to test the robustness of the studied model. Results prove that the proposed fault detection and classification model has the ability to perform the precise diagnosis of MG faults. A comparative study among the proposed, kernel extreme learning machine (KELM), multi KELM, and support vector machine (SVM) approaches is studied to confirm the robust superior performance of the proposed model.

Rolling Element Bearing Fault Diagnosis Using Complex Gaussian Wavelet

2010 ◽  
Author(s):  
P. K. Kankar ◽  
Satish C. Sharma ◽  
S. P. Harsha
Keyword(s):  
Fault Diagnosis ◽  
High Performance ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Fault Classification ◽  
Support Vector ◽  
Wavelet Coefficients ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Rolling Element

This paper is focused on fault diagnosis of bearings due to localized defects i.e. spall on the bearing components, which is essential to the design of high performance rotor bearing system. The methodology proposed in this paper for fault diagnosis of rolling element bearings, utilizes autocorrelation of raw vibration signals to reduce the dimension of vibration signals with minimal loss of significant frequency content. Dimension of vibration signal is reduced to 10% with negligible loss of information. To extract most appropriate features from auto-correlated vibration signals and for effective classification of faults, vibration signals are decomposed using complex Gaussian wavelet. Total 150 signals of healthy and defective bearings at rotor speeds 250, 500, 1000, 1500 and 2000 rpm with three loading conditions are considered. 1-D continuous wavelet coefficients of these samples are calculated at the seventh level of decomposition (27 scales for each sample). Maximum Energy to Shannon Entropy ration criterion is used to determine scale corresponding to characteristic defect frequency. Statistical features are extracted from the wavelet coefficients corresponding to selected scales. Finally, bearing faults are classified using Support Vector Machine (SVM) method. The test results show that the SVM can be used efficiently for bearing fault classification. It is also observed that classification accuracy is improved by using autocorrelation.

scholarly journals Analog Circuit Fault Diagnosis Based on Support Vector Machine Classifier and Fuzzy Feature Selection

Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1496
Author(s):  
Hao Liang ◽  
Yiman Zhu ◽  
Dongyang Zhang ◽  
Le Chang ◽  
Yuming Lu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Mutual Information ◽  
Analog Circuit ◽  
Fault Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Fault Parameters ◽  
Diagnosis Method ◽  
Circuit Fault Diagnosis

In analog circuit, the component parameters have tolerances and the fault component parameters present a wide distribution, which brings obstacle to classification diagnosis. To tackle this problem, this article proposes a soft fault diagnosis method combining the improved barnacles mating optimizer(BMO) algorithm with the support vector machine (SVM) classifier, which can achieve the minimum redundancy and maximum relevance for feature dimension reduction with fuzzy mutual information. To be concrete, first, the improved barnacles mating optimizer algorithm is used to optimize the parameters for learning and classification. We adopt six test functions that are on three data sets from the University of California, Irvine (UCI) machine learning repository to test the performance of SVM classifier with five different optimization algorithms. The results show that the SVM classifier combined with the improved barnacles mating optimizer algorithm is characterized with high accuracy in classification. Second, fuzzy mutual information, enhanced minimum redundancy, and maximum relevance principle are applied to reduce the dimension of the feature vector. Finally, a circuit experiment is carried out to verify that the proposed method can achieve fault classification effectively when the fault parameters are both fixed and distributed. The accuracy of the proposed fault diagnosis method is 92.9% when the fault parameters are distributed, which is 1.8% higher than other classifiers on average. When the fault parameters are fixed, the accuracy rate is 99.07%, which is 0.7% higher than other classifiers on average.

scholarly journals A Fusion Feature Extraction Method Using EEMD and Correlation Coefficient Analysis for Bearing Fault Diagnosis

2018 ◽  
Vol 8 (9) ◽  
pp. 1621 ◽  
Author(s):  
Fan Jiang ◽  
Zhencai Zhu ◽  
Wei Li ◽  
Yong Ren ◽  
Gongbo Zhou ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Correlation Coefficient ◽  
Feature Space ◽  
Support Vector ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis ◽  
Acceleration Sensors ◽  
Reconstructed Signal ◽  
Original Feature

Acceleration sensors are frequently applied to collect vibration signals for bearing fault diagnosis. To fully use these vibration signals of multi-sensors, this paper proposes a new approach to fuse multi-sensor information for bearing fault diagnosis by using ensemble empirical mode decomposition (EEMD), correlation coefficient analysis, and support vector machine (SVM). First, EEMD is applied to decompose the vibration signal into a set of intrinsic mode functions (IMFs), and a correlation coefficient ratio factor (CCRF) is defined to select sensitive IMFs to reconstruct new vibration signals for further feature fusion analysis. Second, an original feature space is constructed from the reconstructed signal. Afterwards, weights are assigned by correlation coefficients among the vibration signals of the considered multi-sensors, and the so-called fused features are extracted by the obtained weights and original feature space. Finally, a trained SVM is employed as the classifier for bearing fault diagnosis. The diagnosis results of the original vibration signals, the first IMF, the proposed reconstruction signal, and the proposed method are 73.33%, 74.17%, 95.83% and 100%, respectively. Therefore, the experiments show that the proposed method has the highest diagnostic accuracy, and it can be regarded as a new way to improve diagnosis results for bearings.

scholarly journals Feature Extraction Strategy with Improved Permutation Entropy and Its Application in Fault Diagnosis of Bearings

2018 ◽  
Vol 2018 ◽  
pp. 1-12 ◽  
Author(s):  
Fan Jiang ◽  
Zhencai Zhu ◽  
Wei Li ◽  
Bo Wu ◽  
Zhe Tong ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Optimal Number ◽  
Permutation Entropy ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Time Frequency ◽  
Bearing Fault ◽  
Bearing Fault Diagnosis

Feature extraction is one of the most difficult aspects of mechanical fault diagnosis, and it is directly related to the accuracy of bearing fault diagnosis. In this study, improved permutation entropy (IPE) is defined as the feature for bearing fault diagnosis. In this method, ensemble empirical mode decomposition (EEMD), a self-adaptive time-frequency analysis method, is used to process the vibration signals, and a set of intrinsic mode functions (IMFs) can thus be obtained. A feature extraction strategy based on statistical analysis is then presented for IPE, where the so-called optimal number of permutation entropy (PE) values used for an IPE is adaptively selected. The obtained IPE-based samples are then input to a support vector machine (SVM) model. Subsequently, a trained SVM can be constructed as the classifier for bearing fault diagnosis. Finally, experimental vibration signals are applied to validate the effectiveness of the proposed method, and the results show that the proposed method can effectively and accurately diagnose bearing faults, such as inner race faults, outer race faults, and ball faults.

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

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.

scholarly journals Engine Fault Detection Approach Based on Angle Domain Signal Model

2021 ◽  
Vol 2068 (1) ◽  
pp. 012034
Author(s):  
Hai Zeng ◽  
Ning Zeng ◽  
Jin Han ◽  
Yan Ding
Keyword(s):  
Fault Diagnosis ◽  
Fault Detection ◽  
Failure Detection ◽  
Vibration Signal ◽  
Bench Test ◽  
Signal Model ◽  
Vibration Signals ◽  
Engine Vibration ◽  
Detection Approach ◽  
Diagnosis Approach

Abstract Engine vibration signals include strong noise and non-stationary signals. By the time domain signal processing approach, it is hard to extract the failure features of engine vibration signals, so it is hard to identify engine failures. For improving the success rate of engine failure detection, an engine angle domain vibration signal model is established and an engine fault detection approach based on the signal model is proposed. The angle domain signal model reveals the modulation feature of the engine angular signal. The engine fault diagnosis approach based on the angle domain signal model involves equal angle sampling and envelope analysis of engine vibration signals. The engine bench test verifies the effectiveness of the engine fault diagnosis approach based on the angle domain signal model. In addition, this approach indicates a new path of engine fault diagnosis and detection.

Sign in / Sign up

Export Citation Format

Share Document