Detection of Damaged Tooth by Support Vector Machines

2014 ◽  
Vol 627 ◽  
pp. 79-83
Author(s):  
Qing Rong Fan ◽  
Kiyotaka Ikejo ◽  
Kazuteru Nagamura
Keyword(s):  
Support Vector Machines ◽  
Gear Tooth ◽  
Vibration Signal ◽  
Original Data ◽  
Cyclic Fatigue ◽  
Mean Value ◽  
Support Vector ◽  
Statistical Parameters ◽  
Machine System ◽  
Vector Machines

Gear is one of the most important and commonly used components in machine system. Early detection of gear damage is crucial to prevent the machine system from malfunction. This paper proposes a method for detection of damaged tooth based on support vector machines. Statistical parameters of standard deviation, root mean square value, maximum value and mean value are extracted from the vibration signal as representative features of tooth conditions to be input to the support vector machine classifier. The validity of the presented method is confirmed by the application of detecting early damaged tooth during the cyclic fatigue test. The vibration acceleration on gear box is acquired as original data. Furthermore, the signal of each gear tooth is separately extracted from the signal for a further analysis.The experimental results demonstrate the effectiveness of the proposed method.

Support vector machines for detection and characterization of rolling element bearing faults

2001 ◽  
Vol 215 (9) ◽  
pp. 1065-1074 ◽  
Author(s):  
L. B. Jack ◽  
A. K. Nandi
Keyword(s):  
Support Vector Machines ◽  
Vibration Signal ◽  
Training Data ◽  
Rolling Element Bearing ◽  
Support Vector ◽  
Statistical Estimates ◽  
Vector Machines ◽  
Rolling Element ◽  
Fault Characterization

Artificial neural networks (ANNs) have been used to detect faults in rotating machinery for a number of years, using statistical estimates of the vibration signal as input features, and they have been shown to be highly successful in this type of application. Support vector machines (SVMs) are a more recent development, and little use has been made of them in the condition monitoring (CM) arena. The availability of a limited amount of training data creates some problems for the use of SVMs, and a strategy is offered that improves the generalization performance significantly in cases where only limited training data are available. This paper examines the performance of both types of classifier in one given scenario—a multiclass fault characterization example.

Evaluation of Human Femur Bone Radiographic Images Using AdaBoost and Support Vector Machines

2011 ◽  
Author(s):  
Thomas Christy Bobby ◽  
Swaminathan Ramakrishnan
Keyword(s):  
Support Vector Machines ◽  
Principal Component ◽  
Support Vector ◽  
Statistical Parameters ◽  
Radiographic Images ◽  
Human Femur ◽  
Femur Bone ◽  
Vector Machines ◽  
Binarization Algorithm ◽  
Automated Image Processing

In this work, classification of normal and abnormal human femur bone images are carried out using Support Vector Machines (SVM) and AdaBoost classifiers. The trabecular (soft bone) regions of human femur bone images (N = 44) recorded under standard conditions are used for the study. The acquired images are subjected to auto threshold binarization algorithm to recognize the presence of mineralization and trabecular structures in the digitized images. The mechanical strength regions such as primary compressive and tensile are delineated by semi-automated image processing methods from the digitized femur bone images. The first and higher order statistical parameters are calculated from the intensity values of the delineated regions of interest and their gray level co-occurrence matrices respectively. The significant parameters are found using principal component analysis. The first two most significant parameters are used as input to the classifiers. Statistical classification tools such as SVM and AdaBoost are employed for the classification. Results show that the AdaBoost classifier performs better in terms of sensitivity and specificity for the chosen parameters for primary compressive and tensile regions compared to SVM.

Local Fault Assessment in a Helical Geared System via Sound and Vibration Parameters Using Multiclass SVM Classifiers

2016 ◽  
Vol 41 (3) ◽  
pp. 559-571
Author(s):  
Muniyappa Amarnath
Keyword(s):  
Support Vector Machines ◽  
Power Transmission ◽  
Gear Tooth ◽  
Industrial Applications ◽  
Support Vector ◽  
Feed Forward Neural Network ◽  
Secondary Damage ◽  
Vector Machines ◽  
Monitoring Procedure ◽  
Vibration Parameters

Abstract A gear system transmits power by means of meshing gear teeth and is conceptually simple and effective in power transmission. Thus typical applications include electric utilities, ships, helicopters, and many other industrial applications. Monitoring the condition of large gearboxes in industries has attracted increasing interest in the recent years owing to the need for decreasing the downtime on production machinery and for reducing the extent of secondary damage caused by failures. This paper addresses the development of a condition monitoring procedure for a gear transmission system using artificial neural networks (ANNs) and support vector machines (SVMs). Seven conditions of the gear were investigated: healthy gear and gear with six stages of depthwise wear simulated on the gear tooth. The features extracted from the measured vibration and sound signals were mean, root mean square (rms), variance, skewness, and kurtosis, which are known to be sensitive to different degrees of faults in rotating machine elements. These characteristics were used as an input features to ANN and SVM. The results show that the multilayer feed forward neural network and multiclass support vector machines can be effectively used in the diagnosis of various gear faults.

Application of Continuous Wavelet Features and Multi-Class Sphere SVM to Chatter Prediction

2011 ◽  
Vol 188 ◽  
pp. 675-680 ◽  
Author(s):  
Shi Wu ◽  
D.K. Jia ◽  
X.L. Liu ◽  
F.G. Yan ◽  
Y.F. Li
Keyword(s):  
Support Vector Machines ◽  
Binary Classification ◽  
Forecast Accuracy ◽  
Vibration Signal ◽  
Test Sample ◽  
Recognition System ◽  
Support Vector ◽  
Continuous Wavelet ◽  
Vector Machines ◽  
Milling Chatter

A cutting chatter forecast method based on continuous wavelet feature and multi-class spherical Support Vector Machines is studied in this paper. The method based on continuous wavelet transform extracts the cutting vibration signal feature and uses multi-class spherical Support Vector Machines to discern the chatter. In order to simplify computational complexity when binary classification SVM turn to multi-class classification, the algorithm makes every kind of samples have a spherical SVM. In the feature space identified the test sample and spherical SVM centre distance as a decision-making function. Experiments show that using combine spherical SVM with continuous wavelet feature Vector has good recognition effect in the milling chatter recognition system. Chatter inoculation forecast accuracy reaches 95%, and chatter outbreak forecast accuracy reaches 97.5%.

scholarly journals Locating Impact on Structural Plate Using Principal Component Analysis and Support Vector Machines

2013 ◽  
Vol 2013 ◽  
pp. 1-8 ◽  
Author(s):  
Heming Fu ◽  
Qingsong Xu
Keyword(s):  
Principal Component Analysis ◽  
Support Vector Machines ◽  
Principal Component ◽  
Original Data ◽  
Component Analysis ◽  
Support Vector ◽  
Data Sets ◽  
Vector Machines ◽  
Pca Algorithm ◽  
The Impact

A new method which integrates principal component analysis (PCA) and support vector machines (SVM) is presented to predict the location of impact on a clamped aluminum plate structure. When the plate is knocked using an instrumented hammer, the induced time-varying strain signals are collected by four piezoelectric sensors which are mounted on the plate surface. The PCA algorithm is adopted for the dimension reduction of the large original data sets. Afterwards, a new two-layer SVM regression framework is proposed to improve the impact location accuracy. For a comparison study, the conventional backpropagation neural networks (BPNN) approach is implemented as well. Experimental results show that the proposed strategy achieves much better locating accuracy in comparison with the conventional approach.

scholarly journals Unsupervised Domain Adaptation Using Exemplar-SVMs with Adaptation Regularization

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-13
Author(s):  
Yiwei He ◽  
Yingjie Tian ◽  
Jingjing Tang ◽  
Yue Ma
Keyword(s):  
Support Vector Machines ◽  
Selection Bias ◽  
Visual Recognition ◽  
Domain Adaptation ◽  
Sample Selection ◽  
Original Data ◽  
Sample Selection Bias ◽  
Support Vector ◽  
Target Domain ◽  
Vector Machines

Domain adaptation has recently attracted attention for visual recognition. It assumes that source and target domain data are drawn from the same feature space but different margin distributions and its motivation is to utilize the source domain instances to assist in training a robust classifier for target domain tasks. Previous studies always focus on reducing the distribution mismatch across domains. However, in many real-world applications, there also exist problems of sample selection bias among instances in a domain; this would reduce the generalization performance of learners. To address this issue, we propose a novel model named Domain Adaptation Exemplar Support Vector Machines (DAESVMs) based on exemplar support vector machines (exemplar-SVMs). Our approach aims to address the problems of sample selection bias and domain adaptation simultaneously. Comparing with usual domain adaptation problems, we go a step further in slacking the assumption of i.i.d. First, we formulate the DAESVMs training classifiers with reducing Maximum Mean Discrepancy (MMD) among domains by mapping data into a latent space and preserving properties of original data, and then, we integrate classifiers to make a prediction for target domain instances. Our experiments were conducted on Office and Caltech10 datasets and verify the effectiveness of the model we proposed.

scholarly journals An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7587
Author(s):  
Ayaz Kafeel ◽  
Sumair Aziz ◽  
Muhammad Awais ◽  
Muhammad Attique Khan ◽  
Kamran Afaq ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Fault Detection ◽  
Signal Analysis ◽  
Vibration Signal ◽  
Gaussian Kernel ◽  
Support Vector ◽  
Spectral Features ◽  
Rotating Machines ◽  
Vector Machines ◽  
Vibration Signal Analysis

Accurate and early detection of machine faults is an important step in the preventive maintenance of industrial enterprises. It is essential to avoid unexpected downtime as well as to ensure the reliability of equipment and safety of humans. In the case of rotating machines, significant information about machine’s health and condition is present in the spectrum of its vibration signal. This work proposes a fault detection system of rotating machines using vibration signal analysis. First, a dataset of 3-dimensional vibration signals is acquired from large induction motors representing healthy and faulty states. The signal conditioning is performed using empirical mode decomposition technique. Next, multi-domain feature extraction is done to obtain various combinations of most discriminant temporal and spectral features from the denoised signals. Finally, the classification step is performed with various kernel settings of multiple classifiers including support vector machines, K-nearest neighbors, decision tree and linear discriminant analysis. The classification results demonstrate that a hybrid combination of time and spectral features, classified using support vector machines with Gaussian kernel achieves the best performance with 98.2% accuracy, 96.6% sensitivity, 100% specificity and 1.8% error rate.

Sign in / Sign up

Export Citation Format

Share Document