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.

scholarly journals DETECTION OF DISEASE SYMPTOMS ON HYPERSPECTRAL 3D PLANT MODELS

2016 ◽  
Vol III-7 ◽  
pp. 89-96 ◽  
Author(s):  
Ribana Roscher ◽  
Jan Behmann ◽  
Anne-Katrin Mahlein ◽  
Jan Dupuis ◽  
Heiner Kuhlmann ◽  
...  
Keyword(s):  
Support Vector Machines ◽  
Sparse Representation ◽  
Test Data ◽  
Training Data ◽  
Hyperspectral Images ◽  
Spectral Information ◽  
Support Vector ◽  
Leaf Spot Disease ◽  
Disease Symptoms ◽  
Vector Machines

We analyze the benefit of combining hyperspectral images information with 3D geometry information for the detection of <i>Cercospora</i> leaf spot disease symptoms on sugar beet plants. Besides commonly used one-class Support Vector Machines, we utilize an unsupervised sparse representation-based approach with group sparsity prior. Geometry information is incorporated by representing each sample of interest with an inclination-sorted dictionary, which can be seen as an 1D topographic dictionary. We compare this approach with a sparse representation based approach without geometry information and One-Class Support Vector Machines. One-Class Support Vector Machines are applied to hyperspectral data without geometry information as well as to hyperspectral images with additional pixelwise inclination information. Our results show a gain in accuracy when using geometry information beside spectral information regardless of the used approach. However, both methods have different demands on the data when applied to new test data sets. One-Class Support Vector Machines require full inclination information on test and training data whereas the topographic dictionary approach only need spectral information for reconstruction of test data once the dictionary is build by spectra with inclination.

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.

Sign in / Sign up

Export Citation Format

Share Document