Experimental Frequency-Domain Vibration Based Fault Diagnosis of Roller Element Bearings Using Support Vector Machine

2020 ◽  
Author(s):  
Vishal G Salunkhe ◽  
Ramchandra Ganapati Desavale ◽  
Jagadeesha T.
Keyword(s):  
Mathematical Model ◽  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Experimental Results ◽  
Life Extension ◽  
Support Vector ◽  
Bearing Failure ◽  
Rotating Machines ◽  
Experimental Frequency ◽  
Model Based

Abstract In heavy rotating machines and assembly lines, bearing failure in any one of the rotating machines results in shut down of many other machines and affects the overall cost and quality of the product. Condition monitoring of bearing systems avoids breakdown and saves preventive and corrective maintenance time and cost. This research paper proposes advanced strategies in early fault detection of taper rolling bearings. In view of this, a mathematical model based- fault diagnosis and support vector machine (SVM) is proposed in this work. The mathematical model using dimension analysis by matrix method (DAMM) and SVM is developed to predict the vibration characteristic of the rotor bearing system. Various types of defects created using an electric discharge machine (EDM) are analyzed by correlating dependent and independent parameters. Experiments were performed to classify the rotor dynamic characteristic of healthy and unhealthy bearing. Experimental results are used to validate the model obtained by DAMM and SVM. Experimental results showed that vibration characteristics are evaluated by using a theoretical model and SVM. This contribution to the service life extension and efficiency improvement, so as to reduce bearing failure. Thus, the automatic online diagnosis of bearing faults is possible with a developed model-based by DAMM and SVM.

An Intelligent Prediction for Detecting Bearing Vibration Characteristics Using a Machine Learning Model

2021 ◽  
Vol 4 (3) ◽  
Author(s):  
Vishal G. Salunkhe ◽  
R. G. Desavale
Keyword(s):  
Machine Learning ◽  
Mathematical Model ◽  
Electrical Discharge Machining ◽  
Experimental Results ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Bearing Failure ◽  
Vibration Characteristic ◽  
Model Based ◽  
Dimension Analysis

Abstract Bearing failure in the heavy rotating machines results in shut down of many other machines and affects the overall cost and quality of the product. Condition monitoring of bearing systems acts as a preventive and corrective measure as it avoids breakdown and saves maintenance time and cost. This research paper proposes advanced strategies for early detection and analysis of taper rolling bearings. In view of this, mathematical model-based fault diagnosis and support vector machining (SVM) are proposed in this work. A mathematical model using dimension analysis by the matrix method (Dimension Analysis Method (DAMM)) and SVM is developed that can be used to predict the vibration characteristic of the rotor-bearing system. Types of defects are created using electrical discharge machining (EDM) and analyzed, and correlation is established between dependent and independent parameters. Experiments were performed to evaluate the rotor dynamic characteristic of healthy and unhealthy bearings. Experimental results are used to validate the model obtained by the DAMM and SVM. Experimental results showed that the vibration characteristic could be evaluated by using a theoretical model and SVM. Efforts have been made to extend the service life of the machines and the assembly lines and to improve their efficiency, so as to reduce bearing failure; what provides novelty to these efforts is the use of four machine learning techniques. Thus, an automatic online diagnosis of bearing faults has been made possible with the developed model based on DAMM and SVM.

Analog Circuits Fault Diagnosis Using Multifractal Analysis

2013 ◽  
Vol 721 ◽  
pp. 367-371
Author(s):  
Yong Kui Sun ◽  
Zhi Bin Yu
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Analog Circuits ◽  
Multifractal Analysis ◽  
Multifractal Spectrum ◽  
Experimental Results ◽  
Support Vector ◽  
Diagnosis Accuracy ◽  
Circuit Under Test

Analog circuits fault diagnosis using multifractal analysis is presented in this paper. The faulty response of circuit under test is analyzed by multifratal formalism, and the fault feature consists of multifractal spectrum parameters. Support vector machine is used to identify the faults. Experimental results prove the proposed method is effective and the diagnosis accuracy reaches 98%.

Cost Effective On-Site Fault Diagnosis Home Appliance Using a Smart Phone and Support Vector Machine

2019 ◽  
Author(s):  
Ji Min Baek ◽  
Kyeong Ha Lee ◽  
Seung Ho Lee ◽  
Ja Choon Koo
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Smart Phone ◽  
Poor Performance ◽  
Cost Effective ◽  
Consumer Electronics ◽  
Support Vector ◽  
Rotating Machines ◽  
Pass Filter ◽  
Rotating Machine

Abstract One of the common rotating machines of the consumer electronics might be a washing machine. The rotating machinery normally suffers mechanical failures even during daily operations that results in poor performance or shortening lifetime of the machine. Therefore, engineers have been interested in the earliest fault diagnosis of the rotating machine. Existing fault diagnosis methods for rotating machines have used fast fourier transform (FFT) method in frequency domain to detect abnormal frequency. However, it is difficult to diagnose using the FFT method if the normal frequency components of the rotating machines overlaps with the fault frequencies. In this paper, sets of acoustic signals generated by the washing machines are collected by using a smart phone in which an inexpensive microphone is equipped, and collected data are analyzed using a new algorithm, which combining the skewness, kurtosis, A-weighting filter, high-pass filter (HPF), and FFT. The analyzed data is applied to support vector machine (SVM) to determine defect existence. The proposed algorithm solves the disadvantages of the existing method and is accurate enough to discriminate the data collected by the cheap microphone of the smart phone.

scholarly journals A Transformer Fault Diagnosis Model Based on Chemical Reaction Optimization and Twin Support Vector Machine

Energies ◽  
2019 ◽  
Vol 12 (5) ◽  
pp. 960 ◽  
Author(s):  
Fang Yuan ◽  
Jiang Guo ◽  
Zhihuai Xiao ◽  
Bing Zeng ◽  
Wenqiang Zhu ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Chemical Reaction ◽  
Twin Support Vector Machine ◽  
Support Vector ◽  
Chemical Reaction Optimization ◽  
Model Based ◽  
Reaction Optimization ◽  
Diagnosis Model ◽  
Transformer Fault

The condition monitoring and fault diagnosis of power transformers plays a significant role in the safe, stable and reliable operation of the whole power system. Dissolved gas analysis (DGA) methods are widely used for fault diagnosis, however, their accuracy is limited by the selection of DGA features and the performance of fault diagnosis models, for example, the classical support vector machine (SVM), is easily affected by unbalanced training samples. This paper presents a transformer fault diagnosis model based on chemical reaction optimization and a twin support vector machine. Twin support vector machines (TWSVMs) are used as classifiers for solving problems involving unbalanced and insufficient samples. Restricted Boltzmann machines (RBMs) are used for data preprocessing to ensure the effective identification of feature parameters and improve the efficiency and accuracy of fault diagnosis. The chemical reaction optimization (CRO) algorithm is used to optimize TWSVM parameters to select the optimal training parameters. The cross-validation (CV) method is used to ensure the reliability and generalization ability of the diagnostic model. Finally, the validity of the model is verified using real fault samples and random testing.

Fault Diagnosis for Electrical Control System of Automobile Based on Support Vector Machine

2014 ◽  
Vol 666 ◽  
pp. 203-207
Author(s):  
Jian Hua Cao
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Control System ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Experimental Results ◽  
Support Vector ◽  
Electrical Control ◽  
Diagnosis Method ◽  
The Common

This paper is to present a fault diagnosis method for electrical control system of automobile based on support vector machine. We collect the common fault states of electrical control system of automobile to analyze the fault diagnosis ability of electrical control system of automobile based on support vector machine. It can be seen that the accuracy of fault diagnosis for electrical control system of automobile by support vector machine is 92.31%; and the accuracy of fault diagnosis for electrical control system of automobile by BP neural network is 80.77%. The experimental results show that the accuracy of fault diagnosis for electrical control system of automobile of support vector machine is higher than that of BP neural network.

Sign in / Sign up

Export Citation Format

Share Document