A New Method for Fault Detection of Rotating Machines in Motion Control Applications Using PROFIdrive Information and Support Vector Machine Classifier

2020 ◽  
Vol 143 (4) ◽  
Author(s):  
Andre Luis Dias ◽  
Afonso Celso Turcato ◽  
Guilherme Serpa Sestito ◽  
Murilo Silveira Rocha ◽  
Dennis Brandão ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Motion Control ◽  
Diagnostic System ◽  
Operating Conditions ◽  
Support Vector ◽  
Electric Motors ◽  
Rotating Machines ◽  
Worst Case ◽  
Control Applications ◽  
Mechanical Faults

Abstract Electric motors are widely used in the industry. Several studies have proposed methods to detect anomalies in their operation, but always using sensors dedicated to this purpose. In this sense, this work aims to fill gaps in related works presenting a method for the detection of faults in rotating machines driven by electric motors in motion control applications using PROFINET network and PROFIdrive profile. The proposed method does not require any additional or dedicated sensors to provide data to the diagnostic system. Instead, the proposed methodology is based on the analysis of data transmitted in the communication network, which already exists for control purposes. Support vector machine (SVM) is used as a classifier of five different mechanical faults. The results provide that the methodology is feasible and efficient under different machine operating conditions, achieving, in the worst case, 97.78% efficiency.

Support Vector Machine Based Diagnostic System for Breast Cancer Using Swarm Intelligence

2011 ◽  
Vol 36 (4) ◽  
pp. 2505-2519 ◽  
Author(s):  
Hui-Ling Chen ◽  
Bo Yang ◽  
Gang Wang ◽  
Su-Jing Wang ◽  
Jie Liu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Support Vector Machine ◽  
Swarm Intelligence ◽  
Diagnostic System ◽  
Support Vector

scholarly journals Design of Fractal Features-Based Partial Discharge Pattern Recognition using Multi Support Vector Machine Method

2018 ◽  
Vol 159 ◽  
pp. 02048
Author(s):  
Rahayu ◽  
G.T. Anuraga ◽  
H. Prasetia ◽  
Umar Khayam
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machine ◽  
High Voltage ◽  
Partial Discharge ◽  
Diagnostic System ◽  
Diagnostic Technique ◽  
Recognition System ◽  
Support Vector ◽  
Machine Method ◽  
Pattern Recognition System

Partial Discharge (PD) is one of the causes of insulation deteriorisation mode and impacts on the reliability of high voltage equipment. Therefore, PD measurement is used for diagnostic technique of high voltage equipment. Diagnostic output of high voltage equipment contain information about PD type, PD cause, PD location and PD severity. after identification, a proper preventive maintenance pattern can be performed. Therefore PD pattern recognition system is very important on PD diagnostic system to recognize the PD pattern and determine the level of hazard that occurs in specimen object or high voltage equipment‥ In this paper, PD pattern recognition system is designed with fractal geometry approach and support vector machine (SVM) algorithm. The coding and programming of graphical user interface of the application is done. Each PD type and hazard level on various insulating materials (solid, liquid and gas) have the dimensions of the fractal and the lacunarity. The type of PD (void, corona) and its danger level (bad, fair and good) can be identified with the support vector machine (SVM)

Modeling of Flexible Structures by Means of Least Square Support Vector Machine

2015 ◽  
Author(s):  
Hammam Tamimi ◽  
Dirk Söffker
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Flexible Structures ◽  
Operating Conditions ◽  
Least Square ◽  
Support Vector ◽  
Suitable Model ◽  
Support Vector Machine Algorithm ◽  
Training Time ◽  
Svm Algorithm

This paper investigates modeling of flexible structures by means of the least squares support vector machine (LS-SVM) algorithm. Modeling is the first step to obtain a suitable model-based controller for any given system. Accurate modeling of a flexible structure based on experimental data using LS-SVM algorithm requires less knowledge about the physical system. Least squares support vector machine algorithm can achieve global and unique solution when compared with other soft computing algorithms. Also, LS-SVM algorithm requires less training time. In this paper, the successful use of support vector machine algorithm to model the flexible cantilever is demonstrated. The acquired model is able to provide accurate prediction of the system output under different operating conditions. Experimental results demonstrate the efficiency and high precision of the proposed approach.

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.

Online Diagnostics of Mechanical and Electrical Faults in Induction Motor Using Multiclass Support Vector Machine Algorithms Based on Frequency Domain Vibration and Current Signals

2019 ◽  
Vol 5 (3) ◽  
Author(s):  
Purushottam Gangsar ◽  
Rajiv Tiwari
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Frequency Domain ◽  
Induction Motor ◽  
Sampling Rate ◽  
Computation Time ◽  
Current Data ◽  
Operating Conditions ◽  
Support Vector ◽  
Electrical Faults

This paper demonstrates the development of a flexible fault diagnosis methodology that can detect up to ten different faults in the induction motor (IM), simultaneously. The major IM electrical faults, such as the broken rotor bar (BRB), phase unbalance (PUF), and stator winding fault (SWF), and mechanical faults, such as bearing fault (BF), unbalanced rotor (UR), bowed rotor (BR), and misaligned rotor (MR), are considered with different fault severities for the diagnosis. The experiments are conducted with three varying loads and seven different speeds, and the frequency domain vibration and current data are acquired at a relatively low sampling rate of 1 kHz. Several statistical features are extracted and then the best feature-set is selected using the wrapper model. Thereafter, a data classification tool based on the support vector machine (SVM) is used for the fault characterization. Initially, a multi-fault diagnosis is performed by training and testing the SVM at the same operating conditions (i.e., load and speed). The performance of the classifier is found to be very good at all IM operating conditions. The main focus of this study lies in overcoming the fault diagnosis, where the data are unavailable at required operating conditions. This is accomplished by employing interpolation and extrapolation strategies for different loads and speeds. The proposed methodology not only solves practical problem of unavailability of data at different operating conditions but also shows good performance and takes low computation time, which are vital requirements of an online intelligent condition monitoring system.

Engine Fault Diagnostic System Based on Non-Linear Support Vector Machine

2012 ◽  
Vol 229-231 ◽  
pp. 534-537
Author(s):  
Gao Huan Xu ◽  
Jun Xiang Ye
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Diagnostic System ◽  
Support Vector ◽  
Linear Support Vector Machine ◽  
Diagnosis System ◽  
The Core ◽  
Wavelet Energy ◽  
Non Linear ◽  
Fault Diagnosis System

The car engine failures in the course of time and place have many possibilities. The engine fault diagnosis system developed in .NET platform. The core of the system make use of noise wavelet energy features and non-linear support vector machine classification. After the experiment, the system has fairly good results.

scholarly journals Support-Vector Machine Approach for Robust Fault Diagnosis of Electric Vehicle Permanent Magnet Synchronous Motor

2020 ◽  
Vol 12 (1) ◽  
pp. 10
Author(s):  
Chunheng Zhao ◽  
Yi Li ◽  
Matthew Wessner ◽  
Chinmay Rathod ◽  
Pierluigi Pisu
Keyword(s):  
Support Vector Machine ◽  
Fault Diagnosis ◽  
Permanent Magnet ◽  
High Performance ◽  
Permanent Magnet Synchronous Motor ◽  
Synchronous Motor ◽  
Industrial Applications ◽  
Operating Conditions ◽  
Support Vector ◽  
Svm Classifier

Permanent magnet synchronous motor (PMSM) is a leading technology for electric vehicles (EVs) and other high-performance industrial applications. These challenging applications demand robust fault diagnosis schemes, but conventional strategies based on models, system knowledge, and signal transformation have limitations that degrade the agility of diagnosing faults. These methods require extremely detailed design and consideration to remain robust against noise and disturbances in the actual application. Recent advancements in artificial intelligence and machine learning have proven to be promising next-generation solutions for fault diagnosis. In this paper, a support-vector machine (SVM) utilizing sparse representation is developed to perform sensor fault diagnosis of a PMSM. A simulation model of the pertinent PMSM drive system for automotive applications is used to generate a set of labelled training example sets that the SVM uses to determine margins between normal and faulty operating conditions. The PMSM model includes input as a torque reference profile and disturbance as a constant road grade, against both of which faults must be detectable. Even with limited training, the SVM classifier developed in this paper is capable of diagnosing faults with a high degree of accuracy, suggesting that such methods are feasible for the demanding fault diagnosis challenge in PMSM.

Sign in / Sign up

Export Citation Format

Share Document