Jong-Duk Son

Decision-level fusion based on wavelet decomposition for induction motor fault diagnosis using transient current signal

In this paper, we propose and implement a decision-level fusion model by combining the information of multi-level wavelet decomposition for fault diagnosis of induction motor using transient stator current signal. Firstly, the start-up transient current signals are collected from different faulty motors. Then signal preprocessing is conducted containing smoothing and subtracting to reduce the influence of line frequency in transient current signals. Next, we employ discrete wavelet transform technique to decompose the preprocessed signals into different frequency ranges of products, and then features are extracted from decomposed detail components. Finally, two decision-level fusion strategies, Bayesian belief fusion and multi-agent fusion, are employed. That is, fault features are classified using several classifiers and generated decisions are fused using a specific fusion algorithm. The proposed approach is evaluated by an experiment of fault diagnosis for induction motors. Experiment results show that excellent diagnosis performance can be obtained.

Development of smart sensors system for machine fault diagnosis

Machine fault diagnosis is a traditional maintenance problem. In the past, the maintenance using tradition sensors is money-cost, which limits wide application in industry. To develop a cost-effective maintenance technique, this paper presents a novel research using smart sensor systems for machine fault diagnosis. In this paper, a smart sensors system is developed which acquires three types of signals involving vibration, current, and flux from induction motors. And then, support vector machine, linear discriminant analysis, k-nearest neighbors, and random forests algorithm are employed as classifiers for fault diagnosis. The parameters of these classifiers are optimized by using cross-validation method. The experimental results show that smart sensor system has the similar performance for applying in intelligent machine fault diagnosis with reduced product cost. Developed smart sensors have feasibility to apply for intelligent fault diagnosis.

A Comparison of Classifier Performance for Fault Diagnosis of Induction Motor using Multi-type Signals

Fault detection and diagnosis is the most important technology in condition-based maintenance (CBM) systems, which typically starts from collecting signatures of running machines by multiple sensors for subsequent accurate analysis. Recently, there has been an increasing requirement of selecting special sensors, which are cheap, robust, easily installed, and good classifiers that have accurate classification, stable performance, and short calculating time. This article carries out a comparative study of various classification algorithms for fault diagnosis of electric motors using different types of signals. The authors evaluate experimentally the relative performances of five classifiers using five types of steady-state signals based on three kinds of performance evaluation strategies: training-test, cross-validation, and similar measure. First, the raw signals are collected and features are extracted from the collected signals. Then, the extracted features are classified using the five classification algorithms. Next, an overall comparison of the five classifiers is described, and experiment results are discussed. Finally, conclusions are summarized and suggestions are offered.

Vibration-based Energy Harvester for Wireless Condition Monitoring System

Historically, industrial condition monitoring has been performed by costly hard-wired sensors or infrequent checks by maintenance personnel equipped with hand held monitoring equipment. Self- powered wireless condition monitoring systems provides on-line monitoring of critical plant and machinery providing major operating cost benefits. A vibration energy harvester(VEH) is a device that converts kinetic energy occurred by machine vibration into useable electrical energy. Using VEHs to power wireless monitoring systems can yield significant benefits: increased reliability, lower life time costs and no battery disposal issues, etc. This paper proposes the novel prototype design and manufacturing of a VEH that can eliminate the effect by failed batteries.

Smart Sensor for Machine Condition Monitoring Using Wireless LAN

Smart sensor is known as intelligent sensor, it is different with other conventional sensors in the case of intelligent system embedded on it. Smart sensor has many benefits e.g. low-cost in usage, self-decision and self-diagnosis abilities. This sensor consists of perception element(sensing element), signal processing and technology of communication. In this work, a bridge and structure of smart sensor has been investigated to be capable to condition monitoring routine. This investigation involves low power consumption, software programming, fast data acquisition ability, and authoritativeness warranty. Moreover, this work also develops smart sensor to be capable to perform high sampling rate, high resolution of ADC, high memory capacity, and good communication for data transfer. The result shows that the developed smart sensor is promising to be applied to various industrial fields.

An Integrated Software for Machine Diagnostics and Prognostics Using Wireless Sensors

This study presents an integrated software for machine health diagnosis and prognosis based on signals measured by wireless sensors. This software consists of four sequential modules: data processing, data analysis and condition monitoring, diagnosis, and prognosis. The algorithms used in the diagnostics and prognostics modules are developed based on our recent studies. Additionally, some methods for feature representation, feature selection, feature extraction, etc are also introduced in this study. The aim of this software is to offer comprehensive system for industrial problems. In order to verify, a measured the data from K-Water pump and simulated data of induction motors are used. The results indicate that this software will can be used as a reliability tool to real application.

Framework Development for Fault Prediction in Hot Rolling Mill System

This paper proposes a framework to predict the mechanical fault of hot rolling mill system (HRMS). The optimum process of HRMS is usually identified by the rotating velocity of working roll. Therefore, observing the velocity of working roll is relevant to early know the HRMS condition. In this paper, we propose the framework which consists of two methods namely spectrum matrix which related to case-based fast Fourier transform(FFT) analysis, and three dimensional condition monitoring based on novel visualization. Validation of the proposed method has been conducted using vibration data acquired from HRMS by accelerometer sensors. The acquired data was also tested by developed software referred as hot rolling mill facility analysis module. The result is plausible and promising, and the developed software will be enhanced to be capable in prediction of remaining useful life of HRMS.