• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.420-422
• /
• 1998

All Fault Detection and Diagnosis(FDD) methods utilize classification techniques. The objective of this study was to demonstrate the application of classification techniques to the problem of diagnosing faults in data generated by a variable-air-volume(VAV) air-handling unit(AHU) simulation model and to describe the characteristics of the techniques considered. Artificial neural network classifier and fuzzy clustering classifier were considered for fault diagnostics.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.4
• /
• pp.444-451
• /
• 1999

A diagnostic rule-base design method for enhancing fault detection and isolation performance of multiple obsever based fault detection isolation schemes (FIDS) is presented. The diagnostic rule-base has a hierarchical framework to perform detection and isolation of faults of interest, and diagnosis of process faults. The decision unit comprises a rule base and a fuzzy inference engine and removes some difficulties of conventional decision unit which includes crisp logic with threshold values. Emphasis is placed on the design and evaluation methods of the diagnostic rult-base. The suggested scheme is applied to the FDIS design for a DC motor driven centrifugal pump system.

• Journal of Mechanical Science and Technology
• /
• v.20 no.7
• /
• pp.929-940
• /
• 2006

Early detection and diagnosis of incipient induction machine faults increases machinery availability, reduces consequential damage, and improves operational efficiency. However, fault detection using analytical methods is not always possible because it requires perfect knowledge of a process model. This paper proposes a neural network based expert system for diagnosing problems with induction motors using vibration analysis. The short-time Fourier transform (STFT) is used to process the quasi-steady vibration signals, and the neural network is trained and tested using the vibration spectra. The efficiency of the developed neural network expert system is evaluated. The results show that a neural network expert system can be developed based on vibration measurements acquired on-line from the machine.

• Proceedings of the KIEE Conference
• /
• 2001.07b
• /
• pp.996-998
• /
• 2001

This paper presents an approach based on knowledge models to detect and isolate faults in a voltage source inverter. These faults do not affect the existing system protections. A diagnosis system which uses only the input variables of the drive is presented. It is based on the analysis of the current-vector trajectory and of the instantaneous frequency in faulty mode. These two methods have been verified in simulation results.

• Proceedings of the KIEE Conference
• /
• 1998.07b
• /
• pp.410-413
• /
• 1998

A passive approach for enhancing fault detection and isolation performance of multiple observer based fault detection isolation schemes(FDIS) is proposed. The FDIS has a hierarchical framework to perform detection and isolation of faults of interest, and diagnosis of process faults. The decision unit comprises of a rule base and fuzzy inference engine and removes some difficulties of conventional decision unit which includes crisp logic and threshold values. Emphasis is placed on the design and evaluation methods of the diagnostic rule base. The suggested scheme is applied for the FDIS design for a DC motor driven centrifugal pump system.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.11
• /
• pp.874-882
• /
• 2003

The condition assessment of engineering systems has increased in importance because the manpower needed to operate and supervise various plants has been reduced. Especially, induction motors are at the core of most engineering processes, and there is an indispensable need to monitor their health and performance. So detection and diagnosis of motor faults is a base to improve efficiency of the industrial plant. In this paper, a model-based fault detection system is developed for induction motors, using steady state vibration signals. Early various fault detection systems using vibration signals are a trivial method and those methods are prone to have missed fault or false alarms. The suggested motor fault detection system was developed using a model-based reference value. The stationary signal had been extracted from the non-stationary signal using a data segmentation method. The signal processing method applied in this research is FFT. A reference model with spectra signal is developed and then the residuals of the vibration signal are generated. The ratio of RMS values of vibration residuals is proposed as a fault indicator for detecting faults. The developed fault detection system is tested on 800 hp motor and it is shown to be effective for detecting faults in the air-gap eccentricities and broken rotor bars. The suggested system is shown to be effective for reducing missed faults and false alarms. Moreover, the suggested system has advantages in the automation of fault detection algorithms in a random signal system, and the reference model is not complicated.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.17 no.11
• /
• pp.1279-1289
• /
• 1992

Fault-tolerant system in improved the reliability and safety by using hardware and software redundancy. Fault mask and detection, identification techniques are conditionally used with system's application areas. Here DMR system is operated with standby and fail-safe module method that has minimal hardware and software redundancy, then its reliablity and safety comparison is presented respectively. Also this paper proposed an effective methods of dealing with transient faults as compared system's MTTFs to transient faults tolerance capabilities of self-diagnosis program.

• KEPCO Journal on Electric Power and Energy
• /
• v.4 no.2
• /
• pp.89-99
• /
• 2018

Downtime and malfunction of industrial rotor machines represents a crucial cost burden and productivity loss. Fault diagnosis of this equipment has recently been carried out to detect their fault(s) and cause(s) by using fault classification methods. However, these methods are of limited use in detecting rotor faults because of their hypersensitivity to unexpected and different equipment conditions individually. These limitations tend to affect the accuracy of fault classification since fault-related features calculated from vibration signal are moved to other regions or changed. To improve the limited diagnosis accuracy of existing methods, we propose a new approach for fault diagnosis of rotor machines based on the model generated by supervised learning. Our work is based on feature residual values from vibration signals as fault indices. Our diagnostic model is a robust and flexible process that, once learned from historical data only one time, allows it to apply to different target systems without optimization of algorithms. The performance of the proposed method was evaluated by comparing its results with conventional methods for fault diagnosis of rotor machines. The experimental results show that the proposed method can be used to achieve better fault diagnosis, even when applied to systems with different normal-state signals, scales, and structures, without tuning or the use of a complementary algorithm. The effectiveness of the method was assessed by simulation using various rotor machine models.

• Journal of the Korean Society of Safety
• /
• v.19 no.1
• /
• pp.23-30
• /
• 2004

Modern production systems are very complex by request of automation, and failure modes that occur in thisautomatic system are very various and complex. The efficient fault diagnosis for these complex systems is essential for productivity loss prevention and cost saving. Traditional fault diagnostic system which perforns sequential fault diagnosis can cause catastrophic failure during diagnosis when fault propagation is very fast. This paper describes the Real-time Intelligent Multiple Fault Diagnosis System (RIMFDS). RIMFDS assesses current machine condition by using sensor signals. This system deals with multiple fault diagnosis, comprising of two main parts. One is a personal computer for remote signal generation and transmission and the other is a host system for multiple fault diagnosis. The signal generator generates various faulty signals and image information and sends them to the host. The host has various modules and agents for efficient multiple fault diagnosis. A SUN workstation is used as a host for multiple fault modules and agents for efficient multiple fault diagnosis. A SUN workstation is used as a host for multiple fault diagnosis and graphic representation of the results. RIMFDS diagnoses multiple faults with fast fault propagation and complex physical phenomenon. The new system based on multiprocessing diagnoses by using Hierarchical Artificial Neural Network (HANN).

• Smart Structures and Systems
• /
• v.29 no.6
• /
• pp.757-766
• /
• 2022

To train deep learning algorithms, a sufficient number of data are required. However, in most engineering systems, the acquisition of fault data is difficult or sometimes not feasible, while normal data are secured. The dearth of data is one of the major challenges to developing deep learning models, and fault diagnosis in particular cannot be made in the absence of fault data. With this context, this paper proposes an anomaly detection methodology for rotating machines using only normal data with self-labeling. Since only normal data are used for anomaly detection, a self-labeling method is used to generate a new labeled dataset. The overall procedure includes the following three steps: (1) transformation of normal data to self-labeled data based on a pretext task, (2) training the convolutional neural networks (CNN), and (3) anomaly detection using defined anomaly score based on the softmax output of the trained CNN. The softmax value of the abnormal sample shows different behavior from the normal softmax values. To verify the proposed method, four case studies were conducted, on the Case Western Reserve University (CWRU) bearing dataset, IEEE PHM 2012 data challenge dataset, PHMAP 2021 data challenge dataset, and laboratory bearing testbed; and the results were compared to those of existing machine learning and deep learning methods. The results showed that the proposed algorithm could detect faults in the bearing testbed and compressor with over 99.7% accuracy. In particular, it was possible to detect not only bearing faults but also structural faults such as unbalance and belt looseness with very high accuracy. Compared with the existing GAN, the autoencoder-based anomaly detection algorithm, the proposed method showed high anomaly detection performance.