• Journal of Advanced Marine Engineering and Technology
• /
• v.18 no.5
• /
• pp.36-45
• /
• 1994

This paper describes how to identify standard numbers and to diagnose defects of the ball bearings. The first stage of the networks is a procedures for identifying standard numbers of the bearings, and the next stage carries out the diagnosis of defects on the outer race and the inner race of bearings. The identification and the diagnosis of bearings were carried out by simulations and experiments.

• Journal of Advanced Marine Engineering and Technology
• /
• v.20 no.1
• /
• pp.13-23
• /
• 1996

Weld defects degrade the strength and safety of astructure and are resulted from the various cases. The complexity of causal relation of weld defects requires an expert for the analysis of weld defects and the measures counter to them. An expert system has the intelligent functions such as the representation of knowledge and the inference. On this research, weld defect are systematically analysed and their causal model is developed. This information is saved to the knowledge base. The suitable inference algorithm for the diagnosis of weld defects is developed and realized with C++ programming.

• Journal of Advanced Marine Engineering and Technology
• /
• v.18 no.3
• /
• pp.85-93
• /
• 1994

A new diagnosis method is developed in this paper, in which the fuzzy set theory is introduced to diagnose the defects of rolling element bearings. The selection of membership function and the fuzzy operation model are discussed in detail here. The system is successfully used for various defects diagnosis of rolling element bearings.

• Journal of KSNVE
• /
• v.5 no.3
• /
• pp.353-360
• /
• 1995

A new automatic diagnostic system for predicting multiple defects in rolling element bearings is developed by taking probbability into account. A database is constructed from the frequency characteristics of tested bearings with various types of defects. The proposed algorithms for the automatic diagnosis of bearing defects are shown to be satisfactory through the experiments. This method can be effectively used for quality control of the rolling bearing in plants.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.19 no.8
• /
• pp.1787-1798
• /
• 1995

Monitoring and diagnosis of the operating machine mean evaluating the condition of a machine such as the detection of the defects and the prediction of the time to failure in the machine elements, while it is running. In this study, a technique of automatic diagnosis using probability concept is studied and the analyses of the pattern comparison are introduced. An expert system, which is able to analyze the automatic identification of the multiple defects in the ball bearings, is also developed. Finally, to confirm the effectiveness of the programmed algorithms, some tests were made with specimens of the ball bearings involving the multiple defects. The proposed system reasonably predicts the defects.

• Electrical & Electronic Materials
• /
• v.7 no.1
• /
• pp.42-48
• /
• 1994

The preventive diagnosis technique for power system is being highlighted as a research area for deterioration of insulation in machinery because of high-voltage power system. We make efforts to develop not only diagnosis of aging state but also detection of defects in the initial stage from preventive diagnosis technique. Especially, partial discharge is actively studied as a non-destructive diagnosis technique and very useful because partial discharge measurement reduces damage than conventional diagnosis technique. The loaded stress during this test is smaller than that of other diagnosis techniques. But the continuous research for various complicated analysis method is required because partial discharge has very small signals and its signals have complex forms. In this paper, the measurement of partial discharge was investigated and studied on many specimens with void. We made samples having artificial voids and measured partial discharge. In order to use as a practical diagnosis technique, we studied ways of measurement, measured illustrations and types of partial discharge which could be used in order to diagnose defects of power machinery.

• Journal of the Korean Society of Industry Convergence
• /
• v.23 no.5
• /
• pp.825-833
• /
• 2020

Currently, the K-Water uses various valves that can be remotely controlled for optimal water management. Valve system fault can be classified into rotor defects, stator defects, bearing defects, and gear defects of induction motors. If the valve cannot be operated due to a gear fault, the water management operation can be greatly affected. For effective water management, there is an urgent need for preemptive repairs to determine whether gear is damaged through failure prediction diagnosis.. Recently, deep learning algorithms are being applied for valve failure diagnosis. However, the method currently applied has a disadvantage of attaching a vibration sensor to the valve. In this paper, propose a new algorithm to determine whether a fault exists using a convolutional neural network (CNN) based on the voltage and current information of the valve without additional sensor mounting. In particular, a normalized Lisasjous diagram was used to maximize the fault classification performance in the CNN-based diagnostic system.

• Journal of the Korean Society for Precision Engineering
• /
• v.13 no.3
• /
• pp.63-69
• /
• 1996

Recently, vibrational signal processing as a tool of machinery diagnosis has been actively studying. In this study, a new scheme for detection and diagnosis of localized defects in ball bearings, using unwrapped phase spectrum of FFT is described. The characteristic phase spectra for such defects shows linearly varying patterns due to the repetitive impact signals generated by localized defects, i.e., one linear line for single defect and various linearly changing shape according to angle between the two defect located points. The effectiveness of this method is confirmed by computer simulation and experiments on bearing with single or double defects at different locations.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1994.11a
• /
• pp.134-138
• /
• 1994

According to request of insulating materials for high-voltage, recently we make effort not only to develop diagnostic skills of aging state but also to discover defects in insulating material in the early. Especially, partial discharge has been actively studied as a non-destructive diagnosis technique and very useful method. Because the method of partial discharge measurement has damages less than other conventional diagnosis technique. In this paper, the characteristics of partial discharge was investigated and studied on many samples with voids. In order to adapt as a practical diagnosis technique, it is studied on the characteristics of partial discharge and insulation breakdown in the high voltage. We suggest that partial discharge measurement can be used in order to diagnose defects in high-voltage insulation materials.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.24 no.5
• /
• pp.525-531
• /
• 2004

In this paper, the concept of infrared thermography(IRT), the principle of measurement of IRT and how to set up the IR camera for the nondestructive testing are described in detail. Also, its utilization and non-destructive testing(NDT) diagnosis are reviewed. By performing the periodic non-touched WDT through the estimation of thermal patterns related with the temperature for the surface targeted, IRT can be applied to the early prevention of the device failure. For the diagnosis utilization, thermal imaging patterns obtained from IRT for heated blocks with internal defects were estimated through the lion-destructive method and discussed the way of IRT estimation from the analysis of characteristics between material defects and thermal imaging patterns.