• Tribology and Lubricants
• /
• 제11권3호
• /
• pp.24-30
• /
• 1995

This paper was undertaken to recognize the pattern of the wear debris by neural network as a link for the development of diagnosis system for movable condition of the lubricated machine surface. The wear test was carried out under different experimental conditions using the wear test device was made in laboratory and wear testing specimen of the pin-on-disk type were rubbed in paraffine series base oil, by varying applied load, sliding distance and mating material. The neural network has been used to pattern recognition of four parameter (diameter, elongation, complex and contrast) of the wear debris and learned the friction condition of five values (material 3, applied load 1, sliding distance 1). The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by the neural network. The characteristic parameter of the large wear debris over a few micron size enlarged recognition ability.

• 한국소음진동공학회논문집
• /
• 제27권2호
• /
• pp.189-194
• /
• 2017

An compressor that is combined with the rotor and pneumatic technology has been researching for the performance of pressure. However, the control of operations, an accurate diagnosis and the maintenance of compressor system are limited though the simple structure of compressor and compression are advantaged to reduce the energy. In this paper, the characteristic of the compressor operating under the normal or abnormal condition is realized. and the efficient diagnosis method is proposed through feature based analysis. Also, by using the GA (genetic algorithm) and SVM (support vector machine) of machine learning, the performance of feature analysis is conducted. Different misalignment mode of learning data for compressor is evaluated using the fault simulator. Therefore, feature based analysis is conducted considering misalignment mode of the compressor and the possibility of a diagnosis of misalignment is evaluated.

• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권4호
• /
• pp.551-559
• /
• 2017

본 논문에서는 베어링 고장진단 성능을 개선하기 위해 실시간 학습 방법을 제안한다. 기존 베어링 고장진단의 문제점은 학습되지 않은 상태에 대해 올바른 분류를 할 수 없다는 점이다. 제안한 4단계 실시간 학습 방법은 새로운 상태를 실시간으로 인지 및 학습하여 새로운 상태의 데이터를 올바르게 분류할 수 있다. 1단계에서는 학습 정보에서 각 클래스의 무게중심과 그 클래스 내 각 특징벡터 사이의 유클리디안 거리를 계산하여 각 클래스별로 거리의 최대값을 계산한다. 2단계에서는 새로 취득된 데이터의 특징벡터와 각 클래스의 무게중심 사이의 유클리디안 거리를 계산하고 각 클래스별 최대 허용 거리와 비교한다. 3단계에서는 새로 취득된 데이터들과 각 클래스 내 무게중심 사이의 거리가 각 클래스의 최대 허용 거리보다 모두 클 경우 새로운 상태의 데이터로 인지하고 새로운 상태 인지 횟수를 증가시킨다. 마지막 4단계에서는 새로운 상태 인지 회수가 10보다 클 경우 새로운 상태의 클래스를 생성하기 위해 새로운 상태로 인지된 10개의 데이터를 새로운 상태의 클래스로 지정하고 분류기를 재학습시킨다. 제안한 방법의 성능을 검증하기 위해 실제 베어링 결함 데이터를 사용하여 제안한 실시간 학습 방법의 효율성을 검증하였다.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 2002년도 proceedings of the second asia international conference on tribology
• /
• pp.455-456
• /
• 2002

Wear is one of the main factors causing breakdown and fault of machine, so ferrography technique analyzing wear particles can be an effective way for condition monitoring and fault diagnosis. On the base of the forward multilayer neural network, a nodes self-deleting neural network model is provided in this paper. This network can itself deletes the nodes to optimize its construction. On the basis of the nodes self-deleting neural network, an intelligent ferrography diagnosis expert system (IFDES) for wear particles recognition and wear diagnosis is described. This intelligent expert system can automatically slim lip knowledge by learning from samples and realize basically the entirely automatic processing from wear particles recognition to wear diagnosis.

• 산업경영시스템학회지
• /
• 제32권4호
• /
• pp.215-222
• /
• 2009

Human voice reacts very sensitively to human's minute physical condition. For instance, human voice disorders affect patients profoundly especially in the case of Parkinson's disease. Acoustic tools such as MDVP, can function as an equipment that measures various voice in different objects. Many different approaches have been applied for analyzing the voice disorders for diagnosis of Parkinson's disease. According to the voice data of suspected Parkinson's patients from UCI Machine Learning Repository, it is reported to have 23 people with Parkinson's disease and 8 healthy people. Applying Mahalanobis Taguchi System (MTS) for diagnosis of Parkinson's disease, the correct diagnosis performance is compared to previous research results.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2008년도 추계학술대회논문집
• /
• pp.43-48
• /
• 2008

Gear system has been widely used in industrial applications and unexpected failures of gears are not only extremely damaging but also lead to economic losses. So, early detection of fault is important for diagnosis machine condition. And acoustic emission is an efficient non destructive testing technique for the diagnosis of machine health and is useful technique for early detection of fault because it can find low-amplitude and high-frequency signal on account of high sensibility. Therefore, in this paper, the AE signal was measured and preprocessed using envelop analysis for gearbox with misalignment between pinion and gear. And then the vibration characteristic of gear misalignment was analyzed.

• 한국정밀공학회지
• /
• 제21권12호
• /
• pp.75-83
• /
• 2004

With the rotating machinery getting more accurate and diversified, the necessity fur an appropriate diagnosis technique and maintenance system has been greatly recognized. However, until now, the operator has executed a monitoring of the machine by the senses or simple the change of RMS (root mean Square) value. So, the diagnostic expert system using the fuzzy inference which the operator can judge easily and expertly a condition of the machine is developed through this study. In this paper, the hardware and software of the diagnostic expert system was composed and the identification of the diagnostic performance of the developed system for 5 fault phenomena was carried out.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2008년도 춘계학술대회논문집
• /
• pp.986-989
• /
• 2008

Recently the agitator are being widely used in the machine plan in order to increase the petrochemical industry. The agitator normally consist of impeller, shaft, hub, reduction gear and the driving motor. It is one of the key design issue to confirm that the vibration caused by the rotation of the shaft should not coincide with the natural frequency of the shaft itself. And petrochemical industry as well as plants have been in operation for long period beyond their original design lives. In this paper the vibration of Ox-Reactor Agitator is measured for check machine condition. The result of diagnosis and solution is discussed in this paper.

• 한국소음진동공학회논문집
• /
• 제18권12호
• /
• pp.1243-1249
• /
• 2008

Gear system has been widely used in industrial applications and unexpected failures of gears are not only extremely damaging but also leading to economic losses. So, early detection of fault is important for diagnosis machine condition. And acoustic emission is an efficient non-destructive testing technique fur the diagnosis of machine health and is useful technique far early detection of fault because it can find low-amplitude and high-frequency signal on account of high sensibility. Therefore, in this paper, the AE signal was measured and preprocessed using envelope analysis for gearbox with misalignment between pinion and gear. And then the gear misalignment's vibration characteristic were analyzed.

• 한국안전학회지
• /
• 제19권1호
• /
• 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).