• 산업경영시스템학회지
• /
• 제40권1호
• /
• pp.57-64
• /
• 2017

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

• 제어로봇시스템학회논문지
• /
• 제7권5호
• /
• pp.375-383
• /
• 2001

As many industrial systems become more complex, it becomes extremely difficult to diagnose the cause of failures. This paper presents a failure diagnosis approach based on discrete event system theory. In particular, the approach is a hybrid of event-based and state-based ones leading to a simpler failure diagnoser with supervisory control capability. The design procedure is presented along with a pump-valve system as an example.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.500-504
• /
• 1995

A neural network based upon the back propagation algorithm was designed and applied to acoustic power spectra of electrohydraulic total artificial hearts in order to diagnose mechanical failure of devices. The trained network distinguished spectra of the mechanically damaged device from those of the undamaged device with overall success rate of 63%. Moreover, the network correctly classified more than 70% of spectra in the frequency bands of 0-100 Hz and 700-950 Hz. Consequently, the neural network analysis was useful for the diagnosis of mechanical failure of a total artificial heart.

• Industrial Engineering and Management Systems
• /
• 제8권4호
• /
• pp.247-256
• /
• 2009

In mass production industries such as steel making that have large equipment, sudden stops of production process due to machine failure can cause severe problems. To prevent such situations, machine diagnosis techniques play important roles. Many methods have been developed focusing on this subject. In this paper, we propose a method for the early detection of the failure on rotating machine, which is the most common theme in the machine failure detection field. A simplified method of calculating autocorrelation function is introduced and is utilized for ARMA model identification. Furthermore, an absolute deterioration factor such as Bicoherence is introduced. Machine diagnosis can be executed by this simplified calculation method of system parameter distance with weight. Proposed method proved to be a practical index for machine diagnosis by numerical examples.

• 대한설비공학회:학술대회논문집
• /
• 대한설비공학회 2008년도 하계학술발표대회 논문집
• /
• pp.36-41
• /
• 2008

Fault detection and diagnosis(FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. An experimental study has been performed on fault detection and diagnosis method for a water chiller. Bayes classifier, which is one of classical pattern classifiers, is adopted in deciding whether fault occurred or not. FDD algorithm can detect refrigerant leak failure, when 20% amount of charged refrigerant for normal operation leaks from the water chiller. The refrigerant leak failure caused COP reduction by 6.7% compared with normal operation performance. When two kinds of faults, such as a decrease in the mass flow rate of cooling water and temperature sensor fault of cooling water inlet, are detected, COP is a little decreased by these faults.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제5B권1호
• /
• pp.78-83
• /
• 2005

Currently in Japan, the use of the small wind turbine is an upward trend. There are already many well established small wind turbine generators in use and their various failures have been reported. The most commonly sighted failure is blade damage. Thus the research purpose was set to develop a simple failure diagnostic system, where an Acoustic Emission (AE) signal was produced from the failure part of a blade which was measured by AE sensor. The failure diagnostic technique was thoroughly examined. Concurrently, the damage part of the blade was imitated, the AE signal was measured, and a FFT(Fast Fourier Transform) analysis was carried out, and was compared with the output characteristic. When one sheet of a blade was damaged 40mm or more, the level was computed at which failure could be diagnosed.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.749-757
• /
• 2007

Recently, with increasing interested in improvement of operational reliability and the systematic maintenance activities, the RCM analysis has been applied and tried to lots of applicable industries. This study covers applying the probability of failure cause to FMEA, and proposes an analytical method for this. Also, the measures of quantitative classification for the result of failure cause probability are addressed. Based on the field data, this thesis presents an identification for causes and characteristics of failure, and reviews them periodically from the above methodologies. As using FMEA applied the probability of failure cause, we in the future can look forward to improvement of efficiency for failure diagnosis & inspection, and reliability.

• 한국정밀공학회지
• /
• 제11권5호
• /
• pp.110-123
• /
• 1994

The development of automatic production systems have required inteligent diagnostic and monitoring function to repair system failure and reduce production loss by the failure. In order to perform accurate functions of intelligent system, inferencing about total system failure and fault analysis due to each mechanical component failures are required. Also the solution about repair and maintenance can be suggested from these analysis results. As an essential component of mechanical system, a bearing system is investigated to define the failure behavior. The bearing failure is caused by lubricant system failure, metallurgical defficiency, mechanical condition(vibration, overloading, misalignment) and environmental effect. This study described roller bearing fault train due to stress variation and metallurgical defficiency from lubricant failure by using FTA.

• 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).

• Clinical and Experimental Pediatrics
• /
• 제58권1호
• /
• pp.28-32
• /
• 2015

Purpose: Diencephalic syndrome is an uncommon cause of failure to thrive in early childhood that is associated with central nervous system neoplasms in the hypothalamic-optic chiasmatic region. It is characterized by complex signs and symptoms related to hypothalamic dysfunction; such nonspecific clinical features may delay diagnosis of the brain tumor. In this study, we analyzed a series of cases in order to define characteristic features of diencephalic syndrome. Methods: We performed a retrospective study of 8 patients with diencephalic syndrome (age, 5-38 months). All cases had presented to Seoul National University Children's Hospital between 1995 and 2013, with the chief complaint of poor weight gain. Results: Diencephalic syndrome with central nervous system (CNS) neoplasm was identified in 8 patients. The mean age at which symptoms were noted was $18{\pm}10.5$ months, and diagnosis after symptom onset was made at the mean age of $11{\pm}9.7$ months. The mean z score was $-3.15{\pm}1.14$ for weight, $-0.12{\pm}1.05$ for height, $1.01{\pm}1.58$ for head circumference, and $-1.76{\pm}1.97$ for weight-for-height. Clinical features included failure to thrive (n=8), hydrocephalus (n=5), recurrent vomiting (n=5), strabismus (n=2), developmental delay (n=2), hyperactivity (n=1), nystagmus (n=1), and diarrhea (n=1). On follow-up evaluation, 3 patients showed improvement and remained in stable remission, 2 patients were still receiving chemotherapy, and 3 patients were discharged for palliative care. Conclusion: Diencephalic syndrome is a rare cause of failure to thrive, and diagnosis is frequently delayed. Thus, it is important to consider the possibility of a CNS neoplasm as a cause of failure to thrive and to ensure early diagnosis.