• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2005년도 전기학술대회논문집
• /
• pp.281-286
• /
• 2005

Almost ship monitoring systems are event driven alarm system which warn only when the measurement value is over or under set point. These kinds of system cannot warn while signal is growing to abnormal state until the signal is over or under the set point and cannot play a role for preventive maintenance system. This paper proposes fault diagnosis method which is able to diagnose and forecast the fault from present operating condition by analyzing monitored signals with present ship monitoring system without additional sensors. By analyzing this data having high correlation coefficient(CC), correlation level of interactive data can be understood. Knowledge base of abnormal detection can be built by referring level of CC(Fault Detection CC, FDCC) to detect abnormal data among monitored data from monitoring system and knowledge base of diagnosis built by referring CC among interactive data for related machine each other to diagnose fault part.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 춘계학술발표대회
• /
• pp.69-71
• /
• 2020

Principal Component Analysis (PCA) is an effective data analysis technique which is commonly used for fault detection on collected data of Wireless Sensor Networks (WSN), However, applying PCA on the whole data make the detection performance low. In this paper, we propose Joint PCA and Adaptive Threshold for Fault Detection (JPATAD). Experimental results on a real dataset show a remarkably higher performance of JPATAD comparing to conventional PCA model in detection of noise which is a popular fault in collected data of sensors.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2005년도 전기학술대회논문집
• /
• pp.251-256
• /
• 2005

There is few study which automatically diagnose the fault from ship's monitored signal. The bigger control and monitoring system is, the more important fault diagnosis and maintenance is to reduce damage brought forth by system fault. This paper proposes fault diagnosis system using a correlation analysis algorithm which is able to diagnose and forecast the fault and is composed to fault detection knowledge base and fault diagnosis knowledge base. For this all kinds of ship's engine room monitored data are classified with combustion subsystem, heat exchange subsystem and electric motor and pump subsystem by analyzing ship's operation data. To verifying capability of fault detection, diagnosis and prediction, Fault Management System(FMS) is developed by C++. Simulation experiment by FMS is carried out with population data set made by log book data of 2 months duration from a large full container ship of H shipping company.

• Journal of Mechanical Science and Technology
• /
• 제18권11호
• /
• pp.1961-1968
• /
• 2004

The design of a reliable and failsafe control system requires that sensor failures be detected and identified within acceptable time limit so that system malfunction can be prevented. This paper presents a model-based approach to sensor fault detection with applications to vehicle stability control systems. The effectiveness of the proposed method is illustrated through test data-based evaluation. Vehicle test data-based evaluation results show that the proposed fault management scheme can be used for the design of a failsafe VSCs.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 춘계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.46-48
• /
• 2007

This paper presents research about improvement of fault detection algorithm in FRTU on the feeder of distribution system. FRTU(Feeder Remote Terminal Unit) is applied to fault detection schemes for phase fault, ground fault, and cold load pickup and Inrush restraint functions distinguish the fault current and the normal load current. FRTU is occurred FI(Fault Indicator) when current is over pick-up value also inrush current is occurred FRTU indicate FI. Discrete wavelet transform(DWT) analysis gives the frequency and time-scale information. The neural network system as a fault detector was trained to discriminate inrush current from the fault status by a gradient descent method. In this paper, fault detection is improved using voltage monitoring system with DWT and neural network. These data were measured in actual 22.9kV distribution system.

• 제어로봇시스템학회논문지
• /
• 제9권11호
• /
• pp.958-962
• /
• 2003

We acquired data of injection molding machine in operation and stored the data in database. We acquired the data of injection molding machine for fault detection and diagnosis (FDD) continuously and estimated the fault results with a fuzzy algorithm. Many of FDD are applied to a huge system, nuclear power plant and a computer numerical control(CNC) machine for processing machinery. But, the research of FDD is rare in injection molding machine compare with computer numerical control machine. We appraise the accuracy of the FDD and the limit of the application to the injection molding machine. We construct the fault detection and diagnosis system based on fuzzy algorithm in the injection molding machine. Data of operating injection molding machine are acquired in order to improve the reliability of detection and diagnosis.

• 설비공학논문집
• /
• 제15권3호
• /
• pp.159-165
• /
• 2003

The fault detection and diagnosis technology may be applied in order to decrease the energy consumption and the maintenance cost of the air-conditioning system. To detect partial faults of the air-conditioning system, a neural network algorithm may be used. In this study, the neural network algorithm using normalized input data by the standard deviation was applied. And the [7$\times$10$\times$10$\times$1] neural network structure was selected. Test results showed that the neural network algorithm using normalized input data was very effective to detect the condenser fouling and the evaporator fan fault of an air-conditioning system.

• 설비공학논문집
• /
• 제27권11호
• /
• pp.587-595
• /
• 2015

In this study, fault symptoms were simulated and analyzed for a single-effect absorption chiller. The fault patterns of fault detection parameters were tabulated using the fault symptom simulation results. Fault detection and diagnosis by a process history-based method were performed for the in-situ experiment of a single-effect absorption chiller. Simulated fault modes for the in-situ experimental study are the decreases in cooling water and chilled water mass flow rates. Five no-fault reference models for fault detection of a single-effect absorption chiller were developed using fault-free steady-state data. A sensitivity analysis of fault detection using the normalized distance method was carried out with respect to fault progress. When mass flow rates of the cooling and chilled water decrease by more than 19.3% and 17.8%, respectively, the fault can be detected using the normalized distance method, and COP reductions are 6.8% and 4.7%, respectively, compared with normal operation performance. The pattern recognition method for fault diagnosis of a single-effect absorption chiller was found to indicate each failure mode accurately.

• Structural Monitoring and Maintenance
• /
• 제5권1호
• /
• pp.51-65
• /
• 2018

A number of sensing techniques have been implemented for detecting defects in civil infrastructures instead of onsite human inspections in structural health monitoring. However, the issue of faults in sensors has not received much attention. This issue may lead to incorrect interpretation of data and false alarms. To overcome these challenges, this article presents a deep learning-based method with a new architecture of Stateful Long Short Term Memory Neural Networks (S-LSTM NN) for detecting sensor fault without going into details of the fault features. As LSTMs are capable of learning data features automatically, and the proposed method works without an accurate mathematical model. The detection of four types of sensor faults are studied in this paper. Non-stationary acceleration responses of a three-span continuous bridge when under operational conditions are studied. A deep network model is applied to the measured bridge data with estimation to detect the sensor fault. Another set of sensor output data is used to supervise the network parameters and backpropagation algorithm to fine tune the parameters to establish a deep self-coding network model. The response residuals between the true value and the predicted value of the deep S-LSTM network was statistically analyzed to determine the fault threshold of sensor. Experimental study with a cable-stayed bridge further indicated that the proposed method is robust in the detection of the sensor fault.