• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.1
• /
• pp.163-169
• /
• 2020

Recently, research on automation and unmanned operation of machines in the industrial field has been conducted with the advent of AI, Big data, and the IoT, which are the core technologies of the Fourth Industrial Revolution. The machines for these automation processes are controlled based on the data collected from the sensors attached to them, and further, the processes are managed. Conventionally, the abnormalities of sensors are periodically checked and managed. However, due to various environmental factors and situations in the industrial field, there are cases where the inspection due to the failure is not missed or failures are not detected to prevent damage due to sensor failure. In addition, even if a failure occurs, it is not immediately detected, which worsens the process loss. Therefore, in order to prevent damage caused by such a sudden sensor failure, it is necessary to identify the failure of the sensor in an embedded system in real-time and to diagnose the failure and determine the type for a quick response. In this paper, a deep neural network-based fault diagnosis system is designed and implemented using Raspberry Pi to classify typical sensor fault types such as erratic fault, hard-over fault, spike fault, and stuck fault. In order to diagnose sensor failure, the network is constructed using Google's proposed Inverted residual block structure of MobilieNetV2. The proposed scheme reduces memory usage and improves the performance of the conventional CNN technique to classify sensor faults.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.20 no.2
• /
• pp.56-66
• /
• 2016

Robustness is essential for model based FDI (Fault Detection and Isolation) and it is inevitable to have modeling errors and sensor signal noises during the process of FDI. This study suggests an improved method by applying NARX (Nonlinear Auto Regressive eXogenous) model and Kalman estimator in order to cope with problems caused by linear model errors and sensor signal noises in the process of fault diagnoses. Fault decision is made by the probability of the trend of gradually accumulated errors applying Fuzzy logic, which are robust to instantaneous sensor signal noises. Reliability of fault diagnosis is verified under various fault simulations.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.878-882
• /
• 2004

In this paper, we propose a hierarchical hybrid neural network for detecting faults of induction motor. Implementing the classifier based on the input and output data, we apply appropriate transform and classification method at each step. In the proposed method, after obtaining the current of state of motor for each period, we transform it by Principle Component Analysis(PCA) to reduce its dimension. Before the training process, we use the conditional Fuzzy C-means(FCM) for obtaining the initial parameters of neural network for more effective learning procedure. From the various simulations, we find that the proposed method shows better performance to detect and diagnosis of induction motor and compare than other methods.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.16 no.10
• /
• pp.932-941
• /
• 2004

The objective of this study is to detect the multi-fault of HVAC system using a new pattern classification technique. To classify the effect of single-fault in determining the pattern, supply air temperature, OA-damper, supply fan, and air flowrate were chosen as experimental parameters. The combination of supply temperature, flow rate, supply fan and OA-damper were chosen as multi-fault conditions. Three kinds of patterns were introduced in the analysis of multi-fault problem. To solve multi-fault problem, the new pattern classification technique using residual ratio analysis was introduced to detect the multi-fault as well as single-fault. The residual ratio could diagnose single-fault or multi-fault into several patterns.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.42 no.7 s.337
• /
• pp.37-44
• /
• 2005

This paper presents effective test patterns and their BIST implementations for SoC and Board interconnects. Initially '6n'algorithm, where 'n' is the total number of interconnect nets, is introduced to completely detect and diagnose both static and crosstalk faults. Then, more economic 4n+1 algorithm is described to perfectly capture the crosstalk faults for the interconnect nets separated within a certain distance. It will be shown that both algorithms can be easily implemented as interconnect BIST hardwares with small area penalty than conventional LFSR.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.19 no.2
• /
• pp.16-22
• /
• 2011

It is recognized that the control surface fault is detected by monitoring the value of the coefficients due to the control surface deviation. It is found out the control surface stuck position by comparing the trim value with the reference value. To detect and isolate the fault, two mixed methods apply to the real-time parameter estimation and similarity measure. If the scatter of aerodynamic coefficients for the fault and normal are closing nearly, fault decision is difficult. Applying similarity measure to decide for fault or not, it makes a clear and easy distinction between fault and normal. Low power processor is applied to the real-time parameter estimator and computation of similarity measure.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.12 no.5
• /
• pp.372-377
• /
• 2007

This paper proposes a novel fault diagnosis method of a electrolytic capacitor used for DC-link voltage smoothing in adjustable speed drives. The equivalent series resistance (ESR) of the electrolytic capacitor is directly estimated from DC-link voltage and load currents and the status of the electrolytic capacitor is determined from the estimated ESR. To compensate the variation of the ESR owing to temperature variation, diodes are located on the same PCB near the capacitor and the temperature of the capacitor is sensed indirectly from the voltage drop of diodes. Simulation and experimental studies show the effectiveness of the proposed method.

• Journal of Hydrogen and New Energy
• /
• v.28 no.3
• /
• pp.252-272
• /
• 2017

Fuel cell systems have to satisfy acceptable operating reliability, sufficient lifetime and price to enter the market in competition with existing products. Fuel cells are made up of complex element technologies and various problems related to the failure of the components can affect the reliability and safety of the system. This problem can be overcome by introducing a monitoring and supervisory control system in addition to automatic control to detect the failure of the fuel cell quickly and properly diagnose the performance degradation. For the fault detection and diagnosis of polymer electrolyte fuel cells, the model based method using the theoretical superposition value and the non-model based method of checking the signal tendency or the converted signal characteristic can be applied. The methods analyzed in this paper can contribute to the development of integrated monitoring and control technology for the whole system as well as the stack.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.20-25
• /
• 1994

절삭공정의 자동화의 무인화를 달성하기 위해서는 경험을 가진 작업자의 역활이 컴퓨터에 의한 자동적인 감시 및 제어시스템으로 대체되어야 한다. 특히 공작기계에서 발생할 수 있는 자체의 고장이나 절삭과정중에 발생하는 이상상태를 실시간으로 검출하여 원인을 자동적으로 진달 할 수 있어야 한다. 절삭가공 공작기계의 이상상태 감시 및 진단의 현황을 살펴보면 주로 공구상태의 감시와 채터 감시가 연구의 대상 이 되고 있다. 공구상태의 감시는 공구의 마모와 파단을 검출하고 있다. 이 중에서 공구의 파단은 발생 즉시 실시간으로 감시되어야 한다. 밀링작업에서는 1회전 이내의 공구회전에 파단을 검출하고 기계를 정지시켜야 한다. 최근의 절삭가공에서는 절삭공구로 강력절삭을 위해 고경도 재료를 사용함에 따라 공구의 파단이 빈번하게 발생하고 있다. 정면밀링과 같은 단속절상에서는 절삭날이 큰 충격을 받으므로 더욱 파단에 대한 감시가 필요하다.

• Journal of Aerospace System Engineering
• /
• v.11 no.3
• /
• pp.22-30
• /
• 2017

This paper examines a survey on recent research regarding health monitoring and management for liquid rocket engines (LRE). For this, we investigated precedent techniques applied to LRE development. Particularly, we focused on open-cycle LRE to apply to KSLV-II (Korea Space Launch Vehicle II). Through this study, we subdivided health monitoring algorithms and analyzed fault detection and diagnosis algorithm developed in China, since China researched open-cycle LRE that have the same cycle as KSLV-II rocket engines. We discuss significant points to be considered regarding development of the KSLV-II.