• 한국신재생에너지학회:학술대회논문집
• /
• 2010.11a
• /
• pp.183.1-183.1
• /
• 2010

본 논문에서는 풍력발전기의 회전속도센서의 고장 발생 시 고장을 검출하고 회전속도센서의 사용 없이 Sensorless 제어로의 전환에 관한 연구를 기술하였다. 최근 풍력발전은 급속한 성장함에 따라 풍력발전기의 대형화 및 해상풍력화 추세에 있다. 특히 해상풍력발전은 바람 및 설치장소의 제약에서 벗어나는 이점에 반해 염해, 습도 및 파도에 의한 진동 발생으로 센서의 고장 발생률이 높을 것으로 예상된다. 이에 따라 풍력발전기의 회전속도센서 고장 발생 시 이를 검출하는 방법을 제시하였다. 또한 회전속도센서의 고장이 검출되면 회전속도센서를 이용한 풍력발전기 제어방식에서 Sensorless 제어로의 전환을 통해 안전하게 풍력발전기를 운전할 수 있도록 하였다. 연구된 제어기법은 PSIM을 이용한 시물레이션을 통해 결과를 검증하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.2
• /
• pp.203-208
• /
• 2016

This paper presents a fault detection and data processing algorithm for acoustic sensor systems using the multiple sensor algorithm that has originally developed for the wireless sensor nodes. The multiple sensor algorithm can increase the reliability of the sensor systems by utilizing and comparing the measurements of the multiple sensors. In the acoustic sensor system, the equivalent sound level($L_{eq}$) is used to detect the faulty sensor. The experiment was conducted to demonstrate the feasibility of the multiple acoustic sensor algorithm, and the results show that the algorithm can detect the faulty sensor and validate the data.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.11a
• /
• pp.192-195
• /
• 2008

A sensor fault detection method for small turbo shaft engine considering multiple trim conditions is proposed. This engine is used in a helicopter. Firstly, under multiple trim conditions, we derive the linearized models from a nonlinear model which includes engine, rotor and feedback control loop. As a fault detection method, we adopt the Kalman filter based method. To keep continuity of estimates between the changes of trim conditions, we reconfigure the initial values of state variables at trim changes. We detect the faults with two steps that when the first filter does not alarm the faults for some sensors, the second filter is runned for other sensor. Via some simulations we show that the proposed method works well under multiple trim conditions.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.41 no.11
• /
• pp.735-742
• /
• 2017

In this study, an effective model-based sensor fault detection methodology that can detect and isolate PEM temperature sensors fault is introduced. In fuel cell vehicle operation process, the stack temperature affects durability of a fuel cell. Thus, it is important for fault algorithm to detect the fault signals. The major objective of sensor fault detection is to guarantee the healthy operations of the fuel cell system and to prevent the stack from high temperature and low temperature. For the residual implementation, parity equation based on the state space is used to detect the sensors fault as stack temperature and coolant inlet temperature, and residual is compared with the healthy temperature signals. Then the residuals are evaluated by various fault scenarios that detect the presence of the sensor fault. In the result, the designed in this study fault algorithm can detect the fault signal.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.386-390
• /
• 2007

센서 네트워크 시스템은 한정된 자원을 갖는 센서노드들을 광대한 영역에 설치하여 새로운 정보를 수집 하고 모니터링 하는 기능을 한다. 센서 노드와 센서의 고장(Sensor node faulty or Sensor faulty)은 열악한 설치 환경이나 제한된 리소스에 의해 종종 발생 되는데 이들 고장은 네트워크 내에서 요구되는 양질의 서비스 제공에 많은 문제를 가져온다. 본 논문에서는 센서 노드의 고장 검출 알고리즘으로 알려져 있는 Consensus 알고리즘과 센서노드에서 사용되는 센서의 고장을 검출할 수 있는 localized faulty sensor detection 알고리즘을 혼합하여 시스템에 안정된 서비스를 제공할 수 있는 방법을 제안하며 실제 시뮬레이션과 제작된 실험장치에 적용함으로써 그 유용성을 확인하고자 한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.760-765
• /
• 2007

The sensor network system which has limited resources is deployed in a wide area and plays an important role of gethering information and monitoring. Generally, fault of sensor nodes which was caused by limited resources and poor environment happens. Futhermore, this fault poses many problems related with required quality of whole network. In this paper, new fault detection algorithm which utilizes both consensus algorithm and localized faulty sensor detection scheme is proposed. To verify the feasibility of the proposed scheme, some simulation and experiment are carried out.

• Journal of Advanced Navigation Technology
• /
• v.7 no.2
• /
• pp.171-179
• /
• 2003

In this paper a neural network-based fault tolerant control system for aircraft sensor and actuator failures is considered. By exploiting flight dynamic relations a set of neural networks is constructed to detect sensor failure and give alternative signal for the faulty sensor. For actuator failures another set of neural networks is designed to perform fault detection, identification, and accomodation which returns the aircraft to a new stable trim. Integrated system is simulated to show the performance of the system with sensor and control surface failures.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.1 no.1
• /
• pp.82-91
• /
• 1998

This paper presents a neural networks based approach for the problem of sensor failure detection and accommodation for ship without physical redundancy in the sensors. The designed model consists of two neural networks. The first neural network is responsible for the failure detection and the second neural network is responsible for the failure identification and accommodation. On the yaw rate sensor of ship, simulation results indicates that the proposed method can be useful as failure detector and sensor estimator.

• 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.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2023.05a
• /
• pp.275-276
• /
• 2023

산업 현장의 기계 시설물 고장 문제는 큰 인명피해와 경제적 손실을 초래할 수 있기 때문에, 기계 시설물의 상태를 기반하여 고장을 진단하는 것은 대단히 중요하다. 따라서, 본 연구에서는 전류 센서 데이터를 활용하여, 시설물의 고장 여부를 진단할 수 있는 알고리즘을 제안한다. 본 연구에 활용된 전류 센서 데이터는 x, y, z축을 가진 3상 전류 데이터로 구성되어 있으며, 2kHz로 1초간 샘플링 되어 있다. 본 연구에서는 2차원적 특성을 가지는 전류 센서 데이터를 분석하기 위해 CNN(Convolution Neural Network)을 활용한다. 시설물의 고장진단에 가장 적합한 모델을 선정하기 위해 CNN의 대표적인 백본 네트워크를 활용하여, 결과를 비교하였다. 실험 결과, 본 연구에서 구성한 후보 백본 네트워크 중 ResNet의 분류 정확도가 98.5%로 가장 높게 나타났다.