• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.1-16
• /
• 2011

In this paper, we proposed the Failure-Diagnostic Context-awareness Middleware (FDCM) for improving the reliability in the USN application service. The middleware diagnoses the failure occurred in sensors or facilities in the indoor USN application system. The new middleware suggested in this paper consists of DataManagement module, ContextProvider module, Contextlnterpreter module, ServiceProvider module and DataStorage module. By analysing the data obtained by the interaction between modules through the diagnostic algorithm, the FDCM determines the malfunction of sensors and equipment devices. Then we verified the performance of middleware by using simulation. As a result, the FDCM showed the high performance in the large systems that many of the sensors and devices are installed.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.2
• /
• pp.141-151
• /
• 2011

This paper suggests the Facility Management System for plant factory promising to be a core technology of the agriculture in the future. This system makes diagnoses that status from sensors or facilities in the factory for exact operation and monitors the internal environment with the control status in real-time. It is expected that we could operate a plant factory safely and effectively by using the system. The system consists of the data management module, the context provider module, the context interpreter module, the service provider module, the data storage and user interface. The system provide with the failure diagnosis service, the facility control service, and the high-reliability monitoring service via the interactions between above modules. The failure diagnosis service determines whether the sensors or facility devices are in failure or not, and informs the administrator of their conditions. The facility control service is activated in case if the facilities need to be managed during the diagnosis for failure or malfunction processes. The high-reliability monitoring service provides the administrator with verified data through the failure diagnosis service. Then we confirmed that the suggested system operates correctly through the system simulation.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1836-1837
• /
• 2006

본 논문에서는 차량용 전자제어식 주차 브레이크(Electric Parking Brake, EPB) 시스템의 고장 허용 제어(fault tolerant control)를 위한 고장 안전 기법(fail-safe logic)을 제안한다. 고장 안전 기법의 구현을 위하여 EPB 구동 모터에 흐르는 전류 리플을 측정하여 센서리스 위치 추정을 한다. 추정값과 홀 센서의 출력을 비교하여 잔차(residual)를 발생하고, 이를 이용하여 시스템 내부의 고장을 진단하고 고장 안전 기법을 통하여 전체 시스템의 오작동을 방지한다. 시스템 오작동을 방지하기 위한 고장 안전 기법에 대하여 정의하고 모의실험을 통하여 내부 시스템의 고장이 발생 시 이 기법이 고장을 진단하고 시스템을 안전하게 운영할 수 있음을 확인하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.237-239
• /
• 2021

Failure and malfunction of the unmanned surveillance facility cost can lead to delays occurring until the person in charge arrives at the unmanned surveillance facility, and theft, damage, and information leakage damage caused by intruders. In addition, due to equipment failure and malfunction, additional costs are incurred due to constant inspection by the manager. In this paper, in order to compensate for the malfunction of unmanned facility costs, we propose a system that diagnoses the monitoring facility in real time, displays the contents of the problem, automatically restores the facility power, and informs the person in charge of the situation by text message. The proposed system is a surveillance facility consisting of main facilities such as video equipment (CCTV), sound equipment, floodlights, etc. And SMS server that can send text messages in real time. Through experiments, the effectiveness of the proposed system was verified.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.355-357
• /
• 2017

With the development of automation technology and the increase of large-scale automation projects, sensors used for state monitor and parameter measurement have become more and more important. Once the sensor faults occur, which will lead to the degradation of automation system's performance, and even disastrous consequences. In this paper, sensor output value modeling is performed using Kung's Algorithm for direct fault diagnosis of sensor, and fault diagnosis method based on decision theory is presented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2708-2716
• /
• 2013

This paper presents implementation of embedded remote monitoring diagnosis system which has effective wireless channel structure and communication protocols with user-friendly UI for intelligent digital vessel. Developed system contains integrated vessel monitoring system, server, exclusive mobile terminal and smart phone. We designed an effective dual structure communication channel and simple but effective communication protocol on the monitoring system. Failures of the wireless communication are minimized and the wrong wireless communication channel is immediately replaced. In addition, we developed an effective embedded Linux UI for LCD. The implemented wireless monitoring system was tested and verified on digital vessel.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.2
• /
• pp.283-288
• /
• 2015

The possible erroneous output data of the sensor nodes can cause the performance limit or the degradation of the reliability in the whole wireless sensor networks(WSN). In this paper, we propose a new sensor node scheme with multiple sensors and a new fault diagnostic algorithm. The algorithm can increase the reliability of the whole WSNs by utilizing measurements of the multiple sensors on the node and by determining the validity of the date by comparing the value of each sensor. It can increase the cost and complexity of the node, but is suitable for the area where the high reliability is critical.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.47-55
• /
• 2015

To verify the function of vehicle is becoming more and more difficult because many electronic control units have been embedded in vehicle with development of electronics industry. The reliability of vehicle should be considered above all important because malfunction of vehicle can cause damage of human life. In this paper, defect diagnosis platform based on CAN network is proposed to improve the reliability of vehicle. Reliability of vehicle is significantly increased by adopting the structural test via dedicated test path after manufacturing. Besides, the test cost is reduced because additional test pins are not required.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.215-220
• /
• 2013

Recently, death number of heart attack in the world is increasing rapidly. Therefore, to solve these problem, it is trend that is making mandatory automatic defibrillator AED establishment to airport, school, at home. However, AED use in an emergency or equipment failure caused malfunctions if equipped with AED may even become obsolete. In this paper, in order to improve this problem, AED Simulator using the fuzzy simulation technique in comparison to existing methods Tilt ambient temperature conditions and in consideration of the conditions, self-diagnostics, error detection at the time to determine whether the development of intelligent simulation. Moreover, in this paper, it proved that fuzzy AED Simulation improved fault detection probability results 30% more than conventional method.

• 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.