• Advances in robotics research
• /
• 제2권1호
• /
• pp.99-112
• /
• 2018

The main contribution of this work is the design of a field programmable gate array (FPGA) based ARX-Laguerre proportional-integral observation (PIO) system for fault detection and identification (FDI) in a multi-input, multi-output (MIMO) nonlinear uncertain dynamical robot manipulators. An ARX-Laguerre method was used in this study to dynamic modeling the robot manipulator in the presence of uncertainty and disturbance. To address the challenges of robustness, fault detection, isolation, and estimation the proposed FPGA-based PI observer was applied to the ARX-Laguerre robot model. The effectiveness and accuracy of FPGA based ARX-Laguerre PIO was tested by first three degrees of the freedom PUMA robot manipulator, yielding 6.3%, 10.73%, and 4.23%, average performance improvement for three types of faults (e.g., actuator fault, sensor faults, and composite fault), respectively.

• 소음진동
• /
• 제8권6호
• /
• pp.1181-1192
• /
• 1998

본 연구에서는 신경조직망을 이용한 항공제어계의 내고장성 성능에 대해 관점을 두었다. 이 내고장성 제어계는 감지기와 작동기의 고장 발견. 확인 그리고 보완으로 이루어진다 SFDIA는 주 신경조직망과 n개의 국소 신경조직망으로 이루어지는데, 여분의 감지기 없이 n개의 감지기로 내고장성 능력을 성취함을 목적으로 한다. 또한, AFDIA는 같은 주 신경조직망과 세개의 신경조직망 제어기들로 구성되며. 이 제어기들은 평형을 유지하는 역할을 하며 고장으로 인한 pitching. rolling. 그리고 yawing moment를 상쇄하는 기능을 한다. 본 연구에서는 특히 잘못된 경보와 고장 확인의 성능이 떨어짐이 없이 SFDIA와 AFDIA의 효과적인 통합 기능을 수행하는데 중점을 두었으며 여러 가지 작동기와 감지기의 고장에 대한 연구 결과가 제시되었다.

• 한국자동차공학회논문집
• /
• 제11권2호
• /
• pp.89-95
• /
• 2003

We consider a problem of application of analytical redundancy to engine synchronization process of spark ignition engines, which is critical to timing for every ECU process including ignition and injection. The engine synchronization process we consider here is performed using the pulse signal obtained by the revolution of crankshaft trigger wheel (CTW) coupled to crank shaft. We propose a discrete-time linear model for the signal, for which we construct FDI (Fault Detection & Isolation) system consisting residual generator and threshold based on linear observer.

• 한국군사과학기술학회지
• /
• 제1권1호
• /
• pp.82-91
• /
• 1998

본 논문에서는 실제 물리적인 여유 센서를 가지지 않는 수중운동체의 센서 고장진단 및 극복에 관한 문제를 신경회로망을 사용하여 접근하였다. 이를 위하여 설계된 신경회로망은 센서 고장 진단을 위한 신경회로망과 고장 확인 및 대체정보 생성을 위한 신경회로망으로 구성하였으며, 온라인(on-line) 학습을 위하여 확장 역전(Extended Back-Propagation) 학습법을 사용하였다. 시뮬레이션은 수중운동체의 방위변화율 센서에 대하여 수행하였으며, 제안된 기법이 센서에 대한 고장진단기와 센서 추정기로 사용할 수 있음을 확인하였다.

• Journal of Computing Science and Engineering
• /
• 제7권4호
• /
• pp.272-284
• /
• 2013

In this paper, we propose a new framework for anomaly detection in medical wireless sensor networks, which are used for remote monitoring of patient vital signs. The proposed framework performs sequential data analysis on a mini gateway used as a base station to detect abnormal changes and to cope with unreliable measurements in collected data without prior knowledge of anomalous events or normal data patterns. The proposed approach is based on the Mahalanobis distance for spatial analysis, and a kernel density estimator for the identification of abnormal temporal patterns. Our main objective is to distinguish between faulty measurements and clinical emergencies in order to reduce false alarms triggered by faulty measurements or ill-behaved sensors. Our experimental results on both real and synthetic medical datasets show that the proposed approach can achieve good detection accuracy with a low false alarm rate (less than 5.5%).

• 한국정밀공학회지
• /
• 제16권2호통권95호
• /
• pp.211-217
• /
• 1999

감지기의 고장 발견, 확인, 보완은 복잡한 항공 시스템의 중요한 문제로 부각되어 왔으며, 그동안 칼만 필터를 이용한 기존 추정기술 혹은 온라인 학습 인공지능 알고리듬 등이 이 같은 문제를 해결하기 위해 제시되어 왔다. 본 연구에서는 여분의 감지기가 없는 항공제어계에 대해 온라인 학습 신경망을 이용한 감지기의 고장 발견, 확인, 그리고 보완에 관해 초점을 둔다. 이 내고장성 항공제어계는 주 신경조직망과 n개의 국소 신경조직망으로 이루어지는데, 포괄적인 감지기의 고장을 발견하는 능력을 가진다. 어떤 경우에서는 기존의 감지기 고장 발견 방법의 성능을 향상시키기 위해 수정된 감지방법이 소개되고 그 보완된 감지방법을 이용하여 기존의 방법과 성능비교가 이루어졌다.

• 한국산학기술학회논문지
• /
• 제2권2호
• /
• pp.81-89
• /
• 2001

우주 항공위성 시스템은 변하는 불확실한 우주항공 환경에(서) 운행되고 지상기지국으로부터의 원격통신 없이 장시간 동안 동작해야 할 자율적인 능력이 요구되고, 결함 없이 임무를 수행하여야 하며, 시스템에서 계측된 데이터의 신뢰성을 유지하기 위한 고장 상태 검출과 오류 수정 시스템을 차보하는 것이 중요하다. 본 논문에서는 확장 칼만 필터 기법을 적용한 동적모델 시뮬레이션 기법(High Fidelity, Dynamic Model-based Simulation)을 제안하였으며, 제안된 시스템은 비정상적인 데이터의 효과적인 검출과 대응이 가능해짐으로써 신뢰성 있는 우주항공위성시스템을 구축하도록 자동 상태 진단/데이터 시스템에 고장검출/오류수정 시스템을 적용하는 것이다. (Autonomous Spacecraft Health Monitoring/Data Validation Control System : ASHMDVCS).

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.97.2-97
• /
• 2002

A method for the non-destructive detection of damage using parameterized partial differential equations and Galerkin approximation techniques is presented. This method provides the theoretical and experimental verification of a nondestructive time domain approach to examine structural damage in smart structure. The time histories of the vibration response of structure were used to identify the presence of damage. Damage in a structure causes changes in the physical coefficients of mass density, elastic modulus and damping coefficient. This paper examines the beam-like structures with PVDF sensor and PZT actuator to perform identification of those physical parameters and to detect the...

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• 한국정밀공학회지
• /
• 제20권4호
• /
• pp.92-102
• /
• 2003

To detect electrical faults of a TFT (Thin Film Transistor) panel for the LCD (Liquid Crystal Display), techniques of converting electric field to an image are used One of them is the PDLC (polymer-dispersed liquid crystal) modulator which changes light transmittance under electric field. The advantage of PDLC modulator in the electric field detection is that it can be used without physically contacting the TFT panel surface. Specific pattern signals are applied to the data and gate electrodes of the panel to charge the pixel electrodes and the image sensor detects the change of transmittance of PDLC positioned in proximity distance above the pixel electrodes. The image represents the status of electric field reflected on the PDLC so that the characteristic of the PDLC itself plays an important role to accurately quantify the defects of TFT panel. In this paper, the image of the PDLC modulator caused by the change of electric field of the pixel electrodes on the TFT panel is acquired and how the characteristics of PDLC reflect the change of electric field to the image is analyzed. When the holding time of PDLC is short, better contrast of electric field image can be obtained by changing the instance of applying the driving voltage to the PDLC.