• 한국산업정보학회논문지
• /
• 제25권6호
• /
• pp.1-13
• /
• 2020

본 논문에서는 원전 비상 상황 발생 시 다수의 신호 오류가 발생했을 때 어떤 신호에 오류가 발생했는지를 추정하는 신호 오류 식별 (Fault identification) 방법론을 개발하였다. 변분 오토인 코더 (Variational autoencoder; VAE) 기반 모델은 기존의 이상 탐지 방법론과 같이 정상 신호 데이터만을 이용하여 훈련이 진행되며, 이후 각 신호에 대한 복원 오차 (Reconstruction error)와 복원 오차를 입력의 특정 부분으로 미분한 값을 이용하여 어떤 부분에 오류가 포함되어 있는지를 예측한다. 데이터 취득을 위하여 시뮬레이션을 수행하였으며, 일련의 실험으로부터 제시한 신호 오류 식별 방법이 적절한 오차 범위 내에서 오류가 발생한 신호를 특정할 수 있음을 확인하였다.

• 자동차안전학회지
• /
• 제13권1호
• /
• pp.14-25
• /
• 2021

This paper presents a RLS based adaptive sliding mode observer (A-SMO) for unknown fault reconstruction in longitudinal autonomous driving. Securing the functional safety of autonomous vehicles from unexpected faults of sensors is essential for avoidance of fatal accidents. Because the magnitude and type of the faults cannot be known exactly, the RLS based A-SMO for unknown acceleration fault reconstruction has been designed with relationship function in this study. It is assumed that longitudinal acceleration of preceding vehicle can be obtained by using the V2V (Vehicle to Vehicle) communication. The kinematic model that represents relative relation between subject and preceding vehicles has been used for fault reconstruction. In order to reconstruct fault signal in acceleration, the magnitude of the injection term has been adjusted by adaptation rule designed based on MIT rule. The proposed A-SMO in this study was developed in Matlab/Simulink environment. Performance evaluation has been conducted using the commercial software (CarMaker) with car-following scenario and evaluation results show that maximum reconstruction error ratios exist within range of ±10%.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.2582-2587
• /
• 2003

This paper proposes an application of sliding mode observer to the problem of fault detection and reconstruction for descriptor systems with both actuator and sensor faults. In detecting and reconstructing the faults simultaneously, first, we will consider the fault detection problem for sensor fault. The detection of sensor fault is achieved from the design of the matrix which eliminates the influence of actuator fault. Secondly, the sliding mode observer which adds the general full-order observer for descriptor system to feedforward injection map and feedforward compensation signal is designed, and through which the sensor fault is reconstructed. Finally, with the reconstructed sensor fault, and by eliminating differential term of the sensor fault, the actuator fault is detected and reconstructed.

• 드라이브 ㆍ 컨트롤
• /
• 제14권2호
• /
• pp.30-36
• /
• 2017

This paper presents a sliding mode observer-based fault detection algorithm for steering inputs of an all-terrain crane. All-terrain cranes with multi-axles have several steering modes for various working purposes. Since steering angles at the other axles except the first wheel are controlled by using the information of steering angle at the first wheel, a reliable signal of the first axle's steering angle should be secured for the driving safety of cranes. For the fault detection of steering input signal, a simplified crane model-based sliding mode observer has been used. Using a sliding mode observer with an equivalent output injection signal that represents an actual fault signal, a fault signal in steering input was reconstructed. The road steering mode of the crane's steering system was used to conduct performance evaluations of a proposed algorithm, and an arbitrary fault signal was applied to the steering angle at the first wheel. Since the road steering mode has different steering strategies according to different speed intervals, performance evaluations were conducted based on the curved path scenario with various speed conditions. The design of algorithms and performance evaluations were conducted on Matlab/Simulink environment, and evaluation results reveal that the proposed algorithm is capable of detecting and reconstructing a fault signal reasonably well.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 추계종합학술대회
• /
• pp.452-456
• /
• 2002

자연환경에 노출된 센서기반의 제어장치는 센서오류가 발생하게 된다. 본 논문에서는 센서의 오류 보정기능을 갖는 고정밀 태양추적장치를 개발하였다. 다항식회귀분석 (Polynomial Regression)과 주성분 분석(Principal Component Analysis)을 응용하였으며 태양추적장치의 센서를 모델링하고 자체 진단하고 복구하는 방법을 연구하였다. 시스템의 정상동작시의 센서간의 상호관계를 이용한 모델링과 센서 표본값의 주분포 모델인 PCA 모델이 이루어지면 이를 기준으로 센서의 여러 가지 오류를 점검하고 오류센서 신호를 재건을 한다.