• 한국항공우주학회지
• /
• 제30권7호
• /
• pp.61-67
• /
• 2002

본 논문에서는 항공기의 제어면 혹은 구동장치가 고장이 났을 때 이를 신속하게 진단규명하고 안정한 상태로 되돌리기 위한 고장보완제어시스템을 설계한다. 제어시스템 설계에는 수렴 속도가 빠른 확장 역전파 알고리즘을 적용한 신경회로망을 이용한다. 제어대상으로는 비선형 운동방정식으로 표현된 F-4 항공기이며 수평미익이나 에일러런의 고장이 발생할 경우에 대하여 제어시스템을 설계하고 시뮬레이션을 통하여 성능을 검증한다.

• 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.

• 한국항공우주학회지
• /
• 제39권2호
• /
• pp.144-152
• /
• 2011

본 논문에서는 인공위성 자세제어 시스템의 고장 검출 기법을 제시하였다. 논문에서는 상호간섭 다중모델을 기반으로 벌점을 이용하여 인공위성 자세 시스템 중 구동기의 완전 고장과 구동력 저하 고장을 검출하였다. 제안한 고장 검출 기법은 2단계로 구분되는데, 먼저 11개의 구동기 고장 관련 모델을 구성하여 구동기 고장 검출을 수행한 후, 구동기의 고장이 검출되면 구동기의 고장 특성에 관련된 하위 모델을 생성하여 실제 발생한 고장이 완전 고장인지 구동력 저하 고장인지를 구분하게 된다. 또한 기존에 제안된 상호간섭 다중모델을 이용한 고장 검출 기법과 비교한 결과, 본 논문에서는 병렬로 구성되었던 고장 모델들을 2단계로 구성하고 각 단계별로 차등화된 벌점을 이용함으로써 구동기 고장 검출 시간을 줄였을 뿐만 아니라, 고장의 특성까지 빠르게 구분할 수 있는 장점이 있음을 확인 하였다.

• 대한기계학회논문집B
• /
• 제34권4호
• /
• pp.333-339
• /
• 2010

고장감지 및 진단(FDD) 시스템의 구축의 기초 연구로 정상상태 진단기에 대한 연구를 수행하였다. 정상상태에 대한 진단은 시스템 전체를 관찰하거나 몇몇 필요한 시스템 파라미터를 모니터링 함으로써 가능하다. 최적화된 정상상태 진단기를 이용하면 FDD 시스템에서 필수적인 정상운전 시의 기준모델(no fault reference model)을 자가학습을 통하여 적용할 수 있다. 본 연구에서는 가정용 열펌프가 냉방조건으로 작동할 경우에 대해 이동창을 기반으로 7개의 측정값들에 대한 표준편차를 분석함으로써 정상상태 판정을 내리도록 하였다. 정상상태 진단기의 작동의 여부는 실내부하를 조절함으로써 확인하였다. 본 연구를 통하여 열펌프 등의 증기압축 사이클 시스템에 대하여 이동창을 기반으로 한 정상상태 진단기 개발 방법을 제시하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.447-452
• /
• 1998

A fault is considered as a variation of physical parameters; therefore the design of fault detection and identification(FDI) can be reduced to the parameter identification of a non linear system and to the association of the set of the estimated parameters with the mode of faults. ANFIS(Adaptive Neuro-Fuzzy Inference System) which contains multiple linear models as consequent part is used to model non linear systems. In this paper, we proposes an FDI system for non linear systems using ANFIS. The proposed diagnositc system consists of two ANFISs which operate in two different modes (parallel-and series-parallel mode). It generates the parameter residuals associated with each modes of faults which can be further processed by additional RBF (Radial Basis function) network to identify the faults. The proposed FDI scheme has been tested by simultation on a two-tank system

• International Journal of Aeronautical and Space Sciences
• /
• 제9권1호
• /
• pp.100-110
• /
• 2008

It is not easy to monitor and identify all engine faults and conditions using conventional fault detection approaches like the GPA (Gas Path Analysis) method due to the nature and complexity of the faults. This study therefore focuses on a model based diagnostic method using Neural Network algorithms proposed for fault detection on a turbo shaft engine (PW 206C) selected as the power plant for a tilt rotor type unmanned aerial vehicle (Smart UAV). The model based diagnosis should be performed by a precise performance model. However component maps for the performance model were not provided by the engine manufacturer. Therefore they were generated by a new component map generation method, namely hybrid method using system identification and genetic algorithms that identifies inversely component characteristics from limited performance deck data provided by the engine manufacturer. Performance simulations at different operating conditions were performed on the PW206C turbo shaft engine using SIMULINK. In order to train the proposed BPNN (Back Propagation Neural Network), performance data sets obtained from performance analysis results using various implanted component degradations were used. The trained NN system could reasonably detect the faulted components including the fault pattern and quantity of the study engine at various operating conditions.

• Smart Structures and Systems
• /
• 제19권2호
• /
• pp.195-202
• /
• 2017

The aim of this paper is to develop a novel method to determine the severity of a damage in a thin plate. This paper presents a novel fault detection and diagnosis approach employing a new electromagnetic acoustic transducer, called EMAT, together with a complex signal processing method. The method consists in the recognition of a fault that exists within the structure, the fault location, i.e. the identification of the geometric position of damage, and the determining the significance of the damage, which indicates the importance or severity of the defect. The main scientific novelties presented in this paper is: to develop of a new type of electromagnetic acoustic transducer; to incorporate wavelet transforms for signal representation enhancements; to investigate multi-parametric analysis for noise identification and defect classification; to study attenuation curves properties for defect localization improvement; flaw sizing and location algorithm development.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.204-210
• /
• 1998

This paper discusses an on-line fuzzy dynamic model(FDM) identification of nonlinear processes for the design of fuzzy model based fault detection and isolation(FDI). The dynamic behavior of a nonlinear process is represented by a fuzzy aggregation of a set of local linear models. The identification is divided into two procedures. The first is the off-line identification of membership function. The second is the on-line identification of the local linear models. Then, we propose a residual generation scheme based on the parameters of local linear models and show that the scheme can be used for the design of FDI

• Smart Structures and Systems
• /
• 제23권4호
• /
• pp.393-403
• /
• 2019

Applying more features gives us better accuracy in modeling; however, increasing the inputs causes the curse of dimensions. In this paper, a new structure has been proposed for fault detecting and identifying (FDI) of high-dimensional systems. This structure consist of two structure. The first part includes Auto-Encoders (AE) as Deep Neural Networks (DNNs) to produce feature engineering process and summarize the features. The second part consists of the Local Model Networks (LMNs) with LOcally LInear MOdel Tree (LOLIMOT) algorithm to model outputs (multiple models). The fault detection is based on these multiple models. Hence the residuals generated by comparing the system output and multiple models have been used to alarm the faults. To show the effectiveness of the proposed structure, it is tested on single-shaft industrial gas turbine prototype model. Finally, a brief comparison between the simulated results and several related works is presented and the well performance of the proposed structure has been illustrated.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.