• 한국통신학회논문지
• /
• 제31권11C호
• /
• pp.1044-1051
• /
• 2006

시스템-레벨 진단 알고리즘은 결함의 개수가 t개를 초과하지 않는다는 t-진단가능 시스템의 특성을 이용한다. 기존의 진단 알고리즘으로 대형 멀티프로세서 시스템에서의 보다 많은 수의 결함을 처리하기에는 한계가 있다. Somani와 Peleg은 진단의 정확 여부를 판단할 수 없는 충분히 작은 개수의 노드가 존재한다는 것을 허용으로써 결함의 갯수가 t개를 초과할 경우에도 시스템을 진단하는 t/k-diagnosable 시스템을 제안하였다. 본 논문에서는 t/k-diagnosable 시스템을 이용한 적응적 방법에 의한 하이퍼큐브 진단 알고리즘을 제안한다. 결함의 개수가 t개를 초과하는 경우에 대하여, k개의 부정확한 진단을 허용한다. 성능 실험 결과 제안 알고리즘은 HADA알고리즘보다 우수함을 보여 주었다. 제안한 알고리즘은 RGC-Ring들의 신드롬을 분석하여 기존의 HADA/IHADA의 기법보다 테스트 라운드를 줄이는 보다 개선된 방법을 제안하였다. 또한 제안 알고리즘은 HYP-DIAG알고리즘과의 성능 비교에서도 유사한 결과를 보여 준다.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권2호
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• 한국소음진동공학회논문집
• /
• 제20권11호
• /
• pp.1009-1017
• /
• 2010

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying various techniques such as signal processing and pattern recognition. Recently, fault diagnosis systems using artificial neural network have been proposed. For effective fault diagnosis, this paper used MLP(multi-layer perceptron) network which is widely used in pattern classification. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes the decision method of the proper feature vectors about each fault signal for neural-network-based fault diagnosis system. We applied LPC coefficients, maximum magnitudes of each spectral section in FFT and RMS(root mean square) and variance of wavelet coefficients as feature vectors and selected appropriate feature vectors as comparing error ratios of fault diagnosis for sound, vibration and current fault signals. From experiment results, LPC coefficients and maximum magnitudes of each spectral section showed 100 % diagnosis ratios for each fault and the method using wavelet coefficients had noise-robust characteristic.

• Journal of Radiation Protection and Research
• /
• 제28권4호
• /
• pp.263-270
• /
• 2003

유방암 진단에 필요한 감마카메라 검출전단부의 최적변수 유도와 유방암 진단조건 하에서의 평가를 위한 몬테카를로 모사를 수행하였다. 모사를 위해 픽셀화된 포토센서에 상응하는 $3mm{\times}3mm$의 구멍과 0.25 mm의 격막두께를 갖는 격자배열구조의 텅스텐 콜리메이터를 이용하였다. 최적변수를 도출하기 위해 검출전단부의 구성 요소를 변화시키면서 기하효율과 공간분해 능의 Trade-Offs 절차를 사용하였다. 최적화된 검출전단부의 사전 성능평가를 위해, 펜텀의 중앙부에 크기가 각기 다르며 콜리메이터 표면으로부터 25 mm 떨어져 있는 유방암이 있고 다른 장기들로부터 나오는 방사선원에 의한 백그라운드 계수를 고려하였다. 유방암의 실제 진단 조건 하에서는 최적화된 검출전단부의 성능이 유방암의 크기와 백그라운드 계수에 따라 저하될 수 있음을 보여 주었다. 따라서 유방암 크기를 변별하는 지표로 쓰이며 검출전단부의 특성에 종속적인 공간분해 능은 유방암의 조기 진단시에는 의미가 없다는 결론을 얻었다.

• Korean Journal of Radiology
• /
• 제22권4호
• /
• pp.612-623
• /
• 2021

Objective: To evaluate the diagnostic performance of a deep learning algorithm for the automated detection of developmental dysplasia of the hip (DDH) on anteroposterior (AP) radiographs. Materials and Methods: Of 2601 hip AP radiographs, 5076 cropped unilateral hip joint images were used to construct a dataset that was further divided into training (80%), validation (10%), or test sets (10%). Three radiologists were asked to label the hip images as normal or DDH. To investigate the diagnostic performance of the deep learning algorithm, we calculated the receiver operating characteristics (ROC), precision-recall curve (PRC) plots, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) and compared them with the performance of radiologists with different levels of experience. Results: The area under the ROC plot generated by the deep learning algorithm and radiologists was 0.988 and 0.988-0.919, respectively. The area under the PRC plot generated by the deep learning algorithm and radiologists was 0.973 and 0.618-0.958, respectively. The sensitivity, specificity, PPV, and NPV of the proposed deep learning algorithm were 98.0, 98.1, 84.5, and 99.8%, respectively. There was no significant difference in the diagnosis of DDH by the algorithm and the radiologist with experience in pediatric radiology (p = 0.180). However, the proposed model showed higher sensitivity, specificity, and PPV, compared to the radiologist without experience in pediatric radiology (p < 0.001). Conclusion: The proposed deep learning algorithm provided an accurate diagnosis of DDH on hip radiographs, which was comparable to the diagnosis by an experienced radiologist.

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2927-2941
• /
• 2022

The primary task of machine fault diagnosis is to judge whether the current state is normal or damaged, so it is a typical binary classification problem with mutual exclusion. Mutually exclusive events and out-of-domain detection have one thing in common: there are two types of data and no intersection. We proposed a fusion model method to improve the accuracy of machine fault diagnosis, which is based on the mutual exclusivity of events and the commonality of out-of-distribution detection, and finally generalized to all binary classification problems. It is reported that the performance of a convolutional neural network (CNN) will decrease as the recognition type increases, so the variational auto-encoder (VAE) is used as the primary model. Two VAE models are used to train the machine's normal and fault sound data. Two reconstruction probabilities will be obtained during the test. The smaller value is transformed into a correction value of another value according to the mutually exclusive characteristics. Finally, the classification result is obtained according to the fusion algorithm. Filtering normal data features from fault data features is proposed, which shields the interference and makes the fault features more prominent. We confirm that good performance improvements have been achieved in the machine fault detection data set, and the results are better than most mainstream models.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2017년도 제48회 춘계학술대회논문집
• /
• pp.218-223
• /
• 2017

본 논문은 75톤급 액체로켓엔진의 상태진단을 위해 칼만 필터를 이용한 고장진단 연구를 수행하였다. 칼만 필터 설계를 위해 75톤급 액체로켓엔진 비선형 시뮬레이션 모델을 공칭 작동점에서 선형화하였으며, 정상 모델의 상태량 변수 4가지를 이용하여 측정값과 추정값 비교를 통해 칼만 필터의 성능을 확인하였다. 이를 이용한 고장진단 알고리즘의 성능을 확인하기 위하여 터보펌프 고장을 모사하였으며 정상 모델의 잔차 변화를 비교하여 칼만 필터를 이용한 고장진단이 가능함을 확인하였다.

• 한국경영과학회지
• /
• 제37권3호
• /
• pp.23-37
• /
• 2012

As Customer Relationship Management (CRM) strategy is becoming a core competence more recently, many companies want a reliable CRM assessment system which enables measuring and diagnosing corporate customer strategies for building an optimized CRM strategy. However, there has been short of researches on developing the CRM diagnosis methodology that is directly applicable to real practices. Drawing upon the theoretical framework of CRM scorecard, we developed and suggested a corporate CRM diagnosis methodology that can systematically understand and assess the corporate CRM capability and performance, guiding their future directions. Companies can search the important but weak areas among various CRM strategy subjects through the proposed diagnostic procedures. This framework has a hierarchical structure that has four evaluative domains each of which has several evaluative subjects consisting of many evaluative themes: the score of upper factor is the weighted average of its subordinate factor scores. And the score of each evaluative theme is the weighted average of quantitative and qualitative evaluative indexes. Quantitative indexes are calculated by analyzing customer and sales data and qualitative ones are derived from survey data. Each evaluative index has more than one measure and its score can be derived from its own formula consisting of the measures. To prove the concept, we applied this framework to a real company and concluded that it might be appropriate to understand the corporate CRM strategy situation, find the pain points, and resolve them for better CRM implementation.

• 설비공학논문집
• /
• 제20권10호
• /
• pp.669-678
• /
• 2008

When operating a complex facility, Fault Detection and Diagnosis (FDD) system is beneficial in equipment management by providing the operator with tools which can help find out a failure of the system. In this research, FDD algorithm was developed using the general pattern classifier method that can be applied to centrifugal chiller system. The simulation model for a centrifugal chiller system was developed in order to obtain characteristic data of turbo chiller system under normal and faulty operation. We tested FDD algorithm of a centrifugal chiller using data from simulation model at full load performance and 60% part load performance. In this research, we presented fault detection method using a normalized distance. Sensitivity analysis of fault detection was carried out with respect to fault progress. FDD algorithm developed in this study was found to indicate each failure modes accurately.