• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• 한국BIM학회 논문집
• /
• 제8권4호
• /
• pp.13-22
• /
• 2018

Future performance prediction of bridges is challenging task for structural engineers. Well-organized information from design, construction and operation stages is essential for the assessment of structures. Digital twin model is a new concept to realize more reliable data platform for management of infrastructures. Damage history including degradation of material, cracking, corrosion, etc. needs to be accumulated in the digital model. The digital model is linked to the analysis model for the assessment of structural performance considering changed mechanical properties of structural components. In this paper, initial definition digital twin model of a PSC-I girder bridge is proposed.

• 한국정보전자통신기술학회논문지
• /
• 제16권2호
• /
• pp.61-68
• /
• 2023

수중통신에서 다중 밴드 기법은 채널 부호화된 동일한 데이터를 여러 주파수 밴드로 나누어 전송하는 기법인데, 이는 수중에서 다중 경로, 도플러 확산 등으로 인한 특정 주파수의 선택적 페이딩 현상을 극복하면서 성능을 향상시키는 기법이다. 이러한 다중 밴드 통신의 단점은 성능이 열악한 특정한 밴드가 전체 성능에 영향을 미친다. 따라서 본 논문에서는 다중 밴드 통신에서 각 밴드의 성능을 예측하여 가장 신뢰성이 높은 밴드를 선택함으로써 성능을 향상시키는데, 본 논문에서는 세 가지 성능을 예측하는 기법을 제시하였으며, 실험을 통하여 프리엠블 오류율을 이용하는 방법이 가장 효율적인 방법임을 확인하였다.

• 전자공학회논문지
• /
• 제53권1호
• /
• pp.51-58
• /
• 2016

반도체 제조공정의 발달로 칩의 성능은 더욱 향상되었으나 회로가 미세해지고 복잡해져 동작 환경에 의한 회로의 노화가 가속화 될 수 있다. 회로의 노화는 성능 저하로 나타나며, 결과적으로 시스템 오류를 발생 시킬 수 있다. 고신뢰 시스템에서는, 노화로 인한 오류가 큰 재난으로 이어질 수 있으므로, 사고를 예방하기 위한 오류 발생 예측 기술이 필수적이다. 본 논문에서는 회로의 정상동작 중에 성능 저하를 감지하여 오류를 예측 할 수 있는 모니터링 기법을 제시한다. 모니터링을 위한 별도의 회로를 추가하지 않고 경계 스캔 셀과 TAP 제어기를 재활용한 IEEE 1149.1 경계 스캔 기반의 온-라인 성능 저하 모니터링 방법을 제시한다. 시뮬레이션을 통하여 제안하는 성능 저하 모니터링 기법을 검증한다.

• Nuclear Engineering and Technology
• /
• 제54권6호
• /
• pp.2107-2119
• /
• 2022

Accurate remaining useful life (RUL) prediction for critical components of nuclear power equipment is an important way to realize aging management of nuclear power equipment. The electric gate valve is one of the most safety-critical and widely distributed mechanical equipment in nuclear power installations. However, the electric gate valve's extended service in nuclear installations causes aging and degradation induced by crack propagation and leakages. Hence, it is necessary to develop a robust RUL prediction method to evaluate its operating state. Although the particle filter(PF) algorithm and its variants can deal with this nonlinear problem effectively, they suffer from severe particle degeneracy and depletion, which leads to its sub-optimal performance. In this study, we combined the whale algorithm with regularized particle filtering(RPF) to rationalize the particle distribution before resampling, so as to solve the problem of particle degradation, and for valve RUL prediction. The valve's crack propagation is studied using the RPF approach, which takes the Paris Law as a condition function. The crack growth is observed and updated using the root-mean-square (RMS) signal collected from the acoustic emission sensor. At the same time, the proposed method is compared with other optimization algorithms, such as particle swarm optimization algorithm, and verified by the realistic valve aging experimental data. The conclusion shows that the proposed method can effectively predict and analyze the typical valve degradation patterns.

• Steel and Composite Structures
• /
• 제8권6호
• /
• pp.441-455
• /
• 2008

This paper presents an effective hysteretic model for the prediction and evaluation of steel reinforced concrete member seismic performance. This model adopts the load-deformation relationship acquired from monotonic load tests and incorporates the double-pivot behavior of composite members subjected to cyclic loads. Deterioration in member stiffness was accounted in the analytical model. The composite member performance assessment control parameters were calibrated from the test results. Comparisons between the cyclic load test results and analytical model validated the proposed method's effectiveness.

• 한국통신학회논문지
• /
• 제22권10호
• /
• pp.2339-2347
• /
• 1997

The performance of the adaptive noise canceller using LMS algorithm is degraded by the gradient noise due to target speech signals. An adaptive noise canceller with speech detector was proposed to reduce this performande degradation. The speech detector utilized the adaptive prediction-error filter adapted by the NLMS algorithm. This paper discusses to enhance the performance of the adaptive noise canceller forthecorlored noise. The affine projection algorithm, which is known as faster than NLMS algorithm for correlated signals, is used to adapt the adaptive filter and the adaptive prediction error filter. When the voice signals are detected by the speech detector, coefficients of adaptive filter are adapted by the sign-error afine projection algorithm which is modified to reduce the miaslignment of adaptive filter coefficients. Otherwirse, they are adapted by affine projection algorithm. To obtain better performance, the proper step size of sign-error affine projection algorithm is discussed. As resutls of computer simulation, it is shown that the performance of the proposed ANC is better than that of conventional one.

• 한국음향학회지
• /
• 제18권6호
• /
• pp.38-43
• /
• 1999

SK Telecom에서 현재 서비스중인 EVRC 보코더는 유선전화 수준의 음질을 제공하는 우수한 음성 부호화기이나, 약전계에서 급격한 음질 저하를 보인다. 본 논문에서는 실제 서비스 상황에서 발생하는 EVRC 보코더의 음질 저하 현상 및 그 원인을 분석하였고, 해결책으로 피치 예측과 점진적 복원 기법을 제안하였다. 다양한 전파환경에 대한 음질 평가방법으로 선호도 실험을 수행하였고, 제안한 방법이 효과적임을 확인하였다.

• 한국공간정보시스템학회 논문지
• /
• 제8권1호
• /
• pp.17-25
• /
• 2006

TPR*-트리는 효과적으로 이동 객체의 미래 위치 예측을 수행하기 위하여 가장 널리 사용되는 인덱스 구조이다. 그러나 TPR*-트리는 인덱스 생성 이후 미래 예측 시점이 증가함에 따라 사장 영역과 영역중복의 문제가 커지며, 이로 인하여 질의 처리 시 액세스되는 TPR*-트리 노드들의 수가 많아지는 성능 문제가 발생한다. 본 논문에서는 실험을 통하여 이러한 성능 저하의 문제점을 정량적으로 규명한다. 먼저, 미래 예측 시점이 증가함에 따라 질의 처리 성능이 얼마나 저하되는가를 보이고, 이동 객체의 위치 갱신 연산이 이러한 성능 저하 문제를 얼마나 완화시키는가를 보인다. 이러한 공헌은 TPR*-트리의 추가적인 성능 개선을 위한 정책을 고안하는데, 중요한 실마리를 제공할 수 있을 것이다.

• 한국태양에너지학회 논문집
• /
• 제37권1호
• /
• pp.81-90
• /
• 2017

We have analyzed the performance of 58 kWp photovoltaic (PV) power systems installed in Jeddah, Saudi Arabia. Performance ratio (PR) of 3 PV systems with 3 desert-type PV modules using monitoring data for 1 year showed 85.5% on average. Annual degradation rate of 5 individual modules achieved 0.26%, the regression model using monitoring data for the specified interval of one year showed 0.22%. Root mean square error (RMSE) of 6 big data analysis models for power output prediction in May 2016 was analyzed 2.94% using a support vector regression model.