• Smart Structures and Systems
• /
• 제33권4호
• /
• pp.301-311
• /
• 2024

This paper proposes a deep convolutional long short-term memory (ConvLSTM)-based crack growth prediction technique for predictive maintenance of structures. Since cracks are one of the critical damage types in a structure, their regular inspection has been mandatory for structural safety and serviceability. To effectively establish the structural maintenance plan using the inspection results, crack propagation or growth prediction is essential. However, conventional crack prediction techniques based on mathematical models are not typically suitable for tracking complex nonlinear crack propagation mechanism on civil structures under harsh environmental conditions. To address the technical issue, a field data-driven crack growth prediction technique using ConvLSTM is newly proposed in this study. The proposed technique consists of the four steps: (1) time-series crack image acquisition, (2) target image stabilization, (3) deep learning-based crack detection and quantification and (4) crack growth prediction. The performance of the proposed technique is experimentally validated using a concrete mock-up specimen by applying step-wise bending loads to generate crack growth. The validation test results reveal the prediction accuracy of 94% on average compared with the ground truth obtained by field measurement.

• 대기
• /
• 제27권2호
• /
• pp.235-249
• /
• 2017

This paper describes methodology verifying near-surface predictability of numerical weather prediction models against the surface synoptic weather station network (SYNOP) observation. As verification variables, temperature, wind, humidity-related variables, total cloud cover, and surface pressure are included in this tool. Quality controlled SYNOP observation through the pre-processing for data assimilation is used. To consider the difference of topographic height between observation and model grid points, vertical inter/extrapolation is applied for temperature, humidity, and surface pressure verification. This verification algorithm is applied for verifying medium-range forecasts by a global forecasting model developed by Korea Institute of Atmospheric Prediction Systems to measure the near-surface predictability of the model and to evaluate the capability of the developed verification tool. It is found that the verification of near-surface prediction against SYNOP observation shows consistency with verification of upper atmosphere against global radiosonde observation, suggesting reliability of those data and demonstrating importance of verification against in-situ measurement as well. Although verifying modeled total cloud cover with observation might have limitation due to the different definition between the model and observation, it is also capable to diagnose the relative bias of model predictability such as a regional reliability and diurnal evolution of the bias.

• 정보처리학회논문지A
• /
• 제16A권5호
• /
• pp.347-356
• /
• 2009

정교한 분기 예측기의 설계는 오늘날의 프로세서 성능 향상에 중요한 역할을 하게 되었다. 분기 예측의 정확도가 더욱 더 중요해 지면서 정확도의 향상을 위한 다수의 기법들이 제안되었지만, 기존의 연구들은 예측 지연 시간을 간과하는 경향이 있었다. 본 논문에서는 예측 지연 시간 문제를 해결하고자 조기 예측 기법 (ESP, Early Start Prediction)을 제안한다. 조기 예측 기법은 분기 예측에 있어서 활용되는 분기 명령어의 주소 대신 그것과 일대일 대응이 되는 기본 블록의 시작 주소 (BB_SA, Basic Block Start Address)를 이용한다. 즉, 분기 명령어의 주소가 사용되는 기존의 환경에서, BB_SA를 활용하여 조기 예측을 시작함으로써, 예측 지연 시간을 숨긴다. 또한 제안된 기법은 짧은 간격 숨김 기법(short interval hiding technique)을 통해 보다 더 나은 성능 향상을 기대할 수 있다. 실험 결과 본 논문에서 제안된 기법은 예측 지연 시간을 줄임으로써, 예측 지연 시간이 1 사이클인 이상적인 분기 예측기의 성능에 0.25% 이내로 근접한 IPC 결과를 얻었다. 또한 기본 블록의 시작주소와 분기 명령어 사이에 짧은 간격을 가질 경우에 대한 개선 방법을 추가적으로 적용시킬 경우, 기존의 방식과 비교하여 평균 4.2%, 최대 10.1%의 IPC 향상을 가져왔다.

• 한국시뮬레이션학회논문지
• /
• 제25권4호
• /
• pp.77-84
• /
• 2016

본 논문은 시스템에 대한 기능 중심의 신뢰도 예측을 수행하기 위한 모델링 방법론을 제안한다. 신뢰도 예측에 대한 다양한 기존 연구들이 있지만, 이 연구들의 공통점은 하드웨어 중심으로 신뢰도 예측을 수행하였다는 점이다. 신뢰성이 제품이 주어진 사용 조건 아래서 의도하는 기간 동안 정해진 기능을 성공적으로 수행하는 능력이라고 정의되는 점에서 보았을 때, 하드웨어 중심의 신뢰도는 논리적 모순을 가진다. 본 논문에서는 기능 중심의 신뢰도 예측을 위해 4-단계 모델링 절차(four-phase modeling procedure)를 제안하였다. 제안되는 모델링 방법론은 네 개의 모델로 구성된다; 1) 구조적 블록 모델(structure block model), 2) 기능 블록 모델 (function block model), 3) 장치 모델 (device model), 그리고 4) 신뢰성 예측 모델 (reliability prediction model). 본 논문에서는 제안하는 모델링 방법론을 이용하여 전자식 안정기에 대한 기능 중심의 신뢰도 예측을 수행하였으며, 하드웨어의 신뢰도를 결정하기 위해 신뢰도 예측 규격 중 하나인 MIL-HDBK-217F를 이용하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.119-127
• /
• 2022

Most of the construction works are conducted outdoors, so the construction workers are affected by weather conditions such as temperature, humidity, and wind velocity which can be evaluated the thermal comfort as environmental factors. In our previous researches, it was found that construction accidents are usually occurred in the discomfort ranges. The safety management, therefore, should be planned in consideration of the thermal comfort and measured by a specialized simulation tool. However, it is very complex, time-consuming, and difficult to model. To address this issue, this study is aimed to develop a framework of a prediction model for improving the prediction accuracy about outdoor thermal comfort considering environmental factors using machine learning algorithms with hyperparameter tuning. This study is done in four steps: i) Establishment of database, ii) Selection of variables to develop prediction model, iii) Development of prediction model; iv) Conducting of hyperparameter tuning. The tree type algorithm is used to develop the prediction model. The results of this study are as follows. First, considering three variables related to environmental factor, the prediction accuracy was 85.74%. Second, the prediction accuracy was 86.55% when considering four environmental factors. Third, after conducting hyperparameter tuning, the prediction accuracy was increased up to 87.28%. This study has several contributions. First, using this prediction model, the thermal comfort can be calculated easily and quickly. Second, using this prediction model, the safety management can be utilized to manage the construction accident considering weather conditions.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.509-523
• /
• 2005

We are developing a novel framework, PRIDE (PRediction In Dynamic Environments), to perform moving object prediction (MOP) for autonomous ground vehicles. The underlying concept is based upon a multi-resolutional, hierarchical approach which incorporates multiple prediction algorithms into a single, unifying framework. The lower levels of the framework utilize estimation-theoretic short-term predictions while the upper levels utilize a probabilistic prediction approach based on situation recognition with an underlying cost model. The estimation-theoretic short-term prediction is via an extended Kalman filter-based algorithm using sensor data to predict the future location of moving objects with an associated confidence measure. The proposed estimation-theoretic approach does not incorporate a priori knowledge such as road networks and traffic signage and assumes uninfluenced constant trajectory and is thus suited for short-term prediction in both on-road and off-road driving. In this article, we analyze the complementary role played by vehicle kinematic models in such short-term prediction of moving objects. In particular, the importance of vehicle process models and their effect on predicting the positions and orientations of moving objects for autonomous ground vehicle navigation are examined. We present results using field data obtained from different autonomous ground vehicles operating in outdoor environments.

• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.524-532
• /
• 2015

All data created in BigData times is included potentially meaning and correlation in data. A variety of data during a day in all society sectors has become created and stored. Research areas in analysis and grasp meaning between data is proceeding briskly. Especially, accuracy of meaning prediction and data imbalance problem between data for analysis is part in course of something important in data analysis field. In this paper, we proposed data prediction model based on data weights and neural network using R for meaning analysis between data. Proposed data prediction model is composed of classification model and analysis model. Classification model is working as weights application of normal distribution and optimum independent variable selection of multiple regression analysis. Analysis model role is increased prediction accuracy of output variable through neural network. Performance evaluation result, we were confirmed superiority of prediction model so that performance of result prediction through primitive data was measured 87.475% by proposed data prediction model.

• 한국정보처리학회논문지
• /
• 제5권10호
• /
• pp.2676-2685
• /
• 1998

본 논문에서는 파이프라인 프로세서의 분기 명령어 처리 성능 향상을 목적으로, BTB의 미스율을 줄이고 분기 예측의 정확도를 개선하기 위해 victim cache를 활용한 2-단계 BTB 구조를 제안한다. 2-단계 BTB는 기존의 BTB에 작은 크기의 victim BTB를 추가한 구조로, 적은 비용으로 BTB 미스율을 개선하고, 동적 예측(dynamic prediction)과 정적 예측 (static prediction)이 함께 사용되는 기존의 통합 분기 예측(Hybrid Branch Prediction) 구조의 예측 정확도를 높이도록 운영된다. 본 논문에서 제안된 2-단계 BTB에 의한 성능 개선을 4개 벤치마크 프로그램에 대한 trace-driven 시뮬레이션을 통해 검증한 결과, 기존의 BTB에 비해 2.5∼8.5%의 비용 증가로 BTB 미스율이 26.5% 개선되고, 기존의 gshare에 비해 64%의 비용 증가로 예측 정확도는 26.75% 개선되었다.

• Journal of Information Processing Systems
• /
• 제11권1호
• /
• pp.39-56
• /
• 2015

Continuous multi-interval prediction (CMIP) is used to continuously predict the trend of a data stream based on various intervals simultaneously. The continuous integrated hierarchical temporal memory (CIHTM) network performs well in CMIP. However, it is not suitable for CMIP in real-time mode, especially when the number of prediction intervals is increased. In this paper, we propose a real-time integrated hierarchical temporal memory (RIHTM) network by introducing a new type of node, which is called a Zeta1FirstSpecializedQueueNode (ZFSQNode), for the real-time continuous multi-interval prediction (RCMIP) of data streams. The ZFSQNode is constructed by using a specialized circular queue (sQUEUE) together with the modules of original hierarchical temporal memory (HTM) nodes. By using a simple structure and the easy operation characteristics of the sQUEUE, entire prediction operations are integrated in the ZFSQNode. In particular, we employed only one ZFSQNode in each level of the RIHTM network during the prediction stage to generate different intervals of prediction results. The RIHTM network efficiently reduces the response time. Our performance evaluation showed that the RIHTM was satisfied to continuously predict the trend of data streams with multi-intervals in the real-time mode.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.523-523
• /
• 2000

We have developed a method to build time series prediction models by Genetic Programming (GP). Our proposed CP includes two new techniques. One is the parameter optimization algorithm, and the other is the new mutation operator. In this paper, the sunspot prediction experiment by our proposed CP was performed. The sunspot prediction is good benchmark, because many researchers have predicted them with various kinds of models. We make three experiments. The first is to compare our proposed method with the conventional methods. The second is to investigate about the relation between a model-building period and prediction precision. In the first and the second experiments, the long-term data of annual sunspots are used. The third is to try the prediction using monthly sunspots. The annual sunspots are a mean of the monthly sunspots. The behaviors of the monthly sunspot cycles in tile annual sunspot data become invisible. In the long-term data of the monthly sunspots, the behavior appears and is complicated. We estimate that the monthly sunspot prediction is more difficult than the annual sunspot prediction. The usefulness of our method in time series prediction is verified by these experiments.