• Structural Engineering and Mechanics
• /
• 제17권3_4호
• /
• pp.483-492
• /
• 2004

This paper presents an efficient algorithm for the estimation of damage location and severity in bridge structures using Probabilistic Neural Network (PNN). Generally, the Back Propagation Neural Network (BPNN)-based damage detection methods need a lot of training patterns for neural network learning process and the optimum architecture of a BPNN is selected by trial and error. In this paper, the PNN instead of the conventional BPNN is used as a pattern classifier. The modal properties of damaged structure are somewhat different from those of undamaged one. The basic idea of proposed algorithm is that the PNN classifies a test pattern which consists of the modal characteristics from damaged structure, how close it is to each training pattern which is composed of the modal characteristics from various structural damage cases. In this algorithm, two PNNs are sequentially used. The first PNN estimates the damage location using mode shape and the results of the first PNN are put into the second PNN for the damage severity estimation using natural frequency. The proposed damage assessment algorithm using the PNN is applied to a cable-stayed bridge to verify its applicability.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 하계학술대회 논문집 D
• /
• pp.2580-2582
• /
• 2004

In this paper, a Neural Network(NN) based approach for classification of two dimensions images. The proposed algorithm is able to apply in the actual industry. The described diagnostic algorithm is presented to defect surface failures on tiles. A way to get data for a digital image process is several kinds of it. The tiles are scanned and the digital images are preprocessed and classified using neural networks. It is important to reduce the amount of input data with problem specific preprocessing. The auto-associative neural network is used for feature generation and selection while the probabilistic neural network is used for classification. The proposed algorithm is evaluated experimentally using one hundred of the real tile images. Sample image data to preprocess have histogram. The histogram is used as input value of probabilistic neural network. Auto-associative neural network compress input data and compressed data is classified using probabilistic neural network. Classified sample images are determined by human state. So it is intervened human subjectivity. But digital image processing and neural network are better than human classification ability. Therefore it is very useful of quality control improvement.

• 한국해양공학회지
• /
• 제32권4호
• /
• pp.215-221
• /
• 2018

In this study, the optimal design of a mooring system was carried out. Unlike almost all design methods, which are based on the deterministic method, this study focused on the probabilistic method. The probabilistic method, especially the design of experiment (DOE), could be a good way to cover some of the drawbacks of the deterministic approach. There various parameters for a mooring system, as widely known, including the weight, length, and stiffness of line. Scenarios for the mooring system parameters were produced using the Latin Hypercube Sampling method of the probabilistic approach. Next, a vessel-mooring system coupled analysis was performed in Orcaflex. A total of 50 scenarios were used in this study to optimize the initial design by means of a genetic algorithm. Finally, after determining the optimal process, a reliability analysis was performed to understand the system validity.

• 품질경영학회지
• /
• 제41권1호
• /
• pp.149-162
• /
• 2013

Purpose: The purpose of this study was to design of a probabilistic model for optimum manpower planning in R&D department by Montecarlo simulation. Methods: We investigate the process and the requirement of manpower planning and scheduling in R&D department. The empirical distributions of necessary time and manpower for R&D projects are developed. From the empirical distributions, we can estimate a probability distribution of optimum manpower in R&D department. A simulation method of estimating the probability distribution of optimum manpower is considered. It is a useful tool for obtaining the sum, the variance and other statistics of the distributions. Results: The real industry cases are given and the properties of the model are investigated by Montecarlo Simulation. we apply the model to the research laboratory of the global company, and investigate and compensate the weak points of the model. Conclusion: The proposed model provides various and correct information such as average, variance, percentile, minimum, maximum and so on. A decision maker of a company can easily develop the future plan and the task of researchers may be allocated properly. we expect that the productivity can be improved by this study. The results of this study can be also applied to other areas including shipbuilding, construction, and consulting areas.

• Journal of Construction Engineering and Project Management
• /
• 제1권1호
• /
• pp.37-43
• /
• 2011

Labor productivity is a significant factor associated with controlling time, cost, and quality. Many researchers have developed models to define methods of measuring the relationship between productivity and various parameters such as the size of working area, maximum working hours, and the crew composition. Most of the previous research has focused on estimating productivity; however, this research concentrates on estimating labor productivity and developing time and cost data for repetitive concrete pouring activity. In Korea, "Standard Estimating" only entails the average productivity data of the construction industry, and it is difficult to predict the time and cost spent on any particular project. As a result, errors occur in estimating duration and cost for individual activities or projects. To address these issues, this research sought to collect data, measure productivity, and develop time and cost data using labor productivity based on field conditions from the collected data. A probabilistic approach is also proposed to develop data. A case study is performed to validate this process using actual data collected from construction sites. It is possible that the result will be used as the EVMS baseline of cost management and schedule management.

• 한국자기학회지
• /
• 제23권2호
• /
• pp.62-67
• /
• 2013

본 논문에서는 전자기 관련 제품의 효율적인 신뢰도 기반 최적설계를 위해 확률구속조건을 평가하는 기법으로 해의 안정성과 효율성이 우수한 목표 성능치법을 제시 하였다. 목표 성능치법을 적용한 신뢰도 기반 최적설계의 효율성 검증을 위하여 스피커 모델과 초전도 자기에너지 저장장치 모델에 대한 최적설계를 수행하였고, 이를 기존 신뢰도 지수법을 적용한 최적설계 결과와 비교하였다. 또한 몬테카를로 수치모사기법을 이용하여 도출된 최적해의 신뢰도를 재 계산 후 비교함으로써 제안된 기법의 신뢰도 평가 결과의 정밀도를 검증하였다.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1990년도 가을 학술발표회 논문집
• /
• pp.22-27
• /
• 1990

Since an eigenvalue problem in structural analysis has been recognized as an important process for the assessment of structural strength, it is usually to be carried out the eigenvalue analysis or buckling analysis of structures when the compression behabiour of the member is dorminant. In general, various variables involved in the eigenvalue problem have also shown their variability. So it is natural to apply the probabilistic analysis into such problem. Since the limit state equation for the eigenvalue analysis or buckling reliability analysis is expressed implicitly in terms of random variables involved, the probabilistic finite element method is combined with the conventional reliability method such as MVFOSM and AFOSM for the determination of probability of failure due to buckling. The accuracy of the results obtained by this method is compared with results from the Monte Carlo simulations. Importance sampling method is specially chosen for overcomming the difficulty in a large simulation number needed for appropriate accurate result. From the results of the case study, it is found that the method developed here has shown good performance for the calculation of probability of buckling failure and could be used for checking the safety of the calculation of probability of buckling failure and could be used for checking the safely of frame structure which might be collapsed by either yielding or buckling.

• 대한조선학회논문집
• /
• 제55권2호
• /
• pp.93-102
• /
• 2018

Quantitative Risk Assessment (QRA) has been used in shipping and offshore industries for many years, supporting the decision-making process to guarantee safe running at different stages of design, fabrication and throughout service life. The assessments of a risk perspective are informed by the frequency of events (probability) and the associated consequences. As the number of offshore platforms increases, so does the length of subsea pipelines, thus there is a need to extend this approach and enable the subsea industry to place more emphasis on uncertainties. On-board operations can lead to objects being dropped on subsea pipelines, which can cause leaks and other pipeline damage. This study explains how to conduct hit frequency analyses of subsea pipelines, using historical data, and how to obtain a finite number of scenarios for the consequences analysis. An example study using probabilistic methods is used.

• Computers and Concrete
• /
• 제15권4호
• /
• pp.485-501
• /
• 2015

Cooling by the flow of water through an embedded cooling pipe has become a common and effective artificial thermal control measure for massive concrete structures. However, an extreme thermal gradient induces significant thermal stress, resulting in thermal cracking. Using a mesoscopic finite-element (FE) mesh, three-phase composites of concrete namely aggregate, mortar matrix and interfacial transition zone (ITZ) are modeled. An equivalent probabilistic model is presented for failure study of concrete by assuming that the material properties conform to the Weibull distribution law. Meanwhile, the correlation coefficient introduced by the statistical method is incorporated into the Weibull distribution formula. Subsequently, a series of numerical analyses are used for investigating the influence of the correlation coefficient on tensile strength and the failure process of concrete based on the equivalent probabilistic model. Finally, as an engineering application, damage and failure behavior of concrete cracks induced by a water-cooling pipe are analyzed in-depth by the presented model. Results show that the random distribution of concrete mechanical parameters and the temperature gradient near water-cooling pipe have a significant influence on the pattern and failure progress of temperature-induced micro-cracking in concrete.

• Computers and Concrete
• /
• 제13권2호
• /
• pp.187-207
• /
• 2014

This paper mainly discusses the influence of the aggregate properties including grading, shape, content and distribution on the chloride diffusion coefficient, as well as the initiation time of steel corrosion from a probabilistic point of view. Towards this goal, a simulation method of random aggregate structure (RAS) based on elliptical particles and a procedure of finite element analysis (FEA) at meso-scale are firstly developed to perform the analysis. Next, the chloride diffusion coefficient ratio between concrete and cement paste $D_{app}/D_{cp}$ is chosen as the index to represent the effect of aggregates on the chloride diffusion process. Identification of the random distribution of this index demonstrates that it can be viewed as actually having a normal distribution. After that, the effect of aggregates on $D_{app}/D_{cp}$ is comprehensively studied, showing that the appropriate properties of aggregates should be decided by both of the average and the deviation of $D_{app}/D_{cp}$. Finally, a case study is conducted to demonstrate the application of this mesoscopic method in predicting the initiation time of steel corrosion in reinforced concrete (RC) structures. The mesoscopic probabilistic method developed in this paper can not only provide more reliable evidences on the proper grading and shape of aggregates, but also play an important role in the probability-based design method.