• 한국지하수토양환경학회지:지하수토양환경
• /
• 제21권3호
• /
• pp.21-34
• /
• 2016

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

• 한국건축시공학회지
• /
• 제11권3호
• /
• pp.238-246
• /
• 2011

Choosing the best-performance materials is a crucial task for the successful completion of a project in the construction field. In general, the process of material selection is performed through the use of information by a highly experienced expert and the purchasing agent, without the assistance of logical decision-making techniques. For this reason, the construction field has considered various artificial intelligence (AI) techniques to support decision systems as their own selection method. This study proposes the application of a systematic and efficient support vector machine (SVM) model to select optimal exterior materials. The dataset of the study is 120 completed construction projects in South Korea. A total of 8 input determinants were identified and verified from the literature review and interviews with experts. Using data classification and normalization, these 120 sets were divided into 3 groups, and then 5 binary classification models were constructed in a one-against-all (OAA) multi classification method. The SVM model, based on the kernel radical basis function, yielded a prediction accuracy rate of 87.5%. This study indicates that the SVM model appears to be feasible as a decision support system for selecting an optimal construction method.

• 한국항공운항학회지
• /
• 제16권4호
• /
• pp.26-34
• /
• 2008

This article provides a comprehensive treatment of cracks in non-homogeneous structural materials such as functionally graded materials (FGMs). It is assumed that the material properties depend only on the coordinate perpendicular to the crack surfaces and vary continuously along the crack faces. By using laminated composite plate model to simulate the material non-homogeneity, we present an algorithm for solving the system based on Laplace transform and Fourier transform techniques. Unlike earlier studies that considered certain assumed property distributions and a single crack problem, the current investigation studies multiple crack problem in the FGMs with arbitrarily varying material properties. As a numerical illustration, transient thermal flow intensity factors for a metal-ceramic joint specimen with a functionally graded interlayer subjected to sudden heating on its boundary are presented. The results obtained demonstrate that the present model is an efficient tool in the fracture analysis of non-homogeneous material with properties varying in the thickness direction.

• 한국정밀공학회지
• /
• 제19권12호
• /
• pp.142-149
• /
• 2002

In this paper, the metal forming process is caused of rise of the unit cost of production in increase of the lead-time and cost because of manufacturing final product through a few the number of processes. Flow control complex forming is proposed to put into formulation in order to apply cold forging from conventional approximate similarity theory, and the forming loads of the real material(AISI 1008) can be calculated by put at the new similarity formula the load by plasticine model material experiment through hub clutch. In order to reduce lead-time and cost the technology is used to manufacture with lower die of this product. By the application synthetic resin as the raw material, it is have the merit such short lead-time, low cost, good surface finish etc., as compared with the machine work.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2002년도 가을 학술발표회 논문집
• /
• pp.789-794
• /
• 2002

The relationship is investigated between material modeling of concrete and the evaluation procedure of thermal stress by the hydration heat. In this respect, some important points are suggested to which special attention should be paid to reasonably evaluate the thermal stress using the widely-used structural analysis programs. This study indicates that proper material model should be used to draw incremental stress evaluation that takes into account the change of elastic modulus with time. Some correction techniques are also presented when using the program that don't have proper built-in procedure for the calculation of the thermal stress.

• 한국전기전자재료학회논문지
• /
• 제17권6호
• /
• pp.668-672
• /
• 2004

Upon Debye's dielectric relaxation theory, we tried simple determination method of trap level in organic EL materials. From dielectric measurements in the 20 Hz - 1 MHz frequency range and in the 150 K - 320K temperature range, the depth of traps in Alq$_3$ filled with remaining electrons was determinated. Comparing to other determination techniques like TSL, or TL, the apparatus all we need is just simple LCR meter, thermometer and cooling method(liquid nitrogen). The mean activation energy is about 0.20 eV. It is in good agreement with previous determinations by other techniques like TSL. This results consolidate the validity of Burrow's transport mechanism model. Further intensified experiment with UV light on the dielectric absorption(Photodipolair effect) was nevertheless disturbed by the photoconductivity component.

• 산업공학
• /
• 제10권3호
• /
• pp.179-187
• /
• 1997

The efficiency of material flow systems in terms of optimal network flow and minimum cost flow has always been an important design and operational goal in material handling and distribution system. In this research, an attempt was made to develop a new algorithm and the model to solve a stochastic material flow network with bidirectional and uncertain flows. A stochastic material flow network with bidirectional flows can be considered from a finite set with unknown demand probabilities of each node. This problem can be formulated as a special case of a two-stage linear programming problem which can be converted into an equivalent linear program. To find the optimal solution of proposed stochastic material flow network, some terminologies and algorithms together with theories are developed based on the partitioning and subgradient techniques. A computer program applying the proposed method was developed and was applied to various problems.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 1996년도 추계학술대회 논문집
• /
• pp.23-25
• /
• 1996

In this paper aims at studying the minimal test pattem of the RAM. This also propose a scheme of testing faults from the new fault model using the LLB. The length of test patterns are 6N(1-wsf), 9.5N(2-wsf), 7N(3-wsfl, 3N(4-wsf) operations in N-bit RAM. This test techniques can write into memory cell the number of write operations is reduced and then much testing time is saved. A test set which detects all positive-negative static t-ws faults for t=0, 1, 2, 3, 4 and detects all pattern sensitive fault in memory array. A new fault model, which encompasses the existing fault model Is proposed.

• 대한기계학회논문집
• /
• 제18권8호
• /
• pp.2073-2080
• /
• 1994

In this paper, a model of material removal in abrasive water jet machining of brittle material is developed, and experimentally evaluated. Abrasive water jet machining proved to yield better material removal rate than other machining techniques for hard and brittle material (alumina ceramics). It was also found that large scale fracture may develop at the exit of the jet from the material. The fracture size was predicted as a function of water jet pressure and size of the hole. Finally, the feasibility of using acoustic emission signals for in-process monitoring of the abrasive water jet machining process is investigated.

• 한국항공운항학회지
• /
• 제19권1호
• /
• pp.15-23
• /
• 2011

The purpose of this paper is to investigate the time behavior of a multiple crack problems. It is assumed that the medium contains cracks perpendicular to the crack surfaces, that the thermo-mechanical properties are continuous functions of the thickness coordinate. we use the laminated composite plate model to simulate the material non-homogeneity. By utilizing the Laplace transform and Fourier transform techniques, the multiple crack problems in the non-homogeneous medium is formulated. Singular integral equations are derived and solved to investigate the multiple crack problems. As a numerical illustration, transient thermal stress intensity factors(TSIFs) for a functionally graded material plate subjected to sudden heating on its boundary are provided. The variation in the TSIFs due to the change in material gradient and the crack position is studied.