• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.239-240
• /
• 2012

With advancements in semiconductor device technologies, manufacturing processes are getting more complex and it became more difficult to maintain tighter process control. As the number of processing step increased for fabricating complex chip structure, potential fault inducing factors are prevail and their allowable margins are continuously reduced. Therefore, one of the key to success in semiconductor manufacturing is highly accurate and fast fault detection and classification at each stage to reduce any undesired variation and identify the cause of the fault. Sensors in the equipment are used to monitor the state of the process. The idea is that whenever there is a fault in the process, it appears as some variation in the output from any of the sensors monitoring the process. These sensors may refer to information about pressure, RF power or gas flow and etc. in the equipment. By relating the data from these sensors to the process condition, any abnormality in the process can be identified, but it still holds some degree of certainty. Our hypothesis in this research is to capture the features of equipment condition data from healthy process library. We can use the health data as a reference for upcoming processes and this is made possible by mathematically modeling of the acquired data. In this work we demonstrate the use of recurrent neural network (RNN) has been used. RNN is a dynamic neural network that makes the output as a function of previous inputs. In our case we have etch equipment tool set data, consisting of 22 parameters and 9 runs. This data was first synchronized using the Dynamic Time Warping (DTW) algorithm. The synchronized data from the sensors in the form of time series is then provided to RNN which trains and restructures itself according to the input and then predicts a value, one step ahead in time, which depends on the past values of data. Eight runs of process data were used to train the network, while in order to check the performance of the network, one run was used as a test input. Next, a mean squared error based probability generating function was used to assign probability of fault in each parameter by comparing the predicted and actual values of the data. In the future we will make use of the Bayesian Networks to classify the detected faults. Bayesian Networks use directed acyclic graphs that relate different parameters through their conditional dependencies in order to find inference among them. The relationships between parameters from the data will be used to generate the structure of Bayesian Network and then posterior probability of different faults will be calculated using inference algorithms.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.3
• /
• pp.205-216
• /
• 2024

Recently, seismic Probabilistic Safety Assessment (PSA) methods have been developed for process plants, such as gas plants, oil refineries, and chemical plants. The framework originated from the PSA of nuclear power plants, which aims to assess the risk of reactor core damage. The original PSA method was modified to adopt the characteristics of a process plant whose purpose is continuous operation without shutdown. Therefore, a fault tree, whose top event is shut down, was constructed and transformed into a Bayesian Network (BN), a probabilistic graph model, for efficient risk-informed decision-making. In this research, the fault tree-based BN from the previous research is further developed to consider the multi-hazard of earthquake-induced fire and explosion (EQ-induced F&E). For this purpose, an event tree describing the occurrence of fire and explosion from a release is first constructed and transformed into a BN. And then, this BN is connected to the previous BN model developed for seismic PSA. A virtual plot plan of a gas plant is introduced as a basis for the construction of the specific EQ-induced F&E BN to test the proposed BN framework. The paper demonstrates the method through two examples of risk-informed decision-making. In particular, the second example verifies how the proposed method can establish a repair and retrofit strategy when a shutdown occurs in a process plant.

• Journal of Korean Society for Quality Management
• /
• v.21 no.2
• /
• pp.1-16
• /
• 1993

Early generations of products had little to no inherent capability to test themselves. The technologies involved often required only visual inspection and limited probing to troubleshoot the system once it was turned over to maintenance personnel. However, as the complexity of military and commercial systems grew, symptoms of failure became less noticeable to the operator. Therefore, the procedure to access, inspect, repair and replace a component became complicated, the requirements for personnel skill and testing equipment increased. and it took too long of a time to maintain a system. Meanwhile, the need for availability became more mission-critical and maintenance become very expensive. The obvious solution was to design in-system circuits or devices to self-test the primary system, the Built-In-Test(BIT) was born. This approach has continued right on up through present systems and is an integral part of systems now being designed. The object of this paper is to present a state-of-the-art research for filtering out the BIT diagnosis mistakes using Bayesian analysis and develop the algorithm for Redundant systems with BIT to improve BIT diagnosis.

• Journal of the Korean Data and Information Science Society
• /
• v.4
• /
• pp.65-74
• /
• 1993

Suppose that we have two populations(or systems), say ${\Pi}_{1}\;and\;{\Pi}_{2}$, to be tested. A random sample of size n from each population is taken and the test for each system will be terminated when the first r failures among n random samples are observed. This kind of test is caned the type-II censored (or item-censored) testing without replacement. Under this scheme we consider the problem of estimating the unknown parameters of interests and the reliability for a given time t for each population.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2003.11a
• /
• pp.669-675
• /
• 2003

This paper examines structural breaks and asymmetries of prices of four domestic petroleum products, i.e., gasoline, kerosene, diesel, and bunker-C, following the changes in the pricing policies pertaining to petroleum products in Korea from the government-controlled pricing system to the market pricing system. We use the monthly wholesale market price data for the sample period between July 1988 and December 2001. Using the four methods: the Chow test, the CUSUM/CUSUMQ tests, the Bayesian approach and the Dufour test, the structural behaviors of the petroleum product prices are examined. We found that structural change occurred in all petroleum products, with the exception of Kerosene, at the point of pricing policy change from government-controlled to the spot-price related pricing system. We, also conducted asymmetric analysis using the Borenstein, Cameron, and Gilbert (1997)'s model and found evidences of price asymmetry for all four product types, but in different pattern for each product.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.16 no.6
• /
• pp.62-70
• /
• 2007

In this study, the natural flaws in welding parts are classified using the signal pattern classification method. The storage digital oscilloscope including FFT function and enveloped waveform generator is used and the signal pattern recognition procedure is made up the digital signal processing, feature extraction, feature selection and classifier design. It is composed with and discussed using the distance classifier that is based on euclidean distance the empirical Bayesian classifier. Feature extraction is performed using the class-mean scatter criteria. The signal pattern classification method is applied to the signal pattern recognition of natural flaws.

• Journal of Environmental Health Sciences
• /
• v.48 no.5
• /
• pp.266-271
• /
• 2022

Background: The selection of distributions of input parameters is an important component in probabilistic exposure assessment. Goodness-of-fit (GOF) methods are used to determine the distribution of exposure factors. However, there are no clear guidelines for choosing an appropriate GOF method. Objectives: The outcomes of probabilistic consumer exposure assessment were compared by using five different GOF methods for the selection of input distributions: chi-squared test, Kolmogorov-Smirnov test (K-S), Anderson-Darling test (A-D), Akaike information criterion (AIC) and Bayesian information criterion (BIC). Methods: Individual exposures were estimated based on product usage factor combinations from 10,000 respondents. The distribution of individual exposure was considered as the true value of population exposures. Results: Among the five GOF methods, probabilistic exposure distributions using the A-D and K-S methods were similar to individual exposure estimations. Comparing the 95th percentiles of the probabilistic distributions and the individual estimations for 10 CPs, there were 0.73 to 1.92 times differences for the A-D method, and 0.73 to 1.60 times differences (excluding tire-shine spray) for the K-S method. Conclusions: There were significant differences in exposure assessment results among the selection of the GOF methods. Therefore, the GOF methods for probabilistic consumer exposure assessment should be carefully selected.

• Korean Journal of Plant Taxonomy
• /
• v.48 no.4
• /
• pp.289-300
• /
• 2018

Coreanomecon is a monotypic and endemic genus in Korea, distributed mainly in the southern regions. Coreanomecon is morphologically similar to Hylomecon by producing red latex, easily distinguished from Chelidonium, which produces yellow latex. Coreanomecon were merged into Hylomecon or Chelidonium depending on the authors. To understand the phylogenetic relationship of Coreanomecon, DNA sequences of chloroplast rbcL and matK and nuclear Internal Transcribed Spacer (ITS) regions were determined from the species of Papaveroideae (Papaveraceae) in Korea and analyzed with the Maximum Parsimony and Bayesian methods. Phylogenetic analyses of Papaveroideae suggest that Coreanomecon is sister to the clade of Chelidonium and Stylophorum in the ITS data and that it is sister to Hylomecon in the chloroplast (cpDNA) data. A constraining analysis using the Shimodaira-Hasegawa test (S-H test) suggested that the ITS data do not reject the sister relationship of Coreanomecon and Hylomecon. The S-H test also suggested that the cpDNA data is compatible with the placement of Coreanomecon as a sister to the clade of Chelidonium and Stylophorum. Although the conflicting phylogenetic results may stem from insufficient phylogenetic signals, they may also be associated with hybridization between Hylomecon and an ancestor of Stylophorum and Chelidonium. The results of this study suggest that Coreanomecon is a distinct lineage as an endemic genus, supporting the morphological data.

• Proceedings of the KOSOMBE Conference
• /
• v.1991 no.05
• /
• pp.65-70
• /
• 1991

A hybrid model which uses a probabilistic model and a MLP(multi layer perceptron) model for pattern recognition of EMG(electromyogram) signals is proposed in this paper. MLP model has problems which do not guarantee global minima of error due to learning method and have different approximation grade to bayesian probabilities due to different amounts and quality of training data, the number of hidden layers and hidden nodes, etc. Especially in the case of new test data which exclude design samples, the latter problem produces quite different results. The error probability of probabilistic model is closely related to the estimation error of the parameters used in the model and fidelity of assumtion. Generally, it is impossible to introduce the bayesian classifier to the probabilistic model of EMG signals because of unknown priori probabilities and is estimated by MLE(maximum likelihood estimate). In this paper we propose the method which get the MAP(maximum a posteriori probability) in the probabilistic model by estimating the priori probability distribution which minimize the error probability using the MLP. This method minimize the error probability of the probabilistic model as long as the realization of the MLP is optimal and approximate the minimum of error probability of each class of both models selectively. Alocating the reference coordinate of EMG signal to the outside of the body make it easy to suit to the applications which it is difficult to define and seperate using internal body coordinate. Simulation results show the benefit of the proposed model compared to use the MLP and the probabilistic model seperately.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.531-540
• /
• 2016

Development of various sensors attached to mobile and wearable devices has led to increasing recognition of current context-based service to the user. In this study, we proposed a probabilistic model for recognizing user's food intake context, which can occur in a great variety of contexts. The model uses low-level sensor data from mobile and wrist-wearable devices that can be widely available in daily life. To cope with innate complexity and fuzziness in high-level activities like food intake, a context model represents the relevant contexts systematically based on 4 components of activity theory and 5 W's, and tree-structured Bayesian network recognizes the probabilistic state. To verify the proposed method, we collected 383 minutes of data from 4 people in a week and found that the proposed method outperforms the conventional machine learning methods in accuracy (93.21%). Also, we conducted a scenario-based test and investigated the effect contribution of individual components for recognition.