• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.12
• /
• pp.3688-3693
• /
• 2009

In this paper the design methode of a separated composition state machine based on the compositive map with connecting two chaotic maps together - sawtooth map $S_2(x)$ and tent map $T_2(x)$ and the result of that is proposed. this paper gives a graph of the chaotic states generated by the composition state machine using the compositive logic of two different chaotic maps - sawtooth map and tent map and also shows that the period of pseudo-random states has the length according to the precision of the discreet truth table.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.5
• /
• pp.413-421
• /
• 2012

In industry, various rotating machinery such as pumps, gas turbines, compressors, electric motors, generators are being used as an important facility. Due to the industrial development, they make high performance(high-speed, high-pressure). As a result, we need more intelligent and reliable machine condition diagnosis techniques. Diagnosis technique using hidden Markov-model is proposed for an accurate and predictable condition diagnosis of various rotating machines and also has overcame the speed limitation of time/frequency method by using compensation of the rotational speed of rotor. In addition, existing artificial intelligence method needs defect state data for fault detection. hidden Markov model can overcome this limitation by using normal state data alone to detect fault of rotational machinery. Vibration analysis of step-up gearbox for wind turbine was applied to the study to ensure the robustness of diagnostic performance about compensation of the rotational speed. To assure the performance of normal state alone method, hidden Markov model was applied to experimental torque measuring gearbox in this study.

• Proceedings of the Korean Powder Metallurgy Institute Conference
• /
• 2006.09b
• /
• pp.1084-1085
• /
• 2006

We studied formation of nanostructured $TiB_2$-Cu composites under shock wave conditions. We investigated the influence of preliminary mechanical activation (MA) of Ti-B-Cu powder mixtures on the peculiarities of the reaction between Ti and B under shock wave. In the MA-ed mixture the reaction proceeded completely while in the non-activated mixture the reagents remained along with the product . titanium diboride. The size of titanium diboride particles in the central part of the compact was 100-300 nm.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.5
• /
• pp.31-39
• /
• 2017

Research in the machine tool industry has focused on ICT-based smart machines rather than hardware technologies related to machine tools. Real-time tool-status monitoring is representative of this type of technology and has become important for measuring sensors during cutting processes. In this paper, we studied several research areas and used a round bar to conduct fundamental research into the axial displacement of the main spindle of a tool when it was subjected to a machining load. We were able to use the gap sensor to detect the axial displacement indirectly by using grooves with various shapes on the round bar and sensing the gaps between the grooves. We then determined the optimal groove shape for monitoring the tool state.

• Journal of Korea Game Society
• /
• v.10 no.3
• /
• pp.93-102
• /
• 2010

This paper is to design and implement the system to simulate spontaneously the group behaviors for the various states of doves. To do this, the group behaviors of doves were divided into the four action models such as 'Flying', 'Landing', 'Eating' and 'Taking off'. The steering forces composing of each action model were found and each action model was designed by using the finite state machine. The designed system was implemented by integrating the Ogre engine. From the simulations of the implemented system, the values of the parameters for the steering forces were found so that it can represent the spontaneous group behaviors of doves.

• Journal of Multimedia Information System
• /
• v.5 no.2
• /
• pp.131-138
• /
• 2018

This work describes a binary image based fast Difference of Gaussian (DoG) filter using zero-dimensional (0-d) convolution and state machine look up tables (LUTs) for image and video stitching hardware platforms. The proposed approach for using binary images to obtain DoG filtering can significantly reduce the data size compared to conventional gray scale based DoG filters, yet binary images still preserve the key features of the image such as contours, edges, and corners. Furthermore, the binary image based DoG filtering can be realized with zero-dimensional convolution and state machine LUTs which eliminates the major portion of the adder and multiplier blocks that are generally used in conventional DoG filter hardware engines. This enables fast computation time along with the data size reduction which can lead to compact and low power image and video stitching hardware blocks. The proposed DoG filter using binary images has been implemented with a FPGA (Altera DE2-115), and the results have been verified.

• The KIPS Transactions:PartD
• /
• v.16D no.1
• /
• pp.65-72
• /
• 2009

Component based development has increasingly become important in the software industry. However, in the current component based development approach with UML, the absence of behavioral description of components brings about a cost problem which causes semantic errors on the testing phase. Accordingly we cannot grasp the usage pattern of component by its provided interfaces which refer to an abstraction of software component. And we cannot guarantee the behavioral conformance of the provided and required interfaces of components. In order to solve these problems, we describe the behaviors of component interfaces by state machine diagram and guarantee their behavior conformance at the modeling phase. We also propose a method to guarantee the behavior conformance of component interfaces with concept of observation equivalence and invocation consistency. And we provide an analyzing tool which checks interface behavior conformance.

• Nuclear Engineering and Technology
• /
• v.52 no.5
• /
• pp.1008-1012
• /
• 2020

In order to make reasonable design for the improvement of comprehensive mechanical properties of RAFM steels, the design system with both machine learning and high-throughput optimization algorithm was established. As the basis of the design system, a dataset of RAFM steels was compiled from previous literatures. Then, feature engineering guided random forests regressors were trained by the dataset and NSGA II algorithm were used for the selection of the optimal solutions from the large-scale solution set with nine composition features and two treatment processing features. The selected optimal solutions by this design system showed prospective mechanical properties, which was also consistent with the physical metallurgy theory. This efficiency design mode could give the enlightenment for the design of other metal structural materials with the requirement of multi-properties.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.603-622
• /
• 2023

Human error (HE) is an important concern in safety-critical systems such as nuclear power plants (NPPs). HE has played a role in many accidents and outage incidents in NPPs. Despite the increased automation in NPPs, HE remains unavoidable. Hence, the need for HE detection is as important as HE prevention efforts. In NPPs, HE is rather rare. Hence, anomaly detection, a widely used machine learning technique for detecting rare anomalous instances, can be repurposed to detect potential HE. In this study, we develop an unsupervised anomaly detection technique based on generative adversarial networks (GANs) to detect anomalies in manually collected surveillance data in NPPs. More specifically, our GAN is trained to detect mismatches between automatically recorded sensor data and manually collected surveillance data, and hence, identify anomalous instances that can be attributed to HE. We test our GAN on both a real-world dataset and an external dataset obtained from a testbed, and we benchmark our results against state-of-the-art unsupervised anomaly detection algorithms, including one-class support vector machine and isolation forest. Our results show that the proposed GAN provides improved anomaly detection performance. Our study is promising for the future development of artificial intelligence based HE detection systems.

• Proceedings of the KSME Conference
• /
• 2005.11a
• /
• pp.61.2-61.2
• /
• 2005