• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1115-1120
• /
• 2003

The present paper shows the possible development of particle swarm optimization (PSO) based fuzzy-neural networks (FNN) which can be employed as an important building block in real life robot systems, controlled by voice-based commands. The PSO is employed to train the FNNs which can accurately output the crisp control signals for the robot systems, based on fuzzy linguistic spoken language commands, issued by an user. The FNN is also trained to capture the user spoken directive in the context of the present performance of the robot system. Hidden Markov Model (HMM) based automatic speech recognizers are developed, as part of the entire system, so that the system can identify important user directives from the running utterances. The system is successfully employed in a real life situation for motion control of a redundant manipulator.

• 한국입자에어로졸학회지
• /
• 제14권1호
• /
• pp.9-16
• /
• 2018

We have developed an electrostatic precipitation (ESP) type air cleaner for indoor air quality and investigated its performances regarding CADR (Clean air delivery rate), single-pass efficiency and gas removal efficiency. The ESP air cleaner used an ACF (Activated carbon fiber) filter for gas removal and the ACF as a high voltage electrode for particle removal. The ESP air cleaner was tested in a chamber with the volume of $1m^3$ regarding CADR and gas removal efficiency. The applied CADR area of the ESP was $1.8m^2$. Gas removal efficiency was tested with 3 gases (Acetaldehyde, Acetic acid, Ammonia). As the results of the gas removal efficiency, the ESP air cleaner shows the removal efficiencies of 90, 98 and 85% for acetaldehyde, acetic acid and ammonia, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.421-426
• /
• 2005

Fuzzy logic, neural network, fuzzy-neural network play an important as the key technology of linguistic modeling for intelligent control and decision making in complex systems. The fuzzy-neural network (FNN) learning represents one of the most effective algorithms to build such linguistic models. This paper proposes particle swarm optimization algorithm based optimal learning fuzzy-neural network (PSOA-FNN). The proposed learning scheme is the fuzzy-neural network structure which can handle linguistic knowledge as tuning membership function of fuzzy logic by particle swarm optimization algorithm. The learning algorithm of the PSOA-FNN is composed of two phases. The first phase is to find the initial membership functions of the fuzzy neural network model. In the second phase, particle swarm optimization algorithm is used for tuning of membership functions of the proposed model.

• 제어로봇시스템학회논문지
• /
• 제17권9호
• /
• pp.947-953
• /
• 2011

Radome aberration error causes degradation of miss distance as well as stability of high maneuver missile system with RF seeker. A study about radome compensation method is important in this kind of missile system design. Several kinds of methods showed good compensation performance in their paper. Proposed adaptive Particle filter estimates line of sight rate excluding the radome induced error. This paper shows effectiveness of adaptive Particle filter as compensation method of radome aberration error. Robust performance of this filter depends on external aiding measurement, target acceleration. Tuning of system error covariance can make this filter unsensitive against the error of target acceleration information. This paper demonstrates practical usage of adaptive Particle filter for reducing miss distance and increasing stability against disturbance of radome aberration error through performance analysis.

• Computers and Concrete
• /
• 제6권2호
• /
• pp.133-153
• /
• 2009

Discrete element modeling (DEM) in concrete technology is concerned with design and use of models that constitute a schematization of reality with operational potentials. This paper discusses the material science principles governing the design of DEM systems and evaluates the consequences for their operational potentials. It surveys the two families in physical discrete element modeling in concrete technology, only touching upon probabilistic DEM concepts as alternatives. Many common DEM systems are based on random sequential addition (RSA) procedures; their operational potentials are limited to low configuration-sensitivity features of material structure, underlying material performance characteristics of low structure-sensitivity. The second family of DEM systems employs concurrent algorithms, involving particle interaction mechanisms. Static and dynamic solutions are realized to solve particle overlap. This second family offers a far more realistic schematization of reality as to particle configuration. The operational potentials of this family involve valid approaches to structure-sensitive mechanical or durability properties. Illustrative 2D examples of fresh cement particle packing and pore formation during maturation are elaborated to demonstrate this. Mainstream fields of present day and expected application of DEM are sketched. Violation of the scientific knowledge of to day underlying these operational potentials will give rise to unreliable solutions.

• 한국분말재료학회지
• /
• 제30권4호
• /
• pp.332-338
• /
• 2023

Thermite welding is an exceptional process that does not require additional energy supplies, resulting in welded joints that exhibit mechanical properties and conductivity equivalent to those of the parent materials. The global adoption of thermite welding is growing across various industries. However, in Korea, limited research is being conducted on the core technology of thermite welding. Currently, domestic production of thermite powder in Korea involves recycling copper oxide (CuO). Unfortunately, controlling the particle size of waste CuO poses challenges, leading to the unwanted formation of pores and cracks during thermite welding. In this study, we investigate the influence of powder particle size on thermite welding in the production of Cu-thermite powder using waste CuO. We conduct the ball milling process for 0.5-24 h using recycled CuO. The evolution of the powder shape and size is analyzed using particle size analysis and scanning electron microscopy (SEM). Furthermore, we examine the thermal reaction characteristics through differential scanning calorimetry. Additionally, the microstructures of the welded samples are observed using optical microscopy and SEM to evaluate the impact of powder particle size on weldability. Lastly, hardness measurements are performed to assess the strengths of the welded materials.

• 품질경영학회지
• /
• 제47권4호
• /
• pp.701-711
• /
• 2019

Purpose: The problem of optimizing redundancy allocation in multi-level systems is considered when each item in a multi-level system has alternative items with the same function. The number of redundancy of multi-level system is allocated to maximize the reliability of the system under path set and cost limitation constraints. Methods: Based on cost limitation and path set constraints, a mathematical model is established to maximize system reliability. Particle swarm optimization is employed for redundant allocation and verified by numerical experiments. Results: Comparing the particle swarm optimization method and the memetic algorithm for the 3 and 4 level systems, the particle swarm optimization method showed better performance for solution quality and search time. Particularly, the particle swarm optimization showed much less than the memetic algorithm for variation of results. Conclusion: The proposed particle swarm optimization considerably shortens the time to search for a feasible solution in MRAP with path set constraints. PS optimization is expected to reduce search time and propose the better solution for various problems related to MRAP.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.539-544
• /
• 2004

본 논문에서는 CONDENSATION 알고리즘을 이용하여 입자 필터(particle filter)에 기반 한 물체 추적 알고리즘을 제안한다. 입자 필터는 조건 확률 전파 모델(Conditional Density Propagation)인 베이지안(Bayesian) 추론 규칙을 적용하는 추적구조를 갖고 있기 때문에 다른 어떤 종류의 추적 알고리즘보다 뛰어난 성능을 보인다. 논문에서는 실험 결과를 통해, 외곽(contour) 추적 입자 필터가 복잡한 환경 속에서 강인한 추적 성능을 나타냄을 증명한다.

• 제어로봇시스템학회논문지
• /
• 제18권6호
• /
• pp.562-570
• /
• 2012

This paper proposes a robust object tracking algorithm using object features and on-line learning based particle filter for mobile robots. Mobile robots with a side-view camera have problems as camera jitter, illumination change, object shape variation and occlusion in variety environments. In order to overcome these problems, color histogram and HOG descriptor are fused for efficient representation of an object. Particle filter is used for robust object tracking with on-line learning method IPCA in non-linear environment. The validity of the proposed algorithm is revealed via experiments with DBs acquired in variety environment. The experiments show that the accuracy performance of particle filter using combined color and shape information associated with online learning (92.4 %) is more robust than that of particle filter using only color information (71.1 %) or particle filter using shape and color information without on-line learning (90.3 %).

• 정보저장시스템학회논문집
• /
• 제2권2호
• /
• pp.123-129
• /
• 2006

The head to disk spacing must be decreased to increase recording densities in hard disk drives. Recently, to decrease the head to disk spacing, smooth disk having no bumps onto the lading zone has used. In this research, we compared the number of particles generated ill HDD with smooth and textured disks. We used a sampling method using a particle sampler and a CPC (condensation particle counter) to detect particles in HDD. First, we sampled and counted particles generated with disk rotational speed and various rest times when the smooth disk and textured disks were used, then analyzed the sampled particles by SEM (scanning electron microscopy) and AES (auger electron spectroscopy). In results of measuring particles, more particles in case of LZT disk drive generated than that of the smooth disk drive in all test modes. The number of particles generated in the smooth disk was very low. The particle generation increased as the rest time increased (smooth/LZT disks) and more particles in case of LZT disk drive generated than that of the smooth disk drive. In results of analyzing particle components, Al, Ti, Si components were detected and we could not found differences between components in case of smooth/LZT disk drive.