• International Journal of Control, Automation, and Systems
• /
• v.1 no.2
• /
• pp.194-202
• /
• 2003

In this paper, we introduce a category of Multi-FNN (Fuzzy-Neural Networks) models, analyze the underlying architectures and propose a comprehensive identification framework. The proposed Multi-FNNs dwell on a concept of fuzzy rule-based FNNs based on HCM clustering and evolutionary fuzzy granulation, and exploit linear inference being treated as a generic inference mechanism. By this nature, this FNN model is geared toward capturing relationships between information granules known as fuzzy sets. The form of the information granules themselves (in particular their distribution and a type of membership function) becomes an important design feature of the FNN model contributing to its structural as well as parametric optimization. The identification environment uses clustering techniques (Hard C - Means, HCM) and exploits genetic optimization as a vehicle of global optimization. The global optimization is augmented by more refined gradient-based learning mechanisms such as standard back-propagation. The HCM algorithm, whose role is to carry out preprocessing of the process data for system modeling, is utilized to determine the structure of Multi-FNNs. The detailed parameters of the Multi-FNN (such as apexes of membership functions, learning rates and momentum coefficients) are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the model. To evaluate the performance of the proposed model, two numeric data sets are experimented with. One is the numerical data coming from a description of a certain nonlinear function and the other is NOx emission process data from a gas turbine power plant.

• Carbon letters
• /
• v.14 no.4
• /
• pp.210-217
• /
• 2013

The synthesis of carbon nanomaterials (CNMs) by a chemical vapor deposition method using three different plant oils as precursors is presented. Because there are four parameters involved in the synthesis of CNM (i.e., the precursor, reaction temperature of the furnace, catalysts, and the carrier gas), each having three variables, it was decided to use the Taguchi optimization method with the 'the larger the better' concept. The best parameter regarding the yield of carbon varied for each type of precursor oil. It was a temperature of $900^{\circ}C$ + Ni as a catalyst for neem oil; $700^{\circ}C$ + Co for karanja oil and $500^{\circ}C$ + Zn as a catalyst for castor oil. The morphology of the nanocarbon produced was also impacted by different parameters. Neem oil and castor oil produced carbon nanotube (CNT) at $900^{\circ}C$; at lower temperatures, sphere-like structures developed. In contrast, karanja oil produced CNTs at all the assessed temperatures. X-ray diffraction and Raman diffraction analyses confirmed that the nanocarbon (both carbon nano beads and CNTs) produced were graphitic in nature.

• New & Renewable Energy
• /
• v.6 no.3
• /
• pp.22-29
• /
• 2010

The concept of Ocean Thermal Energy Conversion (OTEC) is simple and various types of OTEC have been proposed and tried. However the location of OTEC is limited because OTEC requires $20^{\circ}C$ of temperature difference as a minimum, so most of OTEC plants were constructed and experimented in tropical oceans. To solve this we proposed the modified OTEC which uses condenser discharged thermal energy of existing fossil or nuclear power plants. We call this system CTEC (Condenser Thermal Energy Conversion) as this system directly uses $32^{\circ}C$ partially saturated steam in condenser instead of $20{\sim}25^{\circ}C$ surface sea water as heat source. Increased temperature difference can improve thermal efficiency of Rankine cycle, but CTEC should be located near existing plant condenser and the length of cold water pipe between CTEC and deep cold sea water also increase. So friction loss also increases. Calculated result shows the change of efficiency, pumping power, net power and other parameters of modeled 7.9 MW CTEC at given condition. The calculated efficiency of CTEC is little larger than that of typical OTEC as expected. By proper location and optimization, CTEC could be considered another competitive renewable energy system.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.8
• /
• pp.972-979
• /
• 1999

QFT(Quantitative Feedback Theory) is a very practical design technique that emphasizes the use of feedback for achieving the desired system performance tolerances in despite of plant uncertainty and disturbance. The fundamental concept of QFT is a loop shaping procedure that a suitable controller can be found by shaping a nominal loop transfer function. The loop shaping synthesis involves the identification of a structure and the specialization of parameter optimization of a desired system. This paper presents an improved loop shaping approach of QFT with model validation using GA(Genetic Algorithm). The method presented in this paper removes the problems of iterative operation, transformation error, and model validation in the conventional methods without consideration of frequency domain.

• Journal of the Korean Society of Combustion
• /
• v.18 no.3
• /
• pp.1-8
• /
• 2013

Thermodynamic and economic analyses of various types of gas turbine combined cycle power plants have been performed to establish criteria for optimization of power plants. The concept of efficiency, in terms of the difference in energy levels of electricity and heat, was introduced. The efficiency of power and heat generation by power plants with other purposes was estimated, and power generation costs were figured out for various types of combined heat and power plants(i.e., fired and unfired, condensing and non-condensing modes, single or double pressure HRSG).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.10
• /
• pp.319-330
• /
• 2016

Recently, 3D printing technology has been applied to make a concept model and working mockup of an industrial application. On the other hand, this technology has limited applications in industrial products due to the materials and reliability of the 3D printed product. In this study, the components of a full cord switch module are proposed as a case of a 3D printed component that can be used as a substitute for a short period. These are hub-driven and lever lockup components that have the structural characteristics of breaking down frequently in the emergency operating status. To ensure the structural strength for a substitute period, research of structure optimization was performed because 3D printing technology has a limitation in the materials used. After optimizing the structure variables of the hub-driven component, reasonable results can be drawn in that the safety factors of the left and right switching mode are 1.243 (${\Delta}153.67%$) and 3.156 (${\Delta}404.96%$). The lever lockup component has a structural weak point that can break down easily on the lockup-part because of a cantilever shape and bending moment. The rib structure was applied to decrease the deflection. In addition, optimization of the structural variables was performed, showing a safety factor of 7.52(${\Delta}26%$).

• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2821-2823
• /
• 2002

In this paper we propose the Multi-FNN (Fuzzy-Neural Networks) for optimal identification modeling of complex system. The proposed Multi-FNNs is based on a concept of FNNs and exploit linear inference being treated as generic inference mechanisms. In the networks learning, backpropagation(BP) algorithm of neural networks is used to updata the parameters of the network in order to control of nonlinear process with complexity and uncertainty of data, proposed model use a HCM(Hard C-Means)clustering algorithm which carry out the input-output dat a preprocessing function and Genetic Algorithm which carry out optimization of model The HCM clustering method is utilized to determine the structure of Multi-FNNs. The parameters of Multi-FNN model such as apexes of membership function, learning rates, and momentum coefficients are adjusted using genetic algorithms. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization abilities of the model. NOx emission process data of gas turbine power plant is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Journal of Information Science Theory and Practice
• /
• v.7 no.4
• /
• pp.56-64
• /
• 2019

Planting intercropping in rubber plantations is another alternative for generating more income for farmers. However, farmers still lack the knowledge of choosing plants. In addition, information for decision making comes from many sources and is knowledge accumulated by the expert. Therefore, this research aims to create a decision support system for growing rubber trees for individual farmers. It aims to get the highest income and the lowest cost by using semantic web technology so that farmers can access knowledge at all times and reduce the risk of growing crops, and also support the decision supporting system (DSS) to be more intelligent. The integrated intercropping ontology and rule are a part of the decision-making process for selecting plants that is suitable for individual rubber plots. A list of suitable plants is important for decision variables in the allocation of planting areas for each type of plant for multiple purposes. This article presents designing and developing the intercropping ontology for DSS which defines a class based on the principle of intercropping in rubber plantations. It is grouped according to the characteristics and condition of the area of the farmer as a concept of the rubber plantation. It consists of the age of rubber tree, spacing between rows of rubber trees, and water sources for use in agriculture and soil group, including slope, drainage, depth of soil, etc. The use of ontology for recommended plants suitable for individual farmers makes a contribution to the knowledge management field. Besides being useful in DSS by offering options with accuracy, it also reduces the complexity of the problem by reducing decision variables and condition variables in the multi-objective optimization model of DSS.

• Clean Technology
• /
• v.27 no.3
• /
• pp.269-274
• /
• 2021

Bioenergy is generally considered to be one of the options for pursuing carbon neutrality. However, for a period of time, combustion of harvested plant biomass inevitably causes more carbon dioxide in the atmosphere than combustion of fossil fuels. This paper proposes a method that predicts and minimizes the total amount and payback period of this carbon debt. As a case study, a carbon cycle impact assessment was performed for immediate switching of the currently used fossil fuels to biomass. This work points out a fundamental vulnerability in the concept of carbon neutrality. As an action plan for the sustainability of bioenergy, formulas for afforestation proportional to the decrease in the forest area and surplus harvest proportional to the increase in the forest mass are proposed. The results of optimization indicate that the carbon debt payback period is about 70 years, and the carbon dioxide in the atmosphere increases by more than 50% at a maximum and 3% at a steady state. These are theoretically predicted best results, which are expected to be worse in reality. Therefore, biomass is not truly carbon neutral, and it is inappropriate as an energy source alternative to fossil fuels. The method proposed in this work is expected to be able to contribute to the approach to carbon neutrality by minimizing present and future carbon debt of the bioenergy that is already in use.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1243-1244
• /
• 2022

In recent years, the growing interest in off-site construction has led to factories scaling up their manufacturing and production processes in the construction sector. Consequently, continuous large-scale site monitoring in low-variability environments, such as prefabricated components production plants (precast concrete production), has gained increasing importance. Although many studies on computer vision-based site monitoring have been conducted, challenges for deploying this technology for large-scale field applications still remain. One of the issues is collecting and transmitting vast amounts of video data. Continuous site monitoring systems are based on real-time video data collection and analysis, which requires excessive computational resources and network traffic. In addition, it is difficult to integrate various object information with different sizes and scales into a single scene. Various sizes and types of objects (e.g., workers, heavy equipment, and materials) exist in a plant production environment, and these objects should be detected simultaneously for effective site monitoring. However, with the existing object detection algorithms, it is difficult to simultaneously detect objects with significant differences in size because collecting and training massive amounts of object image data with various scales is necessary. This study thus developed a large-scale site monitoring system using edge computing and a small-object detection system to solve these problems. Edge computing is a distributed information technology architecture wherein the image or video data is processed near the originating source, not on a centralized server or cloud. By inferring information from the AI computing module equipped with CCTVs and communicating only the processed information with the server, it is possible to reduce excessive network traffic. Small-object detection is an innovative method to detect different-sized objects by cropping the raw image and setting the appropriate number of rows and columns for image splitting based on the target object size. This enables the detection of small objects from cropped and magnified images. The detected small objects can then be expressed in the original image. In the inference process, this study used the YOLO-v5 algorithm, known for its fast processing speed and widely used for real-time object detection. This method could effectively detect large and even small objects that were difficult to detect with the existing object detection algorithms. When the large-scale site monitoring system was tested, it performed well in detecting small objects, such as workers in a large-scale view of construction sites, which were inaccurately detected by the existing algorithms. Our next goal is to incorporate various safety monitoring and risk analysis algorithms into this system, such as collision risk estimation, based on the time-to-collision concept, enabling the optimization of safety routes by accumulating workers' paths and inferring the risky areas based on workers' trajectory patterns. Through such developments, this continuous large-scale site monitoring system can guide a construction plant's safety management system more effectively.