• Journal of Korean Society of Water and Wastewater
• /
• v.14 no.3
• /
• pp.281-290
• /
• 2000

This study investigates the prediction of daily water supply, which is a necessary for the efficient management of water distribution system. ANFIS, namely artificial intelligence, is a neural network into which fuzzy information is inputted and then processed. In this study, daily water supply was predicted through an application of network-based fuzzy inference system(ANFIS) for daily water supply prediction. This study was investigated methods for predicting water supply based on data about the amount of water which supplied in Kwangju city. For variables choice, four analyses of input data were conducted: correlation analysis, autocorrelation analysis, partial autocorrelation analysis, and cross-correlation analysis. Input variables were (a) the amount of water supply, (b) the mean temperature, and (c) the population of the area supplied with water. Variables were combined in an integrated model. Data of the amount of daily water supply only was modelled and its validity was verified in the case that the meteorological office of weather forecast is not always reliable. Proposed models include accidental cases such as a suspension of water supply. The maximum error rate between the estimation of the model and the actual measurement was 18.46% and the average error was lower than 2.36%. The model is expected to be a real-time estimation of the operational control of water works and water/drain pipes.

• Korean Institute of Interior Design Journal
• /
• v.19 no.6
• /
• pp.38-46
• /
• 2010

The objective of this study is to find an educational method that is able to increase creativity using both left and right directed thinking with complementary cooperation. The premise of experimental study is that analogical inference is a great help to produce a creative design, and the design tasks of residential space are given to 20 students, voluntary participants in four experimental tests. The first test is conducted with fundamental conditions such as site or location, users and their design requirements. Other three tests make a clear distinction with three cases using verbal analogy from many keywords, using visual analogy from many images and using verbal visual analogy from keywords and visual images. Consequently, when students use both verbal and visual analogy in solving design tasks their creative ability qualitatively as well as quantitatively is higher than in using only verbal analogy or visual analogy. Further study will be progressed with the design tasks of residential space in order to have an effective verification by comparing students' design results classified into two groups. One is a control group that consists of sophomore students in a college and another is a comparison group that consists of sophomore students in an university.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• pp.1-30
• /
• 2013

The capitalization of know-how, knowledge management, and the control of the constantly growing information mass has become the new strategic challenge for organizations that aim to capture the entire wealth of knowledge (tacit and explicit). Thus, knowledge mapping is a means of (cognitive) navigation to access the resources of the strategic heritage knowledge of an organization. In this paper, we present a new mapping approach based on the Boolean modeling of critical domain knowledge and on the use of different data sources via the data mining technique in order to improve the process of acquiring knowledge explicitly. To evaluate our approach, we have initiated a process of mapping that is guided by machine learning that is artificially operated in the following two stages: data mining and automatic mapping. Data mining is be initially run from an induction of Boolean case studies (explicit). The mapping rules are then used to automatically improve the Boolean model of the mapping of critical knowledge.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.914-920
• /
• 2002

Nonlinear flow-induced vibration characteristics of a generic missile wing (or control surface) are investigated in this study. The wing model has freeplay structural nonlinearity at its pitch axis. Nonlinear aerodynamic flows with unsteady shock waves are considered in the transonic flow region. To practically consider the effects of freeplay structural nonlinearity, the fictitious mass method (FMM) is applied to structural vibration analysis based on a finite element method (FEM). A computational fluid dynamics (CFD) technique is used for computing the nonlinear unsteady aerodynamics of all-movable wings. The aerodynamic analysis is based on the efficient transonic small-disturbance aerodynamic equations of motion using the potential-flow theory. To solve the nonlinear aeroelastic governing equations including the freeplay effect, a modal-based computational structural dynamic (CSD) analysis technique based on fictitious mass method (FMM) is used in time-domain. In addition, CSD and unsteady CFD techniques are simultaneously coupled to give accurate computational results. Various aeroelastic computations have been performed for a generic missile wing model. Linear and nonlinear aeroelastic computations have been conducted and the characteristics of flow-induced vibration are introduced.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.6
• /
• pp.61-71
• /
• 2003

In the study of control technique for a turbojet engine model, the Takagi-Sugeno fuzzy logic controller has been designed based on the model identification by the well designed PI controlled system through T-S neuro-fuzzy inference system. To enhance this designed controller, those procedures are proposed that certainty factors are adopted to each rule of objective groups which are classified by the fuzzy C-Means algorithm and the satisfaction degrees are matched to meet the objectives. This proposed technique shows its feasibility by upgrading performances of the previously well-designed T-S fuzzy controller.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.564-569
• /
• 2004

Most existing ontologies are suited for static knowledge, so they lack capability of representing procedural knowledge which is essential for an agent's action control or inference in the virtual world. Also they are not prepared to describe objects beyond their fixed ranges of domains as designed. In this paper we propose cyber-microcosm ontology (CMO) which augments procedural aspects and expressive power for multiple forms rather than fixed form as in conventional ontologies. The resulting ontology will provide an enhanced knowledge structure to capture procedural aspects of agents' actions and to facilitate their associated inferencing. The procedural aspects of the CMO are designed based on action frame formed according to diverse elements. They are elaborated in terms of various qualifiers and quantifiers to reflect statistical natures over time and instances.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.12
• /
• pp.7277-7282
• /
• 2014

In this study, the gradient descent algorithm was used for FLC analysis and the algorithm was used to represent the effects of nonlinear parameters, which alter the antecedent and consequence fuzzy variables of FLC. The controller parameters choose the control variable by iteration for gradient descent algorithm. The FLC consists of 7 membership functions, 49 rules and a two inputs - one output system. The system adopted the Min-Max inference method and triangle type membership function with a 13 quantization level.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.48 no.10
• /
• pp.1251-1258
• /
• 1999

The water level control of a steam generator in the unclear power plant is an important process. Most of the water level controllers of the actual plant are PID controllers. But they have limitations in appling for tracking the set point and getting rid of disturbances, so there are some defects to apply in the actual ground even though many research works represented the resolutions to solve it. In this paper, it is suggested that the established simple PID controller in low power has the ability to remove disturbances and trace the set-point, and then possesses the real-time self-tuning function according to the variety of moving peculiarity of a plant. This function realized by making use of fuzzy logic. PID parameters are formulated by a variable ${\alpha}$ and made it fluctuate by a fuzzy inference according to level error and level error change. This mechanism makes application of actual plant effective as well as taking advantage of improving the efficiency of water level controller by way of adding the function of self-tuning instead of replacing PID controller. The computer simulation of this scheme shows the improved performance compare to conventional PID controller.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1314-1317
• /
• 1999

In this paper, we design an Adaptive Neuro-Fuzzy Inference System(ANFIS) Precompensator for the performance improvement of conventional proportional integral derivative (PID) controller that the governor system of power plant constantly maintains the load frequency of two-area power system. The ANFIS Precompensator is expressed as the membership functions of premise parameters and the linear combination of consequent parameters by Sugeno's fuzzy if-then rules using nonlinear input-output relation for the set point automatic modification maintaining conventional PID controller. The proposed compensation design technique is hoped to be satisfactory method overcome difficulty of exact modelling and arising problems by the complex nonlinearities of power system, and our design shows merit that is easily implemented by adding an ANFIS precompenastor to an existing PID controller without replacement.

• Journal of the Korean Society of Industry Convergence
• /
• v.4 no.4
• /
• pp.403-411
• /
• 2001

A criterion for evaluation of burners has changed recently, and the environmental problems are raised as a global issue. Burners with higher thermal efficiency and lower oxygen in the exhaust gas, evaluated better. To comply with environmental regulations, burners must satisfy the $NO_x$ and CO regulation. Consequently. 'good burner' means one whose thermal efficiency is high under the constraint of $NO_x$ and CO consistency. To make existing burner satisfy recent criterion, it is highly recommended to develop a feedback control scheme whose output is the consistency of $NO_x$ and CO. This paper describes the development of a real time flame diagnosis technique that evaluate and diagnose the combustion states, such as consistency of components in exhaust gas, stability of flame in the quantitative sense. In this paper, it was proposed on the flame diagnosis technique of burner using Neuro- Fuzzy algorithm. This study focuses on the relation of the color of the flame and the state of combustion. Neuro- Fuzzy learning algorithm is used in obtaining the fuzzy membership function and rules. Using the constructed inference algorithm, the amount of $NO_x$ and CO of the combustion gas was successfully inferred.