• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• Journal of the Korean Institute of Gas
• /
• v.22 no.2
• /
• pp.90-96
• /
• 2018

Design techniques for minimizing the damage caused by leakage of $H_2S$ gas, contained in natural gas and petroleum, have been widely studied abroad in chemical plants that purify and process natural gas and petroleum. However, there is no domestic engineering practice and regulation of $H_2S$. In accordance with the circumstances, this study proposes the quantitative criteria of process equipment to install $H_2S$ toxic gas detector as 500 ppm and explains the valid basis. The $H_2S$ gas dispersion radius up to IDLH 100 ppm is calculated by ALOHA under previous $H_2S$ gas leak accident scenario. The weather conditions of modeling include the conditions of Ulsan, Yeosu and Daesan, the three major petrochemical complexes in Korea. The long radius up to 100 ppm was derived in order of Ulsan, Daesan, Yeosu. For emergency safety the dispersion radius up to 100 ppm of the $H_2S$ gas obtained in this study should be extended to apply the additional $H_2S$ toxic gas detector, and local climate conditions should be considered.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.14 no.1
• /
• pp.30-37
• /
• 2000

We studied on acquiring of transfer function and tuning of 2-DOF PID controller using ANFIS for the optimum control to turbine's variables variety. Since the shape of a membership function in the ANFIS based on the characteristics of plant. ANFIS based control method is effective for plant that its variable vary. On the other hand, a start-up time is very short and its variable's value for optimal start-up in gas turbine should be varied, but it is very difficult for such a controller to design. In this paper, we tune 2-DOF PID controller after apply a ANFIS to the operating data of Gun-san gas turbine and verify the characteristics. Its results is compared to the conventional PID controller and discuss. We expect this method will be used for another process because it is studied on the real operating data.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.125-137
• /
• 2018

Simulations have been used to evaluate the efficiency of logistics or manufacturing systems and predict the outcomes of the systems. New simulation models are needed to evaluate new alternative plants and layouts during the resource design process. Although it is easy to handle minor changes in parameters by modifying a simulation model, it takes considerable time and effort for simulation modelers to alter the layout, which involves changes in many simulation sub-models. Therefore, this study proposes a method to transfer information in AutoCAD layout to the simulation model automatically. This study also defines a standard document as an Excel Form, and suggests a method to transfer information on the basic layouts, processes, resources, and workers to a simulation model automatically. A simulation tool, called Tecnomatix Plant Simulation 9.0, was used for this study. The proposed approach in this study was applied to a semiconductor wafer factory for a case study.

• Nuclear Engineering and Technology
• /
• v.44 no.8
• /
• pp.919-928
• /
• 2012

The applications of computers and communication system and network technologies in nuclear power plants have expanded recently. This application of digital technologies to the instrumentation and control systems of nuclear power plants brings with it the cyber security concerns similar to other critical infrastructures. Cyber security risk assessments for digital instrumentation and control systems have become more crucial in the development of new systems and in the operation of existing systems. Although the instrumentation and control systems of nuclear power plants are similar to industrial control systems, the former have specifications that differ from the latter in terms of architecture and function, in order to satisfy nuclear safety requirements, which need different methods for the application of cyber security risk assessment. In this paper, the characteristics of nuclear power plant instrumentation and control systems are described, and the considerations needed when conducting cyber security risk assessments in accordance with the lifecycle process of instrumentation and control systems are discussed. For cyber security risk assessments of instrumentation and control systems, the activities and considerations necessary for assessments during the system design phase or component design and equipment supply phase are presented in the following 6 steps: 1) System Identification and Cyber Security Modeling, 2) Asset and Impact Analysis, 3) Threat Analysis, 4) Vulnerability Analysis, 5) Security Control Design, and 6) Penetration test. The results from an application of the method to a digital reactor protection system are described.

• Journal of Advanced Marine Engineering and Technology
• /
• v.19 no.1
• /
• pp.60-70
• /
• 1995

In the field of marine transportation the energy saving is one of the most important factors for profit. In order to reduce the fuel oil consumption the ship's propulsion efficiency must be increased as much as possible. The propulsion efficiency depends upon a combination of an engine and a propeller. The propeller has better efficiency as lower rotational speed. This situation led the engine manufacturers to design the engine that has lower speed, longer stroke and a small number of cylinders. Consequently the variation of rotational torque became larger than before because of the longer delay-time in the fuel oil injection process and an increased output per cylinder. As this new trends the conventional mechanical-hydrualic governors for engine speed control have been replaced by digital speed controllers which adopted the PID control or the optimal control algorithm. But these control algorithms have not enough robustness to suppress the variation of the delay-time and the parameter pertubation. In this paper we consider the delay-time and the perturbation of engine parameters as the modeling uncetainties. Next we design the controller which has zero offset in steady state engine speed, based on the two-degree-of-freedom control theory and $\mu$-synthesis. Thd validity of the controller is investigated through the response simulation. We use a personal computer and an analog computer as the digital controller and the engine (plant) part respectively. And, we certify that the designed controller maintains its performance even though the engine parameters may vary.

• Journal of Environmental Impact Assessment
• /
• v.10 no.1
• /
• pp.73-83
• /
• 2001

Web based integrated sewer management system was developed for the analysis of sewer flow and for the optimal operation of sewer works using ArcView and SWMM. SWMM and ArcView were dynamically linked together using Avenue in order to construct user-friendly information management system. The developed system was applied to the residential area in Choonchun city to verify its utilities. All the relevant field data were analyzed on the basis of the developed system, and the modeling of sewer flow was implemented using RUNOFF, EXTRAN, TRANSPORT in SWMM. This system is now in the process of connection to the management system of stormwater, surface and subsurface environment in order to develop an integrated environmental management system. Futhermore, this system will be a critical part of overall control system of sewer works including sewer network and wastewater treatment plant. As this system can provide comprehensive prediction of flow and pollution profiles, it could serve as a tool not only for the optimal management, but also for the decision support system to examine the efficiency of planning and implementation of sewer projects.

• Proceedings of the KWS Conference
• /
• 2002.10a
• /
• pp.181-186
• /
• 2002

Laser welding application for car body manufacturing has many advantages in the stiffness and the lightness of vehicle, the productivity of assembly line, and the degree of freedom in design. This presentation will express the innovation of car body manufacturing including parameter optimization, process modeling, and system integration. In this application the investment for systems was cut down dramatically by real time switching over the laser path between two welding stations. Points of technical discussion are as follows: optimization of parameters such as laser power, robot speed and trajectory, compact and useful design of jig & fixture to assure welding quality for 3 sheet-layer zinc-coated steel, system integration between 4kW Nd:YAG laser device and the other systems, on-line real time welding quality monitoring system, perfect safety standards for high power laser, minimization of consumption costs such as arc lamp, protective glass for optic, etc. Laser welding has found a place on Hyundai's production plant in conjunction with the startup of mass production of new sports car, and this production system is the result of a collaboration of its engineers. Outer side sheets are joined to inner side sheets by 122 stitch welds totally. And the length is about 2.4meter.

• Journal of Korean Society on Water Environment
• /
• v.21 no.1
• /
• pp.21-28
• /
• 2005

The training and prediction modeling using an artificial neural network was implemented to predict the turbidity of treated water as well as to estimate the optimized feed concentration of polyaluminium chloride (PACl) in a water treatment plant. The parameters used in the input layers were pH, temperature, turbidity and alkalinity, while those in output layers were PACl and turbidity of treated water. Levenberg-Marquadt method of feedforward back-propagation perceptron in the neural network toolbox of MATLAB program was used in this study. Correlation coefficients of the training data with the measured data were 0.9997 for PACl and 0.6850 for turbidity and those of the testing data with measured data were 0.9140 for PACl and 0.3828 for turbidity, when four parameters at input layer, 12-12 nodes each at both the first and the second hidden layers, and two parameters(PACl and turbidity) at output layer were used. Although the predictability of PACl was improved, compared to that of the previous studies to use the only coagulant dose as output layer, turbidity in treated water could not be predicted well. Acquisition of more data through several years obtained with the advanced on-line measuring system could make the artificial neural network useful and practical in actual water treatment plants.

• Journal of the Korean Wood Science and Technology
• /
• v.24 no.2
• /
• pp.71-80
• /
• 1996

Handling the manufacured goods is the most cost-consuming task in material handling system in wooden furniture industries. Fully automated warehouse for cartoned goods of a furniture manufacturing company was analized to provide plant engineers and managers with some important informations on the utility and profitability of the automated storage and retrieval system(AS/RS). Process-oriented simulation modeling tech-niques were used to describe the system and to propose some alternatives to promote the efficiency of AS/RS. Simulation report could be inter-preted as follows: 1. Warehouse for the furniture goods must be designed in accordance with reliable material handling program and constructed with suitable equipments depending on the specification of packed products. 2. An excess of palletized products induced the indigestion and the inefficiency of AS/RS of the furniture industry and put this high-costly system into the shade. 3. Overcrowded AS/RS of the furniture factories could regain its material handling function by cutting down the deposit of products into the automated warehouse. For this purpose, reducing the regular output and direct delivering the outside products to the destination should be considered as the definite counterplan. And additional operation of conventional handy warehouse was also expected to improve the efficiency of main AS/RS.