• International Journal of Control, Automation, and Systems
• /
• v.1 no.3
• /
• pp.321-331
• /
• 2003

Experimental software datasets describing software projects in terms of their complexity and development time have been the subject of intensive modeling. A number of various modeling methodologies and modeling designs have been proposed including such approaches as neural networks, fuzzy, and fuzzy neural network models. In this study, we introduce the concept of the Rule-based fuzzy polynomial neural networks (RFPNN) as a hybrid modeling architecture and discuss its comprehensive design methodology. The development of the RFPNN dwells on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The architecture of the RFPNN results from a synergistic usage of RFNN and PNN. RFNN contribute to the formation of the premise part of the rule-based structure of the RFPNN. The consequence part of the RFPNN is designed using PNN. We discuss two kinds of RFPNN architectures and propose a comprehensive learning algorithm. In particular, it is shown that this network exhibits a dynamic structure. The experimental results include well-known software data such as the NASA dataset concerning software cost estimation and the one describing software modules of the Medical Imaging System (MIS).

• International Journal of Control, Automation, and Systems
• /
• v.1 no.1
• /
• pp.101-110
• /
• 2003

This paper introduces an identification method for nonlinear models in the form of rule-based Fuzzy-Neural Networks (FNN). In this study, the development of the rule-based fuzzy neural networks focuses on the technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms. The FNN modeling and identification environment realizes parameter identification through synergistic usage of clustering techniques, genetic optimization and a complex search method. We use a HCM (Hard C-Means) clustering algorithm to determine initial apexes of the membership functions of the information granules used in this fuzzy model. The parameters such as apexes of membership functions, learning rates, and momentum coefficients are then adjusted using the identification algorithm of a GA hybrid scheme. The proposed GA hybrid scheme effectively combines the GA with the improved com-plex method to guarantee both global optimization and local convergence. An aggregate objective function (performance index) with a weighting factor is introduced to achieve a sound balance between approximation and generalization of the model. According to the selection and adjustment of the weighting factor of this objective function, we reveal how to design a model having sound approximation and generalization abilities. The proposed model is experimented with using several time series data (gas furnace, sewage treatment process, and NOx emission process data from gas turbine power plants).

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.356-361
• /
• 1990

This paper presents a new self organizing fuzzy linguistic control (SOFLC) strategy for application to an arc welding process control. The proposed SOFLC is based on on-line modification of the control rules according to the extent of deviation of the one step ahead predictive output of the process from the desired output. The Predictive output of the process is estimated by a fuzzy predictor which is updated from the input and output data of the process. The rule base of the fuzzy subsets describing the control rules is modified by the improving mechanism based on the hill climbing approach. Simulation results show that this proposed SOFLC improves the response of the process in presence of the variation of the process dynamic characteristics.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.633-634
• /
• 2006

Recently we started a development of the digital meister expert system for the product design supporting in manufacturing industry. Knowledge representation is of major importance in digital moister expert system. This rule-based expert system-knowledges are designed for a certain type of knowledge representation such as rules or logic. The way in which a rule-based expert system represents knowledge affects the development, efficiency, speed, and maintenance. Eventually, this digital moister system is used to the engineer in manufacturing industry for the process control, production management and system management. In this paper, we propose the digital moister system knowledge representation method for product design supporting in manufacturing industry and we present introduction and contents of rule-based knowledge representation supporting tool.

• Journal of Korean Society for Quality Management
• /
• v.20 no.1
• /
• pp.147-157
• /
• 1992

This article describes a prototype expert system for yarn spinning process planning in textile industry. This expert system is intended as a consultant to give the technicians interactive assistance for the appropriate process planning in accordance with used materials, required count, and other factors affected yarn spinning by means of many types of machine. Also, this system has the other function that can be compared the standard values with the measured ones for quality characteristics control. VP-EXPERT-a rule-based microcomputer expert system development tool-provides the expert system components for this development. The details of knowledge organization, rule representation, inference reasoning process, and performance of this expert system are demonstrated with the practical yarn spinning operations.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.492-497
• /
• 1999

Cognition and control of grinding trouble occurring during the grinding process are classified into a quantitative knowledge which depends on experimental data and qualitative knowledge which relies on skillful engineers. Grinding operations include a large number of functional parameters, since there are several ways of coping with grinding trouble. One is the qualitative method which depends on empirical knowledge utilizing the skilful experts from the workshop, the other is the quantitative method which utilizes the experimental data obtained by sensor. But, they are all difficult to accomplish from the grinding trouble-shooting system. The reason is that grinding troubles are not easily controlled in the quantitative method, and therefore, trouble-shooting has mainly relied on the knowledge of skilful engineers. Thus, there is an important issue of how a grinding trouble-shooting system can be designed and what knowledge is utilized among the large amount of grinding trouble information. In this paper, basic strategy to develop the grinding database of rule-based rule, which is strongly depended upon experience and intuition, is described.

• 제어로봇시스템학회:학술대회논문집
• /
• 1990.10a
• /
• pp.117-121
• /
• 1990

The control process involving pure time delays presents a continuing challenge to the control system engineer. The nonlinear nature of the delay which can be introduced into the system make the use of conventional control algorithms a poor prospect. The Smith Predictor was developed to alleviate this problem. Unfortunately the quality of control achieved with the Smith Predictor is known to be sensitive to modelling errors. Only recently have researchers attempted to quantify the Smith Predictor controller's robustness to modelling errors. In several studies stability boundaries were plotted as functions of errors in parameters. But the research results address the question of performance of Smith Predictor controllers, In this paper, the Rule based Expert Systems for performance improvement of the Smith Predictor controller are developed.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.3
• /
• pp.903-911
• /
• 2008

Association rule mining searches for interesting relationships among items in a given large database. Association rules are frequently used by retail stores to assist in marketing, advertising, floor placement, and inventory control. Many data is most quantitative data. There is a need for partitioning techniques to quantitative data. The partitioning process is referred to as binning. We introduce several binning methods ; parameter mean binning, equi-width binning, equi-depth binning, clustering-based binning. So we apply these binning methods to several distribution types of quantitative data and present the best binning method for association rule discovery.

• Proceedings of the KWS Conference
• /
• 2002.05a
• /
• pp.68-70
• /
• 2002

A CCD camera with a laser strip was applied to realize the automation of welding process in GMAW. The Hough transformation was used to extract the laser stripe and to obtain specific weld points. In this study, a neural network based on the generalized delta rule algorithm was adapted for the process control of GMA, such as welding speed, arc voltage and wire feeding speed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1687-1692
• /
• 1991

Burrs, created when metals deform plastically, are by-products of most machining processes. The increasing requirements of precision and reliability in manufacturing processes have led to the development of systems for automated deburring. In this paper the motivations and requirements for automated robotic deburring are discussed. Also, the feasibility of automating the deburring process using fuzzy logic controller is investigated. In implementing the fuzzy logic controller, particular attention is paid to the acoustic emission sensing for the characterization and feedback control of the burr removal process. The results of the experiments reveal the rule based control scheme based on fuzzy logics can be a good alternative to traditional control schemes.