• Journal of the Korean Society of Safety
• /
• v.21 no.3 s.75
• /
• pp.16-21
• /
• 2006

This paper presents a knowledge-based electrical fire cause diagnosis system using the fuzzy reasoning. The cause diagnosis of electrical fires may be approached either by studying electric facilities or by investigating cause using precision instruments at the fire site. However, cause diagnosis methods for electrical fires haven't been systematized yet. The system focused on database(DB) construction and cause diagnosis can diagnose the causes of electrical fires easily and efficiently. The cause diagnosis system for the electrical fire was implemented with entity-relational DB systems using Access 2000, one of DB development tools. Visual Basic is used as a DB building tool. The inference to confirm fire causes is conducted on the knowledge-based by combined approach of a case-based and a rule-based reasoning. A case-based cause diagnosis is designed to match the newly occurred fire case with the past fire cases stored in a DB by a kind of pattern recognition. The rule-based cause diagnosis includes intelligent objects having fuzzy attributes and rules, and is used for handling knowledge about cause reasoning. A rule-based using a fuzzy reasoning has been adopted. To infer the results from fire signs, a fuzzy operation of Yager sum was adopted. The reasoning is conducted on the rule-based reasoning that a rule-based DB system built with many rules derived from the existing diagnosis methods and the expertise in fire investigation. The cause diagnosis system proposes the causes obtained from the diagnosis process and showed possibility of electrical fire causes.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.6
• /
• pp.1318-1324
• /
• 2003

There are two problems in the conventional ART1 algorithm. One is in similarity testing method of the conventional ART1 between input patterns and stored patterns. The other is that vigilance threshold of conventional ART1 influences the number of clusters and the rate of recognition. In this paper, new similarity testing method and dynamical vigilance threshold method are proposed to solve these problems. The former is similarity test method using the rate of norm of exclusive-NOR between input patterns and stored patterns and the rate of nodes have equivalence value, and the latter method dynamically controls vigilance threshold to similarity using fuzzy operations and the sum operation of Yager. To check the performance of new methods, we used 26 alphabet characters and nosed characters. In experiment results, the proposed methods are better than the conventional methods in ART1, because the proposed methods are less sensitive than the conventional methods for initial vigilance and the recognition rate of the proposed methods is higher than that of the conventional methods.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.355-356
• /
• 2005

The problem of maximizing an OWA aggregation of a group of variables that are interrelated and constrained by a collection of linear inequalities is considered by Yager[Fuzzy Sets and Systems, 81(1996) 89-101]. He obtained how this problem can be modelled as a mixed integer linear programming problem. Recently, Carlsson et al. [Fuzzy Sets and Systems, 139(2003) 543-546] obtained a simple algorithm for exact computation of optimal solutions to a constrained OWA aggregation problem with a single constraint on the sum of all decision variables. In this note, we introduce anew approach to the same problem as Carlsson et al. considered. Indeed, it is a direct consequence of a known result of the linear programming problem.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1788-1792
• /
• 2006

The ordered weighted averaging (OWA) operator by Yager has received more and more attention since its appearance. One key point in the OWA operator is to determine its associated weights. Among numerous methods that have appeared in the literature, we notice the maximum entropy OWA (MEOWA) weights that are determined by taking into account two appealing measures characterizing the OWA weights. Instead of maximizing the entropy in the formulation for determining the MEOWA weights, the new method in the article tries to obtain the OWA weights which are evenly spread out around equal weights as much as possible while strictly satisfying the orness value provided in the program. This consideration leads to the least squared OWA (LSOWA) weighting method in which the program tries to obtain the weights that minimize the sum of deviations from the equal weights since entropy is maximized when the weights are equal. Above all, the LSOWA weights display symmetric allocations of weights on the basis of equal weights. The positive or negative allocations of weights from the median as a basis depend on the magnitude of orness specified. Further interval LSOWA weights are constructed when a decision-maker specifies his or her value of orness in uncertain numerical bounds.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.13 no.9
• /
• pp.703-712
• /
• 2003

This paper suggests a fuzzy expert system for fault diagnosis of rotating machinery, based on modulated databases. In the proposed system, alarm and trip levels are set based on ISO, considering operating condition, machinery type and maintenance history. Input signals for diagnosis, such as sub-and super-harmonic components of vibration and mean value, are normalized from 0 to 1 under the threshold level and otherwise equal to one so that chronic faults slightly below the threshold level can be monitored. The database for diagnosis consists of two modules: the well-known Sohre's chart module and if-then type rules. The Sohre's chart is utilized for the most common problems of high-speed turbomachinery, while the rule-based module, which was collected from many papers and reports, is for diagnosing peculiar faults according to the type of machinery. To infer the results from two modules, a fuzzy operation of Yager sum was adopted. Using a simulator constructed in laboratory, experimental verification was performed for the cases of unbalance and resonance which were intended. The experimental results show that the proposed fuzzy expert system has feasibility in practical diagnosis of rotating machinery.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.05a
• /
• pp.303-312
• /
• 2003

This paper suggests a fuzzy expert system for fault diagnosis of rotating machinery, based on modulated databases. In the proposed system, alarm and trip levels are set based on ISO, considering operating condition, machinery type and maintenance history. Input signals for diagnosis, such as sub- and super-harmonic components of vibration and mean value, are normalized from 0 to 1 under the threshold level and otherwise equal to one so that chronic faults slightly below the threshold level can be monitored. The database for diagnosis consists of two modules: the well-known Sohre's chart module and if-then type rules. The Sohre's chart is utilized for the most common problems of high-speed turbomachinery, while the rule-based module, which was collected from many papers and reports, is for diagnosing peculiar faults according to the type of machinery. To infer the results from two modules, a fuzzy operation of Yager sum was adopted. Using a simulator constructed in laboratory, experimental verification was performed for the cases of resonance and housing looseness which were intended. The experimental results show that the proposed fuzzy expert system has feasibility in practical diagnosis of rotating machinery.