Fuzzy Expert System (fuzzy + expert_system)

Distribution by Scientific Domains


Selected Abstracts


A combined S-transform and fuzzy expert system for phase selection in digital relaying

EUROPEAN TRANSACTIONS ON ELECTRICAL POWER, Issue 5 2008
S. R. Samantaray
Abstract This paper presents a new approach for faulty phase selection in transmission line based on combined S-transform and Fuzzy Expert System (FES). The S-transform with complex window is used to generate S-contours (time,frequency contours), which ,time-localizes' the fault. Features such as standard deviation (sd) and change in energy (ce) of the S-contours for half cycle post fault current samples are calculated and fuzzified with simple triangular membership function. The fuzzified inputs are fed to the FES and the corresponding fuzzy rule is fired to provide the output as "1" for faulty phase and ground involved and "0" for no-fault. The proposed integrated approach is tested for all 11 types of shunt faults with a wide range of operating conditions of the power system network. For testing the robustness of the proposed technique, the same is applied for the faults created on experimental set up with different operating conditions and provides accurate results. The output from the FES shows the fastness of the proposed technique and thus suitable for online application. Copyright 2007 John Wiley & Sons, Ltd. [source]


Knowledge acquisition for the development of an upper-body work-related musculoskeletal disorders analysis tool

HUMAN FACTORS AND ERGONOMICS IN MANUFACTURING & SERVICE INDUSTRIES, Issue 2 2007
Isabel Lopes Nunes
ERGO_X is a fuzzy expert system that supports workstation ergonomic analysis and provides advice on corrective measures aimed at improving the overall quality of the ergonomic design. ERGO_X was designed in a modular way to make further developments easier and to allow the selection of different ergonomic analysis contexts. The modularity feature mainly is a result of the knowledge base modular structure. Each module was built as a multilevel tree fuzzy relation. This relation reflects the interaction between attributes that are used to evaluate the level of severity of the relevant risk factors that are present at the analyzed workstation. The aim of this study is to address some aspects related to the knowledge acquisition process involved in the development of the ERGO_X knowledge base. In this regard, the author refers to her knowledge engineering activities in the development of a work-related musculoskeletal disorder module. 2007 Wiley Periodicals, Inc. Hum Factors Man 17: 149,162, 2007. [source]


Application of fuzzy logic to forecast seasonal runoff

HYDROLOGICAL PROCESSES, Issue 18 2003
C. Mahabir
Abstract Each spring in Alberta, Canada, the potential snowmelt runoff is forecast for several basins to assess the water supply situation. Water managers need this forecast to plan water allocations for the following summer season. The Lodge Creek and Middle Creek basins, located in southeastern Alberta, are two basins that require this type of late winter forecast of potential spring runoff. Historically, the forecast has been based upon a combination of regression equations. These results are then interpreted by a forecaster and are modified based on the forecaster's heuristic knowledge of the basin. Unfortunately, this approach has had limited success in the past, in terms of the accuracy of these forecasts, and consequently an alternative methodology is needed. In this study, the applicability of fuzzy logic modelling techniques for forecasting water supply was investigated. Fuzzy logic has been applied successfully in several fields where the relationship between cause and effect (variable and results) are vague. Fuzzy variables were used to organize knowledge that is expressed ,linguistically' into a formal analysis. For example, ,high snowpack', ,average snowpack' and ,low snowpack' became variables. By applying fuzzy logic, a water supply forecast was created that classified potential runoff into three forecast zones: ,low', ,average' and ,high'. Spring runoff forecasts from the fuzzy expert systems were found to be considerably more reliable than the regression models in forecasting the appropriate runoff zone, especially in terms of identifying low or average runoff years. Based on the modelling results in these two basins, it is concluded that fuzzy logic has a promising potential for providing reliable water supply forecasts. Copyright 2003 John Wiley & Sons, Ltd. [source]