퍼지전문가시스템을 이용한 공기압축기 이상진단모델 개발

Abstract

Most systems used in industrial sites, actually have non-linearity and uncertainty. Therefore there are a lot of difficulties in evaluating conditions of these systems. Generally, the quantitative analysis and expression are found hard because the general public cannot easily make an accurate interpretation on the systems. Thus development of a system that utilizes an expertise from skilled analysts is required. With the expertise being used, there should a new attempt to deal with human thinking as well as ambiguity of the language involved in the expression of the thought. The Fuzzy Theory focuses upon human thought and handling the ambiguity caused by the language of expression, both of which are considered a dilemma from a Mathematical perspective. Especially, the Fuzzy Theory has been under research to be applied to home appliances, means of transportation and machineries and there lies hardship in quantitatively analyzing the input-output relationship in a system whose the internal and external environments are both inconsistent and uncertain. Therefore it is applied in a variety of fields by improving some of mathematics-statistical defects found in a status value of the operating system. However, when the system is complex and unstable, there follow some difficulties in describing the patterns. Also the number of control patterns, which is demanded for a precise result, increases drastically. Although the Fuzzy theory is useful, there still lacks a methodical plan for the system. This literature brings up the FE_AFCDM(Fuzzy Expert_Air compressor Fault Condition Diagnosis Model), which involves an electric signal system and computer programming that can upgrade creditability and speed, rather than the complex Non-linear system. Air Compressor mentioned in the paper is an important facility in sites where products are manufactured. Because there could be a ripple effect and loss caused by a breakdown and unstable operation of the system, reliability and objectivity of the facility has to be checked in real time. With this, it has been developed in order to meet the demand on the prevention of safety accidents, the quality maintenance of products and cut in energy usage. In this research, a real-time sensor signal conditioning system and Fuzzy-expert system have been separately set up into an inference algorithm. So that it ensures a fast, accurate, objective and quantitative operational condition value provided to the manager. The first signal conditioning system consists of the embedded micro processor, sensor signal condition amplifier and converters and lastly a hardware that wirelessly transfers the value temperature, pressure and current. The second inference algorithm has designed a software that can, through personal computers, show that information on temperature, pressure and currents are programmed into the Fuzzy membership function and the Fuzzy pattern when the air compressor works. Therefore, FE_AFCDM is suggested in this literature, as an effective system for diagnosing the problems related to the air compressor. It can quantify the uncertain and absurd condition to operate the air compressor facilities safely and financially.