• Title/Summary/Keyword: 이상 진단

Search Result 5,120, Processing Time 0.038 seconds

Intelligent Diagnosis System with Circuit Breaker (배선 진단 시스템 구성을 위한 지능형 차단 시스템)

  • Sung, Hwa-Chang;Park, Jin-Bae;Sho, Je-Yoon;Joo, Young-Hoon
    • Proceedings of the KIEE Conference
    • /
    • 2007.07a
    • /
    • pp.304-305
    • /
    • 2007

  • 본 논문에서는 진단부분에서 서버를 중심으로 받은 정보를 능동적으로 해석하고 이상 유무에 따른 차단 역할 수행하도록 하는 지능형 차단 시스템에 대한 알고리즘 개발을 목표로 하고 있다. 제안하고자 하는 분류 알고리즘이란, 저압 배선에서 받은 신호에 대한 해석과 더불어 이를 각 이상 정도에 따라 분류하는 것을 말한다. 일반적으로, TFDR을 통해 알아 낼 수 있는 이상 유무의 종류는 damage, open 그리고 short 등이다. 도선 이상의 종류 및 특성에 따른 분류를 위하여, 알고리즘 개발을 위한 사전 이론 조사 및 개요 구성을 목표로 하고 있다. 또한, 기존의 통신 선 상에서 이루어진 결과를 토대로 한 퍼지 분류 규칙 생성 및 분류 알고리즘 개발 역시 앞으로 수행 될 예정이며, 이를 통한 지능형 차단 시스템 구축이 최종 목표이다.

  • PDF

The Development and Application of Standard Diagnostic Table for Astringent Persimmon Management (떫은감 경영 표준진단표의 개발 및 현지 적용)

  • Jeon, Jun-Heon;Lee, Seong-Youn;Lee, Jung-Min;Ji, Dong-Hyun;Oh, Chan-Jin
    • Journal of Korean Society of Forest Science
    • /
    • v.104 no.3
    • /
    • pp.488-494
    • /
    • 2015

  • This study aims to develop and apply a standard management self-diagnostic table for forestry households to better manage their astringent persimmon production. The diagnostic table consisted of 3 categories (general status of a forestry household, management performance indicators, level of management) and 18 subcategories. The current management status across 241 households was surveyed among 10 chief astringent persimmon producing municipalities. Scores from the 18 subcategories were aggregated for a total score to evaluate and compare different levels of management. The respondents scored an overall average of 57.4, 62% of which were placed between 40 and 60. Upon close examination Chungcheongnam-do scored a very low score in the 'management system-tree height' subcategory with respect to the average score potentially because of the large population of aged trees in the region. The national average in the 'production skills-time of fruit load adjustment' subcategory was only 1.96 because unlike sweet persimmons astringent persimmons adjust their own load by inducing physiological fruit drop. The national average in the 'management/sales skills-material purchase' subcategory was 2.01; over 60% of the respondents indicated a preference for independent selection and purchase for most materials. The households preferring a group purchase tended to utilize the regional co-op.

  • https://doi.org/10.14578/jkfs.2015.104.3.488 인용 PDF KSCI

Operation Modes Classification of Chemical Processes for History Data-Based Fault Diagnosis Methods (데이터 기반 이상진단법을 위한 화학공정의 조업모드 판별)

  • Lee, Chang Jun;Ko, Jae Wook;Lee, Gibaek
    • Korean Chemical Engineering Research
    • /
    • v.46 no.2
    • /
    • pp.383-388
    • /
    • 2008

  • The safe and efficient operation of the chemical processes has become one of the primary concerns of chemical companies, and a variety of fault diagnosis methods have been developed to diagnose faults when abnormal situations arise. Recently, many research efforts have focused on fault diagnosis methods based on quantitative history data-based methods such as statistical models. However, when the history data-based models trained with the data obtained on an operation mode are applied to another operating condition, the models can make continuous wrong diagnosis, and have limits to be applied to real chemical processes with various operation modes. In order to classify operation modes of chemical processes, this study considers three multivariate models of Euclidean distance, FDA (Fisher's Discriminant Analysis), and PCA (principal component analysis), and integrates them with process dynamics to lead dynamic Euclidean distance, dynamic FDA, and dynamic PCA. A case study of the TE (Tennessee Eastman) process having six operation modes illustrates the conclusion that dynamic PCA model shows the best classification performance.

  • PDF KSCI