ABNORMAL VALUE DIAGNOSTIC DEVICE, ABNORMAL VALUE DIAGNOSTIC METHOD, AND PROGRAM
To provide an abnormal value diagnostic apparatus capable of easily and efficiently selecting a system to be inspected without setting individual thresholds for facilities comprising a plurality of systems.SOLUTION: A data extraction unit acquires information on a normal period of a system and extra...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | English Japanese |
Published |
21.02.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | To provide an abnormal value diagnostic apparatus capable of easily and efficiently selecting a system to be inspected without setting individual thresholds for facilities comprising a plurality of systems.SOLUTION: A data extraction unit acquires information on a normal period of a system and extracts data of the normal period of the system as normal period data from a database and also extracts data of the system in a diagnosis period as a diagnosis-purpose period as diagnostic period data from the database. Based on each of the normal period data and the diagnosis period data, an index calculation unit calculates performance indexes of the normal period and the diagnosis period for each system. A deterioration degree calculation unit calculates a degree of deterioration representing a degree of deterioration of a performance index in a diagnosis period for the normal period for each system. Based on the calculated deterioration degree and a predetermined threshold value, an inspection determination unit determines a system to be inspected among all the systems.SELECTED DRAWING: Figure 1
【課題】複数の系統からなる設備に関して、個別の閾値を設定することなく、簡単かつ効率的に、点検対象の系統を選択することができる異常値診断装置を提供する。【解決手段】データ抽出部は、系統の正常期間の情報を取得し当該系統の正常期間のデータを正常期間データとしてデータベースから抽出するとともに、診断対象とする期間である診断期間の当該系統のデータを診断期間データとしてデータベースから抽出する。指標算出部は、正常期間データと診断期間データのそれぞれに基づいて、正常期間と診断期間の性能指標を、系統ごとに算出する。悪化度算出部は、正常期間に対する診断期間における性能指標の悪化の度合いを表す悪化度を、系統ごとに算出する。点検判定部は、算出された悪化度と、所定の閾値とに基づいて、全系統のうち点検対象とすべき系統を判定する。【選択図】図1 |
---|---|
Bibliography: | Application Number: JP20170149168 |