ABNORMALITY SIGN DETECTION SYSTEM, ABNORMALITY SIGN DETECTION MODEL GENERATION METHOD, AND ABNORMALITY SIGN DETECTION MODEL GENERATION PROGRAM

• Main Authors: AOKI TOSHIO, TAKADO NAOYUKI, MIYAMOTO CHIKASHI, MIYAKE RYOTA, TOMINAGA MASAYA
• Format: Patent
• Language: English; Japanese
• Published: 02.05.2024
• Subjects: CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

To provide an abnormality sign detection technology which suppresses erroneous detection to improve the reliability of an abnormality sign detection function.SOLUTION: A computer 5 is configured to: select a reference process value 31 as reference for calibration; calculate, based on an actual process value 30 and the reference process value 31, a calibration necessity determination coefficient 32 for determining whether or not the actual process value 30 correlates with the reference process value 31; calculate, based on the actual process value 30 and the reference process value 31, a calibration value 34 for calibrating the actual process value 30; determine, based on the calibration necessity determination coefficient 32, whether or not each actual process value 30 correlates with the reference process value 31; calibrate the actual process value 30, which has been determined to correlate with the reference process value 31, with the calibration value 34; generate learning input data including a calibrated process value 35 obtained through the calibration with the calibration value 34; and input the learning input data into an abnormality sign detection model to perform machine learning.SELECTED DRAWING: Figure 2 【課題】誤検知を抑制して異常予兆検知機能の信頼性を向上させることができる異常予兆検知技術を提供する。【解決手段】コンピュータ５は、補正の基準となる基準プロセス値３１を選定し、実プロセス値３０および基準プロセス値３１から、実プロセス値３０が基準プロセス値３１と相関があるか否かを判定するための補正要否判定係数３２を算出し、実プロセス値３０および基準プロセス値３１から、実プロセス値３０を補正するための補正値３４を算出し、補正要否判定係数３２に基づいて、それぞれの実プロセス値３０が基準プロセス値３１と相関があるか否かを判定し、基準プロセス値３１と相関があると判定された実プロセス値３０を補正値３４で補正し、補正値３４で補正した補正後プロセス値３５を含む学習用入力データを生成し、学習用入力データを異常予兆検知モデルに入力して機械学習を行う、ように構成されている。【選択図】図２