ABNORMALITY SIGN DIAGNOSTIC SYSTEM AND ABNORMALITY SIGN DIAGNOSTIC METHOD

• Main Authors: MIYABE SHOZO, YOSHIZAWA TAKASHI, NODA TOJIRO
• Format: Patent
• Language: English; Japanese
• Published: 09.02.2017
• Subjects: CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

PROBLEM TO BE SOLVED: To provide an abnormality sign diagnostic system and the like capable of highly accurately diagnosing whether an abnormality sign of a machine facility is present or not.SOLUTION: An abnormality sign diagnostic system 1 includes: sensor data obtaining means 12 for obtaining sensor data including detection values of a sensor placed in a machine facility 2; learning means for regarding sensor data in a period, in which the machine facility 2 is known to have been working normally, as a learning object and for learning time-series waveforms of the sensor data as a normal model; and diagnosis means for diagnosing whether an abnormality sign of the machine facility 2 is present or not based on the comparison between the normal model and the time-series waveforms of the sensor data to be diagnosed.SELECTED DRAWING: Figure 1 【課題】機械設備の異常予兆の有無を高精度で診断できる異常予兆診断システム等を提供する。【解決手段】異常予兆診断システム１は、機械設備２に設置されたセンサの検出値を含むセンサデータを取得するセンサデータ取得手段１２と、機械設備２が正常であることが既知である期間のセンサデータを学習対象とし、当該センサデータの時系列的な波形を正常モデルとして学習する学習手段と、前記正常モデルと、診断対象のセンサデータの時系列的な波形と、の比較に基づいて、機械設備２の異常予兆の有無を診断する診断手段と、を備える。【選択図】図１