Abnormality diagnosing method and abnormality diagnosing system

Patent metadata

Field	Value
Publication number	US-2017328811-A1
Application number	US-201715664525-A
Country	US
Kind code	A1
Filing date	Jul 31, 2017
Priority date	Feb 18, 2015
Publication date	Nov 16, 2017
Grant date	—

Abstract

An abnormality diagnosing method includes a model generation step of generating a simulation model of a monitoring target, an operation start step of starting an operation of the monitoring target, a measurement step of measuring an internal state quantity in the operating state of the monitoring target and extracting a measured value, a prediction step of inputting into the simulation model same control input value used in the operating state of the monitoring target and calculating a predicted value of the internal state quantity of the monitoring target, a Mahalanobis distance calculation step of calculating a Mahalanobis distance from a difference between the measured value and the predicted value, and an abnormality diagnosis step of diagnosing whether the operating state of the monitoring target is abnormal based on the Mahalanobis distance.

First claim

What is claimed is:

1 . An abnormality diagnosing method of diagnosing an abnormality of a monitoring target having an operating state that includes a non-steady state, the abnormality diagnosing method comprising:
generating a simulation model of the monitoring target; measuring an internal state quantity in the operating state of the monitoring target and extracting a measured value; inputting into the simulation model same control input value used in the operating state of the monitoring target and calculating a predicted value of the internal state quantity of the monitoring target; calculating a Mahalanobis distance from a difference between the measured value and the predicted value; and diagnosing whether the operating state of the monitoring target is abnormal based on the Mahalanobis distance.

2 . The abnormality diagnosing method according to claim 1 , further comprising calculating an error vector that includes the difference and an integral value of the difference as components thereof.

3 . The abnormality diagnosing method according to claim 2 , wherein the calculating of the predicted value is made based on a measured value that was measured immediate previously in a time series.

4 . An abnormality diagnosing system for diagnosing an abnormality of a monitoring target having an operating state that includes a non-steady state, the abnormality diagnosing system comprising:
a simulation model that simulates the monitoring target; a measuring unit configured to measure an internal state quantity in the operating state of the monitoring target; a diagnosing device that calculates a Mahalanobis distance from a difference between a predicted value calculated by the simulation model and a measured value extracted by the measuring unit and diagnoses whether the operating state of the monitoring target is abnormal based on the Mahalanobis distance; and a controlling unit configured to transmit same control input value to at least the monitoring target and the simulation model.

5 . The abnormality diagnosing system according to claim 4 , wherein the diagnosing device calculates the Mahalanobis distance based on an error vector that includes the difference and an integral value of the difference as components thereof.

6 . The abnormality diagnosing system according to claim 5 , wherein the simulation model calculates the predicted value based on a measured value that was measured immediate previously in a time series.

7 . The abnormality diagnosing system according to claim 4 , wherein the monitoring target is an engine for reusable spacecraft.

Assignees

• Ihi Corp

Inventors

• Mori Hatsuo
• Mizukoshi Noriyoshi
• Ogai Takashi
• Maru Yusuke
• Yamamoto Takayuki
• Takeuchi Shinsuke
• Nonaka Satoshi
• Yagishita Tsuyoshi

Classifications

• G06F30/20

  Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) · CPC title

• G06F17/18

  for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} · CPC title

• G01M15/02 Primary

  Details or accessories of testing apparatus · CPC title

• G05B23/0243 Primary

  model based detection method, e.g. first-principles knowledge model · CPC title

• B64G1/52

  Protection, safety or emergency devices; Survival aids · CPC title