Plant monitoring support apparatus, plant monitoring support method, and plant monitoring support program

Patent metadata

Field	Value
Publication number	US-2025315039-A1
Application number	US-202519015186-A
Country	US
Kind code	A1
Filing date	Jan 9, 2025
Priority date	Apr 4, 2024
Publication date	Oct 9, 2025
Grant date	—

Abstract

The plant monitoring support apparatus includes: an acquisition unit that acquire process values of a monitoring target; a reproduction unit that output a reproduced value obtained by using a model for performing data compression on the process values acquired in real time and data restoration on the compressed data; a first calculation unit that calculate deviations of the process values and the reproduced value; a detection unit that detect an anomaly sign of the monitoring target on the basis of a preset threshold and the deviations; a second calculation unit that calculate change amount of the deviations on the basis of a timing at which the anomaly sign is detected; and a selection unit that select a process value that belongs to another attribute and interrelated to the anomaly.

First claim

What is claimed is:

1 . A plant monitoring support apparatus comprising:
an acquisition unit configured to acquire process values of a monitoring target; a reproduction unit configured to output a reproduced value obtained by using a model for performing data compression/restoration on the process values acquired in real time; a first calculation unit configured to calculate deviations of the process values and the reproduced value; a detection unit configured to detect an anomaly sign of the monitoring target depending on a preset threshold and the deviations; a second calculation unit configured to calculate change amount of the deviations depending on a timing at which the anomaly sign is detected; and a selection unit configured to use the change amount for selecting a process value that belongs to another attribute and interrelated to the anomaly.

2 . The plant monitoring support apparatus according to claim 1 , further comprising:
a first processing unit configured to average the deviations in the process values acquired before the timing at which the anomaly sign is detected; and a second processing unit configured to average the deviations in the process values acquired after the timing at which the anomaly sign is detected, wherein the change amount is calculated by using the deviations subjected to averaging.

3 . The plant monitoring support apparatus according to claim 1 , further comprising a standardization unit configured to standardize calculated deviations to obtain standardized deviations,
wherein detection of the anomaly sign and selection of the anomaly interrelated are performed depending on the standardized deviations.

4 . The plant monitoring support apparatus according to claim 1 , further comprising a learning unit configured to cause a model to learn in such a manner that: normal values of the process values are compressed as input data; and restored output data match the input data.

5 . The plant monitoring support apparatus according to claim 1 , further comprising a display configured to display an attribute of a process value to be interrelated by an anomaly.

6 . A plant monitoring support method comprising steps of:
acquiring process values of a monitoring target; outputting a reproduced value obtained by using a model for performing data compression/restoration on the process values acquired in real time; calculating deviations of the process values and the reproduced value; detecting an anomaly sign of the monitoring target depending on a preset threshold and the deviations; calculating change amount of the deviations depending on a timing at which the anomaly sign is detected; and using the change amount for selecting a process value that belongs to another attribute and interrelated to the anomaly.

7 . A computer-readable plant monitoring support program that allows a computer to perform:
an acquisition process of acquiring process values of a monitoring target; an output process of outputting a reproduced value obtained by using a model for performing data compression/restoration on the process values acquired in real time; a calculation process of calculating deviations of the process values and the reproduced value; a detection process of detecting an anomaly sign of the monitoring target depending on a preset threshold and the deviations; another calculation process of calculating change amount of the deviations depending on a timing at which the anomaly sign is detected; and a selection process of using the change amount for selecting a process value that belongs to another attribute and interrelated to the anomaly.

Assignees

• Toshiba Kk
• Toshiba Energy Systems & Solutions Corp

Inventors

• Takado Naoyuki
• Aoki Toshio
• Tominaga Shinya
• Miyake Ryota

Classifications

• G05B23/024

  Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks · CPC title

• G05B23/0289 Primary

  Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection · CPC title