Facility diagnosis device, facility diagnosis method, and facility diagnosis program

Patent metadata

Field	Value
Publication number	US-11003178-B2
Application number	US-201716074942-A
Country	US
Kind code	B2
Filing date	Jan 10, 2017
Priority date	Feb 3, 2016
Publication date	May 11, 2021
Grant date	May 11, 2021

Abstract

A facility diagnosis device includes: a process data acquirer that acquires process data indicating a state of a process executed in a plant; a production data acquirer that acquires production data indicating a production state in the plant; a state information generator that generates state information for estimating an operation state of a facility operating in the process based on the acquired process data or the acquired production data, or the process data and the production data; and a determiner that determines the operation state of the facility based on the acquired process data or the generated state information and the acquired production data.

First claim

The invention claimed is:

1. A facility diagnosis device comprising:
a process data acquirer that acquires process data indicating a state of a process executed in a plant;
a production data acquirer that acquires production data indicating a production state in the plant;
a state information generator that generates state information for estimating an operation state of a facility operating in the process based on at least one of the acquired process data and the acquired production data;
a determination model creator that creates a plurality of populations based on the acquired production data and a plurality of determination models based on the acquired process data, wherein the number of the plurality of determination models corresponds to the number of the plurality of populations, and the plurality of determination models have different threshold values or different algorithms;
a determination model selector that selects a determination model from among the plurality of determination models based on the generated state information;
a determiner that determines the operation state of the facility based on the acquired process data or the generated state information and the acquired production data, wherein the determiner further determines the operation state of the facility using the selected determination model;
a result outputter that outputs, to a display device, a result of the determined operation state of the facility; and
an association inputter that receives an input maintenance data in which the result of the operation state output by the result outputter and an operation state of the facility checked by a worker are associated with one another.

2. The facility diagnosis device according to claim 1 , further comprising a facility data collector that collects facility data measured by a sensor attached to the facility.

3. The facility diagnosis device according to claim 2 , wherein the determination model creator creates the plurality of determination models further based on collected facility data.

4. The facility diagnosis device according to claim 2 , wherein the determination model selector selects the determination model from among the plurality of determination models based on the generated state information or the collected facility data.

5. The facility diagnosis device according to claim 1 , further comprising a maintenance data storer that collects and stores maintenance data of the facility corresponding to the determined operation state of the facility,
wherein the determination model creator creates the plurality of determination models further based on the stored maintenance data.

6. The facility diagnosis device according to claim 5 , wherein the maintenance data storer collects and stores the maintenance data comprising at least one of the maintenance data of the facility and failure data of the facility.

7. A facility diagnosis method comprising:
acquiring process data indicating a state of a process executed in a plant;
acquiring production data indicating a production state in the plant;
generating state information for estimating an operation state of a facility operating in the process based on at least one of the acquired process data and the acquired production data;
creating a plurality of populations based on the acquired production data and a plurality of determination models based on the acquired process data, wherein the number of the plurality of determination models correspond to the number of the plurality of populations, and the plurality of determination models have different threshold values or different algorithms;
selecting a determination model from among the plurality of determination models based on the generated state information;
determining the operation state of the facility based on the acquired process data or the generated state information and the acquired production data and determining the operation state of the facility using the selected determination model;
outputting, to a display device, a result of the determined operation state of the facility; and
receiving an input maintenance data in which the result of the operation state and an operation state of the facility checked by a worker are associated with one another.

8. The facility diagnosis method according to claim 7 , further comprising collecting facility data measured by a sensor attached to the facility.

9. The facility diagnosis method according to claim 8 , wherein the creating of the plurality of determination models comprises creating the determination model further based on the collected facility data.

10. The facility diagnosis method according to claim 8 , wherein the selecting of the created determination model comprises selecting the determination model from among the plurality of determination models based on the generated state information or the collected facility data.

11. The facility diagnosis method according to claim 7 , further comprising collecting and storing maintenance data of the facility corresponding to the determined operation state of the facility, wherein the creating of the plurality of determination models comprises creating the plurality of determination models further based on the stored maintenance data.

12. The facility diagnosis method according to claim 11 , wherein the maintenance data comprises at least one of the maintenance data of the facility and failure data of the facility.

13. A non-transitory computer readable storage medium storing facility diagnosis program for making a computer execute:
acquiring process data indicating a state of a process executed in a plant;
acquiring production data indicating a production state in the plant;
generating state information for estimating an operation state of a facility operating in the process based on at least one of the acquired data and the acquired production data;
creating a plurality of populations based on the acquired production data and a plurality of determination models based on the acquired process data, wherein the number of the plurality of determination models correspond to the number of the plurality of populations, and the plurality of determination models have different threshold values or different algorithms;
selecting a determination model from among the plurality of determination models based on the generated state information;
determining the operation state of the facility based on the acquired process data or the generated state information and the acquired production data and determining the operation state of the facility using the selected determination model;
outputting, to a display device, a result of the determined operation state of the facility; and
receiving an input maintenance data in which the result of the operation state and an operation state of the facility checked by a worker are associated with one another.

Assignees

• Yokogawa Electric Corp

Inventors

• Fujita Sho
• Tomosada Nobuhiro
• Takenaka Kazuma
• Kato Shinya
• KEMMOTSU Taro

Classifications

• G05B23/0254

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title

• G05B23/0221 Primary

  Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods · CPC title

• Y02P90/80

  Management or planning · CPC title

• G05B23/024 Primary

  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

• Y02P90/02

  Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS] · CPC title