Monitoring apparatus, method, and program

Patent metadata

Field	Value
Publication number	US-11892829-B2
Application number	US-202217680374-A
Country	US
Kind code	B2
Filing date	Feb 25, 2022
Priority date	Sep 15, 2021
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

According to one embodiment, a monitoring apparatus includes a processing circuit. The processing circuit is configured to generate second data including a prediction value of a second sensor correlated with a first sensor from first data including a measurement value of the first sensor of which a measurement value changes suddenly in a case where the control signal changes, detect an anomaly of the system or an anomaly of at least one sensor, and make it difficult to detect the anomaly in a case where the determination signal indicates that there is a change in the control signal.

First claim

What is claimed is:

1. A monitoring apparatus comprising:
a processing circuit,
wherein the processing circuit is configured to
acquire measurement values of sensors installed in a system,
acquire a control signal from the system,
acquire a model that generates second data including a prediction value of each of sensors belonging to a second sensor set including, as an element, a second sensor correlated with a first sensor when first data is input, the first data including a measurement value of each of sensors belonging to a first sensor set including, as an element, the first sensor of which a measurement value changes suddenly in a case where the control signal changes during a predetermined operation mode,
generate a determination signal by determining a change in the control signal,
generate the second data including a prediction value of each of the sensors belonging to the second sensor set from the first data included in the measurement value and the model, and
detect an anomaly of the system or an anomaly of at least one sensor belonging to the second sensor set based on a measurement value of each of the sensors belonging to the second sensor set, the second data, the determination signal, and a threshold, and
wherein the processing circuit is configured to restrict detection of the anomaly in a case where the determination signal indicates that there is a change in the control signal.

2. The monitoring apparatus according to claim 1 , wherein the control signal includes any one of a feedback control signal, a feedforward control signal, and a control signal with low correlation with a change in the operation mode and with an irregular change.

3. The monitoring apparatus according to claim 1 , wherein the control signal includes, any one of a boiler input regulator (BIR) signal, a soot blower signal, a signal related to start and stop of a fuel apparatus, a signal indicating a number of starting fuel apparatuses, and a signal indicating switching of a fuel type.

4. The monitoring apparatus according to claim 1 , wherein the processing circuit is configured to restrict detection of the anomaly by executing control so as not to detect the anomaly in a case where the determination signal indicates that there is a change in the control signal.

5. The monitoring apparatus according to claim 1 , wherein the processing circuit is configured to change the threshold depending on the determination signal.

6. The monitoring apparatus according to claim 1 ,
wherein the processing circuit is configured to
temporarily detect an excess of the threshold related to the system or at least one sensor belonging to the second sensor set based on a measurement value of each of sensors belonging to the second sensor set, the second data, and the threshold,
acquire a duration of the excess of the threshold, and
restrict detection of the anomaly as compared with a case where the determination signal indicates no change in the control signal, in a case where the duration is shorter than a predetermined time and the determination signal indicates a change in the control signal.

7. The monitoring apparatus according to claim 1 ,
wherein the processing circuit is configured to
calculate a degree of anomaly in the system based on a measurement value of each of sensors belonging to the second sensor set and the second data, and
detect an anomaly in the system based on the degree of anomaly and the threshold.

8. The monitoring apparatus according to claim 1 ,
wherein processing circuit is configured to
calculate a difference between a measurement value and a prediction value of a sensor belonging to the second sensor set, and
detect an anomaly of the sensor belonging to the second sensor set based on the difference and the threshold.

9. The monitoring apparatus according to claim 1 ,
wherein the processing circuit is configured to restrict detection of the anomaly only in a sensor belonging to a third sensor set including only the first sensor and the second sensor among sensors belonging to the second sensor set in a case where the determination signal indicates that there is a change in the control signal.

10. The monitoring apparatus according to claim 1 , wherein the processing circuit is configured to display, on a display, a first graph representing a time-series change in the measurement value, the prediction value, or a difference between the measurement value and the prediction value and a second graph representing a time-series change in the control signal or the determination signal, side by side or in an overlapping manner with scales of time axes aligned.

11. The monitoring apparatus according to claim 7 , wherein the processing circuit is configured to display, on a display, a second graph representing a time-series change in the control signal or the determination signal and a third graph representing a time-series change in a degree of anomaly in the system, side by side or in an overlapping manner with scales of time axes aligned.

12. The monitoring apparatus according to claim 1 , wherein the processing circuit is configured to set a time for determining a change in the control signal depending on a type of the control signal, a type of the first sensor, a type of the second sensor, or a type of the system.

13. The monitoring apparatus according to claim 6 , wherein the processing circuit is configured to set the predetermined time depending on a type of the control signal, a type of the first sensor, a type of the second sensor, or a type of the system.

14. A method comprising:
acquiring measurement values of sensors installed in a system;
acquiring a control signal from the system;
acquiring a model that generates second data including a prediction value of each of sensors belonging to a second sensor set including, as an element, a second sensor correlated with a first sensor when first data is input, the first data including a measurement value of each of sensors belonging to a first sensor set including, as an element, the first sensor of which a measurement value changes suddenly in a case where the control signal changes during a predetermined operation mode;
generating a determination signal by determining a change in the control signal;
generating the second data including a prediction value of each of the sensors belonging to the second sensor set from the first data included in the measurement value and the model;
detecting an anomaly of the system or an anomaly of at least one sensor belonging to the second sensor set based on a measurement value of each of the sensors belonging to the second sensor set, the second data, the determination signal, and a threshold; and
restricting detection of the anomaly in a case where the determination signal indicates that there is a change in the control signal.

15. A non-transitory computer-readable storage medium storing a program for causing a computer to execute:
a function of acquiring measurement values of sensors installed in a system;
a function of acquiring a control signal from the system;
a function of acquiring a model that generates second data including a prediction value of each of sensors belonging to a second sensor set including, as an element, a second sensor correlated with a first sensor when first data is input, the first data including a measurement value of each of sensors belonging to a first sensor set including, as an element, the first sensor of which a measurement value changes suddenly in a case where the control signal changes during a predetermined operation mode;
a function of generating a determination s

Assignees

• Toshiba Kk
• Toshiba Energy Systems & Solutions Corp
• Toshiba Energy Systems & Soultions Corp

Inventors

• Taguchi Yasunori
• Nakata Kouta
• Naito Susumu
• Kato Yuichi
• Ookuma Eiichi
• Aoki Toshio
• Miyamoto Chikashi

Classifications

• G05B23/0254 Primary

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

• G05B23/0208

  characterized by the configuration of the monitoring system · CPC title

• G05B23/0235 Primary

  based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold · CPC title

• G05B23/0245

  based on a qualitative model, e.g. rule based; if-then decisions · CPC title