Monitoring apparatus and method for monitoring a system

Patent metadata

Field	Value
Publication number	US-11340599-B2
Application number	US-201816629473-A
Country	US
Kind code	B2
Filing date	Jul 9, 2018
Priority date	Jul 10, 2017
Publication date	May 24, 2022
Grant date	May 24, 2022

Abstract

The monitoring of a technical system using sensor data. In the event of the failure of a sensor, in this case, for the failed sensor, virtual sensor data are created on the basis of the remaining functional sensors. In this case, the sensors for the calculation of the virtual sensor data are selected in two stages. In a first step, firstly, possible candidates of sensors are ascertained on the basis of a knowledge-based approach and the topology of the system. A second step involves calculating a mathematical relationship between the sensor data of a faulty sensor and the possible candidates of sensors for the calculation of the virtual sensor data. Those sensors which form a suitable basis for the calculation of the virtual sensor data can be identified in this way.

First claim

The invention claimed is:

1. A monitoring apparatus, comprising:
a receiving device designed to receive sensor data from a plurality of sensors; and
an evaluation device designed to detect a fault in a first sensor of the plurality of sensors, and to calculate virtual sensor data that replaces the sensor data of the faulty first sensor,
wherein the evaluation device, for the calculation of the virtual sensor data, ascertains a list of sensor candidates from the plurality of sensors, determines a respective similarity value for the sensor candidates and calculates the virtual sensor data for the faulty first sensor using the sensor data of the sensor having a highest similarity value.

2. The monitoring apparatus as claimed in claim 1 , wherein the evaluation device is designed to store the received sensor data from the plurality of sensors, and wherein the evaluation device calculates the similarity values using stored sensor data which were stored before a detection of a fault in the first sensor.

3. The monitoring apparatus as claimed in claim 1 , further comprising a database designed to provide information about the plurality of sensors, and wherein the evaluation device is designed to create the list for the sensor candidates using the information about the plurality of sensors that is provided in the database.

4. The monitoring apparatus as claimed in claim 1 , wherein the evaluation device is designed to ascertain the sensor candidates using spatial or functional relationships of the individual sensors.

5. The monitoring apparatus as claimed in claim 1 , wherein the evaluation device is designed to create a computation specification for calculating the virtual sensor data from the sensor data of the sensor having the highest similarity value.

6. The monitoring apparatus as claimed in claim 1 , wherein calculating the virtual sensor data comprises calculating an actual reliability value for the calculated virtual sensor data.

7. An apparatus for monitoring a system, comprising:
a plurality of sensors designed in each case to provide sensor data corresponding in each case to a detected measurement value;
a monitoring apparatus as claimed in claim 1 ; and
a control device designed to control the system using the received sensor data and the calculated virtual sensor data.

8. The monitoring apparatus as claimed in claim 1 , wherein the evaluation device is designed to ascertain the sensor candidates using functional relationships of the individual sensors.

9. A method for monitoring a system, comprising:
receiving sensor data from a plurality of sensors;
detecting a fault in a first sensor of the plurality of sensors;
ascertaining a list of sensor candidates from the plurality of sensors;
determining a similarity value for each sensor in the list of sensor candidates, and
calculating virtual sensor data that replace the sensor data of the first sensor, wherein the virtual sensor data are calculated using the sensor data of the sensor having the highest similarity value.

10. The method as claimed in claim 9 , wherein determining the similarity values comprises a calculation of a correlation between sensor data of the first sensor and sensor data of the sensor candidates.

11. The method as claimed in claim 9 , wherein ascertaining the list of sensor candidates is carried out before detecting a fault in the first sensor.

12. The method as claimed in claim 9 , wherein a quality value is assigned to each sensor in the list of sensor candidates, and wherein a reliability value is calculated for the virtual sensor data using the quality values.

13. The method as claimed in claim 9 , wherein the method furthermore comprises a step for storing the received sensor data of the plurality of sensors, and wherein determining the similarity value is carried out using the stored sensor data which were received before detecting a fault in the first sensor.

14. The method as claimed in claim 13 , wherein determining the similarity value is carried out using stored sensor data within a predetermined time window.

15. The method as claimed in claim 9 , further comprising ascertaining the list of sensor candidates using functional relationships of the individual sensors.

Assignees

• Siemens Ag

Inventors

• Hubauer Thomas
• Ringsquandl Martin

Classifications

• G05B23/0286

  Modifications to the monitored process, e.g. stopping operation or adapting control · CPC title

• G05B23/02

  Electric testing or monitoring · CPC title

• H04Q2209/10

  using a centralized architecture · CPC title

• G05B2219/37325

  Multisensor integration, fusion, redundant · CPC title

• G01D3/08

  with provision for safeguarding the apparatus, e.g. against abnormal operation, against breakdown · CPC title