Granted Patent B2

US 12,247,886 · App. 16/976,194 · Granted Mar 11, 2025

Inventors: Sasu Tarkoma (Helsingin Yliopisto, FI); Tuukka Petäjä (Helsingin Yliopisto, FI); Markku Kulmala (Helsingin Yliopisto, FI); Joni Kujansuu (Helsingin Yliopisto, FI)

Assignee: University of Helsinki

G01K15/005G08C23/00

Abstract

Claims (74)

1. A method comprising calibrating a first sensor in a changing operating environment in a calibration process that comprises:

receiving sensor data from the first sensor;

receiving sensor values from a known calibrating sensor;

obtaining a localized sensor map and profile for the first sensor:

maintaining a sensor specific model for the first sensor using the localized sensor map and profile;

detecting calibration needs by estimating a drift and error of the sensor data, taking into account a difference between the sensor data from the first sensor and the sensor values from the calibrating sensor; and

estimating a correction factor or a correction model to the sensor data using said difference and the sensor specific model; and

using the estimated correction factor or correction model for calibrating the first sensor;

wherein the calibrating sensor is a virtual sensor based on a model of sensor data provided by one or more calibrated sensors,

wherein the calibrating sensor is ranked higher than the first sensor in a hierarchical model,

wherein the first sensor, the calibrating sensor and additional sensors form groups of sensors communicating with each other via a sensor network, and

wherein calibration is performed inside a node of the sensor network and between nodes of the sensor network to provide for improving accurate sensing capabilities.

2. The method of claim 1 , wherein the calibrating sensor ranked higher in the hierarchical model is used to perform the calibrating of the first sensor.

3. The method of claim 1 , wherein:

the first sensor is configured for measuring one or more properties of a chosen system; and

a spatial model of the one or more properties is used to perform a derived calibration of the first sensor using measurements performed apart from the first sensor and subject to different conditions,

wherein the one or more properties comprise multiple air quality parameters, and

wherein the spatial model includes additional data from a regional air quality model.

4. The method of claim 1 , wherein the groups of sensors include stationary sensors and mobile sensors configured to transfer sensor data to the stationary sensor.

5. The method of claim 1 , wherein the detecting calibration needs further takes into account the sensor specific model.

6. The method of claim 1 , wherein the detecting calibration needs further takes into account an operational environment of the first sensor.

7. The method of claim 1 , wherein the detecting calibration needs further takes into account a sensor profile of the first sensor.

8. The method of claim 1 , wherein the detecting calibration needs further takes into account a sensor specific drift profile of the first sensor.

9. The method of claim 1 , wherein the detecting calibration needs further takes into account a sensor specific error profile of the first sensor.

10. The method of claim 1 , wherein the calibrating sensor is controlled by a remote controller.

11. An apparatus for calibrating a first sensor in a changing operating environment, the apparatus comprising:

means for receiving sensor data from the first sensor;

means for receiving sensor values from a known calibrating sensor;

means for obtaining a localized sensor map and profile for the first sensor:

means for maintaining a sensor specific model for the first sensor using the localized sensor map;

means for detecting calibration needs by estimating a drift and error of the sensor data, taking into account a difference between the sensor data from the first sensor and the sensor values from the calibrating sensor; and

means for calibrating the sensor by estimating a correction factor or a correction model to the sensor data using said difference and the sensor specific model;

wherein the calibrating sensor is a virtual sensor based on a model of sensor data provided by one or more calibrated sensors, and

wherein the calibrating sensor is ranked higher than the first sensor in a hierarchical model,

wherein the first sensor, the calibrating sensor and additional sensors form groups of sensors communicating with each other via a sensor network, and

wherein calibration is performed inside a node of the sensor network and between nodes of the sensor network to provide for improving accurate sensing capabilities.

12. The method of claim 1 , wherein the calibrating sensor is further based on knowledge of the operating environment and modelled behavior of the one or more calibrated sensors.

13. A method comprising calibrating a first sensor in a changing operating environment in a calibration process that comprises:

receiving sensor data from the first sensor;

receiving sensor values from a known calibrating sensor;

obtaining a localized sensor map and profile for the first sensor:

maintaining a sensor specific model for the first sensor using the localized sensor map and profile;

detecting calibration needs by estimating a drift and error of the sensor data, taking into account a difference between the sensor data from the first sensor and the sensor values from the calibrating sensor; and

estimating a correction factor or a correction model to the sensor data using said difference and the sensor specific model; and

using the estimated correction factor or correction model for calibrating the first sensor;

wherein the calibrating sensor is a virtual sensor based on a model of sensor data provided by one or more calibrated sensors,

wherein the calibrating sensor is ranked higher than the first sensor in a hierarchical model, and

wherein the calibrating sensor is controlled by a remote controller.

14. The method of claim 13 , wherein the calibrating sensor ranked higher in the hierarchical model is used to perform the calibrating of the first sensor.

15. The method of claim 13 , wherein:

the first sensor is configured for measuring one or more properties of a chosen system; and

a spatial model of the one or more properties is used to perform a derived calibration of the first sensor using measurements performed apart from the first sensor and subject to different conditions, and

wherein the one or more properties comprise multiple air quality parameters, and

wherein the spatial model includes additional data from a regional air quality model.

16. The method of claim 13 , wherein the first sensor, the calibrating sensor and additional sensors form groups of sensors communicating with each other via a sensor network, and

wherein calibration is performed inside a node of the sensor network and between nodes of the sensor network to provide for improving accurate sensing capabilities.

17. An apparatus for calibrating a first sensor in a changing operating environment, the apparatus comprising:

means for receiving sensor data from the first sensor;

means for receiving sensor values from a known calibrating sensor;

means for obtaining a localized sensor map and profile for the first sensor:

means for maintaining a sensor specific model for the first sensor using the localized sensor map;

means for detecting calibration needs by estimating a drift and error of the sensor data, taking into account a difference between the sensor data from the first sensor and the sensor values from the calibrating sensor; and

means for calibrating the sensor by estimating a correction factor or a correction model to the sensor data using said difference and the sensor specific model;

wherein the calibrating sensor is a virtual sensor based on a model of sensor data provided by one or more calibrated sensors,

wherein the calibrating sensor is ranked higher than the first sensor in a hierarchical model, and

wherein the calibrating sensor is controlled by a remote controller.

18. The apparatus of claim 17 , wherein the calibrating sensor ranked higher in the hierarchical model is used to perform the calibrating of the first sensor.

19. The apparatus of claim 17 , wherein:

the first sensor is configured for measuring one or more properties of a chosen system; and

a spatial model of the one or more properties is used to perform a derived calibration of the first sensor using measurements performed apart from the first sensor and subject to different conditions,

wherein the one or more properties comprise multiple air quality parameters, and

wherein the spatial model includes additional data from a regional air quality model.

20. The apparatus of claim 17 , wherein the first sensor, the calibrating sensor and additional sensors form groups of sensors communicating with each other via a sensor network, and

wherein calibration is performed inside a node of the sensor network and between nodes of the sensor network to provide for improving accurate sensing capabilities.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (56)