Search

EP-4431890-B1 - METHOD AND SYSTEM FOR RECALIBRATING PLURALITY OF SENSORS IN TECHNICAL INSTALLATION

EP4431890B1EP 4431890 B1EP4431890 B1EP 4431890B1EP-4431890-B1

Inventors

  • GANAPATHY, Karthik
  • KANNAPPAN, Sathishkumar
  • S, Gobikumar
  • V, Yugesh Kumar

Dates

Publication Date
20260513
Application Date
20230315

Claims (14)

  1. A method of recalibrating a plurality of sensors (108A-N) in a technical installation (106), the method comprising: receiving, by a processing unit (202), a first image of a sensor (108N) of a plurality of sensors (108A-N) in a technical installation (106) and a second image of a standard measurement device (124) attached to the sensor (108N); determining, by the processing unit (202), a first reading associated with the sensor (108N) and a second reading associated with the standard measurement device (124) based on an analysis of the first image and the second image; determining, by the processing unit (202), that the sensor (108N) is in an uncalibrated state by application of an artificial intelligence model on the first reading and the second reading, wherein the artificial intelligence model is configured to determine the uncalibrated state in the sensor; and outputting, by the processing unit (202), a notification to a user based on a determination that the sensor is in the uncalibrated state.
  2. The method according to claim 1, wherein determining whether the sensor is in the uncalibrated state comprises: receiving, by the processing unit (202), a plurality of calibration data items associated with each sensor of the plurality of sensors (108A-N) in the technical installation (106), wherein the plurality of calibration data items comprises information associated with each calibration cycle of a plurality of calibration cycles of the plurality of sensors (108A-N), and the information associated with each calibration cycle of the plurality of calibration cycles comprises a plurality of historical sensor readings, a plurality of historical standard measurement device readings, and a plurality of recorded calibration error of each sensor of the plurality of sensors (108A-N) during each calibration cycle of the plurality of calibration cycles; training, by the processing unit (202), the artificial intelligence model to determine a calibration error of each sensor of the plurality of sensors (108A-N) in the technical installation (106) based on the received plurality of calibration data items; and determining, by the processing unit (202), that the sensor (108N) is in the uncalibrated state by the application of the trained artificial intelligence model on the first reading and the second reading.
  3. The method according to claim 2, wherein the plurality of calibration data items further comprises information associated with an accepted margin of calibration error for each sensor of the plurality of sensors (108A-N), and wherein the plurality of calibration data items further comprises a plurality of feedback signals which used to calibrate each sensor of the plurality of sensors (108A-N) during each calibration cycle of the plurality of calibration cycles.
  4. The method according to claim 3, wherein the method further comprises: determining, by the processing unit (202), a first deviation between a historical sensor reading of the sensor and a historical standard measurement device reading from the plurality of calibration data items; determining, by the processing unit (202), a second deviation between the first reading of the sensor (108N) and the second reading of the standard measurement device (124); determining, by the processing unit (202), whether the first deviation is greater than the second deviation; and predicting, by the processing unit (202), an optimal calibration date for the sensor (108N) based on an application of the trained artificial intelligence model on the first deviation and the second deviation, wherein the optimal calibration date is a future calibration date for each sensor of the plurality of sensors determined by the trained artificial intelligence model based on a past calibration date of the sensor and a determination that the sensor is in the uncalibrated state.
  5. The method according to any of claims 1 to 4, wherein the method further comprises: determining, by the processing unit (202), a rate of degradation of a number of readings of the sensor (108N) based on an analysis of the plurality of calibration data items; determining, by the processing unit (202), whether the determine rate of degradation is greater than a threshold; and notifying, by the processing unit (202), a user to perform predictive maintenance on the sensor (108N) based on the determination that the rate of degradation is greater than the threshold.
  6. The method according to any of claims 1 to 4, wherein the method further comprises: training, by the processing unit (202), the artificial intelligence model to generate a feedback signal to recalibrate the sensor (108N) based on an analysis of the plurality of feedback signals in the plurality of calibration data items; generating, by the processing unit (202), the feedback signal to recalibrate the sensor (108N) based on the determination that the sensor (108N) is in the uncalibrated state; and transmitting, by the processing unit (202), the generated feedback signal to the sensor (108N) to recalibrate the sensor (108N).
  7. The method according to any of claims 1 to 6, wherein determining, by the processing unit (202), the first reading associated with the sensor (108N) of the plurality of sensors (108A-N) and the second reading associated with the standard measurement device (124) comprises: receiving, by the processing unit (202), the first image of the sensor (108N) of the plurality of sensors (108A-N), and the second image of the standard measurement device (124) from an image capture device; applying, by the processing unit (202), an image processing algorithm on the first image and the second image; and determining, by the processing unit (202), the first reading and the second reading based on the application of an image processing algorithm on the first image and the second image.
  8. The method according to any of claims 1 to 7, further comprising: determining, by the processing unit (202), a degree of abnormality of the first reading of the sensor by application of the artificial intelligence model on the first reading and the second reading; determining, by the processing unit (202), whether the degree of abnormality of the first reading is greater than a threshold; and initiating, by the processing unit (202), a process interlock process on an industrial process associated with the sensor based on the determination that the first reading is greater than the threshold.
  9. The method according to any of claims 1 to 7, further comprising: receiving, by the processing unit (202), a first location of the sensor in the technical installation (106); receiving, by the processing unit (202), a second location of the user in the technical installation (106); mapping, by the processing unit (202), the first location and the second location on a map of the technical installation (106) ; generating, by the processing unit (202), a navigational path between the first location and the second location; and displaying, by the processing unit (202), the generated navigational path and the map of the technical installation (106), via a display device.
  10. The method according to any of claims 1 to 8, further comprising: receiving, by the processing unit (202), an image from an augmented reality headset (126); determining, by the processing unit (202), the sensor (108N) in the image based on an application of an object detection algorithm on the received image; and displaying, by the processing unit (202), a notification that the sensor (108N) is in the uncalibrated state based on the determination that the sensor is in the uncalibrated state.
  11. The method according to claim 2, further comprising: validating, by the processing unit (202), one of the received calibration data items by application of the artificial intelligence algorithm on said received calibration data item.
  12. An industrial control system (102) for recalibrating a plurality of sensors in a technical installation, wherein the industrial control system (102) comprises: a processing unit (202); and a memory (204) coupled to the processing unit (202), wherein the memory comprises a sensor recalibration module (112) stored in the form of machine-readable instructions executable by the one or more processor(s), wherein the sensor recalibration module (112) is capable of performing a method according to any of the claims 1-11.
  13. An industrial environment (100) comprising: an industrial control system (102) as claimed in claim 12; a technical installation (106) comprising one or more physical components; and a plurality of human machine interfaces (120A-N) communicatively coupled to the industrial control system (102) via a network (104).
  14. A computer-program product, having machine-readable instructions stored therein, that when executed by a processing unit (202), cause the processors to perform a method according to any of the claims 1-11.

Description

The present invention relates to a field of sensor recalibration, and more particularly relates to a method and system for recalibrating a plurality of sensors in a technical installation. A technical installation such as an industrial plant comprises a plurality of sensors which capture a plurality of readings from one or more portions of the technical installation. The plurality of readings are received by a controller device to determine an operational status of the technical installation. Examples of the plurality of sensors include, but is not limited to a temperature sensor, a pressure sensor, and a vibration sensor. Each sensor of the plurality of sensors is configured to capture a first reading associated with a specific parameter of one or more processes of a plurality of processes running in the technical installation. Each sensor of the plurality of sensors degrade in performance over time. In one example, a sensor of the plurality of sensors becomes uncalibrated over time. Thus, the plurality of sensors have to be regularly recalibrated to a specific industrial standard. Conventionally, an engineer manually compares a reading of a sensor with a reading of a standard measurement device to determine a calibration error of the sensor. The engineer further compares the determined calibration error with an accepted margin of calibration error of the sensor. The accepted margin of calibration error of a sensor depends on a criticality of the plurality of processes of which the sensor measures readings. For example, a first sensor associated with a critical process has an accepted margin of calibration error which is lower than an accepted margin of calibration error of a second sensor associated with a non-critical process. The engineer requires a high degree of expertise in order to determine the accepted margin of error for each sensor of the plurality of sensors. If the sensor is recalibrated when a calibration error of the sensor is lesser than the accepted margin of calibration error of the sensor, a wastage of time, money and labor occurs. Thus, the sensor should be calibrated only when the calibration error is greater than the accepted margin of calibration error of the sensor. The technical installation comprises thousands of such sensors which have to be recalibrated. Thus, manual recalibration of the plurality of sensors is a humongous task because of a sheer number of sensors in the technical installation. Thus, recalibration of the plurality of sensors requires a large amount of labor, time, and expertise. CN 111 504 513 A discloses a calibration method for a digital display thermometer based on an intelligent mobile terminal. JP H06 82267 A discloses a sensor for measuring a variety of physical variables and having a function of particular correcting the temperature drift. KR 2020 0109508 A discloses a sensor module capable of automatically correcting a sensing value. In light of the above, there exists a need for an efficient and cost-effective method and system for recalibration of a plurality of sensors in a technical installation. Therefore, it is an object of the present invention to provide a method and system for recalibration of a plurality of sensors in a technical installation. The object of the invention is achieved by a method for recalibration of a plurality of sensors in a technical installation having the features of claim 1 and a system having the features of claim 12. The technical installation is at least one of a manufacturing plant, a power plant or a waste processing plant. The technical installation has a plurality of devices which are configured to perform a specific functionality such as manufacturing products and generating energy. The technical installation further comprises a plurality of sensors which are configured to capture a plurality of readings from a plurality of processes in the technical installation. The captured plurality of readings are transmitted to a controller device to determine an operational status of the technical installation. Examples of the plurality of sensors include, but is not limited to a temperature sensor, a pressure sensor, and a vibration sensor. For example, each sensor of the plurality of sensors is configured to capture a first reading associated with a specific parameter of a specific portion of the technical installation. In one example, the specific parameter is a temperature parameter. Furthermore, the specific portion of the technical installation is at least one of a pipe, a container, or a furnace in the technical installation. Each sensor of the plurality of sensors degrade in performance over time. In one example, a sensor of the plurality of sensors become uncalibrated over time. To calibrate each sensor of the plurality of sensors, a user attaches a standard measurement device to each sensor of the plurality of sensors and capture a second reading associated with the specific parameter, from the specific portion. Th