Elevator sensor system calibration

Patent metadata

Field	Value
Publication number	US-10829344-B2
Application number	US-201715642465-A
Country	US
Kind code	B2
Filing date	Jul 6, 2017
Priority date	Jul 6, 2017
Publication date	Nov 10, 2020
Grant date	Nov 10, 2020

Abstract

According to an aspect, a method of elevator sensor system calibration includes collecting, by a computing system, a plurality of data from one or more sensors of an elevator sensor system while a calibration device applies a known excitation. The computing system compares an actual response to an expected response to the known excitation using a trained model. The computing system performs analytics model calibration to calibrate the trained model based on one or more response changes between the actual response and the expected response.

First claim

What is claimed is:

1. A method comprising:
collecting, by a computing system, a plurality of data from one or more sensors of an elevator sensor system while a calibration device applies a known excitation, wherein the known excitation comprises a predetermined sequence of one or more vibration frequencies applied at one or more predetermined amplitudes;
comparing, by the computing system, an actual response to an expected response to the known excitation using a trained model; and
performing, by the computing system, analytics model calibration to calibrate the trained model based on one or more response changes between the actual response and the expected response.

2. The method of claim 1 , wherein the trained model is trained by applying the known excitation to a different instance of the elevator sensor system to produce the expected response.

3. The method of claim 1 , wherein performing analytics model calibration comprises applying transfer learning to determine a transfer function based on the one or more response changes across a range of data points produced by the known excitation.

4. The method of claim 3 , wherein a baseline designation of the trained model is shifted according to the transfer function.

5. The method of claim 3 , wherein transfer learning shifts at least one fault detection boundary of the trained model.

6. The method of claim 3 , wherein transfer learning shifts at least one trained regression model.

7. The method of claim 6 , wherein transfer learning shifts at least one trained fault detection model, and a fault designation comprises one or more of: a roller fault, a track fault, a sill fault, a door lock fault, a belt tension fault, a car door fault, and a hall door fault.

8. The method of claim 1 , wherein one or more variations of the known excitation applied by the calibration device at one or more predetermined locations on an elevator system are collected.

9. The method of claim 1 , wherein the data is collected at two or more different landings of an elevator system.

10. An elevator sensor system comprising:
one or more sensors operable to monitor an elevator system; and
a computing system comprising a memory and a processor that collects a plurality of data from the one or more sensors while a calibration device applies a known excitation, compares an actual response to an expected response to the known excitation using a trained model, and performs analytics model calibration to calibrate the trained model based on one or more response changes between the actual response and the expected response, wherein the known excitation comprises a predetermined sequence of one or more vibration frequencies applied at one or more predetermined amplitudes.

11. The elevator sensor system of claim 10 , wherein the trained model is trained by applying the known excitation to a different instance of the elevator sensor system to produce the expected response.

12. The elevator sensor system of claim 11 , wherein performance of analytics model calibration comprises applying transfer learning to determine a transfer function based on the one or more response changes across a range of data points produced by the known excitation.

13. The elevator sensor system of claim 12 , wherein a baseline designation of the trained model is shifted according to the transfer function.

14. The elevator sensor system of claim 12 , wherein transfer learning shifts at least one fault detection boundary of the trained model.

15. The elevator sensor system of claim 12 , wherein transfer learning shifts at least one trained regression model.

16. The elevator sensor system of claim 15 , wherein transfer learning shifts at least one trained fault detection model, and a fault designation comprises one or more of: a roller fault, a track fault, a sill fault, a door lock fault, a belt tension fault, a car door fault, and a hall door fault.

17. The elevator sensor system of claim 10 , wherein one or more variations of the known excitation applied by the calibration device at one or more predetermined locations on an elevator system are collected.

18. The elevator sensor system of claim 10 , wherein the data is collected at two or more different landings.

Assignees

• Otis Elevator Co

Inventors

• Koushik Sudarshan N
• Braunwart Paul R
• Sarkar Soumalya
• Lovett Teems E
• Ekladious George S

Classifications

• B66B5/0037 Primary

  Performance analysers · CPC title

• B66B13/146

  method or algorithm for controlling doors · CPC title

• B66B5/0018 Primary

  Devices monitoring the operating condition of the elevator system · CPC title

• B66B1/3407 Primary

  Setting or modification of parameters of the control system · CPC title

• B66B5/0025 Primary

  for maintenance or repair · CPC title