Evaluation of installation quality of elevator
A machine learning model trained with simulated data effectively addresses the inadequacies in existing elevator quality evaluation methods, offering a reliable and accurate assessment of elevator equipment.
Patent Information
- Authority / Receiving Office
- HK · HK
- Patent Type
- Applications
- Current Assignee / Owner
- KONE OYJ
- Filing Date
- 2026-04-17
- Publication Date
- 2026-07-10
AI Technical Summary
Existing methods for evaluating the quality of elevator equipment are inadequate, lacking comprehensive and efficient assessment tools.
A method utilizing a machine learning model trained with simulated data to evaluate the quality of elevator equipment, involving data reception, input into the model, and setting detection results based on the model output.
Provides a comprehensive and efficient evaluation of elevator equipment quality, enhancing assessment accuracy and reliability.
Smart Images
Figure 00000000_0000_ABST
Abstract
Description
(19) State Intellectual Property Office (12) Invention Patent Application (10) Application Publication Number (43) Application Publication Date (21) Application Number 202380097844.X (22) Application Date 2023.05.12 (85) PCT International Application Entering National Phase Date 2025.11.04 (86) PCT International Application Application Data PCT / FI2023 / 050263 2023.05.12 (87) PCT International Application Publication Data WO2024 / 236216 EN 2024.11.21 (71) Applicant KONE AG Address Helsinki, Finland (72) Inventors G. Royvainen P. Quesma M. Lin (74) Patent Agency Beijing Liu Shen Law Firm 11105 Patent Attorney Xue Yunran (51) Int.Cl. B66B 5 / 00 (2006.01) (54) Title of Invention: Evaluation of Installation Quality of Elevator (57) Abstract: A method for generating data describing the quality of elevator equipment is provided, the method being performed by an apparatus (170) configured to execute a machine learning model trained with simulated data, the method comprising: receiving (210) data describing the operation of at least one entity of an installed elevator; inputting (220) the received data into the machine learning model run by the apparatus (170); and setting (230) a detection result based on the output from the machine learning model to express one of the following: (i) the quality of the elevator equipment is acceptable (230A), (ii) the quality of the elevator equipment is unacceptable (230B). An apparatus (170) and a computer program are also provided. Claims 2 pages Description 7 pages Drawings 2 pages CN 121127431 A 2025.12.12 CN 1 21 12 74 31 A
Claims
1. A method for generating data describing the quality of elevator equipment, the method being performed by an apparatus (170) configured to execute a machine learning model trained using simulation data from a simulation model corresponding to an installed elevator, the method comprising: Receive (210) data describing the operation of at least one entity of the installed elevator, said data being generated using a testing process of said at least one entity of the installed elevator. The received data is input (220) into a machine learning model executed by the device (170). Based on the output from the machine learning model, the detection result is set to indicate one of the following: (i) the quality of the elevator equipment is acceptable (230A), (ii) the quality of the elevator equipment is unacceptable (230B).
2. The method of claim 1, wherein data describing the operation of the at least one entity of the installed elevator is received from at least one of: an elevator door actuator, an accelerometer associated with the elevator car, a magnetometer associated with the elevator car, a microphone, an image sensor, and a depth sensor.
3. The method according to any one of the preceding claims, further comprising: In response to the detection result being set to indicate that the quality of the elevator equipment is unacceptable, a signal is generated to a terminal device communicatively connected to the device (170), the generated signal carrying data indicating the detection result being set to indicate that the quality of the elevator equipment is unacceptable.
4. The method according to claim 3, wherein, The data carried in the generated signal also defines at least one entity that causes the quality of the elevator equipment to be unacceptable.
5. The method according to claim 4, wherein, The data carried in the generated signal also defines one or more instructions to overcome situations indicating that the quality of the elevator equipment is unacceptable.
6. The method according to any one of the preceding claims, further comprising: In response to the test results being set to indicate that the quality of the elevator equipment is acceptable, a quality report is generated for a predefined entity, the quality report including data indicating that the test results are set to indicate that the quality of the elevator equipment is acceptable.
7. An apparatus (170) for generating data describing the quality of elevator equipment, the apparatus (170) being configured to execute a machine learning model trained using simulation data from a simulation model corresponding to an installed elevator for evaluating the quality of the elevator equipment, the apparatus (170) further being configured to: Receive (210) data describing the operation of at least one entity of the installed elevator, said data being generated using a testing process of said at least one entity of the installed elevator. The received data is input (220) into a machine learning model executed by the device (170). Based on the output from the machine learning model, the detection result is set to indicate one of the following: (i) the quality of the elevator equipment is acceptable (230A), (ii) the quality of the elevator equipment is unacceptable (230B).
8. The apparatus (170) according to claim 7, wherein, The device (170) is configured to receive data describing the operation of at least one entity of the installed elevator from at least one of the following: an elevator door actuator, an accelerometer associated with the elevator car, a magnetometer associated with the elevator car, a microphone, an image sensor, and a depth sensor.
9. The apparatus (170) according to claim 7 or claim 8, wherein the apparatus (170) is further configured to: In response to the detection result being set to indicate that the quality of the elevator equipment is unacceptable, a signal is generated to a terminal device communicatively connected to the device (170), the generated signal carrying data indicating the detection result being set to indicate that the quality of the elevator equipment is unacceptable.
10. The apparatus (170) according to claim 9, wherein, The data carried in the generated signal also defines at least one entity that causes the quality of the elevator equipment to be unacceptable.
11. The apparatus (170) according to claim 10, wherein, The data carried in the generated signal also defines one or more instructions to overcome situations indicating that the quality of the elevator equipment is unacceptable.
12. The apparatus (170) according to any one of claims 7 to 11, wherein the apparatus (170) is further configured to: In response to the test results being set to indicate that the quality of the elevator equipment is acceptable, a quality report is generated for a predefined entity, the quality report including data indicating that the test results are set to indicate that the quality of the elevator equipment is acceptable.
13. A computer program comprising instructions for causing the apparatus (170) according to claim 7 to perform the steps of the method according to any one of claims 1 to 6.