Title:
FAULT PREDICTION METHOD AND APPARATUS, MODEL DEPLOYMENT METHOD AND APPARATUS, ELECTRONIC DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2022/056869
Kind Code:
A1
Abstract:
Embodiments of the present invention provide a fault prediction method, being applied to the edge collection end of a switch machine monitoring system. The fault prediction method comprises: deploying a fault type prediction model that is obtained from the service end of the switch machine monitoring system, wherein the fault type prediction module performs training on the basis of training samples, and the training samples comprise the current data of a switch machine collected by the edge collection edge, and a fault type classification tag corresponding to the switch machine; and according to the fault type prediction model, performing edge computing on the collected current data of the switch machine so as to obtain the fault type prediction data of the switch machine. The embodiments of the present invention improve fault prediction efficiency by using the fault type prediction model, and avoid the heavy workload of manually detecting a fault of the switch machine.
More Like This:
| WO/2023/144768 | APPARATUS AND METHOD FOR MONITORING A SWITCH OF A RAILWAY, SUBWAY OR TRAMWAY NETWORK |
| JP3409846 | SWITCH |
Inventors:
ZHU JIAXING (CN)
BOVENSIEPEN DANIEL (CN)
GAN SHANSHAN (CN)
WU WEIQING (CN)
WANG PEIPEI (CN)
WU TENGFEI (CN)
BOVENSIEPEN DANIEL (CN)
GAN SHANSHAN (CN)
WU WEIQING (CN)
WANG PEIPEI (CN)
WU TENGFEI (CN)
Application Number:
PCT/CN2020/116305
Publication Date:
March 24, 2022
Filing Date:
September 18, 2020
Export Citation:
Assignee:
SIEMENS MOBILITY GMBH (DE)
SIEMENS LTD CHINA (CN)
SIEMENS LTD CHINA (CN)
International Classes:
B61L5/06
Domestic Patent References:
| WO2020021282A1 | 2020-01-30 |
Foreign References:
| CN109501834A | 2019-03-22 | |||
| CN110719210A | 2020-01-21 | |||
| CN110749462A | 2020-02-04 | |||
| EP3644581A1 | 2020-04-29 | |||
| CN101893667A | 2010-11-24 |
Attorney, Agent or Firm:
KANGXIN PARTNERS, P.C. (CN)
Download PDF: