Title:
FAULT PREDICTION METHOD BASED ON VEHICLE HISTORICAL DATA, SYSTEM AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2024/078339
Kind Code:
A1
Abstract:
The present application relates to vehicle fault prediction, and specifically relates to a fault prediction method based on vehicle historical data, a computer system used for vehicle fault prediction, and a computer storage medium. The method comprises: A, extracting multiple sample data sets from vehicle historical data, on the basis of different sample selection strategies; B, performing invalid feature rejection and availability screening for each of the multiple sample data sets; and C, training a combined model using each of the multiple sample data sets, and acquiring a fault prediction result on the basis of the trained combined model. The fault prediction scheme provided by the present application combines a combined perspective and the combined model, so that the accuracy of fault prediction is improved while the data mining accuracy and comprehensiveness are improved.
More Like This:
Inventors:
GONG XIN (CN)
WEI HAO (CN)
WEI HAO (CN)
Application Number:
PCT/CN2023/122028
Publication Date:
April 18, 2024
Filing Date:
September 27, 2023
Export Citation:
Assignee:
XPT EDS HEFEI CO LTD (CN)
International Classes:
G06F18/214; G06F18/2431; G06Q10/20
Foreign References:
CN115563503A | 2023-01-03 | |||
CN114742316A | 2022-07-12 | |||
CN113096405A | 2021-07-09 | |||
US20220084335A1 | 2022-03-17 |
Attorney, Agent or Firm:
CHINA PATENT AGENT (H.K.) LTD. (CN)
Download PDF: