Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
FAULT DIAGNOSIS METHOD AND SYSTEM BASED ON QUALITATIVE TREND ANALYSIS AND FIVE-STATE BAYESIAN NETWORK, AND DEVICE AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/071220
Kind Code:
A1
Abstract:
A fault diagnosis method based on qualitative trend analysis and a five-state Bayesian network. The method comprises: sorting multi-variable time sequence data into multi-variable time window data; searching for an optimal segmentation point by means of the multi-variable time window data, so as to acquire two linear segments, and describing the linear segments by using five trend states; constructing a variable causal relationship network, constructing a five-state Bayesian network according to the variable causal relationship network, and calculating conditional probability information between node states in the five-state Bayesian network; and diagnosing an actual trend state of variables by using the conditional probability information, and acquiring a fault generation reason and a fault propagation route.

Inventors:
WU HAO (CN)
REN XIN (CN)
WU QING (CN)
ZHU JINTAO (CN)
LV LIANG (CN)
ZHU JUNJIE (CN)
Application Number:
PCT/CN2022/098676
Publication Date:
May 04, 2023
Filing Date:
June 14, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUANENG CLEAN ENERGY RES INST (CN)
International Classes:
G06K9/62
Foreign References:
CN113988173A2022-01-28
CN111255674A2020-06-09
US6076083A2000-06-13
Other References:
"Doctoral Dissertation", 1 June 2018, NORTH CHINA ELECTRIC POWER UNIVERSITY (BEIJING), CN, article CHEN, DONGCHAO: "Fault Diagnosis Method and Application Research of Turbogenerator Based on Bayesian Network", pages: 1 - 155, XP009545246
"Master's Thesis", 23 March 2018, UNIVERSITY OF ELECTRONIC SCIENCE AND TECHNOLOGY, CN, article LYU, YUHONG: "Research and Application of Time Series Anomaly Detection Algorithm", pages: 1 - 65, XP009545244
LU NINGYUN, HE KELEI, JIANG BIN, LÜ JIANHUA: "A fault prognosis method using Bayesian network", JOURNAL OF SOUTHEAST UNIVERSITY (NATURAL SCIENCE EDITION ), DONGNAN DAXUE, NANJING, CN, vol. 42, no. S1, 30 September 2012 (2012-09-30), CN , pages 87 - 91, XP009545766, ISSN: 1001-0505, DOI: 10.3969/j.issn.1001-0505.2012.S1.019
Attorney, Agent or Firm:
TSINGYIHUA INTELLECTUAL PROPERTY LLC (CN)
Download PDF: