Civil aviation engine gas path anomaly detection method based on piecewise fitting analysis and evaluation
An abnormality detection and engine technology, applied in complex mathematical operations, instruments, data processing applications, etc., can solve the problems of one-sidedness of the engine and the hysteresis of information feedback cannot meet the needs of early warning.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0092] The deviation value of gas path parameters of civil aviation engine belongs to the typical multidimensional time series data without label information, and there is a coupling effect between the parameters. In order to accurately mine the data pattern that characterizes the abnormal state of civil aviation engine, it is necessary to comprehensively consider the time correlation and spatial correlation of multidimensional time series. In order to improve the accuracy and stability of gas path abnormality detection.
[0093] The anomalous forms in time series can be defined as two types of anomalies, which are sequence form anomalies and point form anomalies. In the abnormal detection of engine gas path, the above two types of abnormalities can be called gas path evolution abnormality and gas path mutation abnormality respectively.
[0094] The gas path evolution abnormality refers to the abnormal mode in which the performance of the engine gas path components gradually d...
Embodiment 2
[0183] In the second embodiment, the detection method proposed in the first embodiment is verified through experiments. The data sets used in the experiment are shown in Table 1 in Example 1. They are all selected from 5 civil aviation engines whose model is CFM56-5B2 / 3 and have experienced abnormal modes. The abnormal modes are EGT indication abnormality, LPTACC abnormality and VBV The system is abnormal. Since the detection methods of the three different abnormal modes are similar, this experiment selects one of the civil aviation engines with abnormal EGT indications as an example to illustrate the experiment. The serial number of this engine is #697950. According to the CNR report, this experiment collected a total of There are 5880 samples, including 5879 normal samples and 1 abnormal sample. Part of the sample data and its distribution are shown in Table 6 and Table 7 respectively.
[0184] Table 6#697950 civil aviation engine part data
[0185]
[0186] Table 7 Sam...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com