Air passage fault diagnosis method based on model and fuzzy mode identification

Abstract

The invention discloses an air passage fault diagnosis method based on model and fuzzy mode identification, wherein the air passage fault diagnosis method belongs to the field of engine fault test designing. Through performing mode algorithm matching on an unknown fault with a known fault database, a most possible fault type is found out. The air passage fault diagnosis method overcomes excessive dependence of an existing model-based method to an engine model and furthermore expands application range of a model-based air passage fault diagnosis method. On the condition of low calculation precision of the engine model, a model-based calculation result can be effectively corrected, thereby improving air passage fault diagnosis precision.

Description

technical field [0001] The invention belongs to the field of engine fault test design, and in particular relates to a gas path fault diagnosis method based on model and fuzzy pattern recognition. Background technique [0002] Gas path fault diagnosis (or gas path analysis) refers to identifying and locating performance change trends or faults of the complete engine and gas path components using mathematical methods by monitoring changes in gas path measurement parameter data. Usually, gas path fault diagnosis diagnoses physical faults with complex mechanisms by measuring parameters. The principle is to evaluate the health status of the engine, which depends on the health status of each relatively independent component, and the health status of the components can be determined independently by the engine. Variables, such as efficiency, flow, etc. Since Lou i s A. Urban first proposed a model-based gas path fault diagnosis method in 1972, the gas path fault diagnosis method h...

AI Technical Summary

Problems solved by technology

[0004] (1) The model-based gas path fault diagnosis method is too dependent on the accuracy of the engine simulation model, and the accuracy of the engine model directly affects the calculation accuracy of the model-based method. When the accuracy of the engine model is not high, the model-based method will Large calculation errors and non-convergence occur, and even wrong fault diagnosis results may occur, resulting in failure to realize normal gas circuit fault diagnosis;

[0005] (2) Many model-based methods, including nonlinear weighted least squares, require prior knowledge and data mining, but the covariance matrix is ​​usually random, which leads to random errors;

[0006] (3) The existing model-based gas circuit fault diagnosis method has insufficient processing capacity for test run data, and often has low precision, large error and non-convergence;

[0007] (4) Model-based gas path fault diagnosis methods often produce diffusion effects, resulting in large deviations in health parameters that do not have faults or abnormalities, and affect the accuracy of fault location

Images