Aero-engine fault detection method based on IHPSO-KMSVDD

A technology of IHPSO-KMSVDD and aeroengine, applied in the field of aeroengine fault detection based on IHPSO-KMSVDD

Pending Publication Date: 2021-09-07
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the normal samples contain multiple samples under normal conditions, they often show the distribution of multiple clusters in the feature space, and it is inappropriate to construct only one hypersphere at this time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Aero-engine fault detection method based on IHPSO-KMSVDD
  • Aero-engine fault detection method based on IHPSO-KMSVDD
  • Aero-engine fault detection method based on IHPSO-KMSVDD

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] In the fault detection of aero-engines, the acquisition cost of normal samples and fault samples is different, so it is very popular to complete the fault detection when only normal samples are needed. In view of this, the following steps are implemented:

[0070] Step 1: Establish the IHPSO hyperparameter optimization model, and iteratively cycle until the optimal hyperparameters are found:

[0071]

[0072]

[0073] Among them, t represents the number of iterations, w is the inertia weight, which is proportional to the strength of the global optimization ability, and c 1 and c 2 Indicates the learning factor, r 1 and r 2 It is the abbreviation of the function rand(*), which means a random number between [0,1], r 3 is a random number endowed with a standard normal distribution, that is, r 3 ∈N(0,1). In aero-engine fault detection, it is assumed that there are N sample data, that is, N particles, in a 3-dimensional search space, that is, each particle contain...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an aero-engine fault detection method based on IHPSO-KMSVDD. A multi-sphere support vector data description algorithm is proposed, sample data in different states are surrounded by different hyper-spheres for anomaly detection, the situation that a certain state is completely mistakenly recognized is greatly avoided, and the precision and robustness of an original algorithm are improved. Besides, aiming at the defect that the algorithm hyper-parameter training time is too long, the invention provides an improved particle swarm optimization algorithm for simulating human learning behaviors to optimize hyper-parameters, so that the training time can be effectively shortened. The algorithm is suitable for small and medium-scale classification problems, and has good performance in the aspect of aero-engine fault detection. When the aero-engine breaks down due to abrasion, corrosion, blockage and the like, health parameters of corresponding parts can be changed, and when normal data are doped with fault data of different degrees, the fault data can be continuously recognized with excellent performance under the condition that the fault data are mixed, and the working efficiency is effectively improved.

Description

technical field [0001] The present invention aims at the fault detection of the aero-engine, combines the support vector data description (Support Vector Data Description) and the K-mean clustering algorithm, builds a multi-sphere model, and solves the detection accuracy of component faults under various working conditions of the aero-engine low problem. At the same time, the improved particle swarm optimization (Particle SwarmOptimization) algorithm is used to optimize the hyperparameters, shorten the training time, and improve the real-time detection of aero-engines. Background technique [0002] The aero-engine is the power core of every aircraft, and its safety has always affected people's heartstrings. Once there is a problem with it, it will directly pose a huge threat to people's property safety and even life safety. However, due to the complexity of its structure, the strict precision requirements, and the harsh working environment, the main components are extremely...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/00
CPCG06N3/006G06F18/214
Inventor 赵永平谢云龙叶志锋
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products