Unlock instant, AI-driven research and patent intelligence for your innovation.

Fault diagnosis method based on Lagrangian-particle swarm updating algorithm

A fault diagnosis and particle swarm technology, applied in calculation, calculation model, instrument, etc., can solve problems such as algorithm judgment and many loops, programming difficulty, and unclear structure level, so as to achieve easy programming, improve safety and reliability Sexuality and clear structure

Pending Publication Date: 2019-08-16
NAVAL AERONAUTICAL UNIV
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the theoretical analysis of the existing Lagrangian relaxation algorithm is relatively complicated. The algorithm involves the iterative process of the optimal solution and the Lagrange multiplier. The structure level is not clear. There are many judgments and cycles in the algorithm, and the programming is difficult
[0005] At present, no algorithm has been found that uses the particle swarm method to update the Lagrangian multipliers and improve the Lagrangian relaxation algorithm

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
  • Fault diagnosis method based on Lagrangian-particle swarm updating algorithm
  • Fault diagnosis method based on Lagrangian-particle swarm updating algorithm
  • Fault diagnosis method based on Lagrangian-particle swarm updating algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The fault diagnosis method based on the Lagrangian-particle swarm update algorithm will be further described below in conjunction with specific embodiments:

[0041] The system correlation matrix before Apollo spacecraft launch is shown in Table 1.

[0042] Table 1 Apollo spacecraft system correlation matrix

[0043]

[0044] The prior probability of failure in the selected system is equal to 0.1. If the system faults are 1,5, the tests that detect the faults are 2,4,6,7,8,9,10,11,12,13,14. Algorithms should be able to resolve faults1,5 from test point failures (faults detected).

[0045] Step 1: Use correlation matrix to construct fault diagnosis model.

[0046] The constructed fault diagnosis model is:

[0047]

[0048] Among them, S - In the fault set S, remove the set of faults that are confirmed not to have occurred, (in the process of actual calculation, for the faults that are confirmed to have not occurred x i , take its value as 0 first, and the res...

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 relates to a fault diagnosis method based on Lagrangian-particle swarm updating algorithm. The method comprises the following four steps: establishing a fault diagnosis mathematical model, performing Lagrangian relaxation on the model, searching global optimal particles by using a particle swarm updating method, and substituting the optimal particles into the model to solve a diagnosis result. According to the method, an optimal Lagrangian multiplier is solved by using a particle swarm algorithm, an absolute value of a difference between an upper bound and a lower bound is constructed as a fitness function of a main parameter, and a globally optimal particle is selected based on the fitness function. In order to meet the non-negative condition of a multiplier in an original Lagrangian relaxation algorithm, an exponential function is constructed to slow down the moving speed of the particles in the negative direction, and the particles in the population are limited to be non-negative. Hidden faults in the system can be found, the fault isolation rate is higher, the result of the algorithm is more accurate, and the precision of the algorithm is improved.

Description

technical field [0001] The invention relates to a fault diagnosis method based on a Lagrangian-particle swarm update algorithm, belonging to the field of fault diagnosis. [0002] technical background [0003] Fault diagnosis based on model and test results is a widely used fault diagnosis method at present. Based on the correlation matrix of the system, the method adopts Bayesian theory to establish its fault diagnosis model and uses artificial intelligence algorithm to solve it. [0004] The Lagrangian relaxation algorithm is an artificial intelligence algorithm, which has been maturely applied to solve the fault diagnosis model based on Bayesian theory. However, the theoretical analysis of the existing Lagrangian relaxation algorithm is relatively complicated. The algorithm involves the iterative process of the optimal solution and the Lagrangian multiplier. . [0005] At present, no algorithm has been found to improve the Lagrange relaxation algorithm by using the part...

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
IPC IPC(8): G06F17/50G06N3/00
CPCG06N3/006G06F30/20Y02T10/40
Inventor 吕晓峰马羚张聿远赵建忠邓力张振姚成柱
Owner NAVAL AERONAUTICAL UNIV