Accelerated life test-based ammunition storage reliability prediction method

A technology for accelerated life testing and prediction methods, applied in prediction, neural learning methods, instruments, etc., can solve problems such as insufficient abundance, improve inertial weight and search area, simple calculation process, and make up for the effect of slow convergence

Inactive Publication Date: 2018-06-19
SHENYANG LIGONG UNIV
View PDF0 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the research on the reliability of ammunition storage based on data is not rich enough. Most of the existing reliability research is based on the mechanism model, and the model of BP neural network optimized by particle swarm algorithm is applied to the special field of reliability prediction of ammunition storage. At present, No relevant literature has been found at home and abroad

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
  • Accelerated life test-based ammunition storage reliability prediction method
  • Accelerated life test-based ammunition storage reliability prediction method
  • Accelerated life test-based ammunition storage reliability prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] See figure 1 , the ammunition storage reliability prediction method based on the accelerated life test of the present embodiment specifically includes the following steps:

[0047] 1. Select an appropriate data set, and according to the adopted constant humidity step temperature accelerated test data set, select four indicators of test sample size, temperature stress, storage humidity and storage time to predict the number of ammunition failures, in which the sample size and humidity are constant Invariant, set to 1 during network training.

[0048] 2. Based on the environmental factor method, the storage time under all levels of stress is converted, and the environmental factor method of Bayes theory is used for processing. The environmental factor is defined as the ratio of the life parameter under two levels of stress. The relative environmental factor is obtained by calculating the life parameter, and further carried out The conversion of storage equivalent time un...

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 discloses an accelerated life test-based ammunition storage reliability prediction method. The invention aims to mainly improve the prediction accuracy of the reliability of ammunition storage and solve the problems of large calculation amount and difficulty in guaranteeing the prediction accuracy of small sample data of a traditional prediction method. The method of the invention includes the following planning steps that: an improved global particle swarm optimization-BP neural network model (IGPSO-BP model) is established for an accelerated life test data set, particle positions in a particle swarm optimization algorithm are defined as weights and thresholds in a BP neural network; optimized network weight parameters are obtained through a process of finding optimal particle positions, and the global search ability of the particle swarm optimization algorithm is utilized to the greatest extent, and the local search ability of the BP neural network is fully utilized; and an indirect method is used to predict the reliability of the ammunition storage. With the method of the invention adopted, test time can be shortened, a calculation process is simple, the specific life distribution type of an ammunition product and the specific function relationship of the specific life distribution type are not needed to be analyzed, and limitations of the traditional prediction method can be broken.

Description

technical field [0001] The invention relates to the technical field of ammunition storage reliability, in particular to a method for predicting ammunition storage reliability based on accelerated life tests. Background technique [0002] The reliability of ammunition storage is an important basis for measuring the quality of ammunition, and it is also the core element of evaluating military logistics technology. During the storage of ammunition, due to environmental and human factors, the quality of ammunition will change accordingly, which may cause the ammunition to fail. The use of overdue ammunition will not only fail to guarantee its safety, but may even cause personal injury; and decommissioning before reaching the limit of ammunition life will increase the economic cost of military equipment. Therefore, it is not only of military significance but also of economic value to carry out research on the reliability of ammunition storage and grasp it as accurately as possib...

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): G06Q10/04G06Q50/00G06N3/08
CPCG06N3/086G06Q10/04G06Q50/00
Inventor 宫华冯丹刘芳许可
Owner SHENYANG LIGONG UNIV
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