Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Solid engine test data analysis method based on BP neural network

A technology of BP neural network and solid engine, applied in the direction of neural learning method, biological neural network model, neural architecture, etc., can solve problems such as lengthy calculation process, and achieve the effect of avoiding calculation process

Pending Publication Date: 2022-03-18
内蒙航天动力机械测试所
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, there are a large number of different calculation formulas for different test result parameters, so if you want to get more results, you need a lengthy calculation process

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
  • Solid engine test data analysis method based on BP neural network
  • Solid engine test data analysis method based on BP neural network
  • Solid engine test data analysis method based on BP neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Develop a neural network backpropagation algorithm based on artificial intelligence, which can predict and evaluate solid motors that have not been tested, and use a large number of historical data resources to continuously iteratively correct them, providing a solution to the problems existing in traditional solid motor tests. This is an effective technical approach. When there are potential hidden dangers in the prediction results, the loss can be stopped in time according to the prediction results, and the test can be carried out after updating and optimizing. On the other hand, there are some empirical parameters in the field of solid motors, and the gradient descent method in the backpropagation neural network gradually optimizes the parameters through continuous iterative correction.

[0042] The basic principle of the present invention is to build a specific structure for solid engine test data based on the neural network framework in the field of artificial intel...

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 the field of solid engine tests, in particular to a solid engine test data analysis method based on a BP neural network. The method comprises the steps that S1, a BP neural network modeling system is built, a three-layer neural network is selected as a basic framework, the function of an input layer is to import preprocessed data into the neural network, the function of an output layer is to export predicted data, and a hidden layer is changed into white box modularization processing in a black box convolution mode in the convolutional neural network; s2, calculating a state and an activation value of each layer through a BP model iterative algorithm until the last layer; the error of each layer is calculated, and the error calculation process is carried out forwards from the last layer; updating parameters; and the previous two steps are iterated until the conditions are met. According to the method, main feedback parameters of a new solid engine test can be predicted, comparison and error analysis with real test data are carried out, and iterative correction is carried out continuously, so that errors are reduced, and the prediction classification capability of a neural network model is improved.

Description

technical field [0001] The invention relates to the field of solid engine tests, in particular to a method for analyzing test data of solid engines based on BP neural network. Background technique [0002] Solid motor testing is an essential link in the development of solid motors. However, according to statistics, the current status of solid motor testing includes problems such as high cost and long preparation period. At the same time, there are still some problems in the process of testing solid motors. The possibility of causing casualties is not ruled out, which has laid a serious safety hazard for the occurrence of the accident. [0003] At present, the existing technical solution similar to the present invention is a solid engine virtual test technology platform, which can also provide test virtual data of a certain type of solid engine without real test. The working principle of the solid engine virtual test technology platform is based on a large number of formulas...

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): G06F30/27G06Q10/04G06N3/04G06N3/08
CPCG06F30/27G06N3/04G06N3/084G06Q10/04
Inventor 宋媛孙艳涛
Owner 内蒙航天动力机械测试所
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products