CN-117235368-B - Quality technical information recommendation method for space product design analysis procedure

CN117235368BCN 117235368 BCN117235368 BCN 117235368BCN-117235368-B

Abstract

The invention relates to a quality technical information recommendation method for a space product design analysis procedure. The method comprises the steps of obtaining a plurality of quality technical information tables for determining the quality of a space product, wherein the quality technical information tables comprise physical parameters involved in the design and manufacture of the space product, carrying out data compression dimension reduction on the quality technical information tables to obtain quality technical feature vectors, obtaining first priority based on the quality technical feature vectors and a space product quality prediction model, and obtaining a recommended quality technical information table based on the first priority. According to the scheme, data compression dimension reduction processing is adopted, a quality technical information table is input into a space product quality prediction model, and the most suitable quality technical information table is obtained. The method greatly improves the accuracy and the working efficiency of parameter screening, reduces the requirements of experiments and trial and error, is beneficial to realizing the high-quality design and manufacture of space products, and further ensures the high quality and reliability of the space products.

Inventors

LIU GUOCAI
ZHANG DI
LI HUI
ZHAO YIHONG
WANG YANHONG
LIU YU
XIA XIAOCHUN
BAO ZHIWEN
YAO HONGTAO
DUAN BO
MIAO YUTAO
LI YUAN
LI LU

Assignees

中国航天标准化研究所

Dates

Publication Date: 20260508
Application Date: 20231007

Claims (8)

1. A quality technical information recommendation method for a space product design analysis procedure is characterized by comprising the following steps: acquiring a plurality of quality technical information tables for determining the quality of a space product, wherein the quality technical information tables comprise physical parameters involved in the design and manufacture of the space product; Performing data compression and dimension reduction on the quality technical information table to obtain a quality technical feature vector; obtaining a first priority based on the quality technical feature vector and a space product quality prediction model; Obtaining a recommended quality technical information table based on the first priority; The step of obtaining the first priority based on the quality technical feature vector and the space product quality prediction model comprises the steps of inputting the quality technical feature vector into the modeled space product quality prediction model to obtain corresponding path parameters; The first priority is calculated using the following formula: wherein lambda i is the path coefficient of the ith argument, And n is the number of the physical parameters in the corresponding quality technical information table in the calculated quality technical feature vector.
2. The quality technical information recommendation method for a space product design analysis procedure according to claim 1, wherein the step of performing data compression and dimension reduction on the quality technical information table to obtain a quality technical feature vector comprises the steps of: normalizing the data in the quality technical information table by using a multiple function to obtain a normalized quality parameter set; And carrying out additive dimension reduction analysis on the normalized quality parameter set to obtain a quality technical feature vector.
3. The quality technical information recommendation method for a space-based product design analysis process according to claim 2, wherein the mathematical expression of the multivariate function is: Wherein S (x) is a multiple function, x is a physical parameter in a quality technical information table, and c is a gain coefficient; The calculation of the additive dimension reduction analysis uses the following formula: Or (b) Wherein A I S (x) and A II S (x) are quality technical feature vectors, c is a formula of A I S (x) when the values are unified, and c is a formula of A II S (x) when the values are different.
4. The quality technical information recommendation method for a space product design analysis procedure according to any one of claims 1, wherein the space product quality prediction model is a structural equation model.
5. The quality technical information recommendation method for a space product design analysis procedure according to claim 4, wherein the space product quality prediction model contains potential variables, and the number of quality technical feature vectors is the same as the number of potential variables.
6. The quality technical information recommendation method for a space product design analysis procedure according to claim 4, wherein "inputting the quality technical feature vector into a modeled space product quality prediction model to obtain a corresponding path parameter" includes: judging whether the quality technical feature vector meets the multi-element normal distribution; If the quality technical feature vector meets the multi-element normal distribution, the space product quality prediction model uses a maximum likelihood method to obtain path parameters; and when the input quality technical feature vector does not meet the data of the multivariate normal distribution, the spatial product quality prediction model uses asymptotic distribution to freely estimate a fitting index or a self-help method to obtain path parameters.
7. A control device comprising a processor and a storage device, said storage device being adapted to store a plurality of computer programs, characterized in that said computer programs are adapted to be loaded and run by said processor to perform the quality technical information recommendation method for a space-oriented product design analysis procedure according to any one of claims 1 to 6.
8. A computer readable storage medium, in which a plurality of computer programs are stored, characterized in that the computer programs are adapted to be loaded and run by a processor to perform the quality technical information recommendation method for a space-oriented product design analysis procedure according to any one of claims 1 to 6.

Description

Quality technical information recommendation method for space product design analysis procedure Technical Field The invention relates to a quality technical information recommendation method for a space product design analysis procedure. Background In existing space product design and manufacturing techniques, the design and manufacturing process involves a large number of diverse physical parameters that together determine the quality of the product. However, the prior art lacks efficient methods to screen these parameters to find the appropriate parameters that ensure the quality of the space product. Conventional screening methods often rely on a large number of experiments and trial and error, which not only consume significant time and resources, but also make it difficult to ensure that the parameters obtained are optimal or most suitable. Furthermore, the manual processing of numerous physical parameters and corresponding data, especially when the data volume is huge, undoubtedly increases the effort and complexity, which makes it more difficult and challenging to find parameters that affect the key of the product quality. Accordingly, there is a need in the art for a new quality information recommendation scheme to address the above-mentioned problems. Disclosure of Invention The present invention has been made to overcome the above-mentioned drawbacks, and an object of the present invention is to provide a method and apparatus for designing a space product, which solve or at least partially solve the problem that quality information is difficult to optimize in the prior art space product designing and manufacturing technology. In a first aspect, the invention provides a quality technical information recommendation method for a space product design analysis procedure, which comprises the steps of obtaining a plurality of quality technical information tables for determining the quality of a space product, wherein the quality technical information tables comprise physical parameters involved in the design and manufacture of the space product, carrying out data compression and dimension reduction on the quality technical information tables to obtain quality technical feature vectors, obtaining a first priority based on the quality technical feature vectors and a space product quality prediction model, and obtaining a recommended quality technical information table based on the first priority. In addition or alternatively, in the method according to an embodiment of the present invention, the step of performing data compression dimension reduction on the quality technical information table to obtain a quality technical feature vector includes normalizing data in the quality technical information table by using a multivariate function to obtain a normalized quality parameter set, and performing additive dimension reduction analysis on the normalized quality parameter set to obtain the quality technical feature vector. Alternatively or additionally to the above, in a method according to an embodiment of the invention, the mathematical representation of the multivariate function is: Wherein S (x) is a multiple function, x is a physical parameter in a quality technical information table, c is a gain coefficient, and the calculation of the additive dimension reduction analysis uses the following formula: Or (b) Wherein A I S (x) and A II S (x) are quality technical feature vectors. In addition or alternatively, in the method according to an embodiment of the present invention, the step of obtaining the first priority based on the quality technical feature vector and the spatial product quality prediction model includes inputting the quality technical feature vector into the modeled spatial product quality prediction model to obtain a corresponding path parameter, and obtaining the first priority based on the path parameter. Alternatively or additionally to the above, in a method according to an embodiment of the invention, the first priority is calculated using the formula: wherein lambda i is the path coefficient of the ith argument, And n is the number of the physical parameters in the corresponding quality technical information table in the calculated quality technical feature vector. In addition or alternatively, in the method according to an embodiment of the present invention, the step of inputting the quality technical feature vector into the modeled spatial product quality prediction model to obtain the corresponding path parameters includes determining whether the quality technical feature vector satisfies the multivariate normal distribution, if the quality technical feature vector satisfies the multivariate normal distribution, the spatial product quality prediction model uses a maximum likelihood method to obtain the path parameters, and if the input quality technical feature vector does not satisfy the multivariate normal distribution, the spatial product quality prediction model uses an asympto