Aircraft structural part design method based on machine learning

Abstract

The invention discloses an aircraft structural part design method based on machine learning. The aircraft structural part design method comprises the following steps: 1) inputting design requirements and related parameters of an aircraft structural part required to be designed through a human-computer interaction interface; 2) carrying out feature analysis on the aircraft wing structural member through OpenCv auxiliary feature recognition; (3) similar instances are retrieved based on rule type selection and instance reasoning, instances with high similarity are selected, and on the basis of the instances, designers modify the instances according to requirements needing to be designed; 4) classifying the extracted features according to a k-nearest neighbor algorithm, and adding the features as training learning results into a training library of machine learning; and 5) storing the corrected instance and the design solution as new instances in an instance library as a new instance. According to the method, knowledge-model-case library data is expanded, the utilization rate of design parameters of the aircraft structural component is increased, the design quality and design efficiency of the aircraft structural component are improved, and the research and development capability is improved.

Description

Technical field [0001] The present invention relates to the field of aircraft design, in particular to a machine learning-based aircraft structural parts design method. Background [0002] With the progress of the times and the continuous development of digital technology, the performance of modern aircraft in all aspects is getting better and better, and the scientific and technological content is getting higher and higher, which in turn makes the role of aircraft in both civilian and war play a pivotal role. Aircraft structural parts gradually to large-scale, integral and complex direction of development, aircraft structural parts of efficient, high-quality design is to ensure the performance and development of the important conditions, aircraft structural parts have a typical multi-variety, small batch characteristics, is not conducive to the accumulation of knowledge and reuse, aircraft structure is mainly composed of fuselage, landing gear, wings, tails, flight operating sys...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is: based on the problems of low utilization rate, low design efficiency and low design quality of aircraft structural parts based on the design knowledge of designers or systems, the present invention proposes an aircraft structure based on machine learning This method expands the data of the knowledge-model-example library, increases the utilization rate of the design parameters of aircraft structural parts, improves the design quality and design efficiency of aircraft structural parts, and improves the research and development capabilities

Images