Neural network decision method for writing digital aircraft codes by artificial intelligence programmer

Abstract

The invention discloses a neural network decision method for writing digital aircraft codes by an artificial intelligence programmer. The digital aircraft source codes are written by the artificial intelligence programmer instead of a person; specifically by establishing a corresponding relationship between a target sample set and a simulation step length vector decision set of parts of aircraft part models, and performing neural network training, simulation step length vectors of the decision parts are obtained; the digital aircraft source codes can be autonomously written according to task requirements, and the problems of code writing in source code writing, internal simulation step length design of modules in an aircraft model and the like are autonomously decided, so that the person is liberated from a heavy digital aircraft source code writing process. According to the method, autonomous decision of the digital aircraft source codes is reasonably finished; automation and intelligentization of digital aircraft source code writing are realized; and the aircraft simulation cost is reduced.

Description

technical field [0001] The invention relates to the field of aircraft design, and more specifically relates to a neural network decision-making method for artificial intelligence programmers to write digital aircraft codes. Background technique [0002] In the process of aircraft design and development, in order to ensure the high reliability of the final application of the aircraft, it is necessary to adopt a large number of existing design mainstream methods in the design, and it is necessary to conduct simulation verification and ground tests. Among them, some ground tests cannot fully reflect the actual working conditions of the aircraft in orbit, and the cost is high, so it is limited. [0003] Digital aircraft simulation verification is not limited by environmental conditions, and as long as the model is established accurately enough, the working conditions of the aircraft can be better simulated. Therefore, simulation verification methods have been widely used in airc...

AI Technical Summary

Problems solved by technology

[0004] In the process of building a digital aircraft, a large amount of source code needs to be written, and the workload is heavy.

Images