Part manufacturing method, device and apparatus based on industrial neural network and medium

Abstract

The embodiment of the invention discloses a part manufacturing method, device and apparatus based on an industrial neural network and a medium. The method comprises the steps of carding a target entity, a constraint condition, a manufacturing process and an application type corresponding to manufacturing of the composite material part; according to the target entity, the constraint condition, the manufacturing process and the application type, constructing an association graph in a graph database; selecting at least one node in the association map as an algorithm node, and associating the algorithm node with an algorithm library, so that the algorithm node can call an algorithm stored in the algorithm library to calculate data in the algorithm node and the adjacent node; constructing an industrial neural network according to the association graph and an associated algorithm library; and manufacturing the composite material part based on the industrial neural network. According to the scheme, the composite material part is manufactured based on the industrial neural network technology, fragmented data and relations are efficiently integrated and managed, and therefore the relation analysis efficiency is improved.

Description

technical field [0001] The embodiments of the present application relate to the technical field of composite material parts manufacturing, and in particular to a method, device, equipment and medium for manufacturing parts based on an industrial neural network. Background technique [0002] Composite materials are currently one of the most promising materials and are widely used due to their advantages of small specific gravity, good rigidity and high strength. In the past 40 years, the scale of composite materials in manufacturing has gradually expanded. At present, its share in the structural weight of helicopters and fighter jets has exceeded 50%. In some advanced civil aircraft, its structural weight has reached 70%. [0003] In the manufacturing process of composite material parts, there are many process steps and long manufacturing cycle. Most of the process parameter adjustment and process verification require human participation, resulting in low production efficien...

AI Technical Summary

Problems solved by technology

However, the architecture of relational databases is not designed for the analysis of complex relational networks. In order to understand and analyze the relationship between entities, relational databases require table joins. The query of complex joins may take hours or days, and with As the amount of data increases, the cost of computing also increases

Whereas NoSQL databases store all data in one table, relational analysis requires scanning huge tables with millions or billions of rows, which makes it difficult to perform deeper analysis on relationships beyond two or three levels

Images