Engineering design method based on bond graph and genetic programming

Abstract

The invention relates to the technical field of engineering design, in particular to an engineering design method for conducting automated evolution design on mixing field systems or various different field systems based on a bond graph tool and a genetic programming algorithm. The method includes the steps of assigning an embryo physical structure diagram, conducting user input, setting up an initial population of a genetic programming tree, conducting ontoanalysis, conducting evolution operation and ending judgment. Compared with the prior art, the design method is high in expansibility, wide in application range, high in efficiency, high in normalization and capable of designing a complex project meeting the requirements of a designer through an automated method.

Description

technical field The present invention relates to the technical field of engineering design, more specifically, relates to an engineering design method for automatic evolutionary design of mixed domain systems or various different domain systems based on bond graph tools and genetic programming algorithms. Background technique In traditional engineering design, there are a large number of conventional models. Designers form a preliminary design plan of the product based on experience, and then establish a physical prototype based on this, and analyze or test the physical prototype to obtain product performance data. If the data cannot meet the requirements, go back and re-modify the design, then try out the product, then analyze or test again, and repeat this process until a product that meets the performance requirements is obtained. Of course, once the designed product is more complex, the entire design cycle will be longer. Occupied resources will be more, and it is diff...

AI Technical Summary

Problems solved by technology

Although evolutionary design methods have more advantages than traditional design methods in terms of design cycle and design performance, these automatic designs based on evolutionary algorithms also have shortcomings: they are mainly used in the design of single-field systems, such as analog circuit design; and in In the design process, in order to meet the design requirements, they need to occupy a lot of computing resources and consume a lot of computing time

To sum up, there are still many shortcomings in traditional engineering design and existing evolutionary algorithm design: in traditional engineering design, there are problems such as long design cycle, poor versatility, high labor cost, low design efficiency and low product performance;

In the design of existing evolutionary algorithms, there are disadvantages such as single design field, long evolution time, large amount of computing resources, insufficient target search ability, and search target values ​​are often trapped in local optimal values.

Images