Mechanical property prediction method for cast cylinder cover based on rough set and neural network

Abstract

The invention relates to a mechanical property prediction method for a cast cylinder cover based on a rough set and a neural network, and belongs to the related field of cast aluminum alloy cylinder covers. According to the mechanical property prediction method based on the rough set and the BP neural network, index attributes influencing mechanical properties are reduced by using the rough set theory, so that the input dimension of the neural network is reduced, and the reduced index attributes are used as the input of the BP neural network to perform mechanical property prediction. According to the method, on the premise that a large number of tests and analog simulation do not need to be carried out, the mechanical property can be predicted under the almost lossless test condition, the accuracy and efficiency of mechanical property prediction are improved. Meanwhile, the design and production cost is reduced, and the production benefit is improved.

Description

technical field [0001] The invention relates to a method for predicting the mechanical properties of a cast cylinder head based on rough sets and neural networks, and belongs to the related field of cast aluminum alloy cylinder heads. Background technique [0002] In the field of cast aluminum alloy cylinder heads, the fatigue life of the cylinder head is usually determined by the mechanical properties of the cast aluminum alloy, and the processing and production process of the cast aluminum alloy cylinder head largely determines the mechanical properties of the cylinder head. During the processing and production of cast cylinder heads, different microstructures will be produced due to different casting processes, and these microstructures are the main factors affecting the mechanical properties. At present, some researchers establish an empirical formula for the relationship between the microstructure and mechanical properties of the cylinder head by using a large amount of...

AI Technical Summary

Problems solved by technology

At present, some researchers establish empirical formulas for the relationship between the microstructure and mechanical properties of the cylinder head by using a large amount of mechanical property test data. This process consumes a lot of manpower and material resources; the second is to carry out finite element numerical simulation. and an effective prediction method, but the simulation time is long, the number of simulations is large, and there is no intelligent learning function, which cannot meet the needs of efficient and fast prediction

Images