Deep learning-based second-order Helmholtz resonator design method

Abstract

The invention discloses a second-order Helmholtz resonator design method based on deep learning, which is used for designing geometric parameters of a second-order Helmholtz resonator based on two resonant frequencies f1 and f2 of the second-order Helmholtz resonator. The method comprises the steps of generating N sound insulation curves meeting requirements according to specific design requirements, inputting the N sound insulation curves into a pre-established and trained deep neural network model, and outputting N groups of corresponding equivalent electrical parameters; calculating N groups of geometric parameters of the second-order Helmholtz resonators according to the N groups of equivalent electrical parameters based on a conversion relation formula between the geometric parameters and the equivalent electrical parameters of the second-order Helmholtz resonators; and calculating corresponding sound insulation curves according to the geometric parameters of the N groups of second-order Helmholtz resonators, selecting an optimal sound insulation curve from the N sound insulation curves, and taking the geometric parameters of the second-order Helmholtz resonators corresponding to the optimal sound insulation curve as designed structural parameters.

Description

technical field [0001] The invention relates to the field of deep learning, in particular to a deep learning-based second-order Helmholtz resonator design method. Background technique [0002] Acoustic artificial structure is a kind of artificially designed composite structure. The properties of this composite structure mainly depend on its appearance, size, shape and arrangement, so it has many novel physical properties that natural materials do not have. In the practical application of acoustic artificial structures, we often need to design the geometric structure of the unit according to the desired physical properties. This design is a typical reverse design problem. The traditional design route can be divided into two parts: First, we can use some classic physical models and the experience and intuition accumulated from previous practice to determine the framework of the model. For example, we can achieve sound absorption and isolation based on the Helmholtz resonator ...

AI Technical Summary

Problems solved by technology

However, due to the large number of geometric parameters of THR and the coupling between parameters, it is difficult to analyze its physical characteristics

Therefore, on the one hand, the traditional THR design method requires rich experience for structure selection, and on the other hand, it also needs to make a lot of attempts on the target parameters, which not only has high requirements for the designer itself, but also often consumes a lot of time.

Images