Intelligent design method and system for energy dissipater based on neural network and storage medium
The invention provides an intelligent design method of an energy consumer based on a neural network. The method comprises the following steps: S1, calibrating a numerical model; s2, establishing a data set; s3, training the PSO-BP neural network; and S4, establishing a structural design model of the...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides an intelligent design method of an energy consumer based on a neural network. The method comprises the following steps: S1, calibrating a numerical model; s2, establishing a data set; s3, training the PSO-BP neural network; and S4, establishing a structural design model of the energy dissipater. Parameter analysis influencing the mechanical property of the energy dissipater is carried out through numerical simulation, a prediction model from the structural size to the mechanical property of the energy dissipater is established in combination with a PSO-BP neural network, and then an energy dissipater intelligent design model with reverse parameter optimization is established based on the PSO algorithm and the target mechanical property. The problems that an existing research method is complex in calculation, low in calculation efficiency, high in test cost and the like are mainly solved.
本发明提供了基于神经网络的耗能器智能设计方法,包括:S1.数值模型标定;S2.建立数据集;S3.训练PSO-BP神经网络;S4.建立耗能器结构设计模型。本发明利用数值模拟进行影响耗能器力学性能的参数分 |
---|