南京理工大学学报（自然科学版）2017，Vol.41Issue(5)：581-586,6.DOI:10.14177/j.cnki.32-1397n.2017.41.05.007
基于GA-BP神经网络的落锤液压动标装置准静态校准模型
Quasi-static calibration model of drop hammer hydraulic dynamic pressure calibration device based on GA-BP neural network
摘要
Abstract
The drop hammer dynamic pressure calibration device is commonly used for the quasi-static calibration of the piezoelectric pressure transducer for shock wave measurement. In order to quickly and accurately adjust the working parameters of the drop hammer device and generate the required calibration pressure,a mathematical model about the relationship of the working parameters of the drop hammer hydraulic dynamic pressure calibration device with the peak value and pulse width of pressure is established based on the gennetic algorithm-back propagation ( GA-BP ) neural network. The test results show that the model based on the GA-BP neural network has the better high fitting precision and practical engineering application value,and the peak pressure error is not higher than 2% and the pulse width error is less than 1%.关键词
遗传算法反向传播神经网络/落锤装置/压力峰值/压力脉宽/准静态校准模型Key words
gennetic algorithm-back propagation neural network/drop hammer devices/pressure peak value/pressure pulse width/quasi-static calibration models分类
信息技术与安全科学引用本文复制引用
顾廷炜,孔德仁..基于GA-BP神经网络的落锤液压动标装置准静态校准模型[J].南京理工大学学报（自然科学版）,2017,41(5):581-586,6.基金项目
国家自然科学基金(11372143) （11372143）
