本文選題：空間碎片 + 超高速撞擊　； 參考：《航空學(xué)報(bào)》2017年05期

【摘要】：為通過(guò)聲發(fā)射技術(shù)識(shí)別鋁合金蜂窩板超高速撞擊(HVI)的損傷狀態(tài),提出一種基于神經(jīng)網(wǎng)絡(luò)的損傷模式識(shí)別方法。通過(guò)超高速撞擊實(shí)驗(yàn)獲取聲發(fā)射信號(hào),結(jié)合精確源定位技術(shù)、時(shí)頻分析技術(shù)、小波分析技術(shù)及模態(tài)聲發(fā)射技術(shù),提出了10個(gè)與損傷相關(guān)的特征參數(shù),通過(guò)非參數(shù)檢驗(yàn)分析其與損傷的關(guān)系,設(shè)計(jì)了一種基于貝葉斯正則化BP神經(jīng)網(wǎng)絡(luò)的超高速撞擊損傷模式識(shí)別方法。建立最優(yōu)網(wǎng)絡(luò)模型,通過(guò)不同參數(shù)組合識(shí)別能力分析,優(yōu)選出2種特征參數(shù)組合,通過(guò)非同源樣本對(duì)其損傷模式識(shí)別能力進(jìn)行驗(yàn)證。結(jié)果表明:傳播距離與損傷模式無(wú)關(guān),卻是識(shí)別損傷模式的重要參數(shù);125~250kHz頻域的自動(dòng)加窗小波能量比會(huì)降低損傷模式的識(shí)別能力;采用貝葉斯正則化的BP神經(jīng)網(wǎng)絡(luò)可以較好地識(shí)別蜂窩板超高速撞擊損傷模式,參數(shù)組合為傳播距離、上升時(shí)間、持續(xù)時(shí)間、截止頻率、4個(gè)自動(dòng)加窗小波能量比及小波能量熵,共9個(gè)參數(shù),對(duì)任意選取非同源樣本識(shí)別錯(cuò)分率僅為9.38%。
[Abstract]:In order to identify the damage state of the hypervelocity impact (HVI) of aluminum alloy honeycomb panel by acoustic emission technology, a method of damage pattern recognition based on neural network is proposed. The acoustic emission signals are obtained by ultra high speed impact test, combined with the precise source location technology, time frequency analysis, small wave analysis and modal acoustic emission technology, 10 of which are presented. The relationship between damage and damage is analyzed by nonparametric test. A model identification method for hypervelocity impact damage based on Bayesian regularization BP neural network is designed. The optimal network model is established. Through the analysis of different parameters combination recognition ability, 2 combination of characteristic parameters is optimized and the non homologous sample is used. The results show that the propagation distance is independent of the damage mode, but it is an important parameter to identify the damage mode, and the automatic adding window wavelet energy ratio in the 125~250kHz frequency domain can reduce the recognition ability of the damage mode, and the BP neural network with Bayesian regularization can identify the hypervelocity impact damage of the honeycomb plate. The parameter combination is the propagation distance, the rising time, the duration, the cut-off frequency, the 4 automatic window wavelet energy ratio and the wavelet energy entropy, which are 9 parameters, and the error rate is only 9.38%. for the arbitrary selection of non homologous samples.

【作者單位】： 哈爾濱工業(yè)大學(xué)航天學(xué)院;
【基金】：國(guó)家“十二五”空間碎片專項(xiàng)(K0203210) 中央高�；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)資金(HIT.NSRIF.2015029)~~
【分類號(hào)】：V528

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 馬文來(lái),張偉,管公順,龐寶君;橢球彈丸超高速撞擊防護(hù)屏碎片云數(shù)值模擬[J];材料科學(xué)與工藝;2005年03期

2 張偉,龐寶君,賈斌,曲焱U，

本文編號(hào)：1801916