【摘要】：漏磁檢測(cè)是鐵磁材料常用的無損檢測(cè)方法之一,定量識(shí)別是指通過檢測(cè)到的漏磁信號(hào)識(shí)別裂紋的尺寸.采用主成分分析和優(yōu)化神經(jīng)網(wǎng)絡(luò)相結(jié)合的建模方法,建立了微裂紋寬度與深度的預(yù)測(cè)模型.主成分分析去除了數(shù)據(jù)相關(guān)性,減小了輸入樣本維數(shù),顯著簡化了網(wǎng)絡(luò)結(jié)構(gòu);遺傳算法優(yōu)化的BP神經(jīng)網(wǎng)絡(luò)(GA-BP神經(jīng)網(wǎng)絡(luò))可以有效地防止搜索過程中陷入局部最優(yōu)解.通過基于磁偶極子模型的理論計(jì)算與人工刻槽微裂紋漏磁檢測(cè)實(shí)驗(yàn)兩種途徑驗(yàn)證了該算法在微裂紋定量識(shí)別中的應(yīng)用,為裂紋發(fā)展階段的早期定量識(shí)別技術(shù)奠定了一定的基礎(chǔ).
[Abstract]:Magnetic leakage detection is one of the commonly used nondestructive testing methods for ferromagnetic materials. Quantitative identification refers to the identification of crack size by detecting magnetic leakage signals. The prediction model of microcrack width and depth is established by combining principal component analysis and optimization neural network. Principal component analysis (PCA) eliminates the data correlation, reduces the dimension of input samples, and simplifies the network structure significantly. The genetic algorithm optimized BP neural network (GA-BP neural network) can effectively prevent the search process from falling into the local optimal solution. The theoretical calculation based on the magnetic dipole model and the experiment of magnetic flux leakage detection of microcracks in artificial grooves verify the application of the algorithm in the quantitative identification of microcracks, which lays a foundation for the early quantitative identification of microcracks in the development stage.
【作者單位】： 北京理工大學(xué)機(jī)械與車輛學(xué)院;機(jī)械科學(xué)研究總院先進(jìn)制造技術(shù)研究中心;河北環(huán)境工程有限公司;
【基金】：國家自然科學(xué)基金資助項(xiàng)目(51275048)
【分類號(hào)】：TG115.284
，

本文編號(hào)：2386522