發(fā)布時(shí)間：2018-05-27 19:50

  本文選題：鎂碳質(zhì)耐火材料 + 聲發(fā)射�。� 參考：《武漢科技大學(xué)》2015年碩士論文

【摘要】：耐火材料組成成分復(fù)雜，屬于多孔、多相性的微觀非均質(zhì)材料。在損傷過程中所產(chǎn)生的聲發(fā)射信號(hào)包含了損傷源的豐富信息。對(duì)耐火材料損傷特征進(jìn)行有效的提取，并選擇合適的分類器是實(shí)現(xiàn)其損傷模式識(shí)別的關(guān)鍵。本文針對(duì)耐火材料聲發(fā)射信號(hào)具有多重分形性、非線性、非平穩(wěn)的特性，利用多重分形理論、經(jīng)驗(yàn)?zāi)B(tài)分解相結(jié)合的方法進(jìn)行信號(hào)的特征提取，并采用支持向量機(jī)及BP神經(jīng)網(wǎng)絡(luò)兩種分類方法進(jìn)行損傷模式的識(shí)別，對(duì)耐火材料微觀損傷的研究具有積極的意義。本文主要研究?jī)?nèi)容如下： （1）本文以鎂碳質(zhì)耐火材料為研究對(duì)象，通過單軸壓縮試驗(yàn)?zāi)M其受壓應(yīng)力狀態(tài)下?lián)p傷狀況，并采集受壓過程中損傷聲發(fā)射信號(hào)以進(jìn)行分析。根據(jù)復(fù)合材料中不同組成成分損傷時(shí)發(fā)出的信號(hào)頻率成分與其彈性模量及密度相關(guān)，分析并分選耐火材料典型損傷信號(hào)。 （2）為從多重分形各項(xiàng)參數(shù)（Δα、Δf、K、MeanDq）中挑選出最佳損傷特征量，根據(jù)聲發(fā)射信號(hào)的特點(diǎn)建立了一系列不同頻率結(jié)構(gòu)的仿真聲發(fā)射信號(hào)，并通過仿真信號(hào)分析挑選出最佳特征量，最后用實(shí)驗(yàn)信號(hào)進(jìn)行驗(yàn)證。分析結(jié)果表明，多重分形譜寬Δα值能夠很好表征聲發(fā)射信號(hào)的特征，最適合用作損傷特征量。 （3）針對(duì)聲發(fā)射信號(hào)非線性、非平穩(wěn)的特性，通過EMD方法將信號(hào)分解為若干IMF分量，并將整個(gè)信號(hào)及各IMF分量的多重分形譜參數(shù)組成特征向量作為分類器的輸入量。然后分別采用SVM及BP神經(jīng)網(wǎng)絡(luò)兩種模式分類方法對(duì)損傷信號(hào)進(jìn)行模式分類，兩種方法的分類準(zhǔn)確率均達(dá)到了90%以上，這也驗(yàn)證了采用EMD與多重分形譜參數(shù)相結(jié)合的方法對(duì)實(shí)驗(yàn)信號(hào)進(jìn)行損傷特征提取的合理性。 （4）對(duì)SVM及BP神經(jīng)網(wǎng)絡(luò)兩種分類方法在不同訓(xùn)練樣本下的分類結(jié)果進(jìn)行對(duì)比分析，發(fā)現(xiàn)SVM能夠在較小樣本情況下實(shí)現(xiàn)更高分類準(zhǔn)確率，比BP神經(jīng)網(wǎng)絡(luò)方法更具優(yōu)勢(shì)。
[Abstract]:The composition of refractories is complex and belongs to porous and heterogeneous micro heterogeneous materials. The acoustic emission signals generated during the damage process contain abundant information about the source of the damage. It is the key to identify the damage patterns of refractories to extract damage features and select suitable classifiers. Aiming at the multifractal, nonlinear and non-stationary characteristics of acoustic emission signals of refractories, the method of combining multifractal theory and empirical mode decomposition is used to extract the features of the signals. Two classification methods, support vector machine and BP neural network, are used to identify the damage patterns, which is of great significance to the study of micro-damage of refractories. The main contents of this paper are as follows: In this paper, the damage of magnesia-carbon refractories under compression stress is simulated by uniaxial compression test, and the damage acoustic emission signals are collected for analysis. The typical damage signals of refractories were analyzed and sorted according to the correlation between the frequency components and the elastic modulus and density of the different components of composite materials. 2) in order to select the best damage characteristic quantity from the multifractal parameters (螖 偽, 螖 F ~ (1) K) mean DQ, a series of simulated acoustic emission signals with different frequency structures are established according to the characteristics of acoustic emission signals, and the optimum characteristic quantities are selected by analyzing the simulation signals. Finally, the experimental signals are used to verify the results. The results show that the multifractal spectrum width 螖 偽 can well characterize the characteristics of acoustic emission signals, and is the most suitable for damage characteristic quantities. In view of the nonlinearity and nonstationarity of acoustic emission signal, the signal is decomposed into several IMF components by EMD method, and the multifractal spectrum parameters of the whole signal and each IMF component are composed of the eigenvector as the input of the classifier. Then SVM and BP neural network are used to classify the damage signal, and the accuracy of the two methods is over 90%. This also verifies the rationality of the method of combining EMD with multifractal spectral parameters to extract the damage features of experimental signals. (4) the classification results of SVM and BP neural network under different training samples are compared and analyzed. It is found that SVM can achieve higher classification accuracy in the case of smaller samples, and has more advantages than BP neural network method.
【學(xué)位授予單位】：武漢科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TQ175.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 蘇永振;袁慎芳;張炳良;;基于聲發(fā)射和神經(jīng)網(wǎng)絡(luò)的復(fù)合材料沖擊定位[J];傳感器與微系統(tǒng);2009年09期

2 戴光,李偉,張穎,沈桂英;基于人工神經(jīng)網(wǎng)絡(luò)方法識(shí)別聲發(fā)射信號(hào)的有效性[J];大慶石油學(xué)院學(xué)報(bào);2001年01期

3 李卿;邵華;陳群濤;楊明倫;;基于獨(dú)立分量分析的切削聲發(fā)射源信號(hào)分離[J];工具技術(shù);2011年06期

4 鐘香崇;;我國鎂質(zhì)耐火材料發(fā)展的戰(zhàn)略思考[J];硅酸鹽通報(bào);2006年03期

5 韓波;孫利;黃勇;;水質(zhì)評(píng)價(jià)模式識(shí)別的BP神經(jīng)網(wǎng)絡(luò)方法[J];廣州環(huán)境科學(xué);2005年04期

6 劉京紅;姜耀東;祝捷;韓文;;煤巖單軸壓縮聲發(fā)射試驗(yàn)分形特征分析[J];北京理工大學(xué)學(xué)報(bào);2013年04期

7 黃金波;王志剛;劉昌明;;基于小波變換的鎂碳質(zhì)耐火材料受壓損傷聲發(fā)射特征分析[J];材料導(dǎo)報(bào);2013年16期

8 栗麗;晏雄;;復(fù)合材料損傷失效的聲發(fā)射檢測(cè)研究進(jìn)展[J];材料導(dǎo)報(bào);2013年17期

9 李偉;方江濤;戴光;;基于獨(dú)立分量分析和小波變換的低碳鋼點(diǎn)蝕聲發(fā)射信號(hào)特征提取[J];化工機(jī)械;2007年02期

10 張穎 ,陳建萍 ,陳積懋;模態(tài)聲發(fā)射的噪聲剔除技術(shù)[J];航空制造技術(shù);2002年12期

相關(guān)博士學(xué)位論文 前1條

1 郝研;分形維數(shù)特性分析及故障診斷分形方法研究[D];天津大學(xué);2012年

，

本文編號(hào)：1943530