基于多信息融合的鋁合金脈沖GTAW過程焊接缺陷特征提取研究
發(fā)布時(shí)間：2018-08-20 18:59
【摘要】：智能化焊接是智能制造領(lǐng)域中最重要的研究課題之一。而傳感技術(shù)及其信息處理則是實(shí)現(xiàn)焊接過程智能化及自動(dòng)化的關(guān)鍵要素。近年來,具有小型化、無接觸式及大傳輸量等特點(diǎn)的傳感技術(shù)更多地被應(yīng)用到焊接過程及質(zhì)量實(shí)時(shí)控制中,如電弧傳感、視覺傳感、聲音傳感、光譜傳感等,這些傳感利用不同信息源獲取了與焊接質(zhì)量有關(guān)的大規(guī)模信息,但同時(shí)也不可避免地帶來了焊接過程的“大數(shù)據(jù)”。因此,如何去除其中的大量噪聲和冗余信息,更重要的,如何挖掘有效信息并將其及時(shí)反饋與利用在焊接質(zhì)量的實(shí)時(shí)監(jiān)測中是亟需解決的關(guān)鍵問題。本文以鋁合金脈沖GTAW過程為研究對(duì)象,以實(shí)時(shí)預(yù)測識(shí)別焊接動(dòng)態(tài)過程中的典型缺陷為目標(biāo),基于光譜傳感、聲音傳感、電壓傳感及視覺傳感技術(shù),對(duì)焊接缺陷的特征提取、評(píng)價(jià)、選擇以及多信息融合的預(yù)測識(shí)別方法開展了深入研究。搭建了一套脈沖GTAW焊接試驗(yàn)系統(tǒng)及多信息采集平臺(tái),可以實(shí)現(xiàn)對(duì)焊接過程的自動(dòng)控制,對(duì)焊接電弧光譜、聲音、電弧電壓及焊縫圖像信息的自動(dòng)采集與存儲(chǔ)。借助于多源同步信息,分析了多種典型焊接缺陷的產(chǎn)生機(jī)理,以及不同信號(hào)在時(shí)域-頻域-時(shí)頻域所表現(xiàn)出的奇異性,提出了針對(duì)各類傳感的信號(hào)處理及特征提取方法。提出了一種基于感興趣的光譜輻射區(qū)間soi(spectrumofintrests)的光譜統(tǒng)計(jì)特征提取及評(píng)價(jià)方法。根據(jù)最大奇異性原則選擇了8段soi,從中所提取的均方根r、方差d及峰度k三個(gè)統(tǒng)計(jì)特征參數(shù)有效表征了焊接電弧soi輻射的平均強(qiáng)度、奇異程度及形態(tài)特征;利用小波包c(diǎn)oief4小波函數(shù)5層分解的信號(hào)重構(gòu)法有效去除了特征脈沖干擾。進(jìn)一步,基于所提出的snr對(duì)數(shù)特征評(píng)價(jià)準(zhǔn)則,量化了特征參數(shù)對(duì)焊接缺陷的敏感度。其次,基于所選波長為656.28nm的hi譜線和641.63nm的ari譜線,先后提出了譜峰面積、譜峰強(qiáng)度以及譜線方差之比等多個(gè)光譜特征,利于fisher評(píng)價(jià)準(zhǔn)則定量評(píng)價(jià)了各特征值對(duì)焊縫氫致氣孔缺陷的敏感度,基于特征std閾值線實(shí)現(xiàn)了對(duì)焊縫氫氣孔的在線快速監(jiān)測。針對(duì)聲音信號(hào)分別在時(shí)域、頻域及時(shí)頻域開發(fā)了相應(yīng)的特征提取算法。首先,提出了一種基于感興趣的聲音局部信號(hào)lsoi(localsoundofintrests)閾值法統(tǒng)計(jì)特征提取算法,研究了lsoi統(tǒng)計(jì)特征與未焊透及局部下榻缺陷的相關(guān)性;其次,提出了一種基于聲音信號(hào)功率譜密度的頻域分段注意sfsa(soundfrequencysegmentattetion)的統(tǒng)計(jì)特征提取方法,根據(jù)不同的注意機(jī)制,對(duì)weltch功率譜密度頻域區(qū)間進(jìn)行了分段及統(tǒng)計(jì)特征提取,分析了正常熔透及未焊透缺陷與聲音psd頻率的相關(guān)性。提出了一種聲音小波包相對(duì)能量的特征提取及評(píng)價(jià)算法,根據(jù)所選db3小波基函數(shù)及3層分解方式計(jì)算得到了表征不同頻域信號(hào)相對(duì)能量的特征集合e(j),進(jìn)一步提出了最大類間標(biāo)準(zhǔn)差maximumstandarddeviationbetweenclass(msdbc)的特征評(píng)價(jià)準(zhǔn)則,定量評(píng)價(jià)了e(j)對(duì)對(duì)未焊透、正常及焊漏焊縫三種不同的熔透狀態(tài)的可分性,有效剔除了冗余特征。借助于小波包的多域交叉解析能力,發(fā)現(xiàn)7.5~10khz是一段非常重要的頻率區(qū)間,其對(duì)應(yīng)的時(shí)域、頻域及時(shí)頻域信號(hào)特征均對(duì)未焊透及焊漏缺陷表現(xiàn)出高度的相關(guān)性與敏感度。最后基于視覺注意機(jī)制提出的圖像特征參數(shù)roi-1-countrate3、roi-2-countrate3及roi-3-countratio實(shí)現(xiàn)了對(duì)多種焊縫缺陷(焊漏、過熔透及表面氧化的同步檢測。為了挖掘焊接過程“大數(shù)據(jù)”中隱藏的有效信息,選擇有利于學(xué)習(xí)模型的最優(yōu)特征組合,提出了一種數(shù)據(jù)驅(qū)動(dòng)下的混合filter篩選器與wrapper封裝器的hybridimprovedfisherfilterandsvm-cvwrapper(hifscw)特征選擇器。首先,提出了一種自適應(yīng)權(quán)重投票制改進(jìn)fisher法(awvifc)的特征評(píng)價(jià)準(zhǔn)則,作為特征篩選器。其中,根據(jù)統(tǒng)計(jì)的特征投票率,實(shí)現(xiàn)了特征樣本權(quán)重的自適應(yīng)更新,改進(jìn)后的fisher準(zhǔn)則保護(hù)了某些具有較小票數(shù)而較大fisher值的特征,實(shí)現(xiàn)了對(duì)特征的預(yù)篩選。其次,以支持向量機(jī)(svm)作為分類算法,結(jié)合10-fold交叉驗(yàn)證和網(wǎng)格搜索法參數(shù)尋優(yōu),構(gòu)建了作為封裝器的svm-cv分類模型。最后根據(jù)所得的分類準(zhǔn)確率曲線定義了不充足特征子集區(qū)間、互補(bǔ)型特征區(qū)間、最優(yōu)特征子集區(qū)間及冗余特征子集區(qū)間。構(gòu)建了基于特征層融合的電壓-聲音-光譜svm-cv熔透狀態(tài)預(yù)測識(shí)別模型,利用msdbc評(píng)價(jià)準(zhǔn)則篩選得到的特征空間大大簡化了分類融合模型,電壓信息的融入彌補(bǔ)了聲音信息特征識(shí)別未焊透與焊漏的不足。最終在成功預(yù)測缺陷的基礎(chǔ)上,實(shí)現(xiàn)了對(duì)未焊透與焊漏缺陷的精確識(shí)別。缺陷的識(shí)別準(zhǔn)確率從單一傳感模型的74.19%提高到了多傳感融合模型的94.31%。采用焊前打孔預(yù)埋氫化物的方式實(shí)現(xiàn)了對(duì)焊縫氣孔、塌陷及氧化夾渣缺陷的定位可控制造,研究了缺陷產(chǎn)生機(jī)理及其對(duì)應(yīng)信號(hào)特征的奇異性。利用hifscw特征選擇器一方面實(shí)現(xiàn)了最佳特征組合的選擇,另一方面利用其封裝器中的svm-cv分類模型實(shí)現(xiàn)了對(duì)單一及耦合缺陷的預(yù)測和識(shí)別,在最佳特征空間區(qū)間內(nèi),該模型的分類識(shí)別準(zhǔn)確率可達(dá)94.72%。與單一傳感模型相比,融合模型的缺陷識(shí)別準(zhǔn)確率有了較大提高,具有較高魯棒性及穩(wěn)定性。
[Abstract]:Intelligent welding is one of the most important research topics in the field of intelligent manufacturing. Sensing technology and its information processing are the key elements to realize the intelligent and automatic welding process. For example, arc sensing, visual sensing, sound sensing, spectral sensing and so on, these sensors use different information sources to obtain large-scale information related to welding quality, but also inevitably bring about the welding process "big data". Therefore, how to remove a large number of noise and redundant information, more important, how to mine effective trust. In this paper, the pulsed GTAW process of aluminum alloy is studied, and the typical defects in the dynamic process of welding are predicted and identified in real time. Based on spectrum sensing, sound sensing, voltage sensing and visual sensing technology, the welding defects are detected. A set of pulsed GTAW welding test system and multi-information acquisition platform were built to realize automatic control of welding process, automatic acquisition and storage of welding arc spectrum, sound, arc voltage and weld image information. Based on multi-source synchronization information, the generation mechanism of several typical welding defects and the singularity of different signals in time-frequency-time domain are analyzed. A method of signal processing and feature extraction for various sensors is proposed. A spectral statistical feature based on spectral radiation interval SOI (spectral of intrests) of interest is proposed. According to the principle of maximum singularity, eight SOI segments are selected, from which three statistical characteristic parameters, root mean square r, variance D and kurtosis k, are extracted to effectively characterize the average intensity, singularity and morphological characteristics of welding arc SOI radiation; signal reconstruction method based on wavelet packet coief 4 wavelet function 5-level decomposition is used to effectively remove the characteristic pulse. Furthermore, based on the proposed SNR logarithmic characteristic evaluation criterion, the sensitivity of characteristic parameters to weld defects is quantified. Secondly, based on the selected wavelength of 656.28 nm hi line and 641.63 nm ARI line, the spectral peak area, spectral peak intensity and the ratio of spectral line variance are proposed successively, which is beneficial to the determination of Fisher evaluation criterion. The sensitivity of each eigenvalue to weld hydrogen-induced porosity is evaluated quantitatively, and the on-line rapid monitoring of weld hydrogen-induced porosity is realized based on the characteristic STD threshold line. Corresponding feature extraction algorithms are developed for acoustic signals in time domain, frequency domain and time-frequency domain respectively. Firstly, a locally sound local signal LSOI (locally sound local signal of interest) is proposed. Ofintrests thresholding statistical feature extraction algorithm, studied the correlation between LSOI statistical characteristics and underpenetration and local defects; secondly, proposed a frequency domain segmentation attention sfsa (sound frequency segmentation attentions) statistical feature extraction method based on the power spectral density of sound signal, according to different attention mechanisms, the well power was extracted. The frequency domain of spectral density is segmented and extracted, and the correlation between normal penetration and non-penetration defects and PSD frequency is analyzed. A feature extraction and evaluation algorithm of relative energy of acoustic wavelet packet is proposed. The relative energy of signals in different frequency domains is calculated according to the selected db3 wavelet basis function and three-level decomposition method. The feature set E (j) of the quantity is further proposed, and the feature evaluation criterion of maximum standard deviation between classes betweenclass (msdbc) is proposed. The separability of E (j) for three different penetration states, i.e. impermeable, normal and leaky welds, is quantitatively evaluated, and the redundant features are effectively eliminated. It is found that 7.5-10 kHz is a very important frequency range, and its corresponding time-domain, frequency-domain and time-frequency domain signal characteristics show a high degree of correlation and sensitivity to impermeability and weld leakage defects. Finally, the image feature parameters roi-1-countrate3, roi-2-countrate3 and roi-3-countration based on visual attention mechanism are proposed to achieve a variety of features. Synchronous detection of weld defects (leakage, overpenetration and surface oxidation). In order to mine the effective information hidden in the "big data" of the welding process and select the optimal combination of features conducive to the learning model, a data-driven hybrid filter and wrapper packer hybridized Fisher filter dsvm-cvwrapper (hifscw) were proposed. Firstly, an adaptive weighted voting improved Fisher method (awvifc) is proposed as a feature filter. According to the statistical voting rate, the weights of feature samples are updated adaptively. The improved Fisher criterion protects some features with small votes but large Fisher values. Secondly, support vector machine (svm) is used as classification algorithm, and 10-fold cross-validation and grid search method are combined to construct svm-cv classification model as encapsulator. Finally, insufficient feature subset interval, complementary feature interval and optimal feature element are defined according to the classification accuracy curve. The voltage-sound-spectrum svm-cv penetration state prediction and recognition model based on feature layer fusion is constructed. The classification and fusion model is greatly simplified by using the feature space screened by the msdbc evaluation criterion. The integration of voltage information makes up for the shortcomings of sound information feature recognition such as incomplete penetration and welding leakage. Based on the successful prediction of defects, the accurate identification of impermeable and leaky defects was realized. The accuracy of defect identification was improved from 74.19% of single sensor model to 94.31% of multi-sensor fusion model. The mechanism of defect generation and the singularity of corresponding signal features are studied. On the one hand, hifscw feature selector is used to select the best feature combination, on the other hand, the svm-cv classification model in its packer is used to predict and recognize single and coupled defects. In the optimal feature space interval, the model is classified and recognized. Compared with the single sensor model, the fusion model has better robustness and stability.
【學(xué)位授予單位】：上海交通大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：TG441.7
，
本文編號(hào)：2194678
[Abstract]:Intelligent welding is one of the most important research topics in the field of intelligent manufacturing. Sensing technology and its information processing are the key elements to realize the intelligent and automatic welding process. For example, arc sensing, visual sensing, sound sensing, spectral sensing and so on, these sensors use different information sources to obtain large-scale information related to welding quality, but also inevitably bring about the welding process "big data". Therefore, how to remove a large number of noise and redundant information, more important, how to mine effective trust. In this paper, the pulsed GTAW process of aluminum alloy is studied, and the typical defects in the dynamic process of welding are predicted and identified in real time. Based on spectrum sensing, sound sensing, voltage sensing and visual sensing technology, the welding defects are detected. A set of pulsed GTAW welding test system and multi-information acquisition platform were built to realize automatic control of welding process, automatic acquisition and storage of welding arc spectrum, sound, arc voltage and weld image information. Based on multi-source synchronization information, the generation mechanism of several typical welding defects and the singularity of different signals in time-frequency-time domain are analyzed. A method of signal processing and feature extraction for various sensors is proposed. A spectral statistical feature based on spectral radiation interval SOI (spectral of intrests) of interest is proposed. According to the principle of maximum singularity, eight SOI segments are selected, from which three statistical characteristic parameters, root mean square r, variance D and kurtosis k, are extracted to effectively characterize the average intensity, singularity and morphological characteristics of welding arc SOI radiation; signal reconstruction method based on wavelet packet coief 4 wavelet function 5-level decomposition is used to effectively remove the characteristic pulse. Furthermore, based on the proposed SNR logarithmic characteristic evaluation criterion, the sensitivity of characteristic parameters to weld defects is quantified. Secondly, based on the selected wavelength of 656.28 nm hi line and 641.63 nm ARI line, the spectral peak area, spectral peak intensity and the ratio of spectral line variance are proposed successively, which is beneficial to the determination of Fisher evaluation criterion. The sensitivity of each eigenvalue to weld hydrogen-induced porosity is evaluated quantitatively, and the on-line rapid monitoring of weld hydrogen-induced porosity is realized based on the characteristic STD threshold line. Corresponding feature extraction algorithms are developed for acoustic signals in time domain, frequency domain and time-frequency domain respectively. Firstly, a locally sound local signal LSOI (locally sound local signal of interest) is proposed. Ofintrests thresholding statistical feature extraction algorithm, studied the correlation between LSOI statistical characteristics and underpenetration and local defects; secondly, proposed a frequency domain segmentation attention sfsa (sound frequency segmentation attentions) statistical feature extraction method based on the power spectral density of sound signal, according to different attention mechanisms, the well power was extracted. The frequency domain of spectral density is segmented and extracted, and the correlation between normal penetration and non-penetration defects and PSD frequency is analyzed. A feature extraction and evaluation algorithm of relative energy of acoustic wavelet packet is proposed. The relative energy of signals in different frequency domains is calculated according to the selected db3 wavelet basis function and three-level decomposition method. The feature set E (j) of the quantity is further proposed, and the feature evaluation criterion of maximum standard deviation between classes betweenclass (msdbc) is proposed. The separability of E (j) for three different penetration states, i.e. impermeable, normal and leaky welds, is quantitatively evaluated, and the redundant features are effectively eliminated. It is found that 7.5-10 kHz is a very important frequency range, and its corresponding time-domain, frequency-domain and time-frequency domain signal characteristics show a high degree of correlation and sensitivity to impermeability and weld leakage defects. Finally, the image feature parameters roi-1-countrate3, roi-2-countrate3 and roi-3-countration based on visual attention mechanism are proposed to achieve a variety of features. Synchronous detection of weld defects (leakage, overpenetration and surface oxidation). In order to mine the effective information hidden in the "big data" of the welding process and select the optimal combination of features conducive to the learning model, a data-driven hybrid filter and wrapper packer hybridized Fisher filter dsvm-cvwrapper (hifscw) were proposed. Firstly, an adaptive weighted voting improved Fisher method (awvifc) is proposed as a feature filter. According to the statistical voting rate, the weights of feature samples are updated adaptively. The improved Fisher criterion protects some features with small votes but large Fisher values. Secondly, support vector machine (svm) is used as classification algorithm, and 10-fold cross-validation and grid search method are combined to construct svm-cv classification model as encapsulator. Finally, insufficient feature subset interval, complementary feature interval and optimal feature element are defined according to the classification accuracy curve. The voltage-sound-spectrum svm-cv penetration state prediction and recognition model based on feature layer fusion is constructed. The classification and fusion model is greatly simplified by using the feature space screened by the msdbc evaluation criterion. The integration of voltage information makes up for the shortcomings of sound information feature recognition such as incomplete penetration and welding leakage. Based on the successful prediction of defects, the accurate identification of impermeable and leaky defects was realized. The accuracy of defect identification was improved from 74.19% of single sensor model to 94.31% of multi-sensor fusion model. The mechanism of defect generation and the singularity of corresponding signal features are studied. On the one hand, hifscw feature selector is used to select the best feature combination, on the other hand, the svm-cv classification model in its packer is used to predict and recognize single and coupled defects. In the optimal feature space interval, the model is classified and recognized. Compared with the single sensor model, the fusion model has better robustness and stability.
【學(xué)位授予單位】：上海交通大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：TG441.7
，
本文編號(hào)：2194678
本文鏈接：http://sikaile.net/kejilunwen/jinshugongy/2194678.html
最近更新
教材專著
