本文關(guān)鍵詞：電弧焊熔透狀態(tài)視覺檢測(cè)模型研究　出處：《廣東工業(yè)大學(xué)》2015年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 焊接質(zhì)量 熔透狀態(tài) 模式識(shí)別 ICA算法 BP神經(jīng)網(wǎng)絡(luò)

【摘要】：焊接是制造業(yè)的基礎(chǔ)。隨著工業(yè)制造要求的提高,焊接質(zhì)量的要求也變得越來越重要。電弧焊由于自身技術(shù)發(fā)展十分成熟,且適用的范圍也十分廣泛,目前應(yīng)用在諸多領(lǐng)域。因此,人們對(duì)電弧焊的焊接質(zhì)量提出了更高的要求。在越來越注重效率的今天,電弧焊焊接實(shí)時(shí)監(jiān)測(cè)顯得愈發(fā)重要,為此論文研究基于機(jī)器視覺傳感的熔透狀態(tài)監(jiān)測(cè)模型。在實(shí)時(shí)監(jiān)測(cè)焊接質(zhì)量的過程中,必須通過當(dāng)前的焊接狀態(tài)與焊接質(zhì)量之間的關(guān)系建立數(shù)學(xué)模型以獲取熔透實(shí)時(shí)監(jiān)測(cè)狀態(tài)。許多研究表明,焊接過程中形成的熔池與焊縫背部的熔透有著密切的聯(lián)系,而熔透與最終的焊接質(zhì)量聯(lián)系緊密,因此通過提取的熔池特征能與當(dāng)前的焊接質(zhì)量建立對(duì)應(yīng)關(guān)系。通過視覺傳感器拍攝焊接過程的熔池圖像,利用相關(guān)的圖像處理技術(shù)從中提取出最能代表熔池信息的特征參數(shù),再與此時(shí)的焊接質(zhì)量對(duì)應(yīng)起來,建立熔池特征與熔透狀態(tài)之間的數(shù)學(xué)模型。通過多組焊接試驗(yàn)條件驗(yàn)證模型,證明建立的數(shù)學(xué)模型能夠有效地預(yù)測(cè)出當(dāng)前的熔透狀態(tài),最終得到當(dāng)前的焊接質(zhì)量。對(duì)熔透當(dāng)前的狀態(tài)進(jìn)行實(shí)時(shí)監(jiān)測(cè)可以看作是模式識(shí)別的一類,而神經(jīng)網(wǎng)絡(luò)則在模式識(shí)別這一方面有著較高的預(yù)測(cè)精度,因此論文根據(jù)神經(jīng)網(wǎng)絡(luò)的特點(diǎn)設(shè)計(jì)了兩個(gè)不同訓(xùn)練算法的神經(jīng)網(wǎng)絡(luò)：BP算法(Back Propagation Algorithm)和ICA算法(Imperialist Competitive Algorithm),利用神經(jīng)網(wǎng)絡(luò)模型對(duì)熔透狀態(tài)進(jìn)行準(zhǔn)確預(yù)測(cè)。其中,ICA算法是通過模擬帝國(guó)主義競(jìng)爭(zhēng)的過程來得到優(yōu)化問題最優(yōu)解的一種全局優(yōu)化搜索算法。首先,從熔池圖像中提取出3個(gè)特征參數(shù)：熔池面積、熔池熔寬、熔池半長(zhǎng)。其次,采用試湊法確定神經(jīng)網(wǎng)絡(luò)隱含層神經(jīng)元個(gè)數(shù),建立一個(gè)預(yù)測(cè)精度較高的神經(jīng)網(wǎng)絡(luò)模型,最后用兩個(gè)算法訓(xùn)練神經(jīng)網(wǎng)絡(luò),獲得兩個(gè)模型對(duì)熔透各自的識(shí)別率。試驗(yàn)結(jié)果表明選用的BP神經(jīng)網(wǎng)絡(luò)最優(yōu)識(shí)別模型比ICA神經(jīng)網(wǎng)絡(luò)的最優(yōu)模型對(duì)不同焊接條件的熔透狀態(tài)有著很高的預(yù)測(cè)精度。針對(duì)BP神經(jīng)網(wǎng)絡(luò)的識(shí)別精度高但過于依賴初始權(quán)值閾值的特點(diǎn)和ICA算法在全局搜索的優(yōu)點(diǎn),論文將ICA算法與BP神經(jīng)網(wǎng)絡(luò)結(jié)合,利用ICA算法選取BP神經(jīng)網(wǎng)絡(luò)初始權(quán)值及閾值,提出一種ICA-BP神經(jīng)網(wǎng)絡(luò)的熔透識(shí)別模型。首先將模型的權(quán)值閾值作為優(yōu)化問題要求的解,然后根據(jù)熔透狀態(tài)輸出的實(shí)際誤差與期望誤差的差的大小及時(shí)調(diào)整權(quán)值及閾值。其次利用ICA得到神經(jīng)網(wǎng)絡(luò)的初始權(quán)值、閾值,通過BP算法對(duì)神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練,得到使得模型識(shí)別精度最高的一組權(quán)值和閾值。最終利用不同試驗(yàn)條件尋找對(duì)熔透的識(shí)別效果最好的神經(jīng)網(wǎng)絡(luò)模型。試驗(yàn)結(jié)果證明ICA-BP神經(jīng)網(wǎng)絡(luò)對(duì)熔透狀態(tài)的預(yù)測(cè)精度優(yōu)于BP神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)精度。
[Abstract]:Welding is the foundation of the manufacturing industry. With the improvement of industrial manufacturing requirements, the requirement of welding quality is becoming more and more important. Arc welding is widely used in many fields because of its mature technology and wide range of application. Therefore, people have put forward higher requirements for the welding quality of arc welding. Nowadays, more and more attention is paid to efficiency. The real-time monitoring of arc welding is becoming more and more important. Therefore, a penetration monitoring model based on machine vision sensing is studied in this paper. In real-time monitoring of welding quality, we must establish a mathematical model through the relationship between the current welding state and the welding quality, so as to get the real-time monitoring state of penetration. Many studies have shown that the weld pool formed during the welding process is closely related to the penetration of the back of the weld, and the penetration is closely related to the final welding quality. Therefore, the characteristics of the molten pool can be used to establish the corresponding relationship with the current welding quality. The image of molten pool is captured by visual sensor, and the characteristic parameters that represent the information of molten pool are extracted from related image processing technology. Then the mathematical model between molten pool characteristics and penetration state is established based on the corresponding welding quality. Through multi group welding test condition verification model, it is proved that the established mathematical model can effectively predict the current penetration state, and finally get the current welding quality. The current penetration state monitoring can be regarded as a kind of pattern recognition, pattern recognition and neural network in this area has a higher prediction accuracy, so this paper according to the characteristics of the neural network to design a neural network with two different training algorithms: BP algorithm (Back Propagation Algorithm) and ICA algorithm (Imperialist Competitive, Algorithm) by using the neural network model to forecast the penetration state. Among them, ICA algorithm is a global optimization search algorithm to optimize the optimal solution by simulating the process of imperialist competition. First, extract 3 feature parameters from the image of weld pool in molten pool area, pool and pool half length Rongkuan. Secondly, we use the trial and error method to determine the number of neurons in the hidden layer of the neural network, and establish a neural network model with high prediction accuracy. Finally, we use two algorithms to train the neural network, and get the recognition rates of two models for penetration. The experimental results show that the optimal identification model of BP neural network is higher than that of ICA neural network, and has high prediction accuracy for penetration condition of different welding conditions. According to the characteristics and advantages of the ICA search algorithm of BP neural network with high accuracy but is too dependent on the initial weights in the global threshold, the ICA algorithm combined with BP neural network, using ICA algorithm to select BP neural network initial weights and threshold, proposes a ICA-BP neural network fusion recognition model. First, the weight threshold of the model is used as the solution of the optimization problem, and then the weights and thresholds are adjusted according to the difference between the actual error and the expected error of the penetration state output. Secondly, we use ICA to get the initial weights and thresholds of neural network, and train the neural network through BP algorithm, and get a set of weights and thresholds that make the model identification accuracy the highest. Finally, different experimental conditions are used to find the neural network model which has the best recognition effect on penetration. The experimental results show that the prediction accuracy of ICA-BP neural network is better than that of BP neural network.
【學(xué)位授予單位】：廣東工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類號(hào)】：TG441.7;TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 胡笑寒,郭偉;神經(jīng)網(wǎng)絡(luò)在紡織外貿(mào)企業(yè)競(jìng)爭(zhēng)戰(zhàn)略中的應(yīng)用[J];鄭州紡織工學(xué)院學(xué)報(bào);2000年04期

2 羅公亮;從神經(jīng)網(wǎng)絡(luò)到支撐矢量機(jī)(下)[J];冶金自動(dòng)化;2002年01期

3 楊旭華,戴華平,孫優(yōu)賢;基于神經(jīng)網(wǎng)絡(luò)的發(fā)酵時(shí)間和最優(yōu)發(fā)酵溫度模型[J];化工自動(dòng)化及儀表;2004年01期

4 孫波,陳靜,鐘建輝,陳樺;軸類零件設(shè)計(jì)耦合神經(jīng)網(wǎng)絡(luò)的實(shí)例分類模型[J];輕工機(jī)械;2004年01期

5 段善寧,汪玉春;神經(jīng)網(wǎng)絡(luò)技術(shù)在儲(chǔ)運(yùn)工程中的應(yīng)用綜述[J];天然氣與石油;2004年04期

6 吳孟武;周華民;趙朋;李德群;;塑料熔體黏度的神經(jīng)網(wǎng)絡(luò)擬合[J];塑料科技;2007年02期

7 姚尚鋒;楊占營(yíng);鄒彪;;多屬性裝備質(zhì)量綜合評(píng)價(jià)的神經(jīng)網(wǎng)絡(luò)方法[J];廣西輕工業(yè);2007年12期

8 鄧建長(zhǎng);劉海波;;對(duì)礦山安全評(píng)價(jià)中神經(jīng)網(wǎng)絡(luò)的改進(jìn)[J];湖南安全與防災(zāi);2008年05期

9 顧玉鋼;夏智海;莊力健;;基于改進(jìn)神經(jīng)網(wǎng)絡(luò)的疲勞裂紋擴(kuò)展速率預(yù)測(cè)[J];合肥工業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年06期

10 王小完;楊樺;;神經(jīng)網(wǎng)絡(luò)技術(shù)在礦體邊界圈定中的應(yīng)用研究[J];金屬礦山;2009年02期

相關(guān)會(huì)議論文 前10條

1 王雷;陳宗海;;神經(jīng)網(wǎng)絡(luò)在過程系統(tǒng)建模中的應(yīng)用綜述[A];'2002系統(tǒng)仿真技術(shù)及其應(yīng)用學(xué)術(shù)論文集（第四卷）[C];2002年

2 周宗潭;胡德文;;自組織的神經(jīng)網(wǎng)絡(luò)方法和群落生長(zhǎng)模型研究[A];1995年中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議暨智能自動(dòng)化專業(yè)委員會(huì)成立大會(huì)論文集（上冊(cè)）[C];1995年

3 侯媛彬;易繼鍇;楊玉珍;陳雙葉;韓崇昭;;一種能消除混沌現(xiàn)象的神經(jīng)網(wǎng)絡(luò)[A];1996年中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議論文集（上冊(cè)）[C];1996年

4 江銘炎;江銘虎;;一種神經(jīng)網(wǎng)絡(luò)特征壓縮及分類的研究[A];1998年中國(guó)智能自動(dòng)化學(xué)術(shù)會(huì)議論文集（上冊(cè)）[C];1998年

5 陳文新;王長(zhǎng)富;戴蓓倩;;基于神經(jīng)網(wǎng)絡(luò)的漢語四聲識(shí)別[A];第一屆全國(guó)語言識(shí)別學(xué)術(shù)報(bào)告與展示會(huì)論文集[C];1990年

6 劉豐;姜建新;程俊;易克初;;一種用于語音識(shí)別的神經(jīng)網(wǎng)絡(luò)[A];第二屆全國(guó)人機(jī)語音通訊學(xué)術(shù)會(huì)議論文集[C];1992年

7 梁循;;神經(jīng)網(wǎng)絡(luò)中訓(xùn)練樣本空間的分割特性及其應(yīng)用[A];1995中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];1995年

8 黃小原;肖四漢;樊治平;;神經(jīng)網(wǎng)絡(luò)預(yù)警系統(tǒng)及其應(yīng)用[A];1995中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];1995年

9 李艷;邵日祥;方建安;邵世煌;;神經(jīng)網(wǎng)絡(luò)在功率電子及拖動(dòng)控制中的應(yīng)用[A];1996中國(guó)控制與決策學(xué)術(shù)年會(huì)論文集[C];1996年

10 高文忠;顧樹生;平力;;靜態(tài)神經(jīng)網(wǎng)絡(luò)新算法及其收斂性初探[A];1994年中國(guó)控制會(huì)議論文集[C];1994年

相關(guān)重要報(bào)紙文章 前10條

1 美國(guó)明尼蘇達(dá)大學(xué)社會(huì)學(xué)博士 密西西比州立大學(xué)國(guó)家戰(zhàn)略規(guī)劃與分析研究中心資深助理研究員 陳心想;維護(hù)好創(chuàng)新的“神經(jīng)網(wǎng)絡(luò)硬件”[N];中國(guó)教師報(bào);2014年

2 盧業(yè)忠;腦控電腦 驚世駭俗[N];計(jì)算機(jī)世界;2001年

3 葛一鳴 路邊文;人工神經(jīng)網(wǎng)絡(luò)將大顯身手[N];中國(guó)紡織報(bào);2003年

4 中國(guó)科技大學(xué)計(jì)算機(jī)系　邢方亮;神經(jīng)網(wǎng)絡(luò)挑戰(zhàn)人類大腦[N];計(jì)算機(jī)世界;2003年

5 記者 孫剛;“神經(jīng)網(wǎng)絡(luò)”：打開復(fù)雜工藝“黑箱”[N];解放日?qǐng)?bào);2007年

6 本報(bào)記者 劉霞;美用DNA制造出首個(gè)人造神經(jīng)網(wǎng)絡(luò)[N];科技日?qǐng)?bào);2011年

7 健康時(shí)報(bào)特約記者　 張獻(xiàn)懷;干細(xì)胞移植：修復(fù)受損的神經(jīng)網(wǎng)絡(luò)[N];健康時(shí)報(bào);2006年

8 劉力;我半導(dǎo)體神經(jīng)網(wǎng)絡(luò)技術(shù)及應(yīng)用研究達(dá)國(guó)際先進(jìn)水平[N];中國(guó)電子報(bào);2001年

9 ;神經(jīng)網(wǎng)絡(luò)和模糊邏輯[N];世界金屬導(dǎo)報(bào);2002年

10 鄒麗梅 陳耀群;江蘇科大神經(jīng)網(wǎng)絡(luò)應(yīng)用研究通過鑒定[N];中國(guó)船舶報(bào);2006年

相關(guān)博士學(xué)位論文 前10條

1 曾U喺，

本文編號(hào)：1345270