本文選題：數(shù)控機(jī)床 + 故障診斷��； 參考：《青島理工大學(xué)》2016年博士論文

【摘要】：數(shù)控機(jī)床是指采用數(shù)字控制系統(tǒng)的自動(dòng)化機(jī)床,可實(shí)現(xiàn)自動(dòng)換刀以及復(fù)雜曲線、曲面的加工,具有加工精度高、加工質(zhì)量穩(wěn)定、生產(chǎn)效率高的特點(diǎn),因而成為現(xiàn)代制造生產(chǎn)中的關(guān)鍵技術(shù)設(shè)備,其技術(shù)發(fā)展水平與擁有數(shù)目成為體現(xiàn)一個(gè)國(guó)家工業(yè)現(xiàn)代化水平的重要標(biāo)志。從結(jié)構(gòu)組成來(lái)看,數(shù)控機(jī)床是集機(jī)械、電子、液壓等技術(shù)于一體的復(fù)雜系統(tǒng)。在使用過(guò)程中,任何一個(gè)部分出現(xiàn)故障,均會(huì)影響機(jī)床的正常運(yùn)行,尤其機(jī)械部分出現(xiàn)故障時(shí),長(zhǎng)時(shí)間的停機(jī)檢修,導(dǎo)致整個(gè)生產(chǎn)線停產(chǎn),造成巨大的經(jīng)濟(jì)損失。目前數(shù)控機(jī)床機(jī)械部件仍然廣泛采用定期維護(hù)與定期更換的維修制度,這種維修制度下維修過(guò)度與維修不足的矛盾突出,一方面造成人力與物質(zhì)資源的極大浪費(fèi),另一方面無(wú)法避免數(shù)控機(jī)床突發(fā)性故障的發(fā)生。因此,開展數(shù)控機(jī)床狀態(tài)監(jiān)測(cè)與故障診斷研究,實(shí)現(xiàn)維護(hù)方式由定期更換到預(yù)防維護(hù)、預(yù)知維修的轉(zhuǎn)換是非常必要的。本文以信息融合技術(shù)為基礎(chǔ),對(duì)數(shù)控機(jī)床狀態(tài)監(jiān)測(cè)與故障診斷的策略、信號(hào)處理與特征提取的方法、故障模式智能識(shí)別模型的建立以及全局綜合決策融合方法等進(jìn)行了深入地研究,設(shè)計(jì)了基于多層次信息融合的數(shù)控機(jī)床機(jī)械部件狀態(tài)監(jiān)測(cè)與故障診斷系統(tǒng)。論文從切削力分析入手,根據(jù)數(shù)控機(jī)床載荷多變、高頻沖擊的工況以及加工多樣性的特點(diǎn),得出其切削力傳播路徑上的機(jī)械零部件更易發(fā)生故障的結(jié)論,分析了數(shù)控機(jī)床上機(jī)械零部件與普通設(shè)備故障成因的不同,確定了論文的研究對(duì)象以及故障失效形式。研究了基于振動(dòng)、溫度、電機(jī)電流、伺服誤差等多種參量的故障診斷機(jī)理,并按照參量信息來(lái)源的不同,構(gòu)建了由外部傳感器、內(nèi)部信息、程序參數(shù)以及警報(bào)信息組成的數(shù)控機(jī)床多維感知狀態(tài)監(jiān)測(cè)體系,從機(jī)床本體、刀具磨損、加工過(guò)程、工件加工質(zhì)量等多個(gè)角度、多個(gè)方面反映數(shù)控機(jī)床運(yùn)行狀態(tài),實(shí)現(xiàn)數(shù)控機(jī)床的全方面監(jiān)測(cè),為后續(xù)診斷過(guò)程提供充足的信息。通過(guò)實(shí)驗(yàn)數(shù)據(jù)分析發(fā)現(xiàn)僅用傳統(tǒng)的時(shí)域與頻譜分析不能對(duì)復(fù)合故障進(jìn)行有效地區(qū)分,為進(jìn)一步挖掘隱藏在原始信號(hào)中的故障特征,本文提出了小波包與經(jīng)驗(yàn)?zāi)B(tài)分解聯(lián)合的信號(hào)處理方法,利用小波包對(duì)信號(hào)進(jìn)行降噪,并將小波重構(gòu)信號(hào)擴(kuò)展為高頻與低頻兩個(gè)窄帶信號(hào),再分別對(duì)兩個(gè)窄帶信號(hào)進(jìn)行EMD處理的方法。這種小波包與經(jīng)驗(yàn)?zāi)B(tài)分解聯(lián)合的信號(hào)處理方法,利用小波包對(duì)信號(hào)進(jìn)行降噪,大大提高EMD分解的精度與質(zhì)量,而且通過(guò)重構(gòu)節(jié)點(diǎn)的擴(kuò)展,可以更加細(xì)致地分析故障信息。提取EMD分解后每個(gè)IMF的能量作為特征,與時(shí)域特征、頻域特征組成多域混合特征集合�；谔卣髦g相關(guān)性分析的特征選擇方法,以模糊聚類為主要手段進(jìn)行特征降維,獲取敏感特征子集。根據(jù)數(shù)控機(jī)床需要診斷的對(duì)象及其故障多的特點(diǎn),提出了分級(jí)診斷的策略,將診斷劃分為故障定位、故障類別與程度兩個(gè)層次。主網(wǎng)絡(luò)在對(duì)故障定位的同時(shí),負(fù)責(zé)局部子網(wǎng)絡(luò)模型結(jié)果的聚合;局部子網(wǎng)絡(luò)診斷具體的故障類型與程度。通過(guò)任務(wù)分工與協(xié)作,達(dá)到了簡(jiǎn)化網(wǎng)絡(luò)結(jié)構(gòu)的目的。研究了數(shù)控機(jī)床故障診斷的BP神經(jīng)網(wǎng)絡(luò)模型、RBF神經(jīng)網(wǎng)絡(luò)模型及支持向量機(jī)(SVM)模型的構(gòu)建依據(jù)和方法,以敏感特征作為模型輸入,分別構(gòu)建了基于BP、RBF與SVM的數(shù)控機(jī)床故障診斷主網(wǎng)絡(luò)與局部診斷子網(wǎng)絡(luò)的模型,對(duì)比研究了三種模型對(duì)不同故障類別的診斷能力。建立了基于模糊綜合評(píng)判的全局診斷模型與基于加權(quán)D-S證據(jù)理論的全局診斷模型,進(jìn)一步地提高了故障識(shí)別率。首先針對(duì)數(shù)控機(jī)床模糊綜合評(píng)判建模的難點(diǎn),提出了以多分類器的初步診斷結(jié)果為基礎(chǔ),將評(píng)價(jià)因素由高維特征轉(zhuǎn)變?yōu)榈途S的初級(jí)診斷結(jié)果,降低了模型的復(fù)雜程度,成功構(gòu)建了基于信息融合的數(shù)控機(jī)床單級(jí)模糊綜合評(píng)判故障診斷模型,并提出了從正確性與診斷精度兩個(gè)方面評(píng)價(jià)分類器分類能力的方法,構(gòu)造了基于信息熵的評(píng)價(jià)函數(shù)以及分類器整體平均的權(quán)重分配方法,減少了人為主觀因素的影響。構(gòu)造了分類能力評(píng)價(jià)矩陣,有效地解決了分類器對(duì)不同故障類型識(shí)別率差異較大時(shí)的權(quán)重分配問(wèn)題。針對(duì)證據(jù)理論合成規(guī)則在處理高沖突證據(jù)時(shí),得出結(jié)論與事實(shí)相悖的問(wèn)題,提出了基于加權(quán)的證據(jù)理論診斷模型,以分類器故障識(shí)別率作為權(quán)重對(duì)原始證據(jù)進(jìn)行加權(quán),有效地降低了證據(jù)沖突率,故障識(shí)別率得以提高。搭建了數(shù)控機(jī)床故障診斷實(shí)驗(yàn)系統(tǒng),對(duì)本文所提出的模型與方法進(jìn)行了實(shí)驗(yàn)驗(yàn)證。
[Abstract]:CNC machine tool is an automatic machine tool with digital control system, which can realize automatic knife exchange, complicated curve and surface processing. It has the characteristics of high machining precision, stable processing quality and high production efficiency. Therefore, it has become the key technology equipment in modern manufacturing and production, and its technical development level and the number of ownership become a country. The important symbol of the level of industrial modernization. From the structure composition, the CNC machine tool is a complex system which integrates mechanical, electronic, hydraulic and other technologies. In the process of use, any part of the machine can affect the normal operation of the machine tool, especially when the mechanical part occurs the obstacle, long time stop overhaul, causing the whole production line to stop. Production has caused huge economic losses. At present, the mechanical parts of CNC machine tools are still widely used for regular maintenance and regular replacement. The contradiction between excessive maintenance and insufficient maintenance is prominent under this maintenance system. On the one hand, it causes great waste of human and material resources, and on the other hand it can not avoid the occurrence of sudden failure of CNC machine tools. Therefore, the research of state monitoring and fault diagnosis of CNC machine tools is carried out, and the maintenance mode is changed from regular to preventive maintenance. The transformation of predictive maintenance is very necessary. Based on information fusion technology, the strategy of state monitoring and fault diagnosis of CNC machine tools, the method of signal processing and feature extraction, and intelligent identification of fault mode The establishment of the model and the fusion method of global comprehensive decision making are studied deeply. The system of state monitoring and fault diagnosis of the mechanical parts of CNC machine tools based on multilevel information fusion is designed. The paper starts with the analysis of the cutting force, and draws the characteristics of the variable load, the working condition of the high frequency punching and the diversity of the machining. The conclusion that the mechanical parts of the cutting force propagation path are more prone to failure is analyzed. The causes of the failure of the mechanical parts and the common equipment on the CNC machine tools are analyzed. The research objects and the failure modes of the paper are determined. The fault diagnosis mechanism based on the vibration, temperature, motor current and servo error is studied. According to the different sources of the parameter information, a multi-dimensional sensing state monitoring system of CNC machine tools, consisting of external sensors, internal information, program parameters and alarm information, has been constructed. From the machine tool body, tool wear, processing process, workpiece processing quality and many other angles, many sides reflect the running state of CNC machine tools and realize the whole CNC machine tools. It provides sufficient information for the follow-up diagnosis process. Through the analysis of experimental data, it is found that only the traditional time domain and spectrum analysis can not be effectively divided into the complex faults. In order to further excavate the fault features hidden in the original signal, this paper proposes a signal processing method combining the wavelet packet and the empirical mode decomposition. The wavelet packet is used to denoise the signal, and the wavelet reconstruction signal is extended to two narrow band signals of high frequency and low frequency, and then two narrow band signals are processed by EMD. The signal processing method combining the wavelet packet and the empirical mode decomposition is used to reduce the noise by the wavelet packet, which greatly improves the precision and quality of the EMD decomposition. In addition, the fault information can be analyzed more carefully by the expansion of the node. The energy of each IMF after EMD decomposition is extracted as the feature, and the multi domain mixed feature set is formed with the time domain features and frequency domain features. The feature selection method based on the correlation analysis between features is used as the main means to reduce the feature dimension and obtain the sensitivity. Feature subset. According to the characteristics that the CNC machine needs to diagnose and the characteristics of many faults, the strategy of grading diagnosis is put forward, and the diagnosis is divided into two levels of fault location, fault category and degree. The main network is responsible for the aggregation of the results of local subnetwork model while the fault location is located. Degree. Through task division and cooperation, the purpose of simplifying the network structure is achieved. The BP neural network model, the RBF neural network model and the support vector machine (SVM) model for CNC machine tool fault diagnosis are studied. The fault diagnosis of CNC machine tools based on BP, RBF and SVM is constructed by using the sensitive features as the model input. The model of the main network and the local diagnostic subnetwork is used to compare the diagnosis ability of the three models to different fault categories. The global diagnosis model based on fuzzy comprehensive evaluation and the global diagnosis model based on the weighted D-S evidence theory are established, and the fault recognition rate is further improved. First, the fuzzy comprehensive evaluation modeling of CNC machine tools is established. On the basis of the preliminary diagnosis results of multiple classifiers, the evaluation factors are transformed from high dimensional features to low dimension primary diagnosis results, and the complexity of the model is reduced. A single level fuzzy comprehensive evaluation model for numerical control machine tool based on information fusion is successfully constructed, and the correctness and diagnostic accuracy are two. To evaluate the classification ability of the classifier, the evaluation function based on information entropy and the weight allocation method of the overall average of the classifier are constructed, and the influence of the subjective factors is reduced. The classification ability evaluation matrix is constructed, which effectively solves the weight allocation problem when the classifier differs greatly from the recognition rate of different fault types. When the evidence theory synthesis rule is dealing with the high conflict evidence, the conclusion is contrary to the fact. The weighted evidence theory diagnosis model is put forward, which is weighted to the original evidence with the classifier fault recognition rate as the weight, thus effectively reducing the evidence conflict rate, so the recognition rate of the barrier is improved. The fault of the CNC machine tool is built up. The diagnostic experiment system is tested by the model and method proposed in this paper.

【學(xué)位授予單位】：青島理工大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TG659

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 苑津莎;尚海昆;王瑜;靳松;;基于相關(guān)系數(shù)矩陣和概率神經(jīng)網(wǎng)絡(luò)的局部放電模式識(shí)別[J];電力系統(tǒng)保護(hù)與控制;2013年13期

2 ;斯凱孚(SKF)發(fā)布突破性的軸承狀態(tài)監(jiān)測(cè)技術(shù)——斯凱孚洞悉[J];潤(rùn)滑與密封;2013年05期

3 楊虎;;數(shù)控機(jī)床伺服進(jìn)給系統(tǒng)無(wú)傳感器檢測(cè)技術(shù)[J];制造技術(shù)與機(jī)床;2012年06期

4 邵毅敏;涂文兵;葉軍;;新型智能軸承的結(jié)構(gòu)與監(jiān)測(cè)能力分析[J];軸承;2012年05期

5 張勇;呂家將;;數(shù)控機(jī)床跟蹤誤差大故障分析與排除[J];民營(yíng)科技;2011年12期

6 孫艷杰;艾長(zhǎng)勝;;基于切削聲和切削力參數(shù)融合的刀具磨損狀態(tài)監(jiān)測(cè)[J];組合機(jī)床與自動(dòng)化加工技術(shù);2011年05期

7 孔浩;楊勇;王國(guó)胤;;基于多分類器融合的語(yǔ)音識(shí)別方法研究[J];重慶郵電大學(xué)學(xué)報(bào)(自然科學(xué)版);2011年04期

8 鄧三鵬;蔣永翔;徐小力;吳國(guó)新;;基于級(jí)聯(lián)粗糙集的數(shù)控機(jī)床智能診斷方法的研究[J];機(jī)械與電子;2011年04期

9 郭敏;;多源信息融合在故障診斷技術(shù)中的應(yīng)用研究[J];計(jì)算機(jī)與數(shù)字工程;2011年03期

10 王夢(mèng)琦;王端民;楊雪;;基于改進(jìn)模糊綜合評(píng)判的航空發(fā)動(dòng)機(jī)狀態(tài)評(píng)估[J];潤(rùn)滑與密封;2011年01期

相關(guān)博士學(xué)位論文 前10條

1 戰(zhàn)衛(wèi)俠;鋼絲繩斷絲損傷信號(hào)處理及定量識(shí)別方法研究[D];青島理工大學(xué);2013年

2 黃海鳳;數(shù)控機(jī)床滾珠絲杠副性能退化機(jī)理與評(píng)估技術(shù)研究[D];西南交通大學(xué);2013年

3 謝小正;數(shù)控機(jī)床主軸組件故障的知識(shí)發(fā)現(xiàn)研究[D];蘭州理工大學(xué);2013年

4 陳侃;基于多模型決策融合的刀具磨損狀態(tài)監(jiān)測(cè)系統(tǒng)關(guān)鍵技術(shù)研究[D];西南交通大學(xué);2012年

5 吳文杰;基于信息融合的航空發(fā)動(dòng)機(jī)故障診斷方法[D];電子科技大學(xué);2011年

6 吳勝?gòu)?qiáng);核主元分析及證據(jù)理論的多域特征故障診斷新方法研究[D];燕山大學(xué);2011年

7 劉思遠(yuǎn);信息融合和貝葉斯網(wǎng)絡(luò)集成的故障診斷理論方法及實(shí)驗(yàn)研究[D];燕山大學(xué);2010年

8 雷亞國(guó);混合智能技術(shù)及其在故障診斷中的應(yīng)用研究[D];西安交通大學(xué);2007年

9 王志華;基于模式識(shí)別的柴油機(jī)故障診斷技術(shù)研究[D];武漢理工大學(xué);2004年

10 李宏坤;基于信息融合技術(shù)船舶柴油機(jī)故障診斷方法的研究與應(yīng)用[D];大連理工大學(xué);2003年

相關(guān)碩士學(xué)位論文 前10條

1 溫國(guó)強(qiáng);基于多信息源的滾動(dòng)軸承故障診斷方法與實(shí)驗(yàn)研究[D];青島理工大學(xué);2013年

2 吳麗媛;基于粗糙集神經(jīng)網(wǎng)絡(luò)的數(shù)控機(jī)床滾珠絲杠副故障診斷研究[D];青島理工大學(xué);2012年

3 張磊;數(shù)控機(jī)床故障監(jiān)測(cè)與診斷系統(tǒng)的研究[D];山東大學(xué);2012年

4 袁外琳;基于路面材料檢測(cè)系統(tǒng)的遠(yuǎn)程測(cè)控與數(shù)據(jù)融合時(shí)間對(duì)準(zhǔn)[D];長(zhǎng)安大學(xué);2011年

5 楊慧斌;滾動(dòng)軸承故障診斷中的特征提取與選擇方法[D];湖南工業(yè)大學(xué);2011年

6 吳希曦;高檔數(shù)控機(jī)床關(guān)鍵部件故障智能診斷技術(shù)研究[D];西南交通大學(xué);2011年

7 黃柏權(quán);基于性能退化模型的數(shù)控機(jī)床滾珠絲杠副壽命預(yù)測(cè)研究[D];西南交通大學(xué);2011年

8 祁美玲;智能故障診斷融合技術(shù)在數(shù)控機(jī)床故障診斷中的應(yīng)用[D];大連交通大學(xué);2010年

9 張馳;數(shù)控機(jī)床典型故障分析與診斷系統(tǒng)設(shè)計(jì)[D];青島理工大學(xué);2010年

10 林選;基于小波包和EMD相結(jié)合的電機(jī)軸承故障診斷[D];太原理工大學(xué);2010年

，

本文編號(hào)：1867034