發(fā)布時間：2018-03-30 01:08

  本文選題：深孔鉆削　切入點(diǎn)：主軸電機(jī)電流　出處：《西安理工大學(xué)》2017年碩士論文

【摘要】：在制造業(yè)智能化、信息化的背景下,通過在生產(chǎn)制造過程中采集與制造相關(guān)的信息數(shù)據(jù),利用這些信息數(shù)據(jù)達(dá)到對生產(chǎn)過程進(jìn)行監(jiān)測,并在這些數(shù)據(jù)中得到生產(chǎn)過程出現(xiàn)的問題時對生產(chǎn)過程做出調(diào)整有著重要的作用。機(jī)械切削加工中,刀具作為直接與加工表面接觸的部分,刀具也是整個加工系統(tǒng)中最薄弱的環(huán)節(jié),要使自動化的加工過程高效穩(wěn)定地進(jìn)行,研究和開發(fā)加工過程中刀具狀態(tài)監(jiān)測技術(shù)就顯得尤為重要。而現(xiàn)有的刀具狀態(tài)監(jiān)測技術(shù)大多針對車削、銑削加工,很少有針對深孔鉆削的刀具狀態(tài)監(jiān)測方法。本文針對BTA深孔加工的特點(diǎn),整個加工過程在封閉的環(huán)境中進(jìn)行,刀具的磨損狀態(tài)無法直接觀察,由主軸電機(jī)電流與鉆頭磨損之間內(nèi)在關(guān)系,直接從電機(jī)驅(qū)動器中采集了鉆削過程中主軸電機(jī)電流信號作為監(jiān)測信號,并介紹了一種將信號進(jìn)行連續(xù)小波變換的信號分析方法與卷積神經(jīng)網(wǎng)絡(luò)的模式識別方法相融合的刀具狀態(tài)監(jiān)測方法。建立了基于深孔鉆削數(shù)控機(jī)床的數(shù)控系統(tǒng)通訊模塊的主軸電機(jī)電流信號采集系統(tǒng),通過鉆削實(shí)驗(yàn)獲取了主軸電機(jī)電流信號,對采集得到的主軸電流信號進(jìn)行初步分析,記錄了鉆削過程鉆頭磨損量,獲取了鉆頭的磨損規(guī)律信息。結(jié)合鉆頭在不同磨損階段的主軸電流信號特征以及信號時域分析和頻域分析的不足,為了描述信號頻率隨時間的變化規(guī)律,獲取鉆頭的磨損規(guī)律信息及變化特征,采用連續(xù)小波變換,得到不同磨損階段的小波尺度譜。并在連續(xù)小波變換中,通過不同小波基函數(shù)的特征,確定了最佳小波基函數(shù),利用小波信號熵的方法確定了最優(yōu)小波分解層數(shù)。分析結(jié)果發(fā)現(xiàn),鉆頭在不同磨損階段的小波尺度譜表現(xiàn)出了很明顯的不同,很好的反映了信號頻率隨時間變化規(guī)律。在信號小波尺度譜中高頻成分隨時間逐漸減小,而中頻成分則在逐漸增加,很好的映射了鉆頭磨損規(guī)律。針對小波尺度譜在不同磨損階段的明顯不同,直接將小波尺度譜作為狀態(tài)特征,省去了在模式識別前的前處理過程,結(jié)合卷積神經(jīng)網(wǎng)絡(luò)很好地識別圖像的特性,特征提取和模式識別過程都在網(wǎng)絡(luò)結(jié)構(gòu)中完成。將采集到的信號的小波尺度譜,一部分作為訓(xùn)練集,一部分作為訓(xùn)練集,通過訓(xùn)練和測試結(jié)果確定了網(wǎng)絡(luò)結(jié)構(gòu),包括:網(wǎng)絡(luò)卷積層層數(shù)、網(wǎng)絡(luò)卷積核大小以及網(wǎng)絡(luò)卷積核個數(shù)。對訓(xùn)練完成的各層輸出特征圖可視化分析,發(fā)現(xiàn)圖像經(jīng)過各層卷積和采樣之后,圖像像素點(diǎn)減少,但是不同的卷積提取不同的圖像特征,多個卷積核保證了圖像信息的完整性,卷積神經(jīng)網(wǎng)絡(luò)在經(jīng)過訓(xùn)練之后可以很好的提取圖像特征。最后利用訓(xùn)練好的網(wǎng)絡(luò)對一個全新鉆頭的完整鉆削壽命周期中不同磨損狀態(tài)進(jìn)行識別,達(dá)到了很好的識別效果。
[Abstract]:Under the background of manufacturing intelligence and information, through collecting the information data related to manufacturing in the manufacturing process, the information data can be used to monitor the production process. It is very important to adjust the production process when we get the problems in the production process in these data. In machining, the tool is the part that is in direct contact with the machined surface. The tool is also the weakest link in the whole machining system, so the automatic machining process should be carried out efficiently and stably. The research and development of tool condition monitoring technology is particularly important in the process of machining, and most of the existing tool condition monitoring technology is aimed at turning and milling. There are few tool condition monitoring methods for deep hole drilling. According to the characteristics of BTA deep hole machining, the whole machining process is carried out in a closed environment, and the tool wear state can not be observed directly. According to the inherent relationship between spindle motor current and bit wear, the signal of spindle motor current in drilling process is collected directly from the motor driver as the monitoring signal. This paper also introduces a tool condition monitoring method which combines the signal analysis method of continuous wavelet transform and the pattern recognition method of convolution neural network. The NC system based on deep hole drilling NC machine tool is established. The main shaft motor current signal acquisition system based on signal module, The spindle motor current signal was obtained by drilling experiment, and the spindle current signal was preliminarily analyzed, and the bit wear amount during drilling process was recorded. According to the characteristics of spindle current signal in different wear stages of bit and the deficiency of signal analysis in time domain and frequency domain, in order to describe the variation law of signal frequency with time, the information of wear law of bit is obtained. The wavelet scale spectrum of different wear stages is obtained by means of continuous wavelet transform, and the best wavelet basis function is determined by the characteristics of different wavelet basis functions in continuous wavelet transform. Wavelet signal entropy is used to determine the optimal number of wavelet decomposition layers. The results show that the wavelet scale spectrum of bit is very different in different wear stages. In the wavelet scale spectrum of signal, the high frequency component decreases gradually with time, while the intermediate frequency component increases gradually. According to the obvious difference of wavelet scale spectrum in different wear stages, wavelet scale spectrum is taken as the state feature directly, and the pre-processing process before pattern recognition is eliminated. The feature extraction and pattern recognition process are completed in the network structure. The wavelet scale spectrum of the collected signal is regarded as the training set and the other part as the training set, and the wavelet scale spectrum of the acquired signal is regarded as the training set, and the wavelet scale spectrum of the acquired signal is regarded as the training set. The network structure is determined by training and testing results, including: network convolution layer number, network convolution kernel size and network convolution core number. It is found that the pixel points of the image decrease after each layer of convolution and sampling, but different convolution extracts different image features, and the integrity of image information is guaranteed by multiple convolution cores. After training, the convolution neural network can extract image features well. Finally, using the trained neural network to identify the different wear states in the whole drilling life cycle of a new bit, the recognition effect is very good.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TG523;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 余子健;馬德;嚴(yán)曉浪;沈君成;;基于FPGA的卷積神經(jīng)網(wǎng)絡(luò)加速器[J];計(jì)算機(jī)工程;2017年01期

2 唐亮;傅攀;李敏;;基于小波包和PSO優(yōu)化神經(jīng)網(wǎng)絡(luò)的刀具狀態(tài)監(jiān)測[J];中國測試;2016年03期

3 謝楠;馬飛;段明雷;李愛平;;基于主成分分析與C-支持向量機(jī)的刀具磨損狀態(tài)監(jiān)測[J];同濟(jì)大學(xué)學(xué)報(自然科學(xué)版);2016年03期

4 姜楓;張麗紅;;基于隨機(jī)Dropout卷積神經(jīng)網(wǎng)絡(luò)的人體行為識別方法研究[J];測試技術(shù)學(xué)報;2016年01期

5 何翔;任小洪;;基于數(shù)字圖像的刀具磨損狀態(tài)檢測技術(shù)[J];機(jī)床與液壓;2016年03期

6 李岳云;許悅雷;馬時平;史鶴歡;;深度卷積神經(jīng)網(wǎng)絡(luò)的顯著性檢測[J];中國圖象圖形學(xué)報;2016年01期

7 史鶴歡;許悅雷;馬時平;李岳云;李帥;;PCA預(yù)訓(xùn)練的卷積神經(jīng)網(wǎng)絡(luò)目標(biāo)識別算法[J];西安電子科技大學(xué)學(xué)報;2016年03期

8 周偉民;李小麗;;智能制造技術(shù):抓住新產(chǎn)業(yè)革命的核心技術(shù)[J];中國戰(zhàn)略新興產(chǎn)業(yè);2015年09期

9 黃曉斌;沈興全;苗鴻賓;陳振亞;邵振宇;;EA4T空心車軸深孔加工刀具磨損特征的研究[J];工具技術(shù);2014年08期

10 張曙;;工業(yè)4.0和智能制造[J];機(jī)械設(shè)計(jì)與制造工程;2014年08期

相關(guān)博士學(xué)位論文 前1條

1 鄭建明;基于HMM的多特征融合鉆頭磨損監(jiān)測技術(shù)的研究[D];西安理工大學(xué);2004年

相關(guān)碩士學(xué)位論文 前2條

1 鄧柳;基于深度卷積神經(jīng)網(wǎng)絡(luò)的車型識別[D];西南交通大學(xué);2015年

2 孫麗萍;轉(zhuǎn)子故障的小波尺度譜數(shù)字特征提取與診斷技術(shù)研究[D];南京航空航天大學(xué);2010年

，

本文編號：1683666