發(fā)布時(shí)間：2018-01-05 02:18

  本文關(guān)鍵詞：基于神經(jīng)網(wǎng)絡(luò)模型的振動(dòng)篩損傷檢測(cè)研究　出處：《太原理工大學(xué)》2012年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 振動(dòng)篩 非線性特性 系統(tǒng)辨識(shí) 神經(jīng)網(wǎng)絡(luò) 故障診斷

【摘要】：隨著機(jī)械制造技術(shù)的提高和現(xiàn)代工業(yè)發(fā)展的需求,機(jī)械設(shè)備的結(jié)構(gòu)愈來愈復(fù)雜,生產(chǎn)的高效率依賴機(jī)械設(shè)備提供的強(qiáng)大生產(chǎn)能力,設(shè)備的任何故障都會(huì)給生產(chǎn)帶來巨大的損失。因此,在生產(chǎn)中對(duì)設(shè)備進(jìn)行故障診斷是非常有意義的。故障診斷技術(shù)能夠在監(jiān)測(cè)設(shè)備運(yùn)行狀態(tài)的基礎(chǔ)上,分析和診斷出機(jī)械設(shè)備的故障狀態(tài)以及故障發(fā)展的程度。 目前以時(shí)域和頻域分析為主的方法研究具有強(qiáng)非線性特性系統(tǒng)的故障診斷不是很好。本文利用系統(tǒng)辨識(shí)建立振動(dòng)篩縮小模型系統(tǒng)的模型,通過分析辨識(shí)模型的特性,對(duì)直線振動(dòng)篩進(jìn)行故障診斷和裂紋發(fā)展趨勢(shì)研究。 為了從采集到的信號(hào)中提取出特征信息,首先對(duì)實(shí)驗(yàn)測(cè)得的振動(dòng)信號(hào)做預(yù)處理分析,將數(shù)據(jù)進(jìn)行歸一化,然后用小波消噪方法對(duì)信號(hào)消噪、采用最小二乘法消除信號(hào)的趨勢(shì)項(xiàng),最后去除信號(hào)的直流分量。 研究振動(dòng)篩縮小模型下橫梁存在裂紋時(shí)系統(tǒng)的辨識(shí)方法。分別運(yùn)用線性模型、非線性模型、神經(jīng)網(wǎng)絡(luò)模型對(duì)振動(dòng)篩系統(tǒng)進(jìn)行建模,通過分析模型和實(shí)際系統(tǒng)的擬合度,得出神經(jīng)網(wǎng)絡(luò)模型的精度較高。進(jìn)一步通過判斷不同神經(jīng)網(wǎng)絡(luò)辨識(shí)模型的擬合度、檢測(cè)殘差等,選擇神經(jīng)網(wǎng)絡(luò)NNARX模型。最后確定了該模型的各個(gè)參數(shù)(包括網(wǎng)絡(luò)層數(shù)、隱層神經(jīng)元個(gè)數(shù)、激活函數(shù)等)以及各參數(shù)對(duì)辨識(shí)精度的影響。 在振動(dòng)篩縮小模型下橫梁有無裂紋時(shí),分別辨識(shí)出系統(tǒng)的神經(jīng)網(wǎng)絡(luò)模型,通過分析振動(dòng)篩在不同狀態(tài)下實(shí)測(cè)振動(dòng)信號(hào)的幅值譜、辨識(shí)模型的虛擬響應(yīng)譜、模型的權(quán)值,得出分析辨識(shí)模型的特性可以作為判斷振動(dòng)篩是否有裂紋的依據(jù)。 最后,將分析模型特性的方法應(yīng)用到實(shí)際振動(dòng)篩裂紋發(fā)展趨勢(shì)的研究上。辨識(shí)出實(shí)際振動(dòng)篩存在裂紋時(shí)的模型,以天數(shù)增加的方式獲取振動(dòng)篩的振動(dòng)信號(hào),研究辨識(shí)模型在不同時(shí)刻時(shí)權(quán)值的變化,經(jīng)統(tǒng)計(jì)分析得出,隨著時(shí)間的增加,模型的權(quán)值呈逐漸減小且集中的趨勢(shì)。實(shí)驗(yàn)表明,通過分析辨識(shí)模型的權(quán)值來研究振動(dòng)篩裂紋的發(fā)展趨勢(shì)是可行的,也是有意義的。
[Abstract]:With the increase of mechanical manufacturing technology and the needs of modern industrial development, more and more complicated structure of mechanical equipment, strong production capacity of the production of high-efficiency rely on mechanical devices, any equipment failure will bring huge loss to the production. Therefore, the fault diagnosis of the equipment in production is very meaningful for fault diagnosis. Based on the technology can monitor equipment running condition, analyze and diagnose the fault state of mechanical equipment fault and the degree of development.
Research on fault diagnosis method of the time domain and frequency domain analysis which has strong nonlinear characteristics of the system is not very good. In this paper, using system identification to establish vibration sieve scale model system model, by analyzing the characteristics of the two models, the research of fault diagnosis and crack development trend of linear vibrating screen.
In order to extract the feature information from the collected signal, first preprocessing analysis of vibration signal measured, the data were normalized, and then use the wavelet denoising method for signal denoising, eliminating trend signal by using the least square method, finally removing DC component signal.
Study on vibration sieve narrow crack identification method of system model under the beam. By using linear model, nonlinear model, neural network model of vibrating screen system, through the analysis of model and actual system fitting degree, that neural network model is of higher precision. Further by judging the different neural network model fitting. Detection and selection of NNARX neural network model. Finally, the parameters of the model are determined (including network layers, number of neurons in hidden layer activation function, etc.) and the influence of parameters on the identification accuracy.
In the narrow beam model crack free vibration sieve, respectively, to identify the neural network model of the system, through the analysis of vibration sieve in the condition of different amplitude of vibration signal spectrum, virtual spectrum response identification model, model weights, the characteristic analysis of identification model could be used to judge whether there are cracks on the vibration sieve.
Finally, the research methods of the characteristic analysis model is applied to the actual vibration sieve crack on the trend of development. To identify the actual vibration sieve crack model, vibration signal acquisition of vibrating screen to increase in the number of days the way, change of identification model in different time weights, according to statistical analysis, with the increase of time. The model weight decreases gradually and the concentration trend. Experimental results show that the development trend by analyzing the identification model of the weights of the vibration sieve crack is feasible, but also meaningful.

【學(xué)位授予單位】：太原理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2012
【分類號(hào)】：TH237.6;TH165.3

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 劉丹;;基于一種改進(jìn)的BP神經(jīng)網(wǎng)絡(luò)的飛機(jī)目標(biāo)識(shí)別[J];中國高新技術(shù)企業(yè);2011年16期

2 鄭潤娜;陳仕彬;;直線振動(dòng)細(xì)篩設(shè)計(jì)[J];機(jī)械制造與自動(dòng)化;2011年03期

3 戴志超;;神經(jīng)網(wǎng)絡(luò)對(duì)水電機(jī)組振動(dòng)故障的應(yīng)用研究[J];計(jì)算機(jī)仿真;2011年06期

4 李國宏;孫健;夏偉鵬;康紅霞;;基于神經(jīng)網(wǎng)絡(luò)的地空導(dǎo)彈武器系統(tǒng)作戰(zhàn)能力評(píng)估[J];火力與指揮控制;2011年08期

5 黃運(yùn)明;曹君;;振動(dòng)篩重心的計(jì)算機(jī)輔助計(jì)算探討[J];機(jī)械工程師;2011年09期

6 靳玉柱;王忠勇;;基于傳感器的電子火災(zāi)檢測(cè)器的研制[J];福建建材;2011年03期

7 覃玉祝;謝進(jìn);陳永;陳江瑜;何江波;;混沌振動(dòng)篩機(jī)構(gòu)的研究[J];機(jī)械設(shè)計(jì);2011年07期

8 徐進(jìn);彭雄志;胡偉明;唐浩俊;;基于神經(jīng)網(wǎng)絡(luò)的盾構(gòu)機(jī)掘進(jìn)隧道地表沉降預(yù)測(cè)[J];四川建筑;2011年03期

9 黃小華;李德源;呂文閣;成思源;;基于人工神經(jīng)網(wǎng)絡(luò)模型的風(fēng)速預(yù)測(cè)[J];太陽能學(xué)報(bào);2011年02期

10 孟彩茹;馮忠緒;李磊;李學(xué)武;李長歡;;瀝青攪拌設(shè)備多層振動(dòng)篩篩分效率的試驗(yàn)研究[J];武漢理工大學(xué)學(xué)報(bào);2011年07期

相關(guān)會(huì)議論文 前10條

1 王曉曄;杜太行;呂德忠;;多變量非線性合成氨控制系統(tǒng)的建模[A];1998中國控制與決策學(xué)術(shù)年會(huì)論文集[C];1998年

2 呂崗;趙鶴鳴;;一種優(yōu)化前向神經(jīng)網(wǎng)絡(luò)權(quán)值的免疫算法[A];2003年中國智能自動(dòng)化會(huì)議論文集（上冊(cè)）[C];2003年

3 王勝武;王增彬;鄭新奇;;基于神經(jīng)網(wǎng)絡(luò)的宗地地價(jià)評(píng)估探析[A];2005年山東土地學(xué)會(huì)學(xué)術(shù)年會(huì)論文集[C];2005年

4 馮恩波;;間歇生產(chǎn)過程的神經(jīng)網(wǎng)絡(luò)模型及優(yōu)化控制[A];中國科學(xué)技術(shù)協(xié)會(huì)首屆青年學(xué)術(shù)年會(huì)論文集（工科分冊(cè)·上冊(cè)）[C];1992年

5 林是;陳奮銑;郭棟;鄒玲楓;徐慎初;;注入式電致發(fā)光神經(jīng)網(wǎng)絡(luò)[A];中國科學(xué)技術(shù)協(xié)會(huì)首屆青年學(xué)術(shù)年會(huì)論文集（工科分冊(cè)·上冊(cè)）[C];1992年

6 張美戀;林熙;;經(jīng)濟(jì)增長的神經(jīng)網(wǎng)絡(luò)模型[A];1999年中國神經(jīng)網(wǎng)絡(luò)與信號(hào)處理學(xué)術(shù)會(huì)議論文集[C];1999年

7 楊學(xué)增;方棣棠;;神經(jīng)網(wǎng)絡(luò)用于語音識(shí)別初探[A];第一屆全國語言識(shí)別學(xué)術(shù)報(bào)告與展示會(huì)論文集[C];1990年

8 孫慧;王U，

本文編號(hào)：1381136