【摘要】：磨機(jī)是工業(yè)生產(chǎn)中物料粉碎的核心設(shè)備。球磨機(jī)通過(guò)鋼球和研磨物之間的頻繁碰撞實(shí)現(xiàn)物料的粉碎作業(yè)。為保證球磨機(jī)高效、安全地運(yùn)作,必須對(duì)球磨機(jī)內(nèi)部工作狀態(tài)進(jìn)行檢測(cè)。球磨機(jī)負(fù)荷(主要包括物料量和料位)是磨料過(guò)程的重要檢測(cè)指標(biāo),直接影響磨機(jī)的工作效率。然而球磨機(jī)內(nèi)部的工作環(huán)境復(fù)雜多變,難以保證穩(wěn)定的運(yùn)作狀態(tài),對(duì)球磨機(jī)負(fù)荷檢測(cè)帶來(lái)極大阻礙�，F(xiàn)階段工廠主要通過(guò)人工監(jiān)聽(tīng)的方式對(duì)負(fù)荷進(jìn)行估計(jì),存在較大誤差。采用傳統(tǒng)的檢測(cè)方法也存在不能準(zhǔn)確檢測(cè)出磨機(jī)負(fù)荷狀態(tài)的問(wèn)題。本文首先對(duì)傳統(tǒng)主元分析(PCA)結(jié)合極限學(xué)習(xí)機(jī)(ELM)的檢測(cè)方法進(jìn)行深入研究,分別從頻譜分析、主元提取和模型建立三個(gè)方面對(duì)該方法在磨機(jī)負(fù)荷檢測(cè)中存在的缺陷進(jìn)行分析,并提出相應(yīng)的解決方案。然后,結(jié)合磨機(jī)負(fù)荷檢測(cè)的特點(diǎn),本文采用基于頻譜分析的方式,提出將核主元分析(KPCA)和誤差最小化極限學(xué)習(xí)機(jī)(EM_ELM)相結(jié)合的建模檢測(cè)方法,對(duì)磨機(jī)工作時(shí)產(chǎn)生的磨音信號(hào)進(jìn)行建模分析。本文提出的方法結(jié)合小波包去噪對(duì)信號(hào)進(jìn)行前期預(yù)處理,利用最大熵法的現(xiàn)代功率譜估計(jì)方法將信號(hào)轉(zhuǎn)換到頻域分析,采用間接檢測(cè)的方式建立磨機(jī)內(nèi)部負(fù)荷狀態(tài)和外部檢測(cè)信號(hào)之間的模型關(guān)系。最后,結(jié)合工業(yè)現(xiàn)場(chǎng)采集球磨煤機(jī)工作時(shí)的數(shù)據(jù)進(jìn)行實(shí)驗(yàn)測(cè)試,檢測(cè)結(jié)果與傳統(tǒng)的PCA-ELM檢測(cè)方法進(jìn)行測(cè)試對(duì)比。結(jié)果表明,采用本文提出的基于頻譜分析的KPCA-EM_ELM檢測(cè)方法,在測(cè)量準(zhǔn)確度上得到了提高,保證算法的運(yùn)行時(shí)間,提高了檢測(cè)準(zhǔn)確度和效率。為將該檢測(cè)方法運(yùn)用到實(shí)際的球磨機(jī)負(fù)荷檢測(cè)系統(tǒng)中提供了理論依據(jù),對(duì)于提高球磨機(jī)研磨效率、穩(wěn)定生產(chǎn)具有重要的意義和廣闊的應(yīng)用前景。
[Abstract]:Mill is the core equipment for material crushing in industrial production. The ball mill comminutes materials through frequent collisions between steel balls and abrasives. In order to ensure the efficient and safe operation of ball mill, it is necessary to check the internal working state of ball mill. Ball mill load (including material quantity and material level) is an important testing index of abrasive process, which directly affects the working efficiency of mill. However, the internal working environment of ball mill is complex and changeable, it is difficult to ensure stable operation state, which greatly hinders the load detection of ball mill. At present, the factory mainly uses manual monitoring to estimate the load, there is a big error. There is also the problem that the load state of the mill can not be detected accurately by using the traditional detection method. In this paper, the detection methods of traditional principal component analysis (PCA) combined with extreme learning machine (ELM) are studied in detail. The defects of this method in mill load detection are analyzed from three aspects: spectrum analysis, principal component extraction and modeling. And put forward the corresponding solution. Then, considering the characteristics of mill load detection, this paper proposes a modeling and detection method which combines kernel principal component analysis (KPCA) with error minimization learning machine (EM_ELM) based on spectrum analysis. Modeling and analysis of grinding sound signal produced by grinding machine. The method proposed in this paper combines wavelet packet denoising to pre-process the signal and converts the signal to frequency domain analysis by using the modern power spectrum estimation method of maximum entropy method. The model relationship between the internal load state of mill and the external detection signal is established by indirect detection. Finally, the test results are compared with the traditional PCA-ELM detection method, combined with the data collected from the industrial field during the operation of the ball mill. The results show that the proposed KPCA-EM_ELM detection method based on spectrum analysis can improve the measurement accuracy, ensure the running time of the algorithm, and improve the detection accuracy and efficiency. It provides a theoretical basis for the application of this method to the actual load detection system of ball mill. It is of great significance and broad application prospect for improving the grinding efficiency of ball mill and stabilizing production.
【學(xué)位授予單位】：重慶郵電大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類(lèi)號(hào)】：TH69

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張杰;王建民;楊志剛;李艷姣;;基于功率譜分析的球磨機(jī)負(fù)荷模型[J];工礦自動(dòng)化;2013年12期

2 楊曉宇;徐韜光;傅世年;曾磊;邊曉娟;;Classical and modern power spectrum estimation for tune measurement in CSNS RCS[J];Chinese Physics C;2013年11期

3 嚴(yán)東;湯健;趙立杰;;基于特征提取和極限學(xué)習(xí)機(jī)的軟測(cè)量方法[J];控制工程;2013年01期

4 肖紀(jì)恩;;水泥工藝技術(shù)中應(yīng)該重視的幾個(gè)問(wèn)題[J];四川建材;2012年04期

5 趙立杰;湯健;柴天佑;;基于選擇性極限學(xué)習(xí)機(jī)集成的磨機(jī)負(fù)荷軟測(cè)量[J];浙江大學(xué)學(xué)報(bào)(工學(xué)版);2011年12期

6 湯健;鄭秀萍;趙立杰;岳恒;柴天佑;;基于頻域特征提取與信息融合的磨機(jī)負(fù)荷軟測(cè)量[J];儀器儀表學(xué)報(bào);2010年10期

7 湯健;趙立杰;岳恒;柴天佑;;磨機(jī)負(fù)荷檢測(cè)方法研究綜述[J];控制工程;2010年05期

8 閆慶華;程兆剛;段云龍;;AR模型功率譜估計(jì)及Matlab實(shí)現(xiàn)[J];計(jì)算機(jī)與數(shù)字工程;2010年04期

9 杜卓明;屠宏;耿國(guó)華;;KPCA方法過(guò)程研究與應(yīng)用[J];計(jì)算機(jī)工程與應(yīng)用;2010年07期

10 宋仁義;;球磨機(jī)磨音多頻帶檢測(cè)系統(tǒng)的研發(fā)與設(shè)計(jì)[J];礦業(yè)工程;2009年02期

，

本文編號(hào)：2192156