一種磨機(jī)負(fù)荷參數(shù)軟測(cè)量方法
【技術(shù)領(lǐng)域】
[0001] 本發(fā)明涉及軟測(cè)量領(lǐng)域，具體涉及一種磨機(jī)負(fù)荷參數(shù)軟測(cè)量方法。
【背景技術(shù)】
[0002] 磨礦過(guò)程的優(yōu)化運(yùn)行控制需要準(zhǔn)確檢測(cè)磨機(jī)內(nèi)的負(fù)荷參數(shù)（參見(jiàn)文獻(xiàn)[1] P. Zhou, T. Y. Chai, H. Wang, "Intelligent optimal-setting control for grinding circuits of mineral processing, "IEEE Transactions on Automation Science and Engineering, 6 (2009) 730-743.和文獻(xiàn)[2] T.Y. Chai, "Operational optimization and feedback control for complex industrial processes, "Acta Automatica Sinica, 39 (2013) 1744-1757)。磨機(jī)內(nèi)部數(shù)以萬(wàn)計(jì)的鋼球分層排列，不同層的鋼球?qū)δC(jī)內(nèi) 部物料和磨機(jī)筒體的沖擊力具有不同的強(qiáng)度和周期。通常測(cè)量得到的筒體振動(dòng)信號(hào)是具有 不同時(shí)間尺度的多個(gè)子信號(hào)的混合。筒體振動(dòng)是磨機(jī)振聲信號(hào)的主要來(lái)源。因此，這些機(jī) 械振動(dòng)和振聲信號(hào)具有非穩(wěn)態(tài)和多組分特征。優(yōu)秀的領(lǐng)域?qū)＜彝ㄟ^(guò)同時(shí)考慮多種運(yùn)行工況 和多種來(lái)源信息可有效監(jiān)視磨機(jī)負(fù)荷狀態(tài)和部分磨機(jī)內(nèi)部的負(fù)荷參數(shù)。研宄表明，人耳可 以從磨機(jī)振聲信號(hào)中分辨出有價(jià)值信息。事實(shí)上，人耳是一組自適應(yīng)帶通濾波器，人腦具有 多層認(rèn)知結(jié)構(gòu)。領(lǐng)域?qū)＜铱蓮亩嘣刺卣骱投喾N運(yùn)行工況中提取有價(jià)值信息進(jìn)行決策。領(lǐng)域 專(zhuān)家經(jīng)驗(yàn)的差異和有限的精力難以保證磨機(jī)長(zhǎng)期工作在優(yōu)化負(fù)荷狀態(tài)。針對(duì)這些情況，很 有必要模擬領(lǐng)域?qū)＜业恼J(rèn)知過(guò)程建立磨機(jī)負(fù)荷參數(shù)軟測(cè)量模型。
[0003] 在時(shí)域內(nèi)，磨機(jī)筒體振動(dòng)和振聲內(nèi)的有價(jià)值信息被隱含在寬帶隨機(jī)噪聲中（參見(jiàn) 文獻(xiàn)[3] Y.，Zeng，E. Forssberg，"Monitoring grinding parameters by vibration signal measurement-a primary application, " Minerals Engineering, 1994, 7 (4):495-501.)〇 基于機(jī)械振動(dòng)和振聲信號(hào)的磨機(jī)負(fù)荷參數(shù)建模需要關(guān)注3個(gè)子問(wèn)題：多組分信號(hào)自適應(yīng)分 解、多源譜特征自適應(yīng)選擇、基于選擇多種運(yùn)行工況的軟測(cè)量模型構(gòu)建。
[0004] 研宄表明，信號(hào)處理可以簡(jiǎn)化特征的選擇和提取過(guò)程（參見(jiàn)文獻(xiàn)[4] S. Shukla, S. Mishra, and B. Singh, "Power Quality Event Classification Under Noisy Conditions Using EMD-Based De-Noising Techniques, " IEEE Transaction on Industrial Informatics, 10(2014) 1044-1054.)。磨機(jī)負(fù)荷參數(shù)與筒體振動(dòng)和振聲信 號(hào)的功率譜密度（PSD)密切相關(guān)（參見(jiàn)文獻(xiàn)[5] J. Tang，L. J. Zhao, J. W. Zhou，H. Yue，T. Y. Chai, "Experimental analysis of wet mill load based on vibration signals of laboratory-scale ball mill shell, "Minerals Engineering, 23(2010)720-730.)，但這 些譜數(shù)據(jù)通常包含成千上萬(wàn)的特征。很多維數(shù)約簡(jiǎn)算法用于處理具有該特點(diǎn)的數(shù)據(jù)（參見(jiàn) 文獻(xiàn)[6] J. Tang, T. Y. Chai, W. Yu, L. J. Zhao, "Modeling load parameters of ball mill in grinding process based on selective ensemble multi-sensor information, ''IEEE Transactions on Automation Science and Engineering, 10(2013)726-740.)〇 基于 互信息（MI)和偏最小二乘（PLS)的算法可以有效識(shí)別這些特征（參見(jiàn)文獻(xiàn)[6])。為 有效的融合這些頻譜特征，基于集成PLS，選擇性集成（SEN)和核PLS(KPLS)的軟測(cè)量 模型方法已有報(bào)道（參見(jiàn)文獻(xiàn)[7] J. Tang，T. Y. Chai，L. J. Zhao, W. Yu，H. Yue，"Soft sensor for parameters of mill load based on multi-spectral segments PLS sub-models and on-line adaptive weighted fusion algorithm， "Neurocomputi ng，78 (2012) 38-47?文獻(xiàn)[8] J. Tang，T.Y.Chai，W. Yu，L.J. Zhao，"Feature extraction and selection based on vibration spectrum with application to estimate the load parameters of ball mill in grinding process，" Control Engineering Practice，20 (2012) 991-1004.)。但是，快速傅里葉變換（FFT)不適合于具有非穩(wěn)態(tài)特性 的機(jī)械振動(dòng)和振聲信號(hào)的處理（參見(jiàn)文獻(xiàn)[9] Y. G. Lei，Z. J. He，Y. Y. Zi，"Application of the EEMD method to rotor fault diagnosis of rotating machinery，"Mechanical Systems and Signal Processing，23(2009) 1327-1338. )D 離散小波變換、連續(xù)小波 變換（CWT)、小波包變換等時(shí)頻分析方法已經(jīng)被廣泛應(yīng)用于旋轉(zhuǎn)機(jī)械設(shè)備的故障診斷 (參見(jiàn)文獻(xiàn)[10]G. K. Singh, S. A. S. AlKazzaz, "Isolation and identification of dry bearing faults in induction machine using wavelet transform，" Tribology International 42(2009)849-861.;文獻(xiàn)[11] J.Cusido，L. Romeral，J. A. Ortega，J. A. Rosero, and A. Garcia Espinosa, "Fault detection in induction machines using power spectral density in wavelet decomposition，" IEEE Trans. Ind. Electron.,v ol. 55, no. 2, pp. 633-643, Feb. 2008?文獻(xiàn)[12]M. Riera-Guasp，J. A. Antonino-Daviu，M. Pineda-Sanchez,R.Puche-Panadero, J. Perez-Cruz, "A general approach for the transient detection of slip-dependent fault components based on the discrete wavelet transform，" IEEE Trans. Ind. Electron. , 55(2008) 4167-4180.文 獻(xiàn)[13]J.Seshadrinath, B. Singh, and B.K.Panigrahi, "Vibration Analysis Based Interturn Fault Diagnosis in Induction Machines，" Transaction on Industrial Informatics，10 (2014) 340-350?文獻(xiàn)[14]P. K. Kankar，S. C. Sharma，S. P. Harsha，"Rolling element bearing fault diagnosis using auto correlation and continuous wavelet transform，" Journal of Vibration and Control，17(2011)2081-2094.)。但這些方 法不能自適應(yīng)分解本文所面對(duì)的多組分信號(hào)，如面對(duì)任何具體實(shí)際問(wèn)題必須為CWT選擇 合適的母小波。經(jīng)驗(yàn)?zāi)B(tài)分解（EMD)技術(shù)通過(guò)自適應(yīng)分解獲取具有不同時(shí)間尺度的內(nèi) 稟模態(tài)函數(shù)（MFs，也成為子信號(hào)）（參見(jiàn)文獻(xiàn)[15]N.E.Huang，Z.Shen，S.R.Long，"The empirical mode decomposition and the Hilbert spectrum for non-linear and non stationary time series analysis，"Proc. Royal Soc.London A，454(1998)903-995.)， 并且已經(jīng)被廣泛應(yīng)用于旋轉(zhuǎn)設(shè)備故障途斷（參見(jiàn)文獻(xiàn)[16]J.Faiz，V.Ghorbanian，and B. M. Ebrahimi, "EMD-Based Analysis of Industrial Induction Motors With Broken Rotor Bars for Identification of Operating Point at Different Supply Modes，" IEEE Transaction on Industrial Informatics，10 (2014) 957-966.文獻(xiàn)[17] Stuti. Shukla, S. Mishra, and Bhim Singh,uPower Quality Event Classification Under Noisy Conditions Using EMD-Based De-Noising Techniques，" IEEE Transaction on Industrial Informatics，10(2014) 10