铝土矿浮选过程粗选矿浆pH值软测量模型及应用
|
摘要
浮选是按矿物表面物理化学性质的差异来分离各种细粒矿物的一种有效方法。粗选是浮选流程的起始环节,其矿浆的pH值直接反映磨机中碳酸钠的添加量,对后面各个流程的药剂添加量、精矿及尾矿品位都有重要影响。现有的pH值测定仪昂贵、耗时、费力,且具有滞后性,结果易受环境影响,无法长期、连续、稳定、准确地进行测量。
粗选矿浆pH值的影响因素很多,且其变化过程具有非线性特征,很难从化学反应机理上建立矿浆pH值的软测量模型。泡沫图像包含了大量与生产指标相关的信息,图像特征能够实时反映矿浆pH值的变化,为实现矿浆pH值的实时在线检测提供了可能。
论文提取了粗选槽泡沫的颜色、尺寸、纹理等静态特征和速度、稳定度等动态特征,并结合BP神经网络逼近能力较强及RBF神经网络快速跟踪性较好的优点,提出一种基于BP和RBF的混合神经网络软测量模型。由于泡沫图像的特征变量较多且相关性强,直接用于软测量模型将导致计算量大、训练时间久等问题,故采用主元分析对其降维处理来确定软测量模型的辅助变量。同时,由于神经网络隐层节点数及软测量模型的混合系数具有不确定性,本文采用遗传算法对其寻优,并针对传统的遗传算法具有的早熟,最优解附近振荡及收敛较慢等缺点,分别从适应度值标定、维持种群多样性及交叉、变异算子三个方面对其加以改进,提出一种自适应遗传算法。此外,由于浮选现场工况具有时变性,当检测误差超过设定值时,采用阻尼最小二乘法对软测量模型中神经网络的权值和阈值进行在线修正,以提高模型的鲁棒性。
现场运行结果表明,建立的软测量模型具有精度高、动态响应快且鲁棒性强的特点,可以取代离线的化学分析,从而降低劳动强度,同时对磨机中碳酸钠的加药量具有很重要的指导作用,并可推广应用到其它类似工业过程。
Flotation is an effective method for separating various fine grained mineral particles based on the difference of the surface physicochemical properties. Rougher flotation is the beginning of flotation. The pH value of its slurry directly reflects sodium carbonate addition in mill. At the same time, it has significant impact on reagents addition of other processes, concentrate and tailings grade. Present pH determinator wastes time and human resource and has time delay. Furthermore, the result is easily affected by external conditions. It can not be used continuously and stably.
The pH value of rougher flotation is affected by many factors and the change of pH value is a nonlinear process. It is hard to build a soft measurement model for slurry pH value based on chemical reaction mechanism. Froth image includes much information related to production indexes. Its features can reflect the changes of slurry pH value. Therefore, the real time pH value of rougher flotation slurry can be obtained by froth image features.
In this paper, the static features such as color, size and texture as well as dynamic features like velocity and stability are extracted by digital image process technology. At the same time, because BP neural network has good function of approximation ability and RBF neural network can trace the function quickly, a hybrid neural network model based on BP and RBF neural network is proposed. Due to the strong correlation between the froth image features, it may lead a large amout of calculation and a long training time if the features are used in the soft measurement model directly. So the features'dimension is reduced by principal component analysis before they are used as instrumental variable of soft sensor model. Owing to the node number of hidden layer in neural network and hybrid coefficient of soft measurement model are not determined, they are optimized by genetic algorithm. Meanwhile, aiming at the disadvantage of traditional genetic algorithm such as local optimum, oscillation around the optimal value and slow convergence speed, an adaptive genetic algorithm is proposed based on the improvement of calibration of fitness, diversity of population and crossover and mutation operator. In addtion, in order to improve the robustness of the model, Levenberg-Marquardt algorithm is used to modify the weights and threshold of neural network on-line when measurement error exceeds the set value.
Running results show that the soft sensor model has advantages of high precision, fast response and strong robustness. It can replace the offline manual measurement, reduce labor intensity and guide workers to adjust the sodium carbonate addition in the mill. Moreover, it can be popularized in other industrial process.
粗选矿浆pH值的影响因素很多,且其变化过程具有非线性特征,很难从化学反应机理上建立矿浆pH值的软测量模型。泡沫图像包含了大量与生产指标相关的信息,图像特征能够实时反映矿浆pH值的变化,为实现矿浆pH值的实时在线检测提供了可能。
论文提取了粗选槽泡沫的颜色、尺寸、纹理等静态特征和速度、稳定度等动态特征,并结合BP神经网络逼近能力较强及RBF神经网络快速跟踪性较好的优点,提出一种基于BP和RBF的混合神经网络软测量模型。由于泡沫图像的特征变量较多且相关性强,直接用于软测量模型将导致计算量大、训练时间久等问题,故采用主元分析对其降维处理来确定软测量模型的辅助变量。同时,由于神经网络隐层节点数及软测量模型的混合系数具有不确定性,本文采用遗传算法对其寻优,并针对传统的遗传算法具有的早熟,最优解附近振荡及收敛较慢等缺点,分别从适应度值标定、维持种群多样性及交叉、变异算子三个方面对其加以改进,提出一种自适应遗传算法。此外,由于浮选现场工况具有时变性,当检测误差超过设定值时,采用阻尼最小二乘法对软测量模型中神经网络的权值和阈值进行在线修正,以提高模型的鲁棒性。
现场运行结果表明,建立的软测量模型具有精度高、动态响应快且鲁棒性强的特点,可以取代离线的化学分析,从而降低劳动强度,同时对磨机中碳酸钠的加药量具有很重要的指导作用,并可推广应用到其它类似工业过程。
Flotation is an effective method for separating various fine grained mineral particles based on the difference of the surface physicochemical properties. Rougher flotation is the beginning of flotation. The pH value of its slurry directly reflects sodium carbonate addition in mill. At the same time, it has significant impact on reagents addition of other processes, concentrate and tailings grade. Present pH determinator wastes time and human resource and has time delay. Furthermore, the result is easily affected by external conditions. It can not be used continuously and stably.
The pH value of rougher flotation is affected by many factors and the change of pH value is a nonlinear process. It is hard to build a soft measurement model for slurry pH value based on chemical reaction mechanism. Froth image includes much information related to production indexes. Its features can reflect the changes of slurry pH value. Therefore, the real time pH value of rougher flotation slurry can be obtained by froth image features.
In this paper, the static features such as color, size and texture as well as dynamic features like velocity and stability are extracted by digital image process technology. At the same time, because BP neural network has good function of approximation ability and RBF neural network can trace the function quickly, a hybrid neural network model based on BP and RBF neural network is proposed. Due to the strong correlation between the froth image features, it may lead a large amout of calculation and a long training time if the features are used in the soft measurement model directly. So the features'dimension is reduced by principal component analysis before they are used as instrumental variable of soft sensor model. Owing to the node number of hidden layer in neural network and hybrid coefficient of soft measurement model are not determined, they are optimized by genetic algorithm. Meanwhile, aiming at the disadvantage of traditional genetic algorithm such as local optimum, oscillation around the optimal value and slow convergence speed, an adaptive genetic algorithm is proposed based on the improvement of calibration of fitness, diversity of population and crossover and mutation operator. In addtion, in order to improve the robustness of the model, Levenberg-Marquardt algorithm is used to modify the weights and threshold of neural network on-line when measurement error exceeds the set value.
Running results show that the soft sensor model has advantages of high precision, fast response and strong robustness. It can replace the offline manual measurement, reduce labor intensity and guide workers to adjust the sodium carbonate addition in the mill. Moreover, it can be popularized in other industrial process.
引文
[1]谢广元.选矿学[M].江苏徐州：中国矿业大学出版社,2001
[2]Holtham P.N., Nguyen K.K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. Mineral processing,2002,64:163-180
[3]Liu J.J., MacGregor J.F., Duchesne C., et al. Flotation froth monitoring using multiresolutional multivariate image analysis [J]. Minerals Engineering,2005, 18:65-76
[4]何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008,8：96-101
[5]Liu J.J., MacGregor J.F.. Froth based modeling and control of flotation process [J]. Minerals Engineering,2008,21:642-651
[6]Gianni B., Patrick P.J., Jayson T.J., et al. Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes-Part I:Flotation control based on froth textural characteristics [J]. Mineral Engineering,2006,19:734-747
[7]Felipe N., Aldo C.. Visual information model based predictor for froth speed control in flotation process [J]. Minerals Engineering,2009,22:366-371
[8]Sadr-Kazemi N., Cilliers J.J.. An image processing algorithm for measurement of flotation froth bubble size and shape distributions [J]. Minerals Engineering, 1997,10(10):1075-1083
[9]M.瓜里尼.图像处理技术用于评估矿物浮选过程的质量[J].国外金属矿选,1999,36(12)：38-41
[10]A.西普利安诺.采用数字图像处理的浮选专家管理系统[J].国外金属矿选矿,1998,35(10)：44-47
[11]J.S.J.范德文特,D.W.墨尔曼.具有泡沫特征的神经计算机视觉在线显像浮选过程[J].国外金属矿选矿,1999,36(7)：14-19
[12]Harrave J.M., Hall ST.. Diagnosis of concentrate grade and mass flow rate in tin flotation from color and surface texture analysis [J]. Minerals Engineering, 1997,10(6):613-621
[13]弗朗西斯科·E·杜普利.对泡沫浮选工厂的监视和控制：中国.00816493.3[P].2003-02-26
[14]Van M.O., Brown N., Bourke P., Ronkainen S.. Improving flotation plant performance at cadia by controlling and optimizing the rate of froth recovery using outokumpu frothmaster [C]. Conference Proceedings-Seventh Mill Operations Conference:Kalgoorfie,2000,10
[15]李珍香,罗宏宇.浮选泡沫的计算机图像处理与识别方法[P].煤炭技术,1999,18(6)：17-19
[16]刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002,30(3)：198-203
[17]王晓晨,张奕奎,郑士芹.泡沫图像特征与浮选精煤指标关系的研究[J].淮南工业学院学报,2001,21(1)：41-43
[18]曾荣,沃国经.图像处理技术在浮选过程中的应用[J].有色金属,2001,53(4)：70-72
[19]张奕奎,陈凌,王飞.基于图像识别的浮选控制系统[J].工矿自动化,2002,(1)：14-16
[20]Holtham P.N., Nguyen K.K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. International Journal of Mineral Processing,2002,63(3-2):164-180
[21]曾荣.选冶泡沫图像处理的研究及工业应用[D].北京：北京矿冶研究总院,2002
[22]Wang W.X., Li L.. Image Analysis and Computer Vision for Mineral Froth [C]. Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls:Canada,2005,7:1790-1795
[23]Wang W.X., Li L.. Pattern Recognition and Computer vision for Mineral Froth [C]. Proceedings of the IEEE Computer Society of the 18th International Conference on Pattern Recognition (ICPR'06),2006
[24]Zhou K.J., Yang C.H., Gui W.H., et al. Clustering-driven watershed adaptive segmentation of bubble image [J]. Journal of Central South University of Technology,2010,17(5):1049-1057
[25]周开军,王一军,许灿辉.研究改进FCM和形态学的浮选泡沫形态特征提取[J].中南大学学报,2010,41(3)：994-1000
[26]刘金平,桂卫华,牟学民,唐朝晖,李建奇.研究Gabor小波的浮选泡沫图像纹理特征提取[J].仪器仪表学报,2010,31(8)：1769-1775
[27]Yang C.H., Xu C.H, Gui W.H., et al. Application of highlight removal and multivariate image analysis to color measurement of flotation bubble images [J]. International Journal of Imaging Systems and Technology,2009,19:316-322
[28]Yang C.H., Xu C.H., Mu X.M., et al. Bubble size estimation using interfacial morphological information for mineral flotation process monitoring [J]. Transactions of Nonferrous Metals Society of China,2009,19(3):694-699
[29]Yang C.H., Xu C.H., Gui W.H., et al. Nonparametric Density Estimation of Bubble Size Distribution for Monitoring Mineral Flotation Process [C]. In 48th IEEE Conference on Decision and Control, Shanghai,2009,2941-2945
[30]Shuping B.. A simple model for predicting the pH values of acidec narural waters [J]. Analytica Chimica Acta,1995,314:111-119
[31]Berenguel M., Rodriguez F., Acien F.G. Model predictive control of pH in tubular photobioreactors [J]. Journal of process control,2004,14:377-387
[32]Lakshmi N.R., Krishnaswamy P.R., Rangaiah G.P.. An adaptive internal model control strategy for pH neutralization [J]. Chemical Engineering Science,1997, 52(18):3067-3074
[33]Sanaz M., Javad P., Mohammad R., et al. Nonlinear model predictive control of a pH neutralization process based on Wiener-Laguerre model [J]. Chemical Engineering Journal,2009,146:328-337
[34]Jari M.B., Dale E.S., Joao P.H.. Multi-model adaptive control of a simulated pH neutralization process [J]. Control engineering practice,2007,15:663-672
[35]Babuska R., Oosterhoff J., Oudashoorn A., et al. Fuzzy self-tuning PI control of pH in fermentation [J]. Artificial intelligence,2002,15:3-15
[36]Loh A.P., Looi K.O., Fong K.F.. Neural network modelling and control strategies for a pH process [J]. Process control,1995,5(6):355-362
[37]Katarina K.B., Lgor S., Drago M.. Fuzzy predictive control of highly nonlinear pH process [J].1997,21:s613-s618
[38]Mwembeshi M.M., Kent C.A., Salhi S.. A genetic algrothms based approach to intelligent modelling and control of pH in reactors [J]. Computers and chemical engineering,2004,28:1743-1757
[39]Shahin S., Mohammad S., Ali N.. Adaptive nonlinear control of pH neutralization processes using fuzzy approximatiors [J]. control engineering practice,2009,17:1329-1337
[40]赵任辉,杨宗海,施招云,等.用非线性模型对循环水pH值动态预报控制[J].化工自动化及仪表,1993,20(5)：7-12
[41]简文彬.酸性矿井水pH值的回归分析模型[J].煤矿环境保护,1991,6(2)：47-50
[42]王大坤.用灰色系统理论GM(1,1)建立大气降水pH值的预测模型[J].干旱环境监测,1991,5(2)：123-126
[43]刘洪杰.一类描述完全混合水体pH长时变化的缓冲动态数学模型[J].华南 师范大学学报,1990,2：88-95
[44]刘煜.混合水pH值预测计算方法的探讨—平衡常数求解法[J].电力环境保护,1993,9(2)：6-11
[45]吴心传,石羿.多元弱碱pH值计算的新方法[J].沈阳化工学院学报,1991,5(4)：267-274
[46]马胜前,朱建邦,张秉孝.pH值的自适应预估[J].控制信息与控制,1987,6：57-59
[47]齐杰,刘载文,王小艺,等.废水生物处理过程软测量机理模型的研究[C].第19届中国过程控制会议论文集,2008,95-99
[48]何轶,何春来.酸浓度控制系统的研究[J].冶金自动化,2008,S1：249-251
[49]徐国忠.催化裂化分馏塔粗汽油干点的测量与控制[J].石油化工自动化,2001,3：31-33
[50]贾润达,毛志忠,常玉清.钴湿法冶炼萃取过程质量指标的软测量[J].计量学报,2010,31(2)：178-182
[51]程秀玲,李胜玉,单水维.基于软测量的钢坯内部温度场分布研究[J].南方金属,2007,158：11-13
[52]孙德奇,谷俊杰,李洋,等.基于氧量软测量的锅炉在线燃烧优化控制[J].仪器仪表学报,2006,27(6)：530-532
[53]张卫华,梅炽,鄂加强,等.铜精炼炉保温过程铜液温度软测量模型及应用[J].控制理论与应用,2005,1：19-23
[54]刘齐忠,马金魁,康庆山.FCCU轻柴油365℃含量的软测量模型及其控制应用[J].石油化工自动化,2000,5：59-61
[55]张勇,王介生,王伟,等.浮选生产过程经济技术指标的软测量建模[J].控制工程,2005,12(4)：346-349
[56]杨敏,胡斌,费正顺,等.基于DPCA-RBF网络的工业流化床乙烯气相聚合过程的软测量研究[J].仪器仪表学报,2010,31(3)：481-486
[57]王静芳,邹涛,俞立.基于典型相关分析和数据自回归处理的BP神经网络在聚丙烯熔融指数预报中的应用[J].过程控制,2009,36(2)：29-32
[58]许传龙,汤光华,杨道业.基于模糊规则的多模型固相质量流量软测量[J].化工学报,2007,58(9)：2225-2231
[59]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模[J].控制与决策,2005,20(6)：621-624
[60]陈晓方,桂卫华,王雅琳,等.基于智能集成策略的烧结块残硫软测量模型[J].控制理论与应用,2004,21(1)：75-80
[61]应苏如,桂卫华.智能集成模型在苛性比值软测量中的应用[J].中南工业大学学报,2003,34：4-7
[62]田慧欣,毛志忠,王嘉铮.基于ELM新方法的LF终点温度软测量混合模型[J].东北大学学报,2008,29(1)：33-36
[63]王恒,贾平民,陈左亮.基于LS-SVM和机理模型的球磨机料位软测量[J].电力自动化设备,2010,30(7)：92-95
[64]张伟,胡昌华,郑恩让.基于机理与主元分析的纸浆漂白MIMO软测量[J].化工自动化及仪表,2002,29(3)：47-49
[65]赵昀,黄志尧,王宝良,等.基于神经网络及机理分析的气力输送粉料质量流量软测量[J].仪器仪表学报,2000,21(4)：360-363
[66]阳春华,周开军,牟学民,等.基于计算机视觉的浮选泡沫颜色及尺寸测量方法[J].仪器仪表学报,2009,30(4)：717-721
[67]何东健.数字图像处理[M].陕西西安：西安电子科技大学出版社,2008
[68]吴成玉,邰晓英.基于灰度变化统计的图像检索[J].计算机工程与应用,2007,43(16)：83-86
[69]周开军,阳春华,牟学民,等.基于图像特征提取的浮选关键参数智能预测算法[J].控制与决策,2009,24(9)
[70]林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007,32(3)：304-308
[71]周开军,阳春华,牟学民,等.一种基于图像特征提取的浮选回收率预测算法[J].高技术通讯,2009,19(9)：957-963
[72]徐小军,邵英,郭尚芬.基于灰度共生矩阵的火焰图像纹理特征分析[J].计算技术与自动化,2007,26(4)：64-67
[73]刘文礼,路迈西,王凡,等.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003,54(6)：830-835
[74]唐朝晖,刘金平,桂卫华,等.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009,40(6)：1616-1622
[75]何迎晖.数理统计[M].上海：上海高等教育出版社,1989
[76]张青贵.人工神经网络导论[M].北京：中国水利水电出版社,2004
[77]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京：清华大学出版社,2007
[78]Moller M.F.. A scaled conjugate gradient algorithm for fast supervised learning [J]. Neural Networks,1993,6:525-533
[79]Thybats A.. On the optimization of froth flotation by the use of an artificial neural network [J]. journal of china university of mining & technology,2008,18: 418-426
[80]Jorjani E., Asadollahi P.H., Sam A., et al. Prediction of coal response to froth flotation based on coal analysis using regression and artificial neural network [J]. Minerals Engineering,2009,22:970-976
[81]Yuen C.W.M., Wong W.E., Qian S.Q., et al. A hybrid model using genetic algorithm and neural network for classifying garment defects [J]. Expert Systems with Application,2009,36:2037-2047
[82]Durdu omer Faruk. A hybrid neural network and ARIMA model for water quality time series prediction [J]. Engineering Applications of Artificial Intelligence,2010,23:586-594
[83]玄光男,陈润伟.遗传算法与工程优化[M].北京：清华大学出版社,2004
[84]周明,孙树栋.遗传算法原理及应用[M].北京：国防工业出版社,1999
[85]Mishra D., Yadav A., Ray S., et al. Levenberg-Marquardt learning algorithm for Integrate-and-FireNeuron model [J]. Neural Information Processing letters and Reviews,2005,9(2):45-53
[2]Holtham P.N., Nguyen K.K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. Mineral processing,2002,64:163-180
[3]Liu J.J., MacGregor J.F., Duchesne C., et al. Flotation froth monitoring using multiresolutional multivariate image analysis [J]. Minerals Engineering,2005, 18:65-76
[4]何桂春,黄开启.浮选指标与浮选泡沫数字图像关系研究[J].金属矿山,2008,8：96-101
[5]Liu J.J., MacGregor J.F.. Froth based modeling and control of flotation process [J]. Minerals Engineering,2008,21:642-651
[6]Gianni B., Patrick P.J., Jayson T.J., et al. Application of numerical image analysis to process diagnosis and physical parameter measurement in mineral processes-Part I:Flotation control based on froth textural characteristics [J]. Mineral Engineering,2006,19:734-747
[7]Felipe N., Aldo C.. Visual information model based predictor for froth speed control in flotation process [J]. Minerals Engineering,2009,22:366-371
[8]Sadr-Kazemi N., Cilliers J.J.. An image processing algorithm for measurement of flotation froth bubble size and shape distributions [J]. Minerals Engineering, 1997,10(10):1075-1083
[9]M.瓜里尼.图像处理技术用于评估矿物浮选过程的质量[J].国外金属矿选,1999,36(12)：38-41
[10]A.西普利安诺.采用数字图像处理的浮选专家管理系统[J].国外金属矿选矿,1998,35(10)：44-47
[11]J.S.J.范德文特,D.W.墨尔曼.具有泡沫特征的神经计算机视觉在线显像浮选过程[J].国外金属矿选矿,1999,36(7)：14-19
[12]Harrave J.M., Hall ST.. Diagnosis of concentrate grade and mass flow rate in tin flotation from color and surface texture analysis [J]. Minerals Engineering, 1997,10(6):613-621
[13]弗朗西斯科·E·杜普利.对泡沫浮选工厂的监视和控制：中国.00816493.3[P].2003-02-26
[14]Van M.O., Brown N., Bourke P., Ronkainen S.. Improving flotation plant performance at cadia by controlling and optimizing the rate of froth recovery using outokumpu frothmaster [C]. Conference Proceedings-Seventh Mill Operations Conference:Kalgoorfie,2000,10
[15]李珍香,罗宏宇.浮选泡沫的计算机图像处理与识别方法[P].煤炭技术,1999,18(6)：17-19
[16]刘文礼,陈子彤,路迈西.煤泥浮选泡沫的数字图像处理[J].燃料化学学报,2002,30(3)：198-203
[17]王晓晨,张奕奎,郑士芹.泡沫图像特征与浮选精煤指标关系的研究[J].淮南工业学院学报,2001,21(1)：41-43
[18]曾荣,沃国经.图像处理技术在浮选过程中的应用[J].有色金属,2001,53(4)：70-72
[19]张奕奎,陈凌,王飞.基于图像识别的浮选控制系统[J].工矿自动化,2002,(1)：14-16
[20]Holtham P.N., Nguyen K.K.. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. International Journal of Mineral Processing,2002,63(3-2):164-180
[21]曾荣.选冶泡沫图像处理的研究及工业应用[D].北京：北京矿冶研究总院,2002
[22]Wang W.X., Li L.. Image Analysis and Computer Vision for Mineral Froth [C]. Proceedings of the IEEE International Conference on Mechatronics & Automation Niagara Falls:Canada,2005,7:1790-1795
[23]Wang W.X., Li L.. Pattern Recognition and Computer vision for Mineral Froth [C]. Proceedings of the IEEE Computer Society of the 18th International Conference on Pattern Recognition (ICPR'06),2006
[24]Zhou K.J., Yang C.H., Gui W.H., et al. Clustering-driven watershed adaptive segmentation of bubble image [J]. Journal of Central South University of Technology,2010,17(5):1049-1057
[25]周开军,王一军,许灿辉.研究改进FCM和形态学的浮选泡沫形态特征提取[J].中南大学学报,2010,41(3)：994-1000
[26]刘金平,桂卫华,牟学民,唐朝晖,李建奇.研究Gabor小波的浮选泡沫图像纹理特征提取[J].仪器仪表学报,2010,31(8)：1769-1775
[27]Yang C.H., Xu C.H, Gui W.H., et al. Application of highlight removal and multivariate image analysis to color measurement of flotation bubble images [J]. International Journal of Imaging Systems and Technology,2009,19:316-322
[28]Yang C.H., Xu C.H., Mu X.M., et al. Bubble size estimation using interfacial morphological information for mineral flotation process monitoring [J]. Transactions of Nonferrous Metals Society of China,2009,19(3):694-699
[29]Yang C.H., Xu C.H., Gui W.H., et al. Nonparametric Density Estimation of Bubble Size Distribution for Monitoring Mineral Flotation Process [C]. In 48th IEEE Conference on Decision and Control, Shanghai,2009,2941-2945
[30]Shuping B.. A simple model for predicting the pH values of acidec narural waters [J]. Analytica Chimica Acta,1995,314:111-119
[31]Berenguel M., Rodriguez F., Acien F.G. Model predictive control of pH in tubular photobioreactors [J]. Journal of process control,2004,14:377-387
[32]Lakshmi N.R., Krishnaswamy P.R., Rangaiah G.P.. An adaptive internal model control strategy for pH neutralization [J]. Chemical Engineering Science,1997, 52(18):3067-3074
[33]Sanaz M., Javad P., Mohammad R., et al. Nonlinear model predictive control of a pH neutralization process based on Wiener-Laguerre model [J]. Chemical Engineering Journal,2009,146:328-337
[34]Jari M.B., Dale E.S., Joao P.H.. Multi-model adaptive control of a simulated pH neutralization process [J]. Control engineering practice,2007,15:663-672
[35]Babuska R., Oosterhoff J., Oudashoorn A., et al. Fuzzy self-tuning PI control of pH in fermentation [J]. Artificial intelligence,2002,15:3-15
[36]Loh A.P., Looi K.O., Fong K.F.. Neural network modelling and control strategies for a pH process [J]. Process control,1995,5(6):355-362
[37]Katarina K.B., Lgor S., Drago M.. Fuzzy predictive control of highly nonlinear pH process [J].1997,21:s613-s618
[38]Mwembeshi M.M., Kent C.A., Salhi S.. A genetic algrothms based approach to intelligent modelling and control of pH in reactors [J]. Computers and chemical engineering,2004,28:1743-1757
[39]Shahin S., Mohammad S., Ali N.. Adaptive nonlinear control of pH neutralization processes using fuzzy approximatiors [J]. control engineering practice,2009,17:1329-1337
[40]赵任辉,杨宗海,施招云,等.用非线性模型对循环水pH值动态预报控制[J].化工自动化及仪表,1993,20(5)：7-12
[41]简文彬.酸性矿井水pH值的回归分析模型[J].煤矿环境保护,1991,6(2)：47-50
[42]王大坤.用灰色系统理论GM(1,1)建立大气降水pH值的预测模型[J].干旱环境监测,1991,5(2)：123-126
[43]刘洪杰.一类描述完全混合水体pH长时变化的缓冲动态数学模型[J].华南 师范大学学报,1990,2：88-95
[44]刘煜.混合水pH值预测计算方法的探讨—平衡常数求解法[J].电力环境保护,1993,9(2)：6-11
[45]吴心传,石羿.多元弱碱pH值计算的新方法[J].沈阳化工学院学报,1991,5(4)：267-274
[46]马胜前,朱建邦,张秉孝.pH值的自适应预估[J].控制信息与控制,1987,6：57-59
[47]齐杰,刘载文,王小艺,等.废水生物处理过程软测量机理模型的研究[C].第19届中国过程控制会议论文集,2008,95-99
[48]何轶,何春来.酸浓度控制系统的研究[J].冶金自动化,2008,S1：249-251
[49]徐国忠.催化裂化分馏塔粗汽油干点的测量与控制[J].石油化工自动化,2001,3：31-33
[50]贾润达,毛志忠,常玉清.钴湿法冶炼萃取过程质量指标的软测量[J].计量学报,2010,31(2)：178-182
[51]程秀玲,李胜玉,单水维.基于软测量的钢坯内部温度场分布研究[J].南方金属,2007,158：11-13
[52]孙德奇,谷俊杰,李洋,等.基于氧量软测量的锅炉在线燃烧优化控制[J].仪器仪表学报,2006,27(6)：530-532
[53]张卫华,梅炽,鄂加强,等.铜精炼炉保温过程铜液温度软测量模型及应用[J].控制理论与应用,2005,1：19-23
[54]刘齐忠,马金魁,康庆山.FCCU轻柴油365℃含量的软测量模型及其控制应用[J].石油化工自动化,2000,5：59-61
[55]张勇,王介生,王伟,等.浮选生产过程经济技术指标的软测量建模[J].控制工程,2005,12(4)：346-349
[56]杨敏,胡斌,费正顺,等.基于DPCA-RBF网络的工业流化床乙烯气相聚合过程的软测量研究[J].仪器仪表学报,2010,31(3)：481-486
[57]王静芳,邹涛,俞立.基于典型相关分析和数据自回归处理的BP神经网络在聚丙烯熔融指数预报中的应用[J].过程控制,2009,36(2)：29-32
[58]许传龙,汤光华,杨道业.基于模糊规则的多模型固相质量流量软测量[J].化工学报,2007,58(9)：2225-2231
[59]张英,苏宏业,褚健.基于模糊最小二乘支持向量机的软测量建模[J].控制与决策,2005,20(6)：621-624
[60]陈晓方,桂卫华,王雅琳,等.基于智能集成策略的烧结块残硫软测量模型[J].控制理论与应用,2004,21(1)：75-80
[61]应苏如,桂卫华.智能集成模型在苛性比值软测量中的应用[J].中南工业大学学报,2003,34：4-7
[62]田慧欣,毛志忠,王嘉铮.基于ELM新方法的LF终点温度软测量混合模型[J].东北大学学报,2008,29(1)：33-36
[63]王恒,贾平民,陈左亮.基于LS-SVM和机理模型的球磨机料位软测量[J].电力自动化设备,2010,30(7)：92-95
[64]张伟,胡昌华,郑恩让.基于机理与主元分析的纸浆漂白MIMO软测量[J].化工自动化及仪表,2002,29(3)：47-49
[65]赵昀,黄志尧,王宝良,等.基于神经网络及机理分析的气力输送粉料质量流量软测量[J].仪器仪表学报,2000,21(4)：360-363
[66]阳春华,周开军,牟学民,等.基于计算机视觉的浮选泡沫颜色及尺寸测量方法[J].仪器仪表学报,2009,30(4)：717-721
[67]何东健.数字图像处理[M].陕西西安：西安电子科技大学出版社,2008
[68]吴成玉,邰晓英.基于灰度变化统计的图像检索[J].计算机工程与应用,2007,43(16)：83-86
[69]周开军,阳春华,牟学民,等.基于图像特征提取的浮选关键参数智能预测算法[J].控制与决策,2009,24(9)
[70]林小竹,谷莹莹,赵国庆.煤泥浮选泡沫图像分割与特征提取[J].煤炭学报,2007,32(3)：304-308
[71]周开军,阳春华,牟学民,等.一种基于图像特征提取的浮选回收率预测算法[J].高技术通讯,2009,19(9)：957-963
[72]徐小军,邵英,郭尚芬.基于灰度共生矩阵的火焰图像纹理特征分析[J].计算技术与自动化,2007,26(4)：64-67
[73]刘文礼,路迈西,王凡,等.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003,54(6)：830-835
[74]唐朝晖,刘金平,桂卫华,等.基于数字图像处理的浮选泡沫速度特征提取及分析[J].中南大学学报(自然科学版),2009,40(6)：1616-1622
[75]何迎晖.数理统计[M].上海：上海高等教育出版社,1989
[76]张青贵.人工神经网络导论[M].北京：中国水利水电出版社,2004
[77]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京：清华大学出版社,2007
[78]Moller M.F.. A scaled conjugate gradient algorithm for fast supervised learning [J]. Neural Networks,1993,6:525-533
[79]Thybats A.. On the optimization of froth flotation by the use of an artificial neural network [J]. journal of china university of mining & technology,2008,18: 418-426
[80]Jorjani E., Asadollahi P.H., Sam A., et al. Prediction of coal response to froth flotation based on coal analysis using regression and artificial neural network [J]. Minerals Engineering,2009,22:970-976
[81]Yuen C.W.M., Wong W.E., Qian S.Q., et al. A hybrid model using genetic algorithm and neural network for classifying garment defects [J]. Expert Systems with Application,2009,36:2037-2047
[82]Durdu omer Faruk. A hybrid neural network and ARIMA model for water quality time series prediction [J]. Engineering Applications of Artificial Intelligence,2010,23:586-594
[83]玄光男,陈润伟.遗传算法与工程优化[M].北京：清华大学出版社,2004
[84]周明,孙树栋.遗传算法原理及应用[M].北京：国防工业出版社,1999
[85]Mishra D., Yadav A., Ray S., et al. Levenberg-Marquardt learning algorithm for Integrate-and-FireNeuron model [J]. Neural Information Processing letters and Reviews,2005,9(2):45-53