基于泡沫图像的铝土矿浮选pH值软测量及应用
|
摘要
铝土矿浮选是“选矿-拜耳法”氧化铝生产工艺中的一个重要工序。浮选过程中,矿浆pH值能够直接反映生产工况和碳酸钠药剂的消耗量,而浮选矿浆具有流动性差、温度高、强腐蚀性等特点,容易堵塞接触式的pH值检测装置。通常选矿厂主要采用离线化验的方式监测pH值,滞后一个小时,且不能连续监测,难以指导生产操作。实际生产过程中,泡沫图像特征是矿浆pH值的重要指示器,为此,研究基于泡沫图像的铝土矿浮选pH值实时检测具有重要的理论意义和实际应用价值。
论文分析铝土矿浮选工艺机理的基础上,依据泡沫图像与浮选矿浆pH值的关联性,提出泡沫颜色、形态和纹理特征提取方法,建立基于泡沫图像特征与多工况子模型组合的pH软测量模型,实现铝土矿浮选pH值的实时检测,为浮选过程优化控制创造条件。论文主要研究工作及创新性成果如下：
(1)基于铝土矿浮选pH中和过程的复杂反应机理,从铝土矿微粒可浮性、浮选药剂活性和矿浆中离子组成三个方面分析pH值对浮选工况、指标的重要影响。引入理想混合连续搅拌釜式反应器的分析思想,从宏观和微观两个方面,基于质量守恒定律和电荷平衡守则研究pH值与调整碳酸钠加入量的相关性,以及浮选pH中和过程的非线性特性。通过分析大量不同pH值条件下的浮选泡沫图像,确定主要的泡沫图像特征,从浮选机理上证明泡沫图像是pH值的指示器。
(2)针对铝土矿浮选泡沫特征提取难点,研究泡沫颜色、形态和纹理特征提取方法。采用全变差修复模型去除泡沫顶部亮点,通过色彩空间变换实现设备无关性的泡沫颜色鲁棒计算,有效解决泡沫顶部亮点干扰及设备老化导致泡沫颜色失真问题。提出自适应粒子群优选谷底检测阂值的形态特征提取方法,该方法将粒子群算法的惯性权重和加速因子设置为全局最优点适应度的函数优选谷底检测阈值,采用局部灰度极小选择边界检测模板,根据多角度逻辑规则比较分割泡沫图像,获取气泡形态特征,该方法能够避免矿化气泡形态各异,现场光照不均对泡沫图像分割产生的不利影响。针对表层泡沫沿前进方向径向拉长的特点,在灰度共生矩阵上增加方向性差异,通过多角度融合计算空间灰度共生矩阵的二阶统计量描述泡沫纹理,很大程度上提高了纹理计算的准确性,为建立pH值的软测量模型提供数据基础。
(3)针对pH中和过程的非线性特点,提出一种代价约束的稀疏多核最小二乘支持向量回归机方法,建立浮选pH值局部软测量模型。将多核最小二乘支持向量回归机的原始优化问题转化为二阶锥规划形式,定义核函数代价因子约束复杂核函数的权重,以确定最优的组合核函数,这种对不同特性核函数进行凸组合的方法,提高了模型的学习能力和泛化能力,同时,采用改进最近邻山峰聚类和施密特正交化方法约简核矩阵,有效降低计算复杂度,避免多核学习中核函数的代价问题,再根据支持向量的数目以及活动核函数的类型评估多核学习的总代价,减少变量存储空间和计算时间。
(4)针对局部模型难以反映整个浮选工况的问题,提出一种多工况子模型模糊加权组合的全局建模方法。采用特征加权模糊多类分类支持向量机划分浮选工况,在每个工况区间分别建立泡沫图像与pH值的关系子模型。根据泡沫图像不同特征对工况反应的灵敏度差异,提出基于信息增益的泡沫图像特征重要度分配方法,利用泡沫图像对工况的模糊隶属度作为子模型的权重组合多个子模型实现浮选过程全局建模,这种基于泡沫图像的集成建模方法,有效地增强了模型在不同工况条件下的鲁棒性。
(5)以工业现场铝土矿泡沫浮选过程为研究对象,开发浮选过程监控系统,实现了泡沫图像特征的在线提取与矿浆pH值的实时检测。该系统能够实时监控各种工艺参数条件下泡沫外观特征及pH值的变化趋势,及时评估生产状态并更新专家规则,为调整碳酸钠药剂加入量提供操作指导。
Flotation is an important part of alumina production process using 'bayer process with dressing'. Slurry pH is a direct reflection of the production condition and the consumption of sodium carbonate. However the pulp with poor mobility, high temperature and high corrosion, easy to plug the contact pH test device, while off-line tests are adopted by most of concentrators, which leads to a long lag time, and is difficult to continuously detect. Studies have shown that froth image is the indictor of pH, so researching real-time detection of pH values using froth images is great theoretical significance and practical application value.
On the basis of the analysis of bauxite flotation process mechanism, considering the correlation of the bubble images and the pH value of pulp, froth color, size, shape and texture features are extracted, and the soft sensor of pH is established made up of multiple sub-model using image features, which is applied on froth flotation industry successfully. The thesis research and innovation results are as follows:
(1) For the complex reaction mechanism of the pH value neutralization process of bauxite flotation process, the importance and the significant impact of pH on flotation performance is discussed from three aspects of bauxite particles floating, the activity of flotation reagent and ion composition. According to the law of conservation of mass and charge balance from the macro and micro aspects, it is proved that pH is the basis of adjustment of sodium carbonate and there is a typical non-linear characteristic in pH neutralization process based on ideal mixed continuous stirred tank reactor. A number of froth images are analyzed to choose proper image features, which shows that froth image is an indicator of pH.
(2) Considering the difficulty to extracting froth features for bauxite flotation process, indicative function to pH of froth image, the feature extraction of bubble color, size, shape and texture is researched. As the interference of highlight and equipment aging causes color distortion, an image inpainting method is used to remove the top highlight of the bubbles, and then robust calculation with device-independent of froth color is realized based on color space conversion. Around the mineralized bubbles of various shapes, uneven scene illumination adversely affect the bubble image segmentation, the inertia weight and acceleration factor of particle swarm optimization is set to the function of global optimum fitness to detect threshold of valley edge. The local gray minimal is used to select boundary detection template, and then the froth image is segmented according to logic rules to obtain the bubble shape characteristics. In view of the radial elongated features along the forward direction for the surface froth, while the traditional spatial gray level co-occurrence matrix ignores the directional difference, which leads to inaccurate texture calculation, a multi-angle-fused spatial gray level co-occurrence matrix is proposed to calculate second-order statistics to describe texture. The image features provide plentiful data for modeling of pH soft-sensing.
(3) In view of the non-linear characteristics of the pH neutralization process and the characterization to pH of the bubble images, the local soft-sesing model of pH is set up based on multi-kernel least squares support vector regression machine. Multiple kernels with different characteristics are convex combined to improve learning ability and generalization ability of the model. Focusing on the ignorance of cost and computational complexity of multiple kernel learning, a novel cost constraint multi-kernel learing idea is raised. The original optimization problem of multi-kernel least squares support vector regression machine is converted into the form of a second order cone programming, and then a cost factor of mult-kernel learing is difined to to determine the optimal combination of kernel functions. To reduce the computational complexity, an improved nearest neighbor peaks clustering algorithm and Schmidt orthogonalization method are adopted. The total cost of multi-kernel learing is evaluated according to the number of support vectors and active kernel, which saves the variable storage space and computing time.
(4) Aiming at the deficiency of reflecting the entire flotation conditions for the local model, a global modeling using multiple working condition sub-models fuzzy combination is achieved. The flotation process is divided into three working conditions based on feature weighted fuzzy multi-classification support vector machine, and sub-model of bubble image features and pH value is established in each range of conditions. Distribute the importance metric of image features according to sensitivity differences in response to operating conditions based on information gain. The fuzzy membership of the bubble image on the working conditions is used as the combination weight of multiple sub-models to realize global soft sensing model. Effective results using industrial data of off-line froth image are achieved on the recognition of flotation performance and the soft-sensing of pH.
(5) Taking bauxite flotation process in industrial field as a research case, a process monitoring system based on froth image analysis is developed, which could extract froth features on line and detect the pH values of flotation slurry in real time. That the flotation performance can be evaluated and expert rules can be updated according to froth image and pH achieved by soft-sensor, provides operational guidance to adjust the sodium carbonate amount.
论文分析铝土矿浮选工艺机理的基础上,依据泡沫图像与浮选矿浆pH值的关联性,提出泡沫颜色、形态和纹理特征提取方法,建立基于泡沫图像特征与多工况子模型组合的pH软测量模型,实现铝土矿浮选pH值的实时检测,为浮选过程优化控制创造条件。论文主要研究工作及创新性成果如下：
(1)基于铝土矿浮选pH中和过程的复杂反应机理,从铝土矿微粒可浮性、浮选药剂活性和矿浆中离子组成三个方面分析pH值对浮选工况、指标的重要影响。引入理想混合连续搅拌釜式反应器的分析思想,从宏观和微观两个方面,基于质量守恒定律和电荷平衡守则研究pH值与调整碳酸钠加入量的相关性,以及浮选pH中和过程的非线性特性。通过分析大量不同pH值条件下的浮选泡沫图像,确定主要的泡沫图像特征,从浮选机理上证明泡沫图像是pH值的指示器。
(2)针对铝土矿浮选泡沫特征提取难点,研究泡沫颜色、形态和纹理特征提取方法。采用全变差修复模型去除泡沫顶部亮点,通过色彩空间变换实现设备无关性的泡沫颜色鲁棒计算,有效解决泡沫顶部亮点干扰及设备老化导致泡沫颜色失真问题。提出自适应粒子群优选谷底检测阂值的形态特征提取方法,该方法将粒子群算法的惯性权重和加速因子设置为全局最优点适应度的函数优选谷底检测阈值,采用局部灰度极小选择边界检测模板,根据多角度逻辑规则比较分割泡沫图像,获取气泡形态特征,该方法能够避免矿化气泡形态各异,现场光照不均对泡沫图像分割产生的不利影响。针对表层泡沫沿前进方向径向拉长的特点,在灰度共生矩阵上增加方向性差异,通过多角度融合计算空间灰度共生矩阵的二阶统计量描述泡沫纹理,很大程度上提高了纹理计算的准确性,为建立pH值的软测量模型提供数据基础。
(3)针对pH中和过程的非线性特点,提出一种代价约束的稀疏多核最小二乘支持向量回归机方法,建立浮选pH值局部软测量模型。将多核最小二乘支持向量回归机的原始优化问题转化为二阶锥规划形式,定义核函数代价因子约束复杂核函数的权重,以确定最优的组合核函数,这种对不同特性核函数进行凸组合的方法,提高了模型的学习能力和泛化能力,同时,采用改进最近邻山峰聚类和施密特正交化方法约简核矩阵,有效降低计算复杂度,避免多核学习中核函数的代价问题,再根据支持向量的数目以及活动核函数的类型评估多核学习的总代价,减少变量存储空间和计算时间。
(4)针对局部模型难以反映整个浮选工况的问题,提出一种多工况子模型模糊加权组合的全局建模方法。采用特征加权模糊多类分类支持向量机划分浮选工况,在每个工况区间分别建立泡沫图像与pH值的关系子模型。根据泡沫图像不同特征对工况反应的灵敏度差异,提出基于信息增益的泡沫图像特征重要度分配方法,利用泡沫图像对工况的模糊隶属度作为子模型的权重组合多个子模型实现浮选过程全局建模,这种基于泡沫图像的集成建模方法,有效地增强了模型在不同工况条件下的鲁棒性。
(5)以工业现场铝土矿泡沫浮选过程为研究对象,开发浮选过程监控系统,实现了泡沫图像特征的在线提取与矿浆pH值的实时检测。该系统能够实时监控各种工艺参数条件下泡沫外观特征及pH值的变化趋势,及时评估生产状态并更新专家规则,为调整碳酸钠药剂加入量提供操作指导。
Flotation is an important part of alumina production process using 'bayer process with dressing'. Slurry pH is a direct reflection of the production condition and the consumption of sodium carbonate. However the pulp with poor mobility, high temperature and high corrosion, easy to plug the contact pH test device, while off-line tests are adopted by most of concentrators, which leads to a long lag time, and is difficult to continuously detect. Studies have shown that froth image is the indictor of pH, so researching real-time detection of pH values using froth images is great theoretical significance and practical application value.
On the basis of the analysis of bauxite flotation process mechanism, considering the correlation of the bubble images and the pH value of pulp, froth color, size, shape and texture features are extracted, and the soft sensor of pH is established made up of multiple sub-model using image features, which is applied on froth flotation industry successfully. The thesis research and innovation results are as follows:
(1) For the complex reaction mechanism of the pH value neutralization process of bauxite flotation process, the importance and the significant impact of pH on flotation performance is discussed from three aspects of bauxite particles floating, the activity of flotation reagent and ion composition. According to the law of conservation of mass and charge balance from the macro and micro aspects, it is proved that pH is the basis of adjustment of sodium carbonate and there is a typical non-linear characteristic in pH neutralization process based on ideal mixed continuous stirred tank reactor. A number of froth images are analyzed to choose proper image features, which shows that froth image is an indicator of pH.
(2) Considering the difficulty to extracting froth features for bauxite flotation process, indicative function to pH of froth image, the feature extraction of bubble color, size, shape and texture is researched. As the interference of highlight and equipment aging causes color distortion, an image inpainting method is used to remove the top highlight of the bubbles, and then robust calculation with device-independent of froth color is realized based on color space conversion. Around the mineralized bubbles of various shapes, uneven scene illumination adversely affect the bubble image segmentation, the inertia weight and acceleration factor of particle swarm optimization is set to the function of global optimum fitness to detect threshold of valley edge. The local gray minimal is used to select boundary detection template, and then the froth image is segmented according to logic rules to obtain the bubble shape characteristics. In view of the radial elongated features along the forward direction for the surface froth, while the traditional spatial gray level co-occurrence matrix ignores the directional difference, which leads to inaccurate texture calculation, a multi-angle-fused spatial gray level co-occurrence matrix is proposed to calculate second-order statistics to describe texture. The image features provide plentiful data for modeling of pH soft-sensing.
(3) In view of the non-linear characteristics of the pH neutralization process and the characterization to pH of the bubble images, the local soft-sesing model of pH is set up based on multi-kernel least squares support vector regression machine. Multiple kernels with different characteristics are convex combined to improve learning ability and generalization ability of the model. Focusing on the ignorance of cost and computational complexity of multiple kernel learning, a novel cost constraint multi-kernel learing idea is raised. The original optimization problem of multi-kernel least squares support vector regression machine is converted into the form of a second order cone programming, and then a cost factor of mult-kernel learing is difined to to determine the optimal combination of kernel functions. To reduce the computational complexity, an improved nearest neighbor peaks clustering algorithm and Schmidt orthogonalization method are adopted. The total cost of multi-kernel learing is evaluated according to the number of support vectors and active kernel, which saves the variable storage space and computing time.
(4) Aiming at the deficiency of reflecting the entire flotation conditions for the local model, a global modeling using multiple working condition sub-models fuzzy combination is achieved. The flotation process is divided into three working conditions based on feature weighted fuzzy multi-classification support vector machine, and sub-model of bubble image features and pH value is established in each range of conditions. Distribute the importance metric of image features according to sensitivity differences in response to operating conditions based on information gain. The fuzzy membership of the bubble image on the working conditions is used as the combination weight of multiple sub-models to realize global soft sensing model. Effective results using industrial data of off-line froth image are achieved on the recognition of flotation performance and the soft-sensing of pH.
(5) Taking bauxite flotation process in industrial field as a research case, a process monitoring system based on froth image analysis is developed, which could extract froth features on line and detect the pH values of flotation slurry in real time. That the flotation performance can be evaluated and expert rules can be updated according to froth image and pH achieved by soft-sensor, provides operational guidance to adjust the sodium carbonate amount.
引文
[1]. 罗建川.基于铝土矿资源全球化的我国铝工业发展战略研究[D].长沙：中南大学,2006.
[2]. 胡熙庚,黄和慰,毛钜凡,等.浮选理论与工艺[M].长沙：中南工业大学出版社,1991.
[3]. 许灿辉.矿物浮选气泡速度和尺寸分布特征提取方法与应用[D].长沙：中南大学,2011.
[4]. J.V. Mehrabani, M. Noaparast, S.M. Mousavi, et al. Process optimization and modelling of sphalerite flotation from a low-grade Zn-Pb ore using response surface methodology [J]. Separation and Purification Technology,2010, 72:242-249.
[5]. A. A. Al-Shamrani, A. James, H. Xiao. Separation of oil from water by dissolved air flotation [J]. Colloids and Surfaces A:Physicochemical and Engineering Aspects,2002,209:15-26.
[6]. S. Lasocki, J. Antoniuk, J. Moscicki. Environmental protection problems in the vicinity of the Zelazny most flotation wastes depository in Poland[J].Journal of Environmental Science and Health Part a-Toxic/Hazardous Substances & Environmental Engineering,2003, 38(8):1435-1443.
[7]. B. Albijanic, O. Ozdemir, A. V. Nguyen, et al. A review of induction and attachment times of wetting thin films between air bubbles and particles and its relevance in the separation of particles by flotation [J]. Advances in Colloid and Interface Science,2010,159:1-21.
[8]. G. Wang, F. J. Sotillo, G. M. Lilley. Froth flotation process with ph modification [P].2008-8-21.
[9]. 任会峰,阳春华,周璇,等.基于最小二乘支持向量回归机的矿浆酸碱度鲁棒软测量[J].上海交通大学学报,2011,45(8)：1136-1145.
[10]. X. Ma, W. J. Bruckard, R. Holmes. Effect of collector, pH and ionic strength on the cationic flotation of kaolinite [J].International Journal of Mineral Processing,2009,93(1):54-58.
[11]. 阳春华,任会峰,许灿辉,等.基于稀疏多核LSSVM的浮选关键指标软测量.中国有色金属学报,2011,21(12)：3149-3154.
[12]. 黄宋魏,张博亚,胡娟,等.pH计及其在浮选中的应用[J].有色金属(选矿 部分),2008,2：41-45.
[13]. 阳春华,任会峰,桂卫华,等.基于机器视觉的矿物浮选pH软测量方法[J].计算机工程与应用,2011,47(1)：228-248.
[14]. J. Bouchard, A. Desbiens, R. Villar, et al. Column flotation simulation and control:An overview [J]. Minerals Engineering,2009,22(6):519-529.
[15]. G. Luttrell, R. Yoon. A flotation column simulator based on hydrodynamic principles [J]. International Journal of Mineral Processing,1991, 33(1-4):355-368.
[16]. K.V. Sastry, D.D. Lofftus. Mathematical modeling and computer simulation of column flotation [C]. Column Flotation'88, SME, Littleton, CO, USA, 1988:57-68.
[17]. C.-J. Kho, H.-J. Sohn. Column flotation of talc [J]. International Journal of Mineral Processing,1989,27(1-2):157-167.
[18]. G. S. Dbobby, J. A. Finch. Particle size dependence in flotation derived from fundamental model of the capture process [J]. International Journal of Mineral Processing,1987,21(3-4):241-260.
[19]. R. Tuteja, D. Spottiswood, V. Misra. Mathematical models of the column flotation process -a review [J].Minerals Engineering,1994,7 (12):1459-1472.
[20]. B. Oteyaka, H. Soto. Modelling of negative bias column for coarse particles flotation [J]. Minerals Engineering,1995,8 (1-2):91-100.
[21]. S. Gupta, P.-H. Liu, S. Svoronos. Hybrid first-principles/neural networks models for column flotation [J]. AIChE Journal,1999,45(3):557-566.
[22]. M. Maldonado, A. Desbiens, R. del Villar. An update on the estimation of the froth depth using conductivity measurements [J]. Minerals Engineering,2008, 21(12-14):935-939.
[23]. M. Persechini, F. Jota, A. Peres. Dynamic model of a flotation column [J]. Minerals Engineering,2000,13(14-15):1465-1481.
[24]. D. Hyma, A. Salama. Design and implementation of a process control system for column flotation [J]. CIM Bulletin,1993,86 (973):50-54.
[25]. 孙德四,施爱加.灰色预测模型与浮选动力学多重模型[J].金属矿山,2002,8：37-39.
[26]. 周俊武,孙传尧.RBF网络在硫化矿浮选过程建模中的应用研究[J].有色冶金设计与研究,2003,24：135-140.
[27]. 郝振,桂卫华,阳春华,等.基于灰色补偿的浮选过程回收率预测模型[J]. 控制工程,2009,16(1)：66-69.
[28]. 袁红霞,杨英杰.基于RBF网络的胶磷矿浮选精矿指标预测模型[J].化工矿物与加工,2011,2：1-4.
[29]. 刘潭,张勇.基于粗糙集-BP神经网络的浮选槽液位预测[J].辽宁科技大学学报,2010,33(5)：525-529.
[30]. 张勇,王介生.基于PCA-RBF神经网络的浮选过程软测量建模[J].南京航空航天大学学报,2006,38(S1)：116-119.
[31]. 耿增显,柴天佑.基于LS-SVM的浮选过程工艺技术指标软测量[J].系统仿真学报,2008,20(23)：6321-6324.
[32]. C. Aldrich, C. Marais, B.J. Shean, et al.Online monitoring and control of froth flotation systems with machine vision:A review [J]. International Journal of Mineral Processing,2010,96(1-4):1-13.
[33]. D. W. Moolman, C. Aldrich, J. S. J. Deventer, et al. The classification of froth structures in copper flotation plant by means of a neural net [J]. International Journal of Mineral Processing,1995,43(3-4):193-208.
[34]. 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.
[35]. J. M. Hargrave, S. T. Hall. Diagnosis of concentrate grade and mass flow rate in tin flotation from color and surface texture analysis [J]. Minerals Engineering,1997,6(10):613-621.
[36]. J. J. Liu, J. F. MacGregor, C. Duchesne, et al. Flotation froth monitoring using multiresolutional multivariate image analysis [J]. Minerals Engineering,2005, 18(1):65-76.
[37]. H. Hyotyniemi, R.Ylinen. Modeling of visual flotation froth data [J]. Control Engineering Practice,2000,8(10):313-318.
[38]. J. Hatonen, H. Hyotyniemi, J. Miettunen. Using image information and partial least squares method to estimate mineral concentrations in mineral flotation [C]. In:John A. M.. Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials, Hawaii, USA,1999, 459-464.
[39]. G. Bonifazi, S. Serranti, F. Volpe, et al. Characterisation of flotation froth colour and structure by machine vision [J]. Computers & Geosciences,2001, 27(9):1111-1117.
[40]. J.F. Reddick, A.H. Hesketh, S.H. Morar, et al. An evaluationof factors affecting the robustness of colour measurement and its potential to predict the grade of flotation concentrate [J]. Minerals Engineering,2009,22(1):64-69.
[41]. D. W. Moolman, C. Aldrich, J. S. Deventer. The interpretation of flotation froth surfaces by using digital image analysis and neural networks [J]. Chemical Engineering Science,1995,50(22):3501-3513.
[42]. B. Lin, B. Reche, J. K. H. Knudsen, et al. Bubble size estimation for flotation processes [J]. Minerals Engineering,2008,21(7):539-548.
[43]. W. X. Wang, O. Stephansson. A robust bubble delineation algorithm for froth images [C], Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials,1999,1:471-476.
[44]. W. Wang, L. Li. Image analysis and computer vision for mineral froth [C]. IEEE International Conference on Mechatronics and Automation, ICMA,2005, 1790-1795.
[45]. C. Citir, Z. Aktas, R. Berber. Off-line image analysis for froth flotation of coal [J]. Computers & Chemical Engineering,2004,28(5):625-632.
[46]. C. Yang, C. Xu, W. Gui, 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(4): 316-322.
[47]. 谢永芳,陈辉,桂卫华,等.一种新的基于纹理图像的分数阶Sobel算子[C].第三十届中国控制会议,山东烟台,2011：3100-3104.
[48]. G. Bonifazi, S. Serranti, F. Volpe, et al. A combined morphological and color based approach to characterization of froth bubbles [C]. Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials,1999,1:465-470.
[49]. N. Sadr-Kazemi, J.J. Cilliers. An image processing algorithm for measurement of flotation froth bubble size and shape distributions [J]. Minerals Engineering, 1997,10(10):1075-1083.
[50]. 谷莹莹,林小竹,李左丽,等.基于分水岭变换的浮选泡沫图像分割[J].北京石油化工学院学报,2007,15(1)：61-66.
[51]. 阳春华,杨尽英,牟学民,等.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008,30(6)：1286-1290.
[52]. M. Bharati, J. Liu, J.F. MacGregor. Image texture analysis:methods and comparisons [J]. Chemometrics and Intelligent Laboratory Systems,2004, 72(1):57-71.
[53]. G. Bartolacci, P. Pelletier Jr., J. Tessier Jr., 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]. Minerals Engineering,2006, 19(6-8):734-747.
[54]. J.J. Liu, J.F. MacGregor. On the extraction of spectral and spatial information from images [J]. Chemometrics and Intelligent Laboratory Systems,2007, 85(1):119-130.
[55]. 唐朝晖,孙园园,桂卫华,等.基于小波变换的浮选泡沫图像纹理特征提取[J].计算机工程,2011,37(18)：206-208.
[56]. 刘金平,桂卫华,牟学民,等.基于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.
[57]. K.K. Nguyen, P. Holtham. The application of pixel tracing techniques in the flotation process [C]. Proceedings of the first joint Australian and New Zealand biennial conference on Digital Imaging and Vision Computing and Applications.1997:207-212.
[58]. X. Z. Lin, G.A. Zhao, Y.B. Gu. A classification of flotation froth based on geometry [C]. Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation. Art. No.4303987.2007:2716-2720.
[59]. 程翠兰,阳春华,周开军,等.基于非线性模糊纹理谱的浮选泡沫图像纹理特征提取[J].矿业工程研究,2009,24(4)：62-66.
[60].王勇.煤泥浮选泡沫图像特征的研究[D].北京：中国矿业大学(北京)2002.
[61].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,2001,1(1)：41-43.
[62]. 路迈西,王勇,王凡,等.利用阈值分割技术提取煤泥浮选泡沫图像的物理特征[J].煤炭科学技术,2002,30(8)：34-37.
[63]. 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.
[64]. D. W. Moolman, C. Aldrich. Digital image processing as a tool for on-line monitoring of froth in flotation plants [J]. Minerals Engineering,1994,7(9): 1149-1164.
[65]. H. Hyotyniemi, R. Ylinen. Modeling of visual flotation froth data [J]. Control Engineering Practice,2000,8(3):313-318.
[66]. C. P. Botha. An Online Machine Vision Froth Flotation Analysis Platform [D]. South Africa, Stellenbosch:University of Stellenbosch,1999.
[67]. D.P. Kottke, Y. Sun. Motion estimation via cluster matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1994, 16(11):1128-1132.
[68]. J.J. Francis, G. De Jager. An investigation into the suitability of various motion estimation algorithms for froth imaging [C]. Proceedings of the 1998 South African Symposium on Communications and Signal Processing (COMSIG '98),2001:139-142.
[69]. J. Kaartinen, J. Hatonen, H. Hyotyniemi, et al. Machine vision based control of zinc flotation-A case study [J]. Control Engineering Practice,2006,14(12): 1455-1466.
[70]. P. N. Holtham, K. K. Nguyen. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. International Journal of Mineral Processing,2002,64(2-3):163-180.
[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]. 王雅琳,欧文军,阳春华,等.基于PCA和改进BP神经网络的浮选精矿品位在线预测[C].Proceedings of the 29th Chinese Control Conference. Beijing,2010:29-31.
[73]. 章寅.多模型融合软测量方法研究与应用[D].兰州：兰州理工大学,2011.
[74].俞金寿.软测量技术及其应用[J].自动化仪表,2008,29(1)：1-7.
[75]. 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],冶金自动化,2005,29(1)：19-23.
[76]. 李春富.基于数据的软测量建模方法及其应用的研究[D].北京：清华大学,2005.
[77]. 李修亮.软测量建模方法研究与应用[D].杭州：浙江大学,2009.
[78]. P. Kadlec, B. Gabrys, S. Strandt. Data-driven soft sensors in the process industry [J]. Computers & Chemical Engineering,2009,33(4):795-814.
[79]. P. Kadlec, R. Grbic, B. Gabrys. Review of adaptation mechanisms for data-driven soft sensors [J]. Computers & Chemical Engineering,2011, 35(1):1-24.
[80]. F. Ahmed, S. Nazir, Y. Yeo. A new soft sensor based on recursive partial least squares for online melt index predictions in grade-changing HDPE operations [J]. Chemical Product and Process Modeling,2009,4, (1):1934-2659.
[81]. J. Shi, X. Liu. Product Quality Prediction by a Neural Soft-Sensor Based on MSA and PCA [J]. International Journal of Automation and Computing,2006, 1:17-22.
[82]. 张瑶.基于动态递归模糊神经网络的微生物发酵过程软测量方法研究[D].镇江：江苏大学,2010.
[83]. 韩璞,王东风,翟永杰.基于神经网络的火电厂烟气含氧量软测量[J].信息与控制,2001,30(2)：189-192.
[84]. S. Geethalakshmi. Artificial Neural Network Based Soft Sensor for Fermentation of Recombinant Pichia Pastoris [C]. International Conference on advances in Computer Engineering (ACE), Bangalore, Karnataka, India, 2010:148-152.
[85]. 工锡淮,李少远,席裕庚.基于自适应模糊聚类的神经网络软测量建模方法[J].控制与决策,2004,19(8)：951-953.
[86]. 常玉清,王福利,王小刚,等.基于支持向量机的软测量方法及其在生化过程中的应用[J].仪器仪表学报,2006,27(3)：241-271.
[87]. C. Lin, S. Wang. Fuzzy support vector machines [J]. IEEE Transactions on Neural Networks,2002,13(2):464-471.
[88]. 冯瑞.支持向量机及其在工业过程软测量中的应用研究[D].上海：上海交通大学,2003.
[89]. 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.
[90]. P. Stoica, Y. Selen, J. Li. Multi-model approach to model selection [J]. Digital Signal Processing,2004,14(5):399-412.
[91].梅振益.基于数据驱动的多模型软测量研究[D].无锡：江南大学,2011.
[92]. 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(自然科学版),2008,29(1)：33-36.
[93]. 张伟,胡昌华,郑恩让.基于改进竞争聚类的RBFN纸浆漂白MIMO软测量[J].仪器仪表学报,2002,29(3)S 1：288-294.
[94]. 赵昀,黄志尧,王保良,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.
[95]. 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.
[96]. 贾润达,毛志忠,常玉清,等.钴湿法冶炼萃取过程中的组分含量软测量 [J].控制与决策,2009,24(4)：632-636.
[97]. 杨强大,王福利,常玉清,等.并联型混合建模方法在诺西肽发酵过程中的应用[J].系统仿真学报,2009,21(1)：1-4.
[98]. 王恒,贾民平,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.
[99]. K. Chang, S. Chiang. An integrated model for predicting rainfall-induced landslides [J], Geomorphology,2009,105:366-373.
[100].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)：481-487.
[101].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].化工自动化及仪表,2009,36(2)：29-32.
[102].许传龙,汤光华,杨道业,等.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.
[103].李炜,章寅.异类多模型动态融合软测量方法研究与应用[J].化工自动化及仪表,2010,37(8)：42-45.
[104]. X. Li, H. Su, J. Chu. Multiple model soft-sensor based on affinity propagation, gaussian process and bayesian committee machine [J]. Chinese Journal of Chemical Engineering,2009,17(1):95-99.
[105].毛志亮.混合核函数支持向量机在发酵过程建模中的应用研究[D].无锡：江南大学,2011.
[106]. Q. Duan, N. K. Ajami, X. Gao, et al. Multi-model ensemble hydrologic prediction using Bayesian model averaging [J]. Advances in Water Resources, 2007,30(5):1371-1386.
[107]. M. Gonen, E. Alpaydin. Cost-conscious multiple kernel learning [J]. Pattern Recognition Letters,2010,31 (9):959-965.
[108].毛志忠,田慧欣,王琰.基于AdaBoost混合模型的LF炉钢水终点温度软测量[J].仪器仪表学报,2008,29(3)：662-667.
[109].何亮,宋擒豹,海振,等.基于Bagging的组合k-NN预测模型与方法[J].控制与决策,2010,25(1)：48-52.
[110].樊绍胜,王耀南.基于特征选取与多RBF神经网络的冷凝器污垢软测量[J].仪器仪表学报,2008,29(4)：723-728.
[111].杨慧中,邓玉俊.基于自适应增强算法的支持向量机组合模型[J].控制与决策,2011,26(2)：316-319.
[112]. A. Chaouachi, R. M. Kamel, Ken Nagasaka. A novel multi-model neuro-fuzzy-based MPPT for three-phase grid-connected photovoltaic system [J]. Solar Energy,2010,84(12):2219-2229.
[113]. Z. Su, P. Wang, J. Shen, et al.Multi-model strategy based evidential soft sensor model for predicting evaluation of variables with uncertainty [J]. Applied Soft Computing,2011,11(2):2595-2610.
[114]. S. N.Yew, S. Rajagopalan. An adjoined multi-model approach for monitoring batch and transient operations [J]. Computers and Chemical Engineering,2009, 33(4):887-902.
[115].刘家瑞,刘祥民.应用选矿-拜耳法工艺处理一水硬铝石型中低品位铝土矿生产氧化铝的工业实践[J].轻金属,2005,4：11-14.
[116].王永红.铝土矿正浮选尾矿脱水新工艺的研究[D].西安：西安建筑科技大学,2006.
[117].刘焦萍,铝土矿含硅矿物在选矿—拜耳法生产中的行为初探[J].有色金属：选矿部分,2002,1：7-11.
[118]. F.H.B. de Castro, M.C. de Hoces, A.G. Borrego.The effect of pH modifier on the flotation of celestite with sodium oleate and sodium metasilicate [J]. Minerals Engineering,1998,11(10):989-992.
[119].朱腾,王京春,熊智华.基于改进DE-NMPC的酸碱中和反应pH值控制[J].自动化学报,2010,36(1)：159-163.
[120].陈远道.高效铝土矿浮选捕收剂的研究与应用[D].长沙：中南大学,2006.
[121].杜金芳.铝土矿浮选过程粗选矿浆pH值软测量模型及应用[D].长沙：中南大学,2011.
[122].王婷.连续搅拌反应釜(CSTR)反应物浓度软测量方法研究[D].沈阳：东北大学,2008.
[123]. C. T. O'Connor, E. W. Randall, C. M. Goodall. Measurement of the effects of physical and chemical variables on bubble size [J]. International Journal of Mineral Processing,1990,28(1-2):139-149.
[124].周开军,王一军,许灿辉.基于改进FCM和形态学的浮选泡沫形态特征提取[J].中南大学学报(自然科学版),2010,41(3)：994一1000.
[125].李明喜.基于多源图像融合的收获目标准确定位研究[D].镇江：江苏大学,2008.
[126].邱兆美.蝴蝶鳞片微观耦合结构及其光学性能与仿生研究[D].长春：吉林大学,2008.
[127].任会峰,阳春华,周璇,等.基于泡沫图像特征加权SVM的浮选工况识别[J].浙江大学学报(工学版),2011,45(12)：2115-2119.
[128]. G. J. Klinker. A physical approach to color image understanding [J]. International Journal of Computer Vision,1990,4(1):7-38.
[129]. S. Shafer. Using color to separate reflection components [J]. Color Research and Application,1985,10(4):210-218.
[130]. G J. Klinker, S. A. Shafer, T. Kanade. Using a color reflection model to separate highlights from object color [C]. In ICCV, London, UK,1987: 145-150.
[131]. T. Chan, J. Shen. Mathematical models for local nontexture inpainting [J]. SIAM Journal on Applied Mathematics,2002,62(3):1019-1043.
[132].周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].长沙：中南大学,2010.
[133].林瑶,田捷.医学图像分割方法综述[J].模式识别与人工智能,2002,15(2)：192-204.
[134]. C. Yang, C. Xu, X. Mu, 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.
[135]. J. N. Kapur, P. K. Sahoo, A. K. C. Wong. A new method for graylevel picture thresholding using the entropy of the histogram [J].Computer Vision Graphics Image Process,1985,29(3):273-285.
[136]. A. S. Abutaleb. Automatic thresholding of graylevel pictures using two-dimension entropy [J]. Computer Vision Graphics and Image Process, 1989,47(1):22-32.
[137]. P. Y. Pai, C. C. Chang, Y. K. Chan, et al. An adaptable threshold detector, Information Sciences,2011,181(8):1463-1483.
[138]. H. Ren, C. Yang, Z. Zeng, et al. A novel fitness feedback particle swarm optimization [J]. Computer Science Application and Education,2011, 1(1):71-75.
[139]. L.Vincent, P. Soille. Watersheds in digital spaces:an efficient algorithm based on immersion simulations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[140]. H. Zhang, J. E. Fritts, S. A. Goldman. Image segmentation evaluation:a survey of unsupervised methods [J].Computer Vision and Image Understanding,2008,110(2):260-280.
[141].刘占生,窦唯.基于旋转机械振动参数图形融合灰度共生矩阵的故障诊断方法[J].中国电机工程学报,2008,28(2)：88-95.
[142].傅永峰.软测量建模方法研究及其工业应用[D].杭州：浙江大学,2007.
[143].郭景华.基于数据驱动的软测量建模技术应用研究[D].无锡：江南大学,2009.
[144].李津蓉.数据协调模型及显著误差检测技术研究[D].杭州：浙江大学,2003.
[145].杨斌,田永青,朱仲英.智能建模方法中的数据预处理[J].信息与控制,2002,31(4)：380-384.
[146].施闻明,朱琪.惯导系统动态数据预处理方法研究[J].电光与控制,2007,14(5)：172-174.
[147].董纯.软测量技术及其在聚醋酸乙烯聚合度的在线检测中的应用[D].上海：上海交通大学,2008.
[148].刘瑞兰.软测量技术若干问题的研究及工业应用[D].杭州：浙江大学,2004.
[149]. V. N. Vapnik. Statistical Learning Theory [M].New York:Springer-Verlag, 1998.
[150]. J. A. K. Suykens, J. Vandewalle. Least squares support vector machine classifiers [J].Neural Processing Letters,1999,9(3):293-300.
[151].汪洪桥,孙富春,蔡艳宁,等.多核学习方法[J].自动化学报,2010,36(8)：1037-1050.
[152]. F. R. Bach, G. R. G. Lanckriet. Multiple kernel learning, conic duality, and the SMO algorithm [C]. In Proceedings of the 21st International Conference on Machine Learning, New York, USA,2004.
[153].赵永平,孙健国.一类非平坦函数的多核最小二乘支持向量机的鲁棒回归算法[J].信息与控制,2008,37(2)：160-165.
[154]. X. Y. Zeng, X. W. Chen. SMO-based pruning methods for sparse least squares support vector machines [J]. IEEE Transactions on Neural Networks,2005, 16(6):1541-1546.
[155].李勇刚.基于智能集成模型的苛性比值与溶出率软测量及应用研究[D].长沙：中南大学,2004.
[156].朱波.氧化铝生产苛性比值软测量神经网络模型的在线修正方法研究[D].长沙：中南大学,2005.
[157]. J. A. K. Suykens, L. Lukas, J. Vandewalle. Sparse approximation using least squares support vector machines [C]. IEEE International Symposium on Circuits and Systems-ISCAS,2000.
[158].桂卫华,阳春华,李勇刚,等.基于数据驱动的铜闪速熔炼过程操作模式优化及应用[J].自动化学报,2009,35(6)：717-724.
[159].丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1)：2-10.
[160].汪廷华,田盛丰,黄厚宽.特征加权支持向量机[J].电子与信息学报,2009,31(3)：514-518.
[161].阳春华,任会峰,桂卫华,等.基于泡沫纹理信度分配SVM的矿物浮选工况识别[J].仪器仪表学报,2011,32(10)：2205-2209.
[162].哈明虎,王超,张植明,等.不确定统计学习理论[M].北京,科学出版社,2010.
[163]. C. W. HSU, C. J. LIN. A comparison of methods for multi-class support vector machines [J]. IEEE Transactions on Neural Networks,2002,13(2):415-425.
[164].李昆仑,黄厚宽,田盛丰.模糊多类SVM模型[J].电子学报,2004,32(5)：830-832.
[165]. S. Abe, T. Inoue. Fuzzy support vector machines for multiclass problems [C]. The European Symposium on Artificial Neural Networks, Bruges (Belgium), 2002:113-118.
[166].冯瑞,沈伟,张艳珠,等.基于F_SVMs多模型建模方法[J].控制与决策,2003,18(6)：646-650.
[167].李昆仑,黄厚宽,田盛丰,等.模糊多类支持向量机及其在入侵检测中的应用[J].计算机学报,2005,28(2)：274-280.
[168]. N. Barbian, K. Hadler, J. J. Cilliers. The frothstability column:Measuring froth stability at an industrial scale [J]. Minerals Engineering,2006, 19(6-8):713-718.
[2]. 胡熙庚,黄和慰,毛钜凡,等.浮选理论与工艺[M].长沙：中南工业大学出版社,1991.
[3]. 许灿辉.矿物浮选气泡速度和尺寸分布特征提取方法与应用[D].长沙：中南大学,2011.
[4]. J.V. Mehrabani, M. Noaparast, S.M. Mousavi, et al. Process optimization and modelling of sphalerite flotation from a low-grade Zn-Pb ore using response surface methodology [J]. Separation and Purification Technology,2010, 72:242-249.
[5]. A. A. Al-Shamrani, A. James, H. Xiao. Separation of oil from water by dissolved air flotation [J]. Colloids and Surfaces A:Physicochemical and Engineering Aspects,2002,209:15-26.
[6]. S. Lasocki, J. Antoniuk, J. Moscicki. Environmental protection problems in the vicinity of the Zelazny most flotation wastes depository in Poland[J].Journal of Environmental Science and Health Part a-Toxic/Hazardous Substances & Environmental Engineering,2003, 38(8):1435-1443.
[7]. B. Albijanic, O. Ozdemir, A. V. Nguyen, et al. A review of induction and attachment times of wetting thin films between air bubbles and particles and its relevance in the separation of particles by flotation [J]. Advances in Colloid and Interface Science,2010,159:1-21.
[8]. G. Wang, F. J. Sotillo, G. M. Lilley. Froth flotation process with ph modification [P].2008-8-21.
[9]. 任会峰,阳春华,周璇,等.基于最小二乘支持向量回归机的矿浆酸碱度鲁棒软测量[J].上海交通大学学报,2011,45(8)：1136-1145.
[10]. X. Ma, W. J. Bruckard, R. Holmes. Effect of collector, pH and ionic strength on the cationic flotation of kaolinite [J].International Journal of Mineral Processing,2009,93(1):54-58.
[11]. 阳春华,任会峰,许灿辉,等.基于稀疏多核LSSVM的浮选关键指标软测量.中国有色金属学报,2011,21(12)：3149-3154.
[12]. 黄宋魏,张博亚,胡娟,等.pH计及其在浮选中的应用[J].有色金属(选矿 部分),2008,2：41-45.
[13]. 阳春华,任会峰,桂卫华,等.基于机器视觉的矿物浮选pH软测量方法[J].计算机工程与应用,2011,47(1)：228-248.
[14]. J. Bouchard, A. Desbiens, R. Villar, et al. Column flotation simulation and control:An overview [J]. Minerals Engineering,2009,22(6):519-529.
[15]. G. Luttrell, R. Yoon. A flotation column simulator based on hydrodynamic principles [J]. International Journal of Mineral Processing,1991, 33(1-4):355-368.
[16]. K.V. Sastry, D.D. Lofftus. Mathematical modeling and computer simulation of column flotation [C]. Column Flotation'88, SME, Littleton, CO, USA, 1988:57-68.
[17]. C.-J. Kho, H.-J. Sohn. Column flotation of talc [J]. International Journal of Mineral Processing,1989,27(1-2):157-167.
[18]. G. S. Dbobby, J. A. Finch. Particle size dependence in flotation derived from fundamental model of the capture process [J]. International Journal of Mineral Processing,1987,21(3-4):241-260.
[19]. R. Tuteja, D. Spottiswood, V. Misra. Mathematical models of the column flotation process -a review [J].Minerals Engineering,1994,7 (12):1459-1472.
[20]. B. Oteyaka, H. Soto. Modelling of negative bias column for coarse particles flotation [J]. Minerals Engineering,1995,8 (1-2):91-100.
[21]. S. Gupta, P.-H. Liu, S. Svoronos. Hybrid first-principles/neural networks models for column flotation [J]. AIChE Journal,1999,45(3):557-566.
[22]. M. Maldonado, A. Desbiens, R. del Villar. An update on the estimation of the froth depth using conductivity measurements [J]. Minerals Engineering,2008, 21(12-14):935-939.
[23]. M. Persechini, F. Jota, A. Peres. Dynamic model of a flotation column [J]. Minerals Engineering,2000,13(14-15):1465-1481.
[24]. D. Hyma, A. Salama. Design and implementation of a process control system for column flotation [J]. CIM Bulletin,1993,86 (973):50-54.
[25]. 孙德四,施爱加.灰色预测模型与浮选动力学多重模型[J].金属矿山,2002,8：37-39.
[26]. 周俊武,孙传尧.RBF网络在硫化矿浮选过程建模中的应用研究[J].有色冶金设计与研究,2003,24：135-140.
[27]. 郝振,桂卫华,阳春华,等.基于灰色补偿的浮选过程回收率预测模型[J]. 控制工程,2009,16(1)：66-69.
[28]. 袁红霞,杨英杰.基于RBF网络的胶磷矿浮选精矿指标预测模型[J].化工矿物与加工,2011,2：1-4.
[29]. 刘潭,张勇.基于粗糙集-BP神经网络的浮选槽液位预测[J].辽宁科技大学学报,2010,33(5)：525-529.
[30]. 张勇,王介生.基于PCA-RBF神经网络的浮选过程软测量建模[J].南京航空航天大学学报,2006,38(S1)：116-119.
[31]. 耿增显,柴天佑.基于LS-SVM的浮选过程工艺技术指标软测量[J].系统仿真学报,2008,20(23)：6321-6324.
[32]. C. Aldrich, C. Marais, B.J. Shean, et al.Online monitoring and control of froth flotation systems with machine vision:A review [J]. International Journal of Mineral Processing,2010,96(1-4):1-13.
[33]. D. W. Moolman, C. Aldrich, J. S. J. Deventer, et al. The classification of froth structures in copper flotation plant by means of a neural net [J]. International Journal of Mineral Processing,1995,43(3-4):193-208.
[34]. 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.
[35]. J. M. Hargrave, S. T. Hall. Diagnosis of concentrate grade and mass flow rate in tin flotation from color and surface texture analysis [J]. Minerals Engineering,1997,6(10):613-621.
[36]. J. J. Liu, J. F. MacGregor, C. Duchesne, et al. Flotation froth monitoring using multiresolutional multivariate image analysis [J]. Minerals Engineering,2005, 18(1):65-76.
[37]. H. Hyotyniemi, R.Ylinen. Modeling of visual flotation froth data [J]. Control Engineering Practice,2000,8(10):313-318.
[38]. J. Hatonen, H. Hyotyniemi, J. Miettunen. Using image information and partial least squares method to estimate mineral concentrations in mineral flotation [C]. In:John A. M.. Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials, Hawaii, USA,1999, 459-464.
[39]. G. Bonifazi, S. Serranti, F. Volpe, et al. Characterisation of flotation froth colour and structure by machine vision [J]. Computers & Geosciences,2001, 27(9):1111-1117.
[40]. J.F. Reddick, A.H. Hesketh, S.H. Morar, et al. An evaluationof factors affecting the robustness of colour measurement and its potential to predict the grade of flotation concentrate [J]. Minerals Engineering,2009,22(1):64-69.
[41]. D. W. Moolman, C. Aldrich, J. S. Deventer. The interpretation of flotation froth surfaces by using digital image analysis and neural networks [J]. Chemical Engineering Science,1995,50(22):3501-3513.
[42]. B. Lin, B. Reche, J. K. H. Knudsen, et al. Bubble size estimation for flotation processes [J]. Minerals Engineering,2008,21(7):539-548.
[43]. W. X. Wang, O. Stephansson. A robust bubble delineation algorithm for froth images [C], Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials,1999,1:471-476.
[44]. W. Wang, L. Li. Image analysis and computer vision for mineral froth [C]. IEEE International Conference on Mechatronics and Automation, ICMA,2005, 1790-1795.
[45]. C. Citir, Z. Aktas, R. Berber. Off-line image analysis for froth flotation of coal [J]. Computers & Chemical Engineering,2004,28(5):625-632.
[46]. C. Yang, C. Xu, W. Gui, 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(4): 316-322.
[47]. 谢永芳,陈辉,桂卫华,等.一种新的基于纹理图像的分数阶Sobel算子[C].第三十届中国控制会议,山东烟台,2011：3100-3104.
[48]. G. Bonifazi, S. Serranti, F. Volpe, et al. A combined morphological and color based approach to characterization of froth bubbles [C]. Proceedings of the 2nd International Conference on Intelligent Processing and Manufacturing of Materials,1999,1:465-470.
[49]. N. Sadr-Kazemi, J.J. Cilliers. An image processing algorithm for measurement of flotation froth bubble size and shape distributions [J]. Minerals Engineering, 1997,10(10):1075-1083.
[50]. 谷莹莹,林小竹,李左丽,等.基于分水岭变换的浮选泡沫图像分割[J].北京石油化工学院学报,2007,15(1)：61-66.
[51]. 阳春华,杨尽英,牟学民,等.基于聚类预分割和高低精度距离重构的彩色浮选泡沫图像分割[J].电子与信息学报,2008,30(6)：1286-1290.
[52]. M. Bharati, J. Liu, J.F. MacGregor. Image texture analysis:methods and comparisons [J]. Chemometrics and Intelligent Laboratory Systems,2004, 72(1):57-71.
[53]. G. Bartolacci, P. Pelletier Jr., J. Tessier Jr., 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]. Minerals Engineering,2006, 19(6-8):734-747.
[54]. J.J. Liu, J.F. MacGregor. On the extraction of spectral and spatial information from images [J]. Chemometrics and Intelligent Laboratory Systems,2007, 85(1):119-130.
[55]. 唐朝晖,孙园园,桂卫华,等.基于小波变换的浮选泡沫图像纹理特征提取[J].计算机工程,2011,37(18)：206-208.
[56]. 刘金平,桂卫华,牟学民,等.基于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.
[57]. K.K. Nguyen, P. Holtham. The application of pixel tracing techniques in the flotation process [C]. Proceedings of the first joint Australian and New Zealand biennial conference on Digital Imaging and Vision Computing and Applications.1997:207-212.
[58]. X. Z. Lin, G.A. Zhao, Y.B. Gu. A classification of flotation froth based on geometry [C]. Proceedings of the 2007 IEEE International Conference on Mechatronics and Automation. Art. No.4303987.2007:2716-2720.
[59]. 程翠兰,阳春华,周开军,等.基于非线性模糊纹理谱的浮选泡沫图像纹理特征提取[J].矿业工程研究,2009,24(4)：62-66.
[60].王勇.煤泥浮选泡沫图像特征的研究[D].北京：中国矿业大学(北京)2002.
[61].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,2001,1(1)：41-43.
[62]. 路迈西,王勇,王凡,等.利用阈值分割技术提取煤泥浮选泡沫图像的物理特征[J].煤炭科学技术,2002,30(8)：34-37.
[63]. 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.
[64]. D. W. Moolman, C. Aldrich. Digital image processing as a tool for on-line monitoring of froth in flotation plants [J]. Minerals Engineering,1994,7(9): 1149-1164.
[65]. H. Hyotyniemi, R. Ylinen. Modeling of visual flotation froth data [J]. Control Engineering Practice,2000,8(3):313-318.
[66]. C. P. Botha. An Online Machine Vision Froth Flotation Analysis Platform [D]. South Africa, Stellenbosch:University of Stellenbosch,1999.
[67]. D.P. Kottke, Y. Sun. Motion estimation via cluster matching [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1994, 16(11):1128-1132.
[68]. J.J. Francis, G. De Jager. An investigation into the suitability of various motion estimation algorithms for froth imaging [C]. Proceedings of the 1998 South African Symposium on Communications and Signal Processing (COMSIG '98),2001:139-142.
[69]. J. Kaartinen, J. Hatonen, H. Hyotyniemi, et al. Machine vision based control of zinc flotation-A case study [J]. Control Engineering Practice,2006,14(12): 1455-1466.
[70]. P. N. Holtham, K. K. Nguyen. On-line analysis of froth surface in coal and mineral flotation using JKFrothCam [J]. International Journal of Mineral Processing,2002,64(2-3):163-180.
[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]. 王雅琳,欧文军,阳春华,等.基于PCA和改进BP神经网络的浮选精矿品位在线预测[C].Proceedings of the 29th Chinese Control Conference. Beijing,2010:29-31.
[73]. 章寅.多模型融合软测量方法研究与应用[D].兰州：兰州理工大学,2011.
[74].俞金寿.软测量技术及其应用[J].自动化仪表,2008,29(1)：1-7.
[75]. 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],冶金自动化,2005,29(1)：19-23.
[76]. 李春富.基于数据的软测量建模方法及其应用的研究[D].北京：清华大学,2005.
[77]. 李修亮.软测量建模方法研究与应用[D].杭州：浙江大学,2009.
[78]. P. Kadlec, B. Gabrys, S. Strandt. Data-driven soft sensors in the process industry [J]. Computers & Chemical Engineering,2009,33(4):795-814.
[79]. P. Kadlec, R. Grbic, B. Gabrys. Review of adaptation mechanisms for data-driven soft sensors [J]. Computers & Chemical Engineering,2011, 35(1):1-24.
[80]. F. Ahmed, S. Nazir, Y. Yeo. A new soft sensor based on recursive partial least squares for online melt index predictions in grade-changing HDPE operations [J]. Chemical Product and Process Modeling,2009,4, (1):1934-2659.
[81]. J. Shi, X. Liu. Product Quality Prediction by a Neural Soft-Sensor Based on MSA and PCA [J]. International Journal of Automation and Computing,2006, 1:17-22.
[82]. 张瑶.基于动态递归模糊神经网络的微生物发酵过程软测量方法研究[D].镇江：江苏大学,2010.
[83]. 韩璞,王东风,翟永杰.基于神经网络的火电厂烟气含氧量软测量[J].信息与控制,2001,30(2)：189-192.
[84]. S. Geethalakshmi. Artificial Neural Network Based Soft Sensor for Fermentation of Recombinant Pichia Pastoris [C]. International Conference on advances in Computer Engineering (ACE), Bangalore, Karnataka, India, 2010:148-152.
[85]. 工锡淮,李少远,席裕庚.基于自适应模糊聚类的神经网络软测量建模方法[J].控制与决策,2004,19(8)：951-953.
[86]. 常玉清,王福利,王小刚,等.基于支持向量机的软测量方法及其在生化过程中的应用[J].仪器仪表学报,2006,27(3)：241-271.
[87]. C. Lin, S. Wang. Fuzzy support vector machines [J]. IEEE Transactions on Neural Networks,2002,13(2):464-471.
[88]. 冯瑞.支持向量机及其在工业过程软测量中的应用研究[D].上海：上海交通大学,2003.
[89]. 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.
[90]. P. Stoica, Y. Selen, J. Li. Multi-model approach to model selection [J]. Digital Signal Processing,2004,14(5):399-412.
[91].梅振益.基于数据驱动的多模型软测量研究[D].无锡：江南大学,2011.
[92]. 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(自然科学版),2008,29(1)：33-36.
[93]. 张伟,胡昌华,郑恩让.基于改进竞争聚类的RBFN纸浆漂白MIMO软测量[J].仪器仪表学报,2002,29(3)S 1：288-294.
[94]. 赵昀,黄志尧,王保良,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.
[95]. 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.
[96]. 贾润达,毛志忠,常玉清,等.钴湿法冶炼萃取过程中的组分含量软测量 [J].控制与决策,2009,24(4)：632-636.
[97]. 杨强大,王福利,常玉清,等.并联型混合建模方法在诺西肽发酵过程中的应用[J].系统仿真学报,2009,21(1)：1-4.
[98]. 王恒,贾民平,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.
[99]. K. Chang, S. Chiang. An integrated model for predicting rainfall-induced landslides [J], Geomorphology,2009,105:366-373.
[100].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)：481-487.
[101].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].化工自动化及仪表,2009,36(2)：29-32.
[102].许传龙,汤光华,杨道业,等.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.
[103].李炜,章寅.异类多模型动态融合软测量方法研究与应用[J].化工自动化及仪表,2010,37(8)：42-45.
[104]. X. Li, H. Su, J. Chu. Multiple model soft-sensor based on affinity propagation, gaussian process and bayesian committee machine [J]. Chinese Journal of Chemical Engineering,2009,17(1):95-99.
[105].毛志亮.混合核函数支持向量机在发酵过程建模中的应用研究[D].无锡：江南大学,2011.
[106]. Q. Duan, N. K. Ajami, X. Gao, et al. Multi-model ensemble hydrologic prediction using Bayesian model averaging [J]. Advances in Water Resources, 2007,30(5):1371-1386.
[107]. M. Gonen, E. Alpaydin. Cost-conscious multiple kernel learning [J]. Pattern Recognition Letters,2010,31 (9):959-965.
[108].毛志忠,田慧欣,王琰.基于AdaBoost混合模型的LF炉钢水终点温度软测量[J].仪器仪表学报,2008,29(3)：662-667.
[109].何亮,宋擒豹,海振,等.基于Bagging的组合k-NN预测模型与方法[J].控制与决策,2010,25(1)：48-52.
[110].樊绍胜,王耀南.基于特征选取与多RBF神经网络的冷凝器污垢软测量[J].仪器仪表学报,2008,29(4)：723-728.
[111].杨慧中,邓玉俊.基于自适应增强算法的支持向量机组合模型[J].控制与决策,2011,26(2)：316-319.
[112]. A. Chaouachi, R. M. Kamel, Ken Nagasaka. A novel multi-model neuro-fuzzy-based MPPT for three-phase grid-connected photovoltaic system [J]. Solar Energy,2010,84(12):2219-2229.
[113]. Z. Su, P. Wang, J. Shen, et al.Multi-model strategy based evidential soft sensor model for predicting evaluation of variables with uncertainty [J]. Applied Soft Computing,2011,11(2):2595-2610.
[114]. S. N.Yew, S. Rajagopalan. An adjoined multi-model approach for monitoring batch and transient operations [J]. Computers and Chemical Engineering,2009, 33(4):887-902.
[115].刘家瑞,刘祥民.应用选矿-拜耳法工艺处理一水硬铝石型中低品位铝土矿生产氧化铝的工业实践[J].轻金属,2005,4：11-14.
[116].王永红.铝土矿正浮选尾矿脱水新工艺的研究[D].西安：西安建筑科技大学,2006.
[117].刘焦萍,铝土矿含硅矿物在选矿—拜耳法生产中的行为初探[J].有色金属：选矿部分,2002,1：7-11.
[118]. F.H.B. de Castro, M.C. de Hoces, A.G. Borrego.The effect of pH modifier on the flotation of celestite with sodium oleate and sodium metasilicate [J]. Minerals Engineering,1998,11(10):989-992.
[119].朱腾,王京春,熊智华.基于改进DE-NMPC的酸碱中和反应pH值控制[J].自动化学报,2010,36(1)：159-163.
[120].陈远道.高效铝土矿浮选捕收剂的研究与应用[D].长沙：中南大学,2006.
[121].杜金芳.铝土矿浮选过程粗选矿浆pH值软测量模型及应用[D].长沙：中南大学,2011.
[122].王婷.连续搅拌反应釜(CSTR)反应物浓度软测量方法研究[D].沈阳：东北大学,2008.
[123]. C. T. O'Connor, E. W. Randall, C. M. Goodall. Measurement of the effects of physical and chemical variables on bubble size [J]. International Journal of Mineral Processing,1990,28(1-2):139-149.
[124].周开军,王一军,许灿辉.基于改进FCM和形态学的浮选泡沫形态特征提取[J].中南大学学报(自然科学版),2010,41(3)：994一1000.
[125].李明喜.基于多源图像融合的收获目标准确定位研究[D].镇江：江苏大学,2008.
[126].邱兆美.蝴蝶鳞片微观耦合结构及其光学性能与仿生研究[D].长春：吉林大学,2008.
[127].任会峰,阳春华,周璇,等.基于泡沫图像特征加权SVM的浮选工况识别[J].浙江大学学报(工学版),2011,45(12)：2115-2119.
[128]. G. J. Klinker. A physical approach to color image understanding [J]. International Journal of Computer Vision,1990,4(1):7-38.
[129]. S. Shafer. Using color to separate reflection components [J]. Color Research and Application,1985,10(4):210-218.
[130]. G J. Klinker, S. A. Shafer, T. Kanade. Using a color reflection model to separate highlights from object color [C]. In ICCV, London, UK,1987: 145-150.
[131]. T. Chan, J. Shen. Mathematical models for local nontexture inpainting [J]. SIAM Journal on Applied Mathematics,2002,62(3):1019-1043.
[132].周开军.矿物浮选泡沫图像形态特征提取方法与应用[D].长沙：中南大学,2010.
[133].林瑶,田捷.医学图像分割方法综述[J].模式识别与人工智能,2002,15(2)：192-204.
[134]. C. Yang, C. Xu, X. Mu, 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.
[135]. J. N. Kapur, P. K. Sahoo, A. K. C. Wong. A new method for graylevel picture thresholding using the entropy of the histogram [J].Computer Vision Graphics Image Process,1985,29(3):273-285.
[136]. A. S. Abutaleb. Automatic thresholding of graylevel pictures using two-dimension entropy [J]. Computer Vision Graphics and Image Process, 1989,47(1):22-32.
[137]. P. Y. Pai, C. C. Chang, Y. K. Chan, et al. An adaptable threshold detector, Information Sciences,2011,181(8):1463-1483.
[138]. H. Ren, C. Yang, Z. Zeng, et al. A novel fitness feedback particle swarm optimization [J]. Computer Science Application and Education,2011, 1(1):71-75.
[139]. L.Vincent, P. Soille. Watersheds in digital spaces:an efficient algorithm based on immersion simulations [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[140]. H. Zhang, J. E. Fritts, S. A. Goldman. Image segmentation evaluation:a survey of unsupervised methods [J].Computer Vision and Image Understanding,2008,110(2):260-280.
[141].刘占生,窦唯.基于旋转机械振动参数图形融合灰度共生矩阵的故障诊断方法[J].中国电机工程学报,2008,28(2)：88-95.
[142].傅永峰.软测量建模方法研究及其工业应用[D].杭州：浙江大学,2007.
[143].郭景华.基于数据驱动的软测量建模技术应用研究[D].无锡：江南大学,2009.
[144].李津蓉.数据协调模型及显著误差检测技术研究[D].杭州：浙江大学,2003.
[145].杨斌,田永青,朱仲英.智能建模方法中的数据预处理[J].信息与控制,2002,31(4)：380-384.
[146].施闻明,朱琪.惯导系统动态数据预处理方法研究[J].电光与控制,2007,14(5)：172-174.
[147].董纯.软测量技术及其在聚醋酸乙烯聚合度的在线检测中的应用[D].上海：上海交通大学,2008.
[148].刘瑞兰.软测量技术若干问题的研究及工业应用[D].杭州：浙江大学,2004.
[149]. V. N. Vapnik. Statistical Learning Theory [M].New York:Springer-Verlag, 1998.
[150]. J. A. K. Suykens, J. Vandewalle. Least squares support vector machine classifiers [J].Neural Processing Letters,1999,9(3):293-300.
[151].汪洪桥,孙富春,蔡艳宁,等.多核学习方法[J].自动化学报,2010,36(8)：1037-1050.
[152]. F. R. Bach, G. R. G. Lanckriet. Multiple kernel learning, conic duality, and the SMO algorithm [C]. In Proceedings of the 21st International Conference on Machine Learning, New York, USA,2004.
[153].赵永平,孙健国.一类非平坦函数的多核最小二乘支持向量机的鲁棒回归算法[J].信息与控制,2008,37(2)：160-165.
[154]. X. Y. Zeng, X. W. Chen. SMO-based pruning methods for sparse least squares support vector machines [J]. IEEE Transactions on Neural Networks,2005, 16(6):1541-1546.
[155].李勇刚.基于智能集成模型的苛性比值与溶出率软测量及应用研究[D].长沙：中南大学,2004.
[156].朱波.氧化铝生产苛性比值软测量神经网络模型的在线修正方法研究[D].长沙：中南大学,2005.
[157]. J. A. K. Suykens, L. Lukas, J. Vandewalle. Sparse approximation using least squares support vector machines [C]. IEEE International Symposium on Circuits and Systems-ISCAS,2000.
[158].桂卫华,阳春华,李勇刚,等.基于数据驱动的铜闪速熔炼过程操作模式优化及应用[J].自动化学报,2009,35(6)：717-724.
[159].丁世飞,齐丙娟,谭红艳.支持向量机理论与算法研究综述[J].电子科技大学学报,2011,40(1)：2-10.
[160].汪廷华,田盛丰,黄厚宽.特征加权支持向量机[J].电子与信息学报,2009,31(3)：514-518.
[161].阳春华,任会峰,桂卫华,等.基于泡沫纹理信度分配SVM的矿物浮选工况识别[J].仪器仪表学报,2011,32(10)：2205-2209.
[162].哈明虎,王超,张植明,等.不确定统计学习理论[M].北京,科学出版社,2010.
[163]. C. W. HSU, C. J. LIN. A comparison of methods for multi-class support vector machines [J]. IEEE Transactions on Neural Networks,2002,13(2):415-425.
[164].李昆仑,黄厚宽,田盛丰.模糊多类SVM模型[J].电子学报,2004,32(5)：830-832.
[165]. S. Abe, T. Inoue. Fuzzy support vector machines for multiclass problems [C]. The European Symposium on Artificial Neural Networks, Bruges (Belgium), 2002:113-118.
[166].冯瑞,沈伟,张艳珠,等.基于F_SVMs多模型建模方法[J].控制与决策,2003,18(6)：646-650.
[167].李昆仑,黄厚宽,田盛丰,等.模糊多类支持向量机及其在入侵检测中的应用[J].计算机学报,2005,28(2)：274-280.
[168]. N. Barbian, K. Hadler, J. J. Cilliers. The frothstability column:Measuring froth stability at an industrial scale [J]. Minerals Engineering,2006, 19(6-8):713-718.