基于多分类概率极限学习机的污水处理过程操作工况识别

doi:10.3969/j.issn.0438-1157.2012.10.024

化工学报 ›› 2012, Vol. 63 ›› Issue (10): 3173-3182.DOI: 10.3969/j.issn.0438-1157.2012.10.024

基于多分类概率极限学习机的污水处理过程操作工况识别

赵立杰^1,2, 袁德成¹, 柴天佑²

1. 沈阳化工大学信息工程学院, 辽宁沈阳 110042;
2. 东北大学流程工业综合自动化国家重点实验室, 辽宁沈阳 110819

收稿日期:2012-02-05 修回日期:2012-04-10 出版日期:2012-10-05 发布日期:2012-10-05
通讯作者: 赵立杰
作者简介:赵立杰(1972- ),女,博士后,副教授。
基金资助:
国家自然科学基金项目(61203102);中国博士后科学基金项目(20100471464)。

Identification of wastewater operational conditions based on multi-classification probabilistic extreme learning machine

ZHAO Lijie^1,2, YUAN Decheng¹, CHAI Tianyou²

1. School of Information Engineering, Shenyang University of Chemical Technology, Shenyang 110042, Liaoning, China;
2. State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang 110819, Liaoning, China

Received:2012-02-05 Revised:2012-04-10 Online:2012-10-05 Published:2012-10-05
Supported by:
supported by the National Natural Science Foundation of China(61203102)and Postdoctoral Science Foundation of China(20100471464).

摘要/Abstract

摘要： 污水处理过程复杂多变的运行工况以及系统脆弱的抗负荷冲击能力,常常导致污水处理厂运行目标难以实现,有效识别污水操作工况的变化对污水处理过程安全运行和操作优化十分重要。为增强未知样本分类可靠性,在概率极限学习机二分类基础上,将其扩展到多分类概率极限学习机方法(extreme learning machine)。该方法首先采用极限学习机建立污水处理过程实时变量和污水处理过程工况编码之间的预报模型,然后根据类别的输出预报值分别建立每个类训练样本潜在函数的均值,确定所有类的条件概率密度函数,非线性最小二乘辨识条件概率密度函数参数,最后根据贝叶斯原理计算所有类的后验概率,由后验概率最大值判别样本所属类别。以辽宁某城市污水处理厂实时数据为背景进行验证,实验结果表明多分类概率极限学习机分类的可靠性和准确性优于极限学习机分类方法。

关键词: 污水处理, 极限学习机, 贝叶斯决策, 多分类

Abstract: Due to the complex varying operational conditions and weak stability to resist the impact loads of influent flow rate and quality,it is difficult to satisfy operational objective of wastewater treatment plants.Therefore,the effective identification of the operational conditions for the complex wastewater treatment processes becomes one of the most important issues due to the potential advantages to be gained from reduced costs,improved productivity and increased production quality.A multi-classification probabilistic extreme learning machine(ELM)was proposed to enhance the reliability of classification by using the combination of extreme learning machine and the Bayesian decision theory.Extreme learning machine was used to build the output coding model between the real time process variables and the operational condition coding in the wastewater treatment process.ELM prediction values fluctuated around the class encoding following a normal Gaussian distribution.A potential function was calculated for each training sample based on the density methods.The potential functions of the training samples for each class were averaged to obtain the probability density function of each class.Parameters of probability density function for each class were estimated by the nonlinear least squares method.It could decrease the misclassification to classify the unknown samples due to the uncertainty of ELM predictions.The proposed method was verified with the data from a small scale industrial wastewater treatment plant,located in Liaoning province,China.Experimental results showed that the proposed method had a relatively better performance than ELM on classification accuracy.

Key words: wastewater treatment, extreme learning machine, Bayesian classification, multi-classification

中图分类号:

TP274.3

赵立杰, 袁德成, 柴天佑. 基于多分类概率极限学习机的污水处理过程操作工况识别[J]. 化工学报, 2012, 63(10): 3173-3182.

ZHAO Lijie, YUAN Decheng, CHAI Tianyou. Identification of wastewater operational conditions based on multi-classification probabilistic extreme learning machine[J]. CIESC Journal, 2012, 63(10): 3173-3182.

参考文献 15

[1]	Rosen C.A chemometric approach to process monitoring and control with applications to wastewater treatment operation.Sweden:Lund University,2001
[2]	Tomita Rosana K ,Park Song W,Sotomayor Oscar A Z.Analysis of activated sludge process using multivariate statistical tools—a PCA approach[J].Chemical Engineering Journal,2002,90(3):283-290
[3]	Rosen C,Yuan Z.Supervisory control of wastewater treatment plants by combining principal component analysis and fuzzy c-means clustering[J].Water Science Technology,2001,43(7):147-156
[4]	Moon T S,Kim Y J,Kim J R,Cha J H,Kim D H,Kim C W.Identification of process operating state with operational map in municipal wastewater treatment plant[J].Journal of Environmental Management,2009,90(2):772-778
[5]	Pekka Teppola,Satu-Pia Mujunen,Pentti Minkkinen.Adaptive fuzzy C-means clustering in process monitoring[J].Chemometrics and Intelligent Laboratory Systems,1999,45(1/2):23-38
[6]	Achmad Widodo,Bo-Suk Yang.Support vector machine in machine condition monitoring and fault diagnosis[J].Mechanical Systems and Signal Processing,2007,21(6):2560-2574
[7]	Zvi Boger.Application of neural networks to water and wastewater treatment plant operation[J].ISA Transactions,1992,31(1):25-33
[8]	Matthew Barker,William Rayens.Partial least squares for discrimination[J].Journal of Chemometrics,2003,17(3):166-173
[9]	Néstor F Pérez,Joan Ferré,Ricard Boqué.Calculation of the reliability of classification in discriminant partial least-squares binary classification[J].Chemometrics and Intelligent Laboratory Systems,2009,95(2):122-128
[10]	Néstor F Pérez,Joan Ferrér,Ricard Boqué,Multi-class classification with probabilistic discriminant partial least squares(p-DPLS)[J].Analytical Chemical Acts,2010,664(1):27-33
[11]	Huang Guangbin,Zhu Qinyu,Siew Chee-Kheong.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/2/3):489-501
[12]	Huang Guangbin,Wang Dianhui,Lan Yuan.Extreme learning machines:a survey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122
[13]	Zhao Lijie,Diao Xiaokun,Yuan Decheng,Tang Wei.Enhanced classification based on probabilistic extreme learning mache in wastewater treatment process[J].Procedia Engineering,2011,15(1):5563-5567
[14]	Jair Cervantes,Li Xiaoou,Yu Wen,Li Kang.Support vector machine classification for large data sets via minimum enclosing ball clustering[J].Neurocomputing,2008,71(4/5/6):611-619
[15]	Faber M,Rasmus Bro.Standard error of prediction for multiway PLS(Ⅰ):Background and a simulation study[J].Chemometrics and Intelligent Laboratory Systems,2002,61(1/2):133-149

基于多分类概率极限学习机的污水处理过程操作工况识别

Identification of wastewater operational conditions based on multi-classification probabilistic extreme learning machine

PDF (PC)

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献 15

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑书闽, 郭鹏程, 颜建国, 王帅, 李文博, 周淇. 微小通道内过冷流动沸腾阻力特性实验及预测研究[J]. 化工学报, 2023, 74(4): 1549-1560.
[2]	王龙洋, 蒙西, 乔俊飞. 基于改进集合经验模态分解和深度信念网络的出水总磷预测[J]. 化工学报, 2021, 72(5): 2745-2753.
[3]	赵杨, 熊伟丽. 基于多策略自适应差分进化算法的污水处理过程多目标优化控制[J]. 化工学报, 2021, 72(4): 2167-2177.
[4]	张璐, 张嘉成, 韩红桂, 乔俊飞. 基于模糊神经网络的污水处理生化除磷过程控制[J]. 化工学报, 2020, 71(3): 1217-1225.
[5]	代学志,熊伟丽. 基于核极限学习机的快速主动学习方法及其软测量应用[J]. 化工学报, 2020, 71(11): 5226-5236.
[6]	柴伟, 郭龙航, 池彬彬. 污水处理厂出水水质变量区间预测建模[J]. 化工学报, 2019, 70(9): 3449-3457.
[7]	杨新, 麻哲瑞, 申赫男, 陈鸿伟. 基于多尺度特征能量-核极限学习机的双循环流化床气流堵塞故障智能诊断[J]. 化工学报, 2019, 70(7): 2616-2625.
[8]	李霏, 杨翠丽, 李文静, 乔俊飞. 基于均匀分布NSGAII算法的污水处理多目标优化控制[J]. 化工学报, 2019, 70(5): 1868-1878.
[9]	吴菁, 刘乙奇, 刘坚, 黄道平, 邱禹, 于广平. 基于动态多核相关向量机的软测量建模研究[J]. 化工学报, 2019, 70(4): 1472-1484.
[10]	张晓晗, 汪平江, 顾祥柏, 徐圆, 贺彦林, 朱群雄. 基于主元提取的鲁棒极限学习机研究及其化工建模应用[J]. 化工学报, 2019, 70(2): 475-480.
[11]	李永明, 史旭东, 熊伟丽. 基于工况识别的污水处理过程多目标优化控制[J]. 化工学报, 2019, 70(11): 4325-4336.
[12]	牛培峰, 王枭飞, 刘楠, 王愿宁, 常玲芳, 张先臣. ASOS-ELM建模方法及在汽轮机热耗率预测中的应用[J]. 化工学报, 2018, 69(9): 3924-3931.
[13]	许玉格, 孙称立, 赖春伶, 罗飞. 基于不平衡学习的集成极限学习机污水处理故障诊断[J]. 化工学报, 2018, 69(7): 3114-3124.
[14]	张雷, 张小刚, 陈华. 基于Gath-Geva算法和核极限学习机的多阶段间歇过程软测量[J]. 化工学报, 2018, 69(6): 2576-2585.
[15]	韩红桂, 刘峥, 乔俊飞. 基于区间二型模糊神经网络污水处理过程溶解氧浓度控制[J]. 化工学报, 2018, 69(3): 1182-1190.