基于核函数的加权极限学习机污水处理在线故障诊断

doi:10.11949/j.issn.0438-1157.20160118

化工学报 ›› 2016, Vol. 67 ›› Issue (9): 3817-3825.DOI: 10.11949/j.issn.0438-1157.20160118

基于核函数的加权极限学习机污水处理在线故障诊断

许玉格, 邓文凯, 陈立定

华南理工大学自动化科学与工程学院, 广东广州 510640

收稿日期:2016-01-27 修回日期:2016-04-12 出版日期:2016-09-05 发布日期:2016-09-05
通讯作者: 许玉格
基金资助:
国家自然科学基金项目（61473121）；广东省科技计划项目（2016A020221008）；2016年产学研重点项目（201604010032）。

Online fault diagnosis in wastewater treatment process by kernel-based weighted extreme learning machine

XU Yuge, DENG Wenkai, CHEN Liding

School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, Guangdong, China

Received:2016-01-27 Revised:2016-04-12 Online:2016-09-05 Published:2016-09-05
Supported by:
supported by the National Natural Science Foundation of China (61473121), Science and Technology Planning Project of Guangdong Province, China (2016A020221008) and Special Project on the Integration of Industry, Education and Research of Guangdong Province (201604010032).

摘要/Abstract

摘要：

污水生化处理中的运行故障会引起出水水质不达标、运行费用增高和环境二次污染等严重问题，需要及时准确地对运行故障进行诊断。考虑到污水处理过程运行状态数据的不平衡性造成故障诊断准确率下降，提出了一种基于核函数的加权极限学习机污水处理过程实时在线故障诊断方法。该方法以极限学习机为基础，采用加权的方式处理数据的不平衡特性，通过核函数的非线性映射来提高数据线性可分的程度。仿真实验证明，本文建立的污水处理在线故障诊断模型在线测试精度高，泛化性能好，模型在线更新速度快，能够比较好地满足准确性和实时性，实现对污水处理过程的在线故障诊断。

关键词: 加权极限学习机, 核函数, 在线建模, 污水处理, 故障诊断, 仿真实验

Abstract:

Operation faults in biochemical wastewater treatment process often result in serious issues such as effluent water below quality specification, high operation cost, and secondary environmental pollution, therefore spontaneous and accurate diagnoses are required. Considered the poor accuracy of fault diagnosis induced by imbalanced characteristics of the process data in wastewater treatment, a novel online fault diagnostic model for wastewater treatment process was proposed, i.e., the kernel-based weighted extreme learning machine. Based on extreme learning machine (ELM) theory, weighting scheme was used to resolve the data imbalance and the non-linear mapping of kernel function was used to improve the extent of linear separation. Simulation experiments showed that this online fault diagnostic model has higher measuring precision, better generalization ability, and faster online updating speed, and meet the requirement of accuracy and spontaneity. Therefore, the proposed method can be applied in real-time on-line fault diagnosis in wastewater treatment process.

Key words: weighted extreme learning machine, kernel function, on-line modeling, wastewater treatment, fault diagnosis, simulation experiment

中图分类号:

TP18

许玉格, 邓文凯, 陈立定. 基于核函数的加权极限学习机污水处理在线故障诊断[J]. 化工学报, 2016, 67(9): 3817-3825.

XU Yuge, DENG Wenkai, CHEN Liding. Online fault diagnosis in wastewater treatment process by kernel-based weighted extreme learning machine[J]. CIESC Journal, 2016, 67(9): 3817-3825.

参考文献 17

[1]	胡俊刚, 胡雪梅. 城镇污水处理厂运营现状及自动化控制的应用[J]. 武汉理工大学学报, 2002, 11(24):66-69. HU R G, HU X M. Management and automatically control in water treatment[J]. Journal of Wuhan University of Technology, 2002, 11(24):66-69.
[2]	DE LA FUENTE M J, VEGA P. A Neural networks based approach for fault detection and diagnosis:application to a real process[C]//Proceedings of the 4th IEEE Conference on Control Applications (CCA 1995). 1995:188-193.
[3]	施汉昌, 王玉珏. 污水处理厂故障诊断专家系统[J]. 给水排水, 2001, 27(8):88-90. SHI H C, WANG Y J. Diagnostic expert system for WTTP[J]. Water & Water Engineering, 2001, 27(8):88-90.
[4]	陆林花. 聚类算法及其在污水处理工艺故障诊断中的应用研究[D]. 重庆:重庆大学, 2007. LU L H. Research on clustering algorithms and its application of the fault diagnosis of wastewater treatment process[D]. Chongqing:Chongqing University, 2007.
[5]	范昕炜, 杜树新, 吴铁军. 粗SVM分类方法及其在污水处理过程中的应用[J]. 控制与决策, 2004, 19(5):573-576. FAN X W, DU S X, WU T J. Rough support vector machine and its application to wastewater treatment processes[J]. Control and Decision. 2004, 19(5):573-576.
[6]	钱云. 非均衡数据分类算法若干应用研究[D]. 长春:吉林大学, 2014. QIAN Y. Research on application of classification algorithms for imbalanced data[D]. Changchun:Jilin University, 2014.
[7]	LEE H J, AHN B S, PARK Y M. A fault diagnosis expert system for distribution substations[J]. IEEE Trans. on Power Delivery, 2000, 15(1):92-97.
[8]	刘成忠, 韩俊英. 基于邻域粗糙集的支持向量机在污水处理故障诊断中的应用[J]. 甘肃农业大学学报, 2013, 48(3):176-180. LIU C Z, HAN J Y. Application of support vector machine based on neighborhood rough set to sewage treatment fault diagnoses[J]. Journal of Gansu Agricultural University, 2013, 48(3):176-180.
[9]	TIPPING M E. The relevance vector machine[J]. Advances in Neural Information Processing Systems, 1999, 12(3):652-658.
[10]	TIPPING M E, FAUL A C. Fast marginal likelihood maximization for sparse bayesian models[C]//Proc. 9th International Workshop on Artificial Intelligence and Statistics. Key West, 2003:3-6.
[11]	GALAR M, FERNANDEZ A, BARRENECHEA E, et al. An over view of ensemble methods for binary classifiers in multi-class problems:experimental study on one-vs-one and one-vs-all schemes[J]. Pattern Recognit, 2011, 44(8):1761-1776.
[12]	HSU C W, LIN C J. A comparison of methods for multiclass support vector machines[J]. IEEE Trans. Neural Netw., 2002, 3(2):415-425.
[13]	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine:a new learning scheme of feedforward neural networks[C]//Proceedings of 2004 IEEE International Joint Conference on Neural Networks. 2004:985-990.
[14]	HUANG G B, CHEN L. Convex incremental extreme learning machine[J]. Neurocomputing, 2007, 70(16/17/18):3056-3062.
[15]	HUANG G B, WANG D H, LAN Y. Extreme learning machines:a survey[J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2):107-122.
[16]	许继平, 陈晨, 刘载文, 等. 基于软测量理论的BOD在线检测仪研究[J]. 控制工程, 2010, 17(s1):90-92. XU J P, CHEN C, LIU Z W, et al. Research on BOD online detection instrument based on the theory of soft instrument[J]. Control Engineering of China, 2010, 17(s1):90-92.
[17]	BUCHGRABER T, SHUTIN D, POOR H V. A sliding-window online fast variable sparse Bayesian learning algorithm[C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2011, 45(1):2128-2131.

基于核函数的加权极限学习机污水处理在线故障诊断

Online fault diagnosis in wastewater treatment process by kernel-based weighted 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 17

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张逸豪, 王振雷. 基于最大信息系数的分组支持向量数据描述故障检测[J]. 化工学报, 2023, 74(9): 3865-3878.
[2]	明迁, 高逸, 胡剑, 李盛杰, 王金江. 热交换器泄漏故障虚拟感知方法研究[J]. 化工学报, 2023, 74(4): 1836-1846.
[3]	高学金, 程琨, 韩华云, 高慧慧, 齐咏生. 基于中心损失的条件生成式对抗网络的冷水机组故障诊断[J]. 化工学报, 2022, 73(9): 3950-3962.
[4]	杨静, 林振康, 汤君, 樊铖, 孙克宁. 电池系统的故障特征以及多故障的诊断与识别[J]. 化工学报, 2022, 73(8): 3394-3405.
[5]	孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.
[6]	张成, 潘立志, 李元. 基于加权统计特征KICA的故障检测与诊断方法[J]. 化工学报, 2022, 73(2): 827-837.
[7]	张弛, 李浩, 胡海涛, 朱翀, 张玉莹, 南国鹏, 舒悦. 基于自动特征工程的飞行器轴承故障诊断[J]. 化工学报, 2021, 72(S1): 430-436.
[8]	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.
[9]	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.
[10]	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.
[11]	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.
[12]	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.
[13]	邓佳伟, 邓晓刚, 曹玉苹, 张晓玲. 基于加权统计局部核主元分析的非线性化工过程微小故障诊断方法[J]. 化工学报, 2019, 70(7): 2594-2605.
[14]	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.
[15]	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.