Fault detection of wastewater treatment processes by using commute time distance based LE algorithm
CHEN Ru-qing1, LI Jia-chun2, YU Jin-shou3
1. College of Mechanical and Electrical Engineering, Jiaxing University, Jiaxing 314001, China;
2. College of Mathematics, Physics and Information Engineering, Jiaxing University, Jiaxing 314001, China;
3. Research Institute of Automation, East China University of Science and Technology, Shanghai 200237, China
Performance monitoring and fault diagnosis for wastewater treatment processes was of great significance for safeguarding the normal operation of the treatment process and ensuring the standard quality of effluent water. Aiming at the problems of nonlinearity, uncertainty and susceptibility to random noises in wastewater treatment process, an improved Laplacian Eigenmap (LE) manifold learning algorithm based on commuting time distance (CTD) was proposed to realize the feature extraction of the complex process data. In this algorithm, CTD was used to measure the similarity between samples and construct the neighborhood graph. Both theoretical analysis and simulation test proved that the proposed algorithm could efficiently overcome the sensitivity problem caused by neighborhood parameter and improve the robustness of the normal LE algorithm. Then the CTD based LE algorithm was applied in fault detection modeling for actual wastewater treatment process, and the fault monitoring statistic was constructed in the low-dimensional feature subspace. Application results showed that CTD-LE based model can timely detect the faults with lower missing rate and false rate as compared with normal PCA based model and normal LE based model. Application results showed that this method could provide a feasible solution for fault monitoring of complex industrial processes such as wastewater treatment.
陈如清, 李嘉春, 俞金寿. 基于通勤时间距离的LE污水处理过程故障检测方法[J]. 中国环境科学, 2019, 39(2): 657-665.
CHEN Ru-qing, LI Jia-chun, YU Jin-shou. Fault detection of wastewater treatment processes by using commute time distance based LE algorithm. CHINA ENVIRONMENTAL SCIENCECE, 2019, 39(2): 657-665.
王剑,付正辉,郭怀成.基于区间两阶段的城镇污水处理技术优选模型[J]. 中国环境科学, 2017,37(1):108-115. Wang J, Fu Z H, Guo H C. An inexact two-stage stochastic programming model for optimization of sewage treatment technology[J]. China Environmental Science, 2017,37(1):108-115.
[2]
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 Y G, Deng W K, Chen L D. Online fault diagnosis in wastewater treatment process by kernel-based weighted extreme learning machine[J]. CIESC Jorunal, 2016,67(9):3817-3825.
[3]
罗晓,郑向阳,赵丛丛,等.A/O工艺中污泥浓度对微生物群落结构的影响[J]. 中国环境科学, 2018,38(1):275-283. Luo X, Zheng X Y, Zhao C C. Effects of sludge concentration on microbial community structure in A/O process[J]. China Environmental Science, 2018,38(1):275-283.
[4]
黄道平,邱禹,刘乙奇,等.面向污水处理的数据驱动故障诊断及预测方法综述[J]. 华南理工大学学报(自然科学版), 2015,43(3):111-120. Huang D P, Qiu Y, Liu Y Q, et al. Review of data-driven fault diagnosis and prognosis for wastewater treatment[J]. Journal of South China University of Technology (Natural Science Edition), 2015,43(3):111-120.
[5]
肖红军,刘乙奇,黄道平.面向污水处理的动态变分贝叶斯混合因子故障诊断[J]. 控制理论与应用, 2016,33(11):1519-1526. Xiao H J, Liu Y Q, Huang D P. Dynamic fault diagnosis via variational Bayesian mixture factor analysis with application to wastewater treatment[J]. Control Theory & Applications, 2016,33(11):1519-1526.
[6]
Comas J, Rodriguez J, Sancgezmarre M, et al. A knowledge-based approach to the deflocculation problem:Integrating on-line, off-line, and heuristic information[J]. Water Research, 2003,37(10):2377-2387.
[7]
Han H G, Li Y, Qiao J F. A fuzzy neural network approach for online fault detection in waste water treatment process[J]. Computers & Electrical Engineering, 2014,40(7):2216-2226.
[8]
Dovzan D, Logar V, Skrjanc I. Implementation of an evolving fuzzy model (eFuMo) in a monitoring system for a wastewater treatment process[J]. IEEE Transactions on Fuzzy Systems, 2015,23(5):1761-1776.
[9]
Daniel A, Christian R. Multivariate statistical monitoring of continuous wastewater treatment plants[J]. Engineering Applications of Artificial Intelligence, 2008,21(7):1080-1091.
[10]
Baklouti I, Mansouri M, Ben H A, et al. Monitoring of wastewater treatment plants using improved univariate statistical technique[J]. Process safety and Environmental Protection, 2018,116(2):287-300.
[11]
Liu Y Q, Pan Y P, Sun Z H, et al. Statistical monitoring of wastewater treatment plants using variational Bayesian PCA[J]. Industrial & Engineering Chemistry Research, 2014,53(8):3272-3282.
[12]
Li Z C, Yan, X F. Adaptive selective ensemble-independent component analysis models for process monitoring[J]. Industrial & Engineering Chemistry Research, 2018,57(24):8240-8252.
[13]
Samuelsson O, Bjork A, Zambrano J, et al. Gaussian process regression for monitoring and fault detection of wastewater treatment processes[J]. Water Science and Technology, 2017,75(12):2952-2963.
[14]
Miao A M, Ge Z Q, Song Z H, et al. Nonlocal structure constrained neighborhood preserving embedding model and its application for fault detection[J]. Chemometrics and Intelligent Laboratory Systems, 2015,142:184-196.
[15]
陈如清.基于改进MVU的非线性动态过程故障检测方法[J]. 仪器仪表学报, 2013,34(9):2111-2117. Chen R Q. Improved MVU based fault detection method for nonlinear and dynamic process[J]. Chinese Journal of Scientific Instrument, 2013,34(9):2111-2117.
[16]
Mao Q, Wang L, Tsang I W. A unified probabilistic framework for robust manifold learning and embedding[J]. Machine Learning, 2017,106(5):627-650.
[17]
Bruneau M, Mottet T, Moulin S, et al. A clustering package for nucleotide sequences using Laplacian Eigenmaps and Gaussian mixture model[J]. Computers in Biology and Medicine, 2018,93(2):66-74.
[18]
Yan L, Niu X D. Spectral-Angle-based Laplacian Eigenmaps for nonlinear dimensionality reduction of hyperspectral imagery[J]. Photogrammetric Engineering and Remote Sensing, 2014,80(9):849-861.
[19]
Jiang Q S, Zhu Q X, Wang B F, et al. Nonlinear machine fault detection by semi-supervised Laplacian Eigenmaps[J]. Journal of Mechanical Science and Technology, 2017,31(8):3697-3703.
[20]
Kazor K, Holloway R W, Cath T Y, et al. Comparison of linear and nonlinear dimension reduction techniques for automated process monitoring of a decentralized wastewater treatment facility[J]. Stochastic Environmental research and Risk Assessment, 2016,30(5):1527-1544.
[21]
Kim K H, Choi S. Walking on minimax paths for k-NN search[C]. Proc of the 27th AAAI Conf on Artificial Intelligence. Menlo Park, CA:AAAI, 2013:518-525.
[22]
Qiu H J, Hancock E R. Clustering and embedding using commute times[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2007,29(11):1873-1890.
[23]
Albano J A, Messinger D W, Rotman S R. Commute time distance transformation applied to spectral imagery and its utilization in material clustering[J]. Optical Engineering, 2012,51(7):397-407.
[24]
邵超,张啸剑.基于通勤时间距离的流形聚类与可视化[J]. 计算机研究与发展, 2015,52(8):1757-1767. Shao C, Zhang X J. Manifold clustering and visualization with commute time distance[J]. Journal of Computer Research and Development, 2015,52(8):1757-1767.
[25]
Carlsson B, Zambrano J. Fault detection and isolation of sensors in aeration control systems[J]. Water Science and Technology, 2015, 73(3):648-653.
