Multivariate statistical monitoring of subway indoor air quality using dynamic concurrent partial least squares

To maintain the health level of indoor air quality (IAQ) in subway stations, the data-driven multivariate statistical method concurrent partial least squares (CPLS) has been successfully applied for output-relevant and input-relevant sensor faults detection. To cope with the dynamic problem of IAQ data, the augmented matrices are applied to CPLS (DCPLS) to achieve the better performance. DCPLS method simultaneously decomposes the input and output data spaces into five subspaces for comprehensive monitoring: a joint input-output subspace, an output principal subspace, an output-residual subspace, an input-principal subspace, and an input-residual subspace. Results of using the underground IAQ data in a subway station demonstrate that the monitoring capability of DCPLS is superior than those of PLS and CPLS. More specifically, the fault detection rates of the bias of PM 10 and PM 2.5 using DCPLS can be improved by approximately 13% and 15%, respectively, in comparison with those of CPLS.

[1]  Sophie Lanone,et al.  Biological effects of particles from the paris subway system. , 2007, Chemical research in toxicology.

[2]  ChangKyoo Yoo,et al.  Multivariate Monitoring and Local Interpretation of Indoor Air Quality in Seoul's Metro System , 2010 .

[3]  Donghua Zhou,et al.  Total projection to latent structures for process monitoring , 2009 .

[4]  ChangKyoo Yoo,et al.  Statistical monitoring of dynamic processes based on dynamic independent component analysis , 2004 .

[5]  Daoping Huang,et al.  Development of Interval Soft Sensors Using Enhanced Just-in-Time Learning and Inductive Confidence Predictor , 2012 .

[6]  B H Jun,et al.  Fault detection using dynamic time warping (DTW) algorithm and discriminant analysis for swine wastewater treatment. , 2011, Journal of hazardous materials.

[7]  Soon Keat Tan,et al.  Localized, Adaptive Recursive Partial Least Squares Regression for Dynamic System Modeling , 2012 .

[8]  Richard D. Braatz,et al.  Indoor air quality control for improving passenger health in subway platforms using an outdoor air quality dependent ventilation system , 2015 .

[9]  Hongbin Liu,et al.  Process modeling based on nonlinear PLS models using a prior knowledge-driven time difference method , 2016 .

[10]  Lennart Möller,et al.  Subway particles are more genotoxic than street particles and induce oxidative stress in cultured human lung cells. , 2005, Chemical research in toxicology.

[11]  ChangKyoo Yoo,et al.  Evaluation of passenger health risk assessment of sustainable indoor air quality monitoring in metro systems based on a non-Gaussian dynamic sensor validation method. , 2014, Journal of hazardous materials.

[12]  ChangKyoo Yoo,et al.  Adaptive neuro-fuzzy inference system based faulty sensor monitoring of indoor air quality in a subway station , 2013, Korean Journal of Chemical Engineering.

[13]  Barry M. Wise,et al.  The process chemometrics approach to process monitoring and fault detection , 1995 .

[14]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[15]  S. Joe Qin,et al.  Statistical process monitoring: basics and beyond , 2003 .

[16]  ChangKyoo Yoo,et al.  Sensor fault identification and reconstruction of indoor air quality (IAQ) data using a multivariate non-Gaussian model in underground building space , 2013 .

[17]  Christos Georgakis,et al.  Disturbance detection and isolation by dynamic principal component analysis , 1995 .

[18]  O. Alfano,et al.  A methodology for modeling photocatalytic reactors for indoor pollution control using previously estimated kinetic parameters. , 2012, Journal of hazardous materials.

[19]  S. Joe Qin,et al.  Quality‐relevant and process‐relevant fault monitoring with concurrent projection to latent structures , 2013 .

[20]  Bin Liu,et al.  A Mixture of Variational Canonical Correlation Analysis for Nonlinear and Quality-Relevant Process Monitoring , 2018, IEEE Transactions on Industrial Electronics.

[21]  ChangKyoo Yoo,et al.  Online monitoring and interpretation of periodic diurnal and seasonal variations of indoor air pollutants in a subway station using parallel factor analysis (PARAFAC) , 2014 .

[22]  A Seaton,et al.  The London Underground: dust and hazards to health , 2005, Occupational and Environmental Medicine.

[23]  Si-Zhao Joe Qin,et al.  Survey on data-driven industrial process monitoring and diagnosis , 2012, Annu. Rev. Control..

[24]  E. Bräuner,et al.  Typical benign indoor aerosol concentrations in public spaces and designing biosensors for pathogen detection: A review , 2014 .

[25]  John F. MacGregor,et al.  Process monitoring and diagnosis by multiblock PLS methods , 1994 .

[26]  Duckshin Park,et al.  A multivariate study for characterizing particulate matter (PM(10), PM(2.5), and PM(1)) in Seoul metropolitan subway stations, Korea. , 2015, Journal of hazardous materials.

[27]  S. Wold,et al.  The kernel algorithm for PLS , 1993 .

[28]  Hongbin Liu,et al.  Modeling of subway indoor air quality using Gaussian process regression. , 2018, Journal of hazardous materials.

[29]  ChangKyoo Yoo,et al.  A robust localized soft sensor for particulate matter modeling in Seoul metro systems. , 2016, Journal of hazardous materials.

[30]  ChangKyoo Yoo,et al.  Sensor Validation for Monitoring Indoor Air Quality in a Subway Station , 2012 .

[31]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[32]  Jeong Tai Kim,et al.  Predictive monitoring and diagnosis of periodic air pollution in a subway station. , 2010, Journal of hazardous materials.