Data-derived soft sensors in biological wastewater treatment - With application of multivariate statistical methods

Henri Haimi

Data-derived soft sensors in biological wastewater treatment - With application of multivariate statistical methods

Julkaisun otsikon käännös: Datapohjaiset virtuaaliset anturit biologisessa jätevedenkäsittelyssä: tilastollisten monimuuttujamenetelmien sovelluksia

Henri Haimi

Tutkimustuotos: Doctoral Thesis › Collection of Articles

Abstrakti

Jäteveden käsittelyvaatimukset ovat kiristyneet asteittain, mihin on vaikuttanut lisääntynyt vesistöjen ekologista tilaa koskeva valveutuneisuus ja, toisaalta, puhdistustekniikoiden kehittyminen. Korkealaatuinen prosessinvalvonta ja -ohjaus ovat olennaisia edellytyksiä tiukentuvien käsittelytavoitteiden saavuttamiseen kustannustehokkaasti. Niihin puolestaan tarvitaan luotettavaa reaaliaikaista informaatiota tärkeistä prosessimuuttujista. Vaikka ajantasaisesti muuttujia analysoivat instrumentit ovat kehittyneet merkittävästi, ei niiden suorituskyky biologisten käsittelyprosessien vaativissa olosuhteissa ole aina riittävä. Väitöskirjan päätavoite oli suunnitella perinteistä instrumentaatiota täydentäviä ohjelmistotyökaluja, jotka mahdollistavat käsittelyprosessien tehokkaamman ja riskittömämmän operoinnin. Koska nykyaikaiset laitokset ovat hyvin instrumentoituja ja niiden historiallista käyttödataa on runsaasti saatavilla, tutkimuksissa käytettiin datapohjaisia lähestymistapoja. Tutkielmassa kehitettiin usein termillä "soft sensor" kutsuttavia virtuaalisia antureita, joissa hyödynnetään dataa prosessoivia ennustavia malleja. Tässä työssä virtuaalisissa antureissa käytetyt mallit perustuvat tilastollisiin monimuuttujamenetelmiin. Niiden suunnittelussa hyödynnettiin erityisesti pääkomponenttianalyysiä muunnoksineen sekä pienimpään neliösummaan perustuvia regressiomenetelmiä. Liikkuvan ikkunan tekniikoita sovellettiin mallien mukauttamiseen prosessien vaihteleviin olosuhteisiin. Työssä tarkasteltiin sekä lineaarisia että epälineaarisia regressiomenetelmiä. Väitöstyön tekniset tutkimukset koskevat suurta yhdyskuntajätevedenpuhdistamoa. Biologisen jälkisuodatusyksikön operointia tukemaan kehitettiin nitraattikonsentraatioita ajantasaisesti ennustavia virtuaalisia antureita. Tutkimuksen jatkeena suunniteltiin mallien tuottamien estimaattien ja niitä vastaavien instrumenttimittausten toisiaan täydentävän käytön mahdollistava vaihtamisjärjestelmä. Virtuaalisten anturien osoitettiin mallintavan nitraattikonsentraatioita tarkasti ja, etenkin integroituina vaihtamisjärjestelmään, lisäävän yksikön ohjauksen käyttövarmuutta. Lisäksi prosessi- ja instrumenttianomalioiden valvontaan soveltuvaa virtuaalista anturia tutkittiin aktiivilieteprosessissa. Ehdotettu järjestelmä anomalian havaitsemiseen edesauttaa mittausten tehokasta käyttöä prosessinohjauksessa. Virtuaalisten anturien demonstroitiin soveltuvan tarkasteltuihin käyttökohteisiin ja omaavan varteenotettavaa potentiaalia käsittelylaitosten operoinnin tukemiseen. Käytettyjen monimuuttujatekniikoiden osoitettiin pystyvän suodattamaan helposti ymmärrettävää ja käyttökelpoista informaatiota monidimensionaalisesta datasta.

Julkaisun otsikon käännös	Datapohjaiset virtuaaliset anturit biologisessa jätevedenkäsittelyssä: tilastollisten monimuuttujamenetelmien sovelluksia
Alkuperäiskieli	Englanti
Pätevyys	Tohtorintutkinto
Myöntävä instituutio	Aalto-yliopisto
Valvoja/neuvonantaja	Vahala, Riku, Vastuuprofessori Mulas, Michela, Ohjaaja Corona, Francesco, Ohjaaja
Kustantaja	Aalto University
Painoksen ISBN	978-952-60-6649-3
Sähköinen ISBN	978-952-60-6650-9
Tila	Julkaistu - 2016
OKM-julkaisutyyppi	G5 Artikkeliväitöskirja

Tutkimusalat

datapohjainen mallinnus
tilastolliset monimuuttujamenetelmät
prosessinvalvonta
virtuaaliset anturit
jätevedenkäsittely

Pääsy asiakirjaan

http://urn.fi/URN:ISBN:978-952-60-6650-9Lisenssi: Määrittelemätön

Siteeraa tätä

@phdthesis{a72becbf3b904a678dbd87a610d60124,

title = "Data-derived soft sensors in biological wastewater treatment - With application of multivariate statistical methods",

abstract = "The increased awareness about the ecological status of the waterbodies and, on the other hand, the advances in the treatment technology have acted as driving forces behind the gradual tightening of wastewater purification requirements. Achieving the stringent treatment targets of wastewater treatment plants cost-efficiently is crucially dependent on the high-grade monitoring and control of the process units. Those, in turn, necessitate reliable real-time information about the primary process variables. In spite of the considerable developments of on-line sensors, demanding conditions in biological treatment processes sometimes give rise to an insufficient performance of instruments. The main motivation for this thesis was to design software tools that enable more efficient and safer treatment process operation by complementing conventional instrumentation. Since modern facilities are amply instrumented and there are plenty of accessible historical data, data-derived approaches were used in the studies. The data were processed together with predictive models providing virtual instruments often referred to as soft sensors. In this thesis, the models at the core of the soft sensors are based on multivariate statistics. In particular, principal component analysis with its variants and least-squares-based regression methods were employed in the soft sensor development. The moving-window techniques were applied so as to adapt the models to time-varying wastewater treatment processes. Both linear and nonlinear regression methods were explored.The technical studies of the thesis concern a large-scale municipal wastewater treatment plant. An array of soft sensors for the on-line prediction of nitrate concentrations was developed to support the operation of the biological post-filtration unit. Then, a system that enables the complementary use of the soft sensor estimates and the corresponding hardware instrument measurements was designed. The soft sensors were found to model nitrate concentrations accurately and, especially when integrated with the proposed switching system, to allow for a more secure control of the unit. In addition, a soft sensor for detecting process and instrument anomalies in the activated sludge process was investigated. The presented anomaly detection system motivates a more efficient use of sensors in the process control.It was demonstrated that soft sensors were applicable to the considered tasks and that they have strong potential for providing support to the operations of treatment facilities. The employed multivariate techniques proved to be capable of extracting easily understandable and practicable information from the high-dimensional data.",

keywords = "data-derived modelling, multivariate statistics, process monitoring, soft sensors, wastewater treatment, datapohjainen mallinnus, tilastolliset monimuuttujamenetelm{\"a}t, prosessinvalvonta, virtuaaliset anturit, j{\"a}tevedenk{\"a}sittely, data-derived modelling, multivariate statistics, process monitoring, soft sensors, wastewater treatment",

author = "Henri Haimi",

year = "2016",

language = "English",

isbn = "978-952-60-6649-3",

series = "Aalto University publication series DOCTORAL DISSERTATIONS",

publisher = "Aalto University",

number = "24",

address = "Finland",

school = "Aalto University",

}

TY - BOOK

T1 - Data-derived soft sensors in biological wastewater treatment - With application of multivariate statistical methods

AU - Haimi, Henri

PY - 2016

Y1 - 2016

N2 - The increased awareness about the ecological status of the waterbodies and, on the other hand, the advances in the treatment technology have acted as driving forces behind the gradual tightening of wastewater purification requirements. Achieving the stringent treatment targets of wastewater treatment plants cost-efficiently is crucially dependent on the high-grade monitoring and control of the process units. Those, in turn, necessitate reliable real-time information about the primary process variables. In spite of the considerable developments of on-line sensors, demanding conditions in biological treatment processes sometimes give rise to an insufficient performance of instruments. The main motivation for this thesis was to design software tools that enable more efficient and safer treatment process operation by complementing conventional instrumentation. Since modern facilities are amply instrumented and there are plenty of accessible historical data, data-derived approaches were used in the studies. The data were processed together with predictive models providing virtual instruments often referred to as soft sensors. In this thesis, the models at the core of the soft sensors are based on multivariate statistics. In particular, principal component analysis with its variants and least-squares-based regression methods were employed in the soft sensor development. The moving-window techniques were applied so as to adapt the models to time-varying wastewater treatment processes. Both linear and nonlinear regression methods were explored.The technical studies of the thesis concern a large-scale municipal wastewater treatment plant. An array of soft sensors for the on-line prediction of nitrate concentrations was developed to support the operation of the biological post-filtration unit. Then, a system that enables the complementary use of the soft sensor estimates and the corresponding hardware instrument measurements was designed. The soft sensors were found to model nitrate concentrations accurately and, especially when integrated with the proposed switching system, to allow for a more secure control of the unit. In addition, a soft sensor for detecting process and instrument anomalies in the activated sludge process was investigated. The presented anomaly detection system motivates a more efficient use of sensors in the process control.It was demonstrated that soft sensors were applicable to the considered tasks and that they have strong potential for providing support to the operations of treatment facilities. The employed multivariate techniques proved to be capable of extracting easily understandable and practicable information from the high-dimensional data.

AB - The increased awareness about the ecological status of the waterbodies and, on the other hand, the advances in the treatment technology have acted as driving forces behind the gradual tightening of wastewater purification requirements. Achieving the stringent treatment targets of wastewater treatment plants cost-efficiently is crucially dependent on the high-grade monitoring and control of the process units. Those, in turn, necessitate reliable real-time information about the primary process variables. In spite of the considerable developments of on-line sensors, demanding conditions in biological treatment processes sometimes give rise to an insufficient performance of instruments. The main motivation for this thesis was to design software tools that enable more efficient and safer treatment process operation by complementing conventional instrumentation. Since modern facilities are amply instrumented and there are plenty of accessible historical data, data-derived approaches were used in the studies. The data were processed together with predictive models providing virtual instruments often referred to as soft sensors. In this thesis, the models at the core of the soft sensors are based on multivariate statistics. In particular, principal component analysis with its variants and least-squares-based regression methods were employed in the soft sensor development. The moving-window techniques were applied so as to adapt the models to time-varying wastewater treatment processes. Both linear and nonlinear regression methods were explored.The technical studies of the thesis concern a large-scale municipal wastewater treatment plant. An array of soft sensors for the on-line prediction of nitrate concentrations was developed to support the operation of the biological post-filtration unit. Then, a system that enables the complementary use of the soft sensor estimates and the corresponding hardware instrument measurements was designed. The soft sensors were found to model nitrate concentrations accurately and, especially when integrated with the proposed switching system, to allow for a more secure control of the unit. In addition, a soft sensor for detecting process and instrument anomalies in the activated sludge process was investigated. The presented anomaly detection system motivates a more efficient use of sensors in the process control.It was demonstrated that soft sensors were applicable to the considered tasks and that they have strong potential for providing support to the operations of treatment facilities. The employed multivariate techniques proved to be capable of extracting easily understandable and practicable information from the high-dimensional data.

KW - data-derived modelling

KW - multivariate statistics

KW - process monitoring

KW - soft sensors

KW - wastewater treatment

KW - datapohjainen mallinnus

KW - tilastolliset monimuuttujamenetelmät

KW - prosessinvalvonta

KW - virtuaaliset anturit

KW - jätevedenkäsittely

KW - data-derived modelling

KW - multivariate statistics

KW - process monitoring

KW - soft sensors

KW - wastewater treatment

M3 - Doctoral Thesis

SN - 978-952-60-6649-3

T3 - Aalto University publication series DOCTORAL DISSERTATIONS

PB - Aalto University

ER -

Data-derived soft sensors in biological wastewater treatment - With application of multivariate statistical methods

Abstrakti

Tutkimusalat

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä