hh.sePublikasjoner
Endre søk
Link to record
Permanent link

Direct link
BETA
Ejnarsson, Marcus
Publikasjoner (4 av 4) Visa alla publikasjoner
Ejnarsson, M., Verikas, A. & Nilsson, C. M. (2009). Multi-resolution screening of paper formation variations on production line. Expert systems with applications, 36(2, part 2), 3144-3152
Åpne denne publikasjonen i ny fane eller vindu >>Multi-resolution screening of paper formation variations on production line
2009 (engelsk)Inngår i: Expert systems with applications, ISSN 0957-4174, E-ISSN 1873-6793, Vol. 36, nr 2, part 2, s. 3144-3152Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This paper is concerned with a technique for detecting and monitoring abnormal paper formation variations in machine direction online in various frequency regions. A paper web is illuminated by two red diode lasers and the reflected light recorded as two time series of high resolution measurements constitute the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as kernel based novelty detection applied to a multi-resolution time series representation obtained from the band-pass filtering of the Fourier power spectrum of the time series block. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the kernel canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The experimental investigations performed have shown good repetitiveness and stability of the paper formation abnormalities detection results. The tools developed are used for online paper formation monitoring in a paper mill.

sted, utgiver, år, opplag, sider
Amsterdam: Elsevier, 2009
Emneord
Paper production, Support vector machine, Fourier transform, Canonical correlation analysis, Novelty detection
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-2176 (URN)10.1016/j.eswa.2008.01.043 (DOI)000262178100057 ()2-s2.0-56349109871 (Scopus ID)2082/2573 (Lokal ID)2082/2573 (Arkivnummer)2082/2573 (OAI)
Tilgjengelig fra: 2008-12-03 Laget: 2008-12-03 Sist oppdatert: 2018-03-23bibliografisk kontrollert
Ejnarsson, M. (2008). Data Mining and Analysis for Characterizing Paper from On-line Multisensor Measurements. (Licentiate dissertation). Göteborg: Department of Signals and Systems, Chalmers University of Technology
Åpne denne publikasjonen i ny fane eller vindu >>Data Mining and Analysis for Characterizing Paper from On-line Multisensor Measurements
2008 (engelsk)Licentiatavhandling, monografi (Annet vitenskapelig)
Abstract [en]

The objective of this thesis is to develop a multi-resolution tool for screening paper formation variations, aiming to detect abnormalities in various frequency regions ranging from millimeters to several meters. The abnormalities detected in different frequency regions give an indication for the paper maker about specific disturbances in the paper production process. A paper web, running at a speed of 30 m/s, is illuminated by two red diode lasers and the reflected light are recorded as two time series of high resolution measurements constitutes the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as a kernel based novelty detection applied to a multi-resolution time series representation obtained from the frequency bands of the Fourier power spectra of the blocks. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The experimental investigations performed have shown that the presented paper formation deficiencies monitoring technique and the system can be used for on-line monitoring of paper deficiencies manifesting themselves in a broad frequency range. A software, implementing the technique, was developed and used for online paper formation monitoring at a Swedish paper mill.

sted, utgiver, år, opplag, sider
Göteborg: Department of Signals and Systems, Chalmers University of Technology, 2008. s. 62
Serie
Technical report R, ISSN 1403-266X ; 2008:2
Emneord
Feature Extraction, Kernel Based Novelty Detection, Kernel CCA, Monitoring, Newsprint, Paper Web, Time-Series Representation
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-1975 (URN)2082/2370 (Lokal ID)2082/2370 (Arkivnummer)2082/2370 (OAI)
Presentation
2008-02-08, Wigforssalen, Högskolan i Halmstad, Kristian IV:s väg 3, Halmstad, 10:00 (engelsk)
Opponent
Tilgjengelig fra: 2008-09-29 Laget: 2008-09-29 Sist oppdatert: 2020-05-25bibliografisk kontrollert
Ejnarsson, M., Nilsson, C.-M. & Verikas, A. (2007). Screening paper Formation variations on production line. In: Okuno, HG and Ali, M (Ed.), New Trends in Applied Artificial Intelligence, Proceedings: . Paper presented at 20th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems Location, Kyoto, JAPAN, JUN 26-29, 2007 (pp. 511-520). Berlin: Springer Berlin/Heidelberg
Åpne denne publikasjonen i ny fane eller vindu >>Screening paper Formation variations on production line
2007 (engelsk)Inngår i: New Trends in Applied Artificial Intelligence, Proceedings / [ed] Okuno, HG and Ali, M, Berlin: Springer Berlin/Heidelberg, 2007, s. 511-520Konferansepaper, Publicerat paper (Annet vitenskapelig)
Abstract [en]

This paper is concerned with a multi–resolution tool for screening paper formation variations in various frequency regions on production line. A paper web is illuminated by two red diode lasers and the reflected light recorded as two time series of high resolution measurements constitute the input signal to the papermaking process monitoring system. The time series are divided into blocks and each block is analyzed separately. The task is treated as kernel based novelty detection applied to a multi–resolution time series representation obtained from the band-pass filtering of the Fourier power spectrum of the series. The frequency content of each frequency region is characterized by a feature vector, which is transformed using the canonical correlation analysis and then categorized into the inlier or outlier class by the novelty detector. The ratio of outlying data points, significantly exceeding the predetermined value, indicates abnormalities in the paper formation. The tools developed are used for online paper formation monitoring in a paper mill.

sted, utgiver, år, opplag, sider
Berlin: Springer Berlin/Heidelberg, 2007
Serie
Lecture Notes in Artificial Intelligence, ISSN 0302-9743 ; 4570
Emneord
Screening, Paper
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-2103 (URN)10.1007/978-3-540-73325-6_51 (DOI)000248621400051 ()2-s2.0-34948896581 (Scopus ID)2082/2498 (Lokal ID)978-3-540-73322-5 (ISBN)2082/2498 (Arkivnummer)2082/2498 (OAI)
Konferanse
20th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems Location, Kyoto, JAPAN, JUN 26-29, 2007
Tilgjengelig fra: 2008-11-04 Laget: 2008-11-04 Sist oppdatert: 2018-03-23bibliografisk kontrollert
Ejnarsson, M., Nilsson, C. M. & Verikas, A. (2006). A Kernel based multi-resolution time series analysis for screening deficiencies in paper production. In: Jun Wang (Ed.), Advances in neural networks - ISNN 2006: third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 ; proceedings. III. Paper presented at third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 (pp. 1111-1116). Berlin: Springer Berlin/Heidelberg
Åpne denne publikasjonen i ny fane eller vindu >>A Kernel based multi-resolution time series analysis for screening deficiencies in paper production
2006 (engelsk)Inngår i: Advances in neural networks - ISNN 2006: third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006 ; proceedings. III / [ed] Jun Wang, Berlin: Springer Berlin/Heidelberg, 2006, s. 1111-1116Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

This paper is concerned with a multi-resolution tool for analysis of a time series aiming to detect abnormalities in various frequency regions. The task is treated as a kernel based novelty detection applied to a multi-level time series representation obtained from the discrete wavelet transform. Having a priori knowledge that the abnormalities manifest themselves in several frequency regions, a committee of detectors utilizing data dependent aggregation weights is build by combining outputs of detectors operating in those regions.

sted, utgiver, år, opplag, sider
Berlin: Springer Berlin/Heidelberg, 2006
Serie
Lecture Notes in Computer Science, ISSN 0302-9743 ; Volume 3973/2006
Emneord
Discrete transformation, Discrete time, Discrete wavelet, Time analysis, Kernel method, Medical screening, Screening, Neural network
HSV kategori
Identifikatorer
urn:nbn:se:hh:diva-2003 (URN)10.1007/11760191 (DOI)000239485300162 ()2-s2.0-33745927697 (Scopus ID)2082/2398 (Lokal ID)978-3-540-34482-7 (ISBN)2082/2398 (Arkivnummer)2082/2398 (OAI)
Konferanse
third International Symposium on Neural Networks, Chengdu, China, May 28 - June 1, 2006
Tilgjengelig fra: 2008-10-06 Laget: 2008-10-06 Sist oppdatert: 2020-05-14bibliografisk kontrollert
Organisasjoner