Quality Classification and Monitoring Using Adaptive Metric Distance and Neural Networks: Application in Pickling Process
Modern manufacturing facilities are large scale,
highly complex, and operate with large number of variables under
closed loop control. Early and accurate fault detection and diagnosis
for these plants can minimise down time, increase the safety of plant
operations, and reduce manufacturing costs. Fault detection and
isolation is more complex particularly in the case of the faulty analog
control systems. Analog control systems are not equipped with
monitoring function where the process parameters are continually
visualised. In this situation, It is very difficult to find the relationship
between the fault importance and its consequences on the product
failure. We consider in this paper an approach to fault detection and
analysis of its effect on the production quality using an adaptive
centring and scaling in the pickling process in cold rolling. The fault
appeared on one of the power unit driving a rotary machine, this
machine can not track a reference speed given by another machine.
The length of metal loop is then in continuous oscillation, this affects
the product quality. Using a computerised data acquisition system,
the main machine parameters have been monitored. The fault has
been detected and isolated on basis of analysis of monitored data.
Normal and faulty situation have been obtained by an artificial neural
network (ANN) model which is implemented to simulate the normal
and faulty status of rotary machine. Correlation between the product
quality defined by an index and the residual is used to quality
classification.
[1] S.Bouhouche, "Contribution to quality and process optimisation using
mathematical modeling", Ph.D thesis, Institut f├╗r Maschinenbau, ISSN:
1617-3309, ID-Nr: 104 TU Bergakademie Freiberg Germany, 2002
[2] M.Norgaard, O. Ravn, N.K. Poulsen and L.K. Hansen, "Neural
Nerworks for Modelling and Control of Dynamic Systems", ISBN 1-
85233-227-1, Springer-Verlag, Second Edition, 2001
[3] L.H.Chiang, E.L. Russel land R.D. Braatz, "Fault detection and
Diagnosis in Industrial Systems", ISBN 1-85233-327-8, Springer-
Verlag, Second Edition, 2001
[4] S.Bouhouche, M.S.Boucherit and M.Lahreche, "Improvement of
breakout detection system in continuous casting process using neural
networks", IEEE Proceedings on Advanced Process Control -
Applications for Industry Workshop, Vancouver, Canada, pp 53-63,
2001
[5] G.Sorgrl, T.Poppe and M.schlang, "Real-time control with neural
networks in steel processing", European Commission for Technical
Steel Research, ECSC Workshop, Proceedings of Application of
Artificial Neural Network Systems in the Steel Industry, Brussels, 22-23
January1998,
[6] D.Pham and X.Liu, "State space identification of dynamic systems
using neural networks", Engineering Application in Artificial
Intelligence, pp 198-203, (3),1990.
[7] D.Lee, J.S.Lee and T.Kang, "Adaptive fuzzy control of the molten steel
level in a strip casting process", Control Engineering Practices, (11), pp
1511-1520, 1996
[8] C.Harris, M.Brown, K.M.Bossley, D.J.Mills and F.Ming, "Advances in
neuro-fuzzy algorithms for real-time modelling and control,
Engineering", Application of Artificial Intelligence, 9, (1), pp 1-16,
1996
[9] T.Kim and S.R.T.Kumara, "Boundary defect recognition using neural
networks", International Journal of Production Research, 35, (9), pp
2397-2412, 1997,
[10] A.P.Loh, K.O.Looi and K.F.Fong, "Neural network modelling and
control strategies for a pH process", Journal of Process Control, 15 (6),
pp 355-362, 1995
[11] W.Zhenni, D.Christine, T.Ming and J.A.Morris, "A procedure for
determining the topology of multilayer feedforward neural networks",
Neural Networks, 7, (2), pp 291-300, 1994,
[12] D.Pham and X.Liu, "State space identification of dynamic systems
using neural networks", Engineering Application in Artificial
Intelligence, (3), pp 198-203, 1990.
[13] Bouhouche.S, Boucherit.MS, Lahreche.M and Bast.J, "Controlled
Solidification in Continuous Casting Using Neural Networks", Book
EPMESC IX Conference, Hong Kong November 2003
[1] S.Bouhouche, "Contribution to quality and process optimisation using
mathematical modeling", Ph.D thesis, Institut f├╗r Maschinenbau, ISSN:
1617-3309, ID-Nr: 104 TU Bergakademie Freiberg Germany, 2002
[2] M.Norgaard, O. Ravn, N.K. Poulsen and L.K. Hansen, "Neural
Nerworks for Modelling and Control of Dynamic Systems", ISBN 1-
85233-227-1, Springer-Verlag, Second Edition, 2001
[3] L.H.Chiang, E.L. Russel land R.D. Braatz, "Fault detection and
Diagnosis in Industrial Systems", ISBN 1-85233-327-8, Springer-
Verlag, Second Edition, 2001
[4] S.Bouhouche, M.S.Boucherit and M.Lahreche, "Improvement of
breakout detection system in continuous casting process using neural
networks", IEEE Proceedings on Advanced Process Control -
Applications for Industry Workshop, Vancouver, Canada, pp 53-63,
2001
[5] G.Sorgrl, T.Poppe and M.schlang, "Real-time control with neural
networks in steel processing", European Commission for Technical
Steel Research, ECSC Workshop, Proceedings of Application of
Artificial Neural Network Systems in the Steel Industry, Brussels, 22-23
January1998,
[6] D.Pham and X.Liu, "State space identification of dynamic systems
using neural networks", Engineering Application in Artificial
Intelligence, pp 198-203, (3),1990.
[7] D.Lee, J.S.Lee and T.Kang, "Adaptive fuzzy control of the molten steel
level in a strip casting process", Control Engineering Practices, (11), pp
1511-1520, 1996
[8] C.Harris, M.Brown, K.M.Bossley, D.J.Mills and F.Ming, "Advances in
neuro-fuzzy algorithms for real-time modelling and control,
Engineering", Application of Artificial Intelligence, 9, (1), pp 1-16,
1996
[9] T.Kim and S.R.T.Kumara, "Boundary defect recognition using neural
networks", International Journal of Production Research, 35, (9), pp
2397-2412, 1997,
[10] A.P.Loh, K.O.Looi and K.F.Fong, "Neural network modelling and
control strategies for a pH process", Journal of Process Control, 15 (6),
pp 355-362, 1995
[11] W.Zhenni, D.Christine, T.Ming and J.A.Morris, "A procedure for
determining the topology of multilayer feedforward neural networks",
Neural Networks, 7, (2), pp 291-300, 1994,
[12] D.Pham and X.Liu, "State space identification of dynamic systems
using neural networks", Engineering Application in Artificial
Intelligence, (3), pp 198-203, 1990.
[13] Bouhouche.S, Boucherit.MS, Lahreche.M and Bast.J, "Controlled
Solidification in Continuous Casting Using Neural Networks", Book
EPMESC IX Conference, Hong Kong November 2003
@article{"International Journal of Architectural, Civil and Construction Sciences:51323", author = "S. Bouhouche and M. Lahreche and S. Ziani and J. Bast", title = "Quality Classification and Monitoring Using Adaptive Metric Distance and Neural Networks: Application in Pickling Process", abstract = "Modern manufacturing facilities are large scale,
highly complex, and operate with large number of variables under
closed loop control. Early and accurate fault detection and diagnosis
for these plants can minimise down time, increase the safety of plant
operations, and reduce manufacturing costs. Fault detection and
isolation is more complex particularly in the case of the faulty analog
control systems. Analog control systems are not equipped with
monitoring function where the process parameters are continually
visualised. In this situation, It is very difficult to find the relationship
between the fault importance and its consequences on the product
failure. We consider in this paper an approach to fault detection and
analysis of its effect on the production quality using an adaptive
centring and scaling in the pickling process in cold rolling. The fault
appeared on one of the power unit driving a rotary machine, this
machine can not track a reference speed given by another machine.
The length of metal loop is then in continuous oscillation, this affects
the product quality. Using a computerised data acquisition system,
the main machine parameters have been monitored. The fault has
been detected and isolated on basis of analysis of monitored data.
Normal and faulty situation have been obtained by an artificial neural
network (ANN) model which is implemented to simulate the normal
and faulty status of rotary machine. Correlation between the product
quality defined by an index and the residual is used to quality
classification.", keywords = "Modeling, fault detection and diagnosis, parameters
estimation, neural networks, Fault Detection and Diagnosis (FDD),
pickling process.", volume = "2", number = "9", pages = "203-6", }