A Quality-Based Nonlinear Fault Diagnosis Framework Focusing on Industrial Multimode Batch Processes

Peng, Kaixiang; Zhang, Kai; You, Bo; Dong, Jie; Wang, Zidong

doi:10.1109/tie.2016.2520906

Cited by 82 publications

(37 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure shows a diagram of the finishing mill rolling process (FMRP) that consists of 7 groups of stands. In each group of stands, there are 4 rollers: two that work directly on the strip and two that support the working rollers . Before a strip reaches a given stand, the rolling force for the upper supporting roller is computed based on the desired rate of thickness reduction, while the bending force is found using an empirical equation.…”

Section: Process Descriptionmentioning

confidence: 99%

“…Before a strip reaches a given stand, the rolling force for the upper supporting roller is computed based on the desired rate of thickness reduction, while the bending force is found using an empirical equation. The actual change in the steel thickness is determined by the rolling force, temperature, bending force, and other physical properties that depend on the specific steel batch . Thus, a first principles model can be difficult to obtain.…”

Section: Process Descriptionmentioning

confidence: 99%

“…In practice, the individual stands are not autonomous, but are combined together using various control methods. After the last stand, the steel thickness is measured using an online, X‐ray device, that is located at a distance from the stands . The difference between the measured and setpoint thicknesses can then be fed back to the current or previous stands to adjust the milling force.…”

Section: Process Descriptionmentioning

confidence: 99%

“…Furthermore, since the thickness cannot be calculated between two stands, the gap measurement between the two working rollers can be used as a proxy variable. It has been found that the thickness of the steel strip after each stand is approximately equal to the gap between the working rollers plus the ratio between the applied force and the roller's stiffness . However, since the stiffness can be difficult to calculate precisely, it is impossible to adjust the downstream stands based on the upstream thickness.…”

Section: Process Descriptionmentioning

confidence: 99%

See 3 more Smart Citations

Modelling the strip thickness in hot steel rolling mills using least‐squares support vector machines

et al. 2017

Self Cite

View full text Add to dashboard Cite

The development and implementation of better control strategies to improve the overall performance of a plant is often hampered by the lack of available measurements of key quality variables. One way to resolve this problem is to develop a soft sensor that is capable of providing process information as often as necessary for control. One potential area for implementation is in a hot steel rolling mill, where the final strip thickness is the most important variable to consider. Difficulties with this approach include the fact that the data may not be available when needed or that different conditions (operating points) will produce different process conditions. In this paper, a soft sensor is developed for the hot steel rolling mill process using least-squares support vector machines and a properly designed bias update term. It is shown that the system can handle multiple different operating conditions (different strip thickness setpoints, and input conditions).

show abstract

Section: Process Descriptionmentioning

confidence: 99%

Section: Process Descriptionmentioning

confidence: 99%

Section: Process Descriptionmentioning

confidence: 99%

Section: Process Descriptionmentioning

confidence: 99%

See 2 more Smart Citations

Modelling the strip thickness in hot steel rolling mills using least‐squares support vector machines

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…Later process monitoring work extends the use of PLS for fault diagnosis and identification [27][28][29][30].…”

Section: Introductionmentioning

confidence: 99%

Quality-related process monitoring for dynamic non-Gaussian batch process with multi-phase using a new data-driven method

Peng

Zhang

et al. 2016

Neurocomputing

Self Cite

View full text Add to dashboard Cite

Sliding Mode Control for an Inhomogeneous Heat Equation with Global Constraint

Zhang

2017

Asian Journal of Control

View full text Add to dashboard Cite

In this paper, an inhomogeneous heat equation with distributed load is controlled, on the basis of an infinite dimensional generalization of sliding-mode control method. The control law is designed so that: (i) the temperature can track a desired reference signal, and (ii) the temperature can remain in a constrained region. We show that, with the designed control, the tracking error is bounded stable without violation of the constraint. The stability is proved under the designed control law. Numerical simulations are given to illustrate the effectiveness of the designed control law.

show abstract

A Quality-Based Nonlinear Fault Diagnosis Framework Focusing on Industrial Multimode Batch Processes

Cited by 82 publications

References 31 publications

Modelling the strip thickness in hot steel rolling mills using least‐squares support vector machines

Modelling the strip thickness in hot steel rolling mills using least‐squares support vector machines

Quality-related process monitoring for dynamic non-Gaussian batch process with multi-phase using a new data-driven method

Sliding Mode Control for an Inhomogeneous Heat Equation with Global Constraint

Contact Info

Product

Resources

About