Multivariable data analysis of a cold rolling control system to minimise defects

Takami, Kourosh Mousavi; Mahmoudi, Jafar; Dahlquist, Erik; Lindenmo, Magnus

doi:10.1007/s00170-010-2946-2

Cited by 19 publications

(13 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The score plot generated by PCA displays the principal components (PCs) responsible for the maximum variation within the data and highlights clustering or outliers, while the loading plot stresses the influence of the variables in the PCs. Variables with high absolute loading values on each PC have a strong contribution to that PC (Takami, Mahmoudi, Dahlquist, & Lindenmo, 2011).…”

Section: Multivariate Analysesmentioning

confidence: 97%

Discrimination of arabica coffee cultivars by electrospray ionization Fourier transform ion cyclotron resonance mass spectrometry and chemometrics

Garrett

Schmidt

Pereira

et al. 2013

LWT - Food Science and Technology

View full text Add to dashboard Cite

Section: Multivariate Analysesmentioning

confidence: 97%

Discrimination of arabica coffee cultivars by electrospray ionization Fourier transform ion cyclotron resonance mass spectrometry and chemometrics

Garrett

Schmidt

Pereira

et al. 2013

LWT - Food Science and Technology

View full text Add to dashboard Cite

“…One of the primary processes in electrical steel strip production, cold rolling enhances strip properties by changing the microstructure and thickness of the steel. These enhanced properties include surface smoothness, tensile strength, yield strength and hardness [10].…”

Section: Cold Rolling Process and Its Mechanical Modelsmentioning

confidence: 99%

“…With the deployment of various sensors and accurate measurement devices throughout the modern cold rolling process, process data such as coil entry and exit speed, forward and backwards tension, roll gap position and eccentricity of the cold rolling system are measured in real-time, and a large amount of multivariate time-series data is collected and stored. In this data-rich environment, data-driven approaches to investigating strip breakage have previously been applied in a handful of works [5,10,11].…”

Section: Introductionmentioning

confidence: 99%

Multi-faceted modelling for strip breakage in cold rolling using machine learning

Chen

Liu

Valera‐Medina

et al. 2020

International Journal of Production Research

View full text Add to dashboard Cite

In the cold rolling process of steel strip products, strip breakage is an undesired production failure which can lead to yield loss, reduced work speed and equipment damage. In order to perform a root cause analysis, conventional physics-based approaches which focus on mechanical and metallurgical principles have been applied in a retrospective manner. With the advancement of data acquisition technologies, a large amount of process monitoring data is collected by various sensors deployed along the cold rolling process; however, conventional approaches cannot take advantage of these data. In this paper, a machine learning-based approach is proposed to characterise and model strip breakage in a predictive manner. First, in order to match the temporal characteristic of strip breakage which occurs instantaneously, historical multivariate time-series data of a cold rolling process were extracted in a run-tofailure manner, and a sliding window strategy was adopted for data annotation. Second, breakage-centric features were identified from three facets -physics-based approaches, empirical knowledge and data-driven features. Finally, these features were used as inputs for strip breakage modelling using recurrent neural networks (RNNs), which are specialised in discovering underlying patterns embedded in time-series data. An experimental study using real-world data collected from a cold-rolled electrical steel strip manufacturer revealed the effectiveness of the proposed approach.

show abstract

“…As one of the main processes in electrical steel strip production, cold rolling enhances strip properties by changing the microstructure and thickness of the steel. These enhanced properties include yield strength, tensile strength, surface smoothness and hardness [6].…”

Section: A Cold Rolling Process and Research On The Cause Of Strip Snapmentioning

confidence: 99%

“…According to these works, causes of strip snap in cold rolling are various: equipment factors, material defects, improper operation, sensor malfunction and production adjustment. Recently, researches of these strip snap cause analysis have been conducted by employing data analytics [6,7]. The studies carried out based on a subset of selected variables from hundreds of process measurements to analyze the correlations between these selected variables and strip snap.…”

Section: Introductionmentioning

confidence: 99%

Strip Snap Analytics in Cold Rolling Process Using Machine Learning

Chen

Liu

Valera‐Medina

et al. 2019

2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

Strip snap, also known as strip breakage or belt tearing, is an undesirable quality incident which results in yield loss and reduced work speed in the cold rolling process of strip products. Therefore, it is necessary to reveal a functional relationship between certain selected variables and strip snap event for the aim of quality improvement. In this study, the probability of strip snap occurrence was quantified by a selected measured variable. Several machine learning algorithms were adopted to predict this target probability. To validate this approach, a case study was conducted based on real-world data collected from an electrical steel reversing mill. The excessively good performance indicates several variables which are strongly correlated with the target.

show abstract

Multivariable data analysis of a cold rolling control system to minimise defects

Cited by 19 publications

References 3 publications

Discrimination of arabica coffee cultivars by electrospray ionization Fourier transform ion cyclotron resonance mass spectrometry and chemometrics

Discrimination of arabica coffee cultivars by electrospray ionization Fourier transform ion cyclotron resonance mass spectrometry and chemometrics

Multi-faceted modelling for strip breakage in cold rolling using machine learning

Strip Snap Analytics in Cold Rolling Process Using Machine Learning

Contact Info

Product

Resources

About