Strip Snap Analytics in Cold Rolling Process Using Machine Learning

Chen, Zheyuan; Liu, Ying; Valera‐Medina, Agustin; Robinson, Fiona

doi:10.1109/coase.2019.8842967

Cited by 7 publications

(4 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have begun to apply data analysis methods to strip breakage modelling in recent years [18]. The data collected in production, such as friction conditions, roll pressure, and temperature, often vary greatly, so theoretical analysis is challenging, and it is complicated to analyse these factors using formulas [19].…”

Section: B Previous Studies On Strip Breakage Modellingmentioning

confidence: 99%

See 1 more Smart Citation

Sliding Window Filter Based Strip Breakage Modelling for Failure Prediction

Yang

Chen

Liu

et al. 2021

2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)

Self Cite

View full text Add to dashboard Cite

In the production of cold-rolled strip products, strip breakage is one of the most common failures during the cold rolling process. However, the existing prediction models on strip breakage use the conventional sliding window algorithm to process the time series data collected from the actual production, resulting in a massive amount of non-informative data, which increases the computational cost for data-driven modelling. In order to tackle this issue, this article proposed a sliding window filter method to optimise the data pre-processing of the strip breakage. Firstly, based on the existing research and understanding of strip breakage, the data characteristics in the process of strip breakage was analysed. Based on the analysis, sample variance (VAR) and length normalised complexity estimate (LNCE) were chosen to determine how informative the time window was related to strip breakage. Secondly, compared with the conventional sliding window approach, the sliding windows were classified through a filter using VAR and LNCE. Thirdly, the filtered data was fed into the Recurrent Neural Network (RNN) for strip breakage modelling. An experimental study based on actual production data collected by a cold-rolled strip manufacturer was conducted to verify this method's effectiveness. The results show that pre-processing data using the sliding window filter decreases the model's computational cost.

show abstract

Section: B Previous Studies On Strip Breakage Modellingmentioning

confidence: 99%

“…The author of this paper also used this method to establish a strip breakage analysis and prediction model in the previous study [19]. The model is based on the analysis of the existing features.…”

Section: B Previous Studies On Strip Breakage Modellingmentioning

confidence: 99%

Sliding Window Filter Based Strip Breakage Modelling for Failure Prediction

Yang

Chen

Liu

et al. 2021

2021 IEEE 17th International Conference on Automation Science and Engineering (CASE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The team, led by Zheyuan Chen [7,8] worked on the elimination of strip breaks during rolling through advanced data analysis. They managed to establish twenty key parameters that influence strip breaks, but they did not succeed in determining an explicit root cause of strip breaks.…”

Section: Introductionmentioning

confidence: 99%

“…The other research paper of the team led by Zheyuan Chen [ 7 , 8 ] on the elimination of strip breaks in the rolling process proposes the implementation of a width-meter at both the entry and exit end of the rolling mill. This theory is based on strip necking during rolling.…”

Section: Introductionmentioning

confidence: 99%

The Research of the Rolling Speed Influence on the Mechanism of Strip Breaks in the Steel Rolling Process

Rusňák¹,

Malega

Svetlík

et al. 2020

Materials

View full text Add to dashboard Cite

This paper evaluates the results of research aimed at changing the rolling speed and the effect of foreign particles in the steel strip, as well as the forces in the rolling process. It also compares the correlation of lab results, theoretical expectations and real-life observations. It supplements the already existing practices aimed at strip-break elimination that were developed and implemented worldwide. Records from a five-stand tandem mill were used for the data analysis. The historical databases developed based on incidents (strip breaks) since 2013 were used; the detailed position of each strip break was documented, along with defects found at the portions of steel strips that broke or the information that no defect was found. The paper contains an evaluation of metallographic analyses of the samples of the strip breaks.

show abstract