Physical modeling and control of dynamic foaming in an LD-converter process

Birk, Wolfgang; Arvanitidis, I.; Jönsson, Pär G.; Medvedev, Alexander

doi:10.1109/28.936398

Cited by 17 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, for example, Buydens et al [10] published results from a technique including sound as well as vibration measurements for optimization and control of slag foaming in the EAF. In addition to the plant studies, several investigations on foaming behavior were carried out using physical modeling, as exemplified by the works of Komarov et al [11] and Birk et al [12].…”

mentioning

confidence: 99%

Observation on foaming of EAF slags in the production of stainless steel

Vidacak¹,

Arvanitidis

Jönsson³

et al. 2002

Scand Jof Metallurgy

Self Cite

View full text Add to dashboard Cite

This study focused on slag‐foaming phenomena, the main emphasis being on slags used in the electric arc furnace (EAF) practice in the manufacture of stainless steel. Plant trials were carried out at Sandvik Steel for slags of high and low chromium content. The viscosity of the slags was predicted using a mathematical model for multi‐component slags developed at KTH, Stockholm. Next, the foaming characteristics were predicted using different relationships suggested in the literature. The predicted foaming behavior was then compared to estimations of foaming determined visually and acoustically by operators. Sound measurements were also carried out during the trials. In comparing foaming characteristics determined from sound measurements with the operator estimations, a relationship was found to exist between the two.

show abstract

mentioning

confidence: 99%

Observation on foaming of EAF slags in the production of stainless steel

Vidacak¹,

Arvanitidis

Jönsson³

et al. 2002

Scand Jof Metallurgy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Various methods for detecting slopping during blowing have been reported, including detection by a surveillance camera at the furnace mouth, [57][58][59] measuring furnace vibration with an accelerometer 60) and detection by acoustic signals. 61) M. Shakirov et al 62) reported the classification of slopping. Cicutti et al 63,64) conducted detailed research by an acoustic analysis during blowing.…”

Section: Sensing Techniques For Convertermentioning

confidence: 99%

Development and Prospects of Refining Techniques in Steelmaking Process

Kikuchi¹

2020

ISIJ Int.

View full text Add to dashboard Cite

The development of refining techniques in the steelmaking process over the last 60 years and the prospects for the future were reviewed. In Japan, hot metal pretreatment started in the 1960s with the aim of reducing refining costs and improving quality, and its purposes have now transitioned to meeting new requirements for reduced treatment time, reuse of steelmaking slag and use of diverse iron sources. In converter refining, in addition to high speed decarburization, visualization of phenomena and sensing modeling techniques are becoming more important for combined use with data science techniques. In ladle metallurgy (secondary refining), techniques to realize high speed treatment and heating of the molten steel are key issues. The necessity of process revolution to contribute to a sustainable social environment is also discussed briefly.

show abstract

“…Physical modeling of foaming is an arduous process as it requires estimation of foam height, which is dynamic in nature and differs for different bioprocesses . Machine learning based modeling helps mitigate the necessity for foam height estimation, and it can be generalized for any process, as it uses the available operational data for prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Physical modeling of foaming is an arduous process as it requires estimation of foam height, which is dynamic in nature and differs for different bioprocesses. 9 Machine learning based modeling helps mitigate the necessity for foam height estimation, and it can be generalized for any process, as it uses the available operational data for prediction. Recently, machine learning based methods have found several applications in sectors where mechanistic modeling is precluded by the inability to develop a model or generalize it for a process.…”

Section: Introductionmentioning

confidence: 99%

110th Anniversary: Ensemble-Based Machine Learning for Industrial Fermenter Classification and Foaming Control

Agarwal

Liu

McDowell

2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In the industrial sector, foaming remains an inevitable side effect of mixing, shearing, powder incorporation, and the metabolic activities of microorganisms in a bioprocess. Excessive foaming can interfere with the mixing of reactants and lead to problems such as decreased effective reactor volume, microbial contamination, product loss, and increased reaction time. Physical modeling of foaming is an arduous process as it requires estimation of foam height, which is dynamic in nature and varies for different processes. This work demonstrates a novel application of ensemblebased machine learning methods for prediction of different fermenter types in a fermentation process (to allow for successful data integration) and of the onset of foaming. Ensemble-based methods are robust nonlinear modeling techniques that aggregate a set of learners to obtain better predictive performance than a single learner. We apply two ensemble frameworks, extreme gradient boosting (XGBoost) and random forest (RF), to build classification and regression models. We use real plant data for 64 batches from four fermenters with different material, geometry, and equipment specifications. Our first task is to develop an ensemble-based fermenter classification model that uses well-known fermentation independent variables for each batch alone, without having to incorporate explicitly the design specifications. The resulting fermenter classification model is able to differentiate or classify the fermenter type with an accuracy of 99.49% for our integrated data sets of over 183 000 instances. This enables us to integrate multiple plant data sets from different fermenter specifications and develop a generalized foaming prediction model. Next, we build classification and regression models for foaming prediction. The resulting models are able to predict the foaming indicator (the exhaust differential pressure) to achieve an accuracy of 82.39% and an RMSE value of ±12 mbarg, which is well within the tolerance for foaming prediction in industrial practice. These results demonstrate the effectiveness of ensemble-based machine learning models for fermenter classification, data integration, and foaming prediction involving multiple fermenter design specifications. Using these tools, we can orchestrate the addition of chemical antifoam agents (AFA) or defoamers in an ad hoc manner to mitigate the adverse effects of excessive AFA addition. Our work differentiates itself from previous work in this area through the following contributions: (1) accurate ensemble-based classification modeling to differentiate fermenter types on the basis of known independent variables alone, without prior knowledge of fermenter design specifications, thus allowing for data integration of multiple plant data sets to build better prediction models; (2) accurate prediction of foaming based on exhaust differential pressure using both classification and regression models; and (3) usage of a large, industrial, multivariate fermenter data set.

show abstract

Physical modeling and control of dynamic foaming in an LD-converter process

Cited by 17 publications

References 5 publications

Observation on foaming of EAF slags in the production of stainless steel

Observation on foaming of EAF slags in the production of stainless steel

Development and Prospects of Refining Techniques in Steelmaking Process

110th Anniversary: Ensemble-Based Machine Learning for Industrial Fermenter Classification and Foaming Control

Contact Info

Product

Resources

About