Adaptive Prediction of Steel Hardness on Hot Strip Mill Using Neural Networks and K-Means Classifier

Bèle, Bertrand; Collette, Jean-Luc; Ianotto, Michel; Vienot, Pierre

doi:10.1016/s1474-6670(17)31011-x

Cited by 2 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As described in [23], [25], specimens with various impedances due to the initial permeability and shapes of the valves exhibit a homogeneous magnetic response along the area. To reasonably predict the magnetic response for the valve specimens, the FEM is simulated in terms of three factors: the magnetic induction intensity, eddy current density, and electric vector density.…”

Section: B Fem Simulationmentioning

confidence: 96%

“…For the hardness classification used for online testing, one needs to integrate a special feature value acquisition module and a PC loaded with the aforementioned software. The abovementioned algorithm is almost impossible to use for a detection device mainly based on an embedded processing device such as an FPGA and digital signal processing (DSP), which increases the design complexity of the detection device [23], [24]. It is necessary to redesign the algorithm implementation structure in a new programming environment.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A New Method of Eddy Current Impedance-Extracting and Hardness-Classifying for Valves

Xie

Huang

2020

IEEE Access

View full text Add to dashboard Cite

This paper describes a new method of eddy current impedance extraction and hardness classification for valves, which is used in online classification. A finite element simulation is conducted to estimate the base magnetic response in specimens with various initial permeabilities, and a scatter diagram between the hardness calibration and initial permeability is plotted experimentally; thus, the hardness classification model is obtained by using the initial permeability as the intermediate variable. A lock-in amplifier is commonly used to measure the amplitudes of impedance components in conventional eddy current testing. This study replaces the lock-in amplifier with a cross-correlation algorithm with the objective of integrating the impedance processing with the subsequent classification. Moreover, an incremental and decremental support vector machine is used to classify the valve specimens based on the extracted impedance due to its demonstrated excellent performance for both linearly separable and nonlinearly indivisible problems. The cross-correlation algorithm and the incremental and decremental support vector machine are implemented on a field-programmable gate array, which has the advantage of parallel processing and can satisfy the online requirements. A comparison with the traditional impedance comparison method shows that the proposed method not only is suitable for online hardness classification but also achieves good performance in correlating impedance amplitude changes caused by a temperature increase of the coil and various heat treatment conditions with the hardness values. INDEX TERMS Eddy current testing, finite element model, cross-correlation algorithm, incremental and decremental support vector machine, impedance extraction, hardness classification.

show abstract

Section: B Fem Simulationmentioning

confidence: 96%

Section: Related Workmentioning

confidence: 99%

A New Method of Eddy Current Impedance-Extracting and Hardness-Classifying for Valves

Xie

Huang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Ozerdem e Kolukisa(2008), num trabalho semelhante, utilizaram o carbono, o silício e o manganês. A estes três elementos, Vallim(2008) acrescentou o cromo e o cobre Bèle et al (2004). acrescentam fósforo, enxofre, alumínio,…”

unclassified

Inteligência computacional aplicada à adaptação na modelagem matemática do processo de laminação a frio de aços planos.

Filho¹,

dos

View full text Add to dashboard Cite

Inteligência Computacional (mais especificamente, Redes Neurais Artificiais) para tornar mais eficiente a adaptação de dois importantes parâmetros: o limite de escoamento do material e o coeficiente de atrito entre a tira e os cilindros de trabalho. O texto apresenta os fundamentos teóricos, a metodologia de desenvolvimento e a implantação da solução, bem como os resultados preliminares obtidos com a aplicação da proposta num laminador real. Finalmente, discutem-se esses resultados, apresentam-se as conclusões, sumarizam-se as contribuições da pesquisa e se sugerem futuras linhas de pesquisa para extensão dos resultados. Palavras-chave: Automação industrial. Laminação. Redes neurais. Inteligência artificial. ABSTRACT SANTOS FILHO, A. L. Computational intelligence applied to the adaptation of mathematical modeling in flat steel cold rolling process. 2009. 179 p. Tese (Doutorado) -Escola Politécnica, Universidade de São Paulo, 2009.Flat steel cold rolling is a complex industrial process, carried out into a very harsh environment, characterized by uncertain parameters, large delay times, multiple inputs and outputs, and having a strong interaction between the diverse variables (GUO, 2000). The control system of such a process obtains its setpoints from a mathematical model, responsible for process optimization. Given process peculiarity, the mathematical model must have adaptive features, that is, its parameters need to be continuously adjusted, on the basis of actual operational results. Adaptation is an essential characteristic for achieving product quality requirements and, as a consequence, for the plant feasibility itself. First of all, this work surveys the strategies commonly used in the development of cold rolling adaptive models, pointing out their strengths and deficiencies. Following to this, aiming at the minimization of such deficiencies and by this way improving the performance of the model, this work proposes the application of Computational Intelligence techniques (specifically Artificial Neural Networks) in order to bestow greater effectiveness to the adaptation of two important parameters, namely, the material flow stress and the friction coefficient between rolled strip and rolling cylinders. The text presents the theoretical foundations, the methodology and the implementation of the solution, as so the preliminary results after its application in a real steel mill plant. Finally, the text presents the conclusions, sums up the contributions of the research work and suggests further research to improve the results.

show abstract

Adaptive Prediction of Steel Hardness on Hot Strip Mill Using Neural Networks and K-Means Classifier

Cited by 2 publications

References 3 publications

A New Method of Eddy Current Impedance-Extracting and Hardness-Classifying for Valves

A New Method of Eddy Current Impedance-Extracting and Hardness-Classifying for Valves

Inteligência computacional aplicada à adaptação na modelagem matemática do processo de laminação a frio de aços planos.

Contact Info

Product

Resources

About