A Method for Steel Ladle Lining Optimization Applying Thermomechanical Modeling and Taguchi Approaches

Hou, Aidong; Jin, Shengli; Harmuth, Harald; Gruber, Dietmar

doi:10.1007/s11837-018-3063-1

Cited by 20 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is noteworthy that the prediction performance of this BP‐ANN model with BR for maximum tensile stress is inferior to that for end temperature and maximum compressive stress. A previous study showed that 7 of the 10 defined factors contribute 91% to the maximum tensile stress, followed by 5 factors contributing 94% to the end temperature, and 1 factor contributing 93% to the maximum compressive stress. The high dimensionality occurring in the factor‐response space increases the complexity of the problem and results in under‐fitting.…”

Section: Resultsmentioning

confidence: 96%

“…The performance of a steel ladle is influenced by many factors; for instance, material properties, lining thicknesses, and process conditions. Efforts have been made to evaluate the performance of steel ladle linings from thermal and thermomechanical viewpoints using finite element (FE) methods, especially taking into account the application of insulation and preheating time . Integrated consideration of lining concepts for a steel ladle is also of importance to support steel industry 4.0 in refractory application .…”

Section: Introductionmentioning

confidence: 99%

“…Integrated consideration of lining concepts for a steel ladle is also of importance to support steel industry 4.0 in refractory application . Recently, the authors applied the Taguchi method to optimize lining design configurations with FE simulations within a defined variable span of lining thickness and material properties . The impact of factors on the thermal and thermomechanical responses was quantitatively assessed using the analysis of variance and signal‐to‐noise ratio.…”

Section: Introductionmentioning

confidence: 99%

“…The sufficiency of the dataset, feasible node number in the hidden layer for a case study with 10 variables, and the training algorithms were investigated. Later, a BP‐ANN model with optimized settings was applied to predict the results of two lining concepts proposed in the Hou et al…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Thermal and Thermomechanical Responses Prediction of a Steel Ladle Using a Back‐Propagation Artificial Neural Network Combining Multiple Orthogonal Arrays

Hou

Jin

Harmuth

et al. 2019

steel research int.

Self Cite

View full text Add to dashboard Cite

To facilitate industrial vessel lining design for various material properties and lining configurations, a method, being composed of the back-propagation artificial neural network (BP-ANN) with multiple orthogonal arrays, is developed, and a steel ladle from secondary steel metallurgy is chosen for a case study. Ten geometrical and material property variations of this steel ladle lining are selected as inputs for the BP-ANN model. A total of 160 lining configurations nearly evenly distributed within the ten variations space are designed for finite element (FE) simulations in terms of five orthogonal arrays. Leave-One-Out cross validation within various combinations of orthogonal arrays determines 7 nodes in the hidden layer, a minimum ratio of 16 between dataset size and number of input nodes, and a Bayesian regularization training algorithm as the optimal definitions for the BP-ANN model. The thermal and thermomechanical responses of two optimal lining concepts from a previous study using the Taguchi method are predicted with acceptable accuracy.

show abstract

Section: Resultsmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Thermal and Thermomechanical Responses Prediction of a Steel Ladle Using a Back‐Propagation Artificial Neural Network Combining Multiple Orthogonal Arrays

Hou

Jin

Harmuth

et al. 2019

steel research int.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The preferable node number range in the hidden layer for each response was proposed afterward. In the second group, different combinations of significant input variables for the individual response were selected according to the ANOVA results of the previous work [27] and listed in Table 3 with their contribution summations to the response. For each combination, several BP-ANN models were employed with the node number of the hidden layer in the range proposed from the first group tests.…”

Section: Bp-ann Architecturementioning

confidence: 99%

Influence of Variation/Response Space Complexity and Variable Completeness on BP-ANN Model Establishment: Case Study of Steel Ladle Lining

et al. 2019

Self Cite

View full text Add to dashboard Cite

Artificial neural network (ANN) is widely applied as a predictive tool to solve complex problems. The performance of an ANN model is significantly affected by the applied architectural parameters such as the node number in a hidden layer, which is largely determined by the complexity of cases, the quality of the dataset, and the sufficiency of variables. In the present study, the impact of variation/response space complexity and variable completeness on backpropagation (BP) ANN model establishment was investigated, with a steel ladle lining from secondary steel metallurgy as the case study. The variation dataset for analysis comprised 160 lining configurations of ten variables. Thermal and thermomechanical responses were obtained via finite element (FE) modeling with elastic material behavior. Guidelines were proposed to define node numbers in the hidden layer for each response as a function of the node number in the input layer weighted with the percent value of the significant variables contributing above 90% to the response, as well as the node number in the output layer. The minimum numbers of input variables required to achieve acceptable prediction performance were three, five, and six for the maximum compressive stress, the end temperature, and the maximum tensile stress. empirical equations into other fields are far less satisfying. Equations (1) and (2) show more robust applications, yet they yield a rather larger number for trials.

show abstract

Multi‐Response Optimization of the Thermal and Thermomechanical Behavior of a Steel Ladle Lining using Grey Relational Analysis and Technique for Order Preference by Similarity to Ideal Solution

Hou

Gruber

Jin

2022

steel research int.

Self Cite

View full text Add to dashboard Cite

The present research attempts to simultaneously optimize the thermal and thermomechanical behavior of a steel ladle lining. The lining configurations are designed with an L32 orthogonal array considering the input parameters of various material properties and lining thicknesses. From the finite‐element (FE) simulations, three responses are evaluated: the end temperature and maximum tensile stress at the steel shell and the maximum compressive stress at the hot face of the working lining. Multi‐response optimization is performed through grey relational analysis (GRA) and the technique for order preference by similarity to ideal solution (TOPSIS) by applying a distinguishing coefficient of 0.5 in GRA and the signal‐to‐noise (S/N) ratio‐based weight in both techniques. Both GRA and TOPSIS results yield the same best solution (the fourth lining configuration) and the same optimal levels for significant factors. Analysis of variance (ANOVA) is used to identify the significance of the factors and their contributions to the overall performance characteristic. The results demonstrate that the top five factors with the analyses of GRA and TOPSIS are the same and their total contribution is similar.

show abstract

A Method for Steel Ladle Lining Optimization Applying Thermomechanical Modeling and Taguchi Approaches

Cited by 20 publications

References 11 publications

Thermal and Thermomechanical Responses Prediction of a Steel Ladle Using a Back‐Propagation Artificial Neural Network Combining Multiple Orthogonal Arrays

Thermal and Thermomechanical Responses Prediction of a Steel Ladle Using a Back‐Propagation Artificial Neural Network Combining Multiple Orthogonal Arrays

Influence of Variation/Response Space Complexity and Variable Completeness on BP-ANN Model Establishment: Case Study of Steel Ladle Lining

Multi‐Response Optimization of the Thermal and Thermomechanical Behavior of a Steel Ladle Lining using Grey Relational Analysis and Technique for Order Preference by Similarity to Ideal Solution

Contact Info

Product

Resources

About