Soumitra Kumar Dinda

Argon gas injection in slab continuous casting is common practice to counter SEN clogging phenomena. Bubble characteristics determine the probability of bubble-driven defects such as steel cleanliness, liquid steel reoxidation, and sliver and blister defects. 1:2 scaled water model studies were performed with the help of an advanced high-speed-high-resolution camera shadowgraph imaging technique. Bubble Sauter mean diameter and count were calculated using Trainable Weka segmentation, a machine learning image-based segmentation in the ImageJ platform for different processing conditions such as gas flow rate, liquid flow rate, mold width, and submerged entry nozzle (SEN) depth. A predictive model was developed on the experimental data using an artificial neural network (ANN) algorithm to optimize the bubble mean diameter and count sampling strategy. The model performance is optimized based on the cross-validated adjusted R2. The model shows significant promise with bootstrapping aggregation, five-fold cross-validation, and improved accuracy.

Flow efficiency in a two‐strand continuous casting tundish is studied by analyzing the residential time distribution (RTD) curves in a small‐scale tundish water model using a conductive NaCl solution tracer. The velocity fields in the tundish water model are measured by particle image velocimetry, which is used to validate the results of the mathematical model in the article. It is found that the tracer concentration has a significant impact on the predicted dead volume fraction in the RTD analysis. Validated mathematical modeling of the computational fluid dynamics (CFD) technology is performed to explore the root cause of the defective results in the RTD analysis. It is found that the flow inside the tundish is sensitive to density variations caused by the injected tracer. A denser tracer will stay lower in the tundish by gravity and flow out of the tundish more quickly. A proper tracer concentration in the water model experiments is discussed to visualize the dead volume and improve tundish furniture design efficiently for future work, a new method using CFD modeling is proposed in this article, which can directly demonstrate the dead volume's location.

As complete elimination of porosity from the weld is very difficult, the next option available is to minimize this weld porosity, which is crucial for the safe performance of the welded components. However, this investigation through experiments alone is very tedious and time consuming. Additionally, very limited models are available in the literature for accurate prediction of different porosity attributes. The present study, thus, addressees both the experimental as well as modelling aspect on the study of micro-porosity during Electron Beam Welding (EBW) of SS304 plates. Welding parameters are reported to have significant influence on the micro-porosity. Hence, the influences of these parameters on micro-porosity attributes, namely pores number, average diameter, and sphericity are extensively studied experimentally employing optical microscopy (OM), scanning electron microscopy (SEM), X-ray computed tomography (XCT), and Raman spectroscopy. This is followed by an elaborate modelling through seven popular and well-recognized Machine Learning Algorithms (MLAs) namely, Multi-Layer Perceptron (MLP), Support Vector Regression (SVR), M5P model trees regression, Reduced Error Pruning Tree (REPTree), Random Forest (RF), Instance-based k-nearest neighbor algorithm (IBk) and Locally Weighted Learning (LWL). These different techniques enhance the chance of obtaining the better predictions of the said micro-porosity attributes by overcoming the effect of data-dependence and other limitations of individual MLAs. The different model-predicted micro-porosity data are also validated through experimental data. Statistical tests and Monte-Carlo reliability analysis are additionally utilized to evaluate the performances of the employed algorithms. IBk and MLP are overall found to perform well.