Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Dynamic differential annealed optimization: New metaheuristic optimization algorithm for engineering applications

A review of recent progress in mechanical and corrosion properties of dual phase steels

Automatic recognition of SEM microstructure and phases of steel using LBP and random decision forest operator

The mechanical and corrosion behaviors of low carbon DP steel were studied based on different processing routes: (1) intercritical annealing (IA), (2) step quenching (SQ) via austenitization and quick transferring of the sample to the second furnace, and (3) Slow SQ via furnace cooling to the desired temperature. The properties were found to be highly dependent on the volume fraction of martensite (VM) and the density of ferrite/martensite interfaces. However, at the same martensite content, the mechanical properties of Slow SQ sheet were inferior than those of SQ and IA sheets, which were related to the relatively poor work-hardening behavior due to the severe partitioning of Mn between ferrite and martensite phases. The latter was also responsible for an increase in the corrosion current density (icorr) via galvanic corrosion. These results were analyzed based on the polarization curves and Nyquist plots obtained from the electrochemical impedance spectroscopy test. This study revealed that the SQ route can result in both better mechanical performance and higher corrosion resistance.

Processing Route Effects on the Mechanical and Corrosion Properties of Dual Phase Steel

Designing dual-phase steels with improved performance using ANN and GA in tandem

An automated morphological classification of ferrite-martensite dual-phase microstructures

Present work proposes a new methodology for removal of noise (artifacts) from the micrograph, which normally poses a problem during segmentation of phases and measurement of their volume percentages. Segmentation of the phases is one of the primary steps towards quantification of microstructures. Dual-phase steel micrographs, generated from light microscope, consisting of ferrite (white) and martensite (black) phases are segmented by implementation of Otsu threshold algorithm, a well-known threshold algorithm of digital image processing. After thresholding, the noise removing algorithm is applied in different modes. The obtained results are compared with the findings of a commercial metallographic image processing software (Axio Vision). The proposed scheme is found to segment ferrite-martensite dual-phase micrographs successfully.

https://dpi-proceedings.com/index.php/dtetr/article/viewFile/11061/10613

Tanusree Dutta

Papers

Designing dual-phase steels with improved performance using ANN and GA in tandem

An automated morphological classification of ferrite-martensite dual-phase microstructures

Noise Removal and Image Segmentation in Micrographs of Ferrite-Martensite Dual-Phase Steel