Bachelor and Master in Metallurgical Engineering passionate about transformation and development, control and quality of processes and products with continuous improvement. Data-driven decision making for process tracking, product improvement and business insights. Monitoring in industrial plants in the implementation of projects and application of products.

Knowledge of the Lean Six Sigma methodology with the use of tools for continuous improvement. Management and leadership in decision making not only to solve problems but also to help enrich the individual and the team.

Education

Metallurgical Engineer — Ifes

○ Material science, processing and application of metallic and non-metallic alloys. Data analysis for pattern recognition, mathematical modeling for processes and products aiming at control and quality.

MSc Metallurgical and Materials Engineering | Ifes

○ Master's in Process Control and Simulation in Numerical modelling and analysis of rheological properties of steel slags (e.g. ironmaking, steelmaking, continuous casting).

Publications

— Costa I, Anjos PQ, Martins AP, Carvalho CS, Vieira EA. Physical Properties of Fluxants Commercial Perittetics formed form the Additional Residue of Calcite Marble. Anais do Contecc 2019: ISSN 2358117-4, Ano 6, Volume 1. https://www.confea.org.br/sites/default/files/uploads-imce/Contecc2019/Mec%C3%A2nica%20e%20Metal%C3%BArgica/PROPRI~1.PDF

— Anjos PQ, Kill JD, Oliveira JR, Grillo FF, Dagostini VS. Influence of Slag Composition on the Desulphurization Process in the Ladle Furnace. 51° Seminário de Fusão, Refino e Solidificação de Metais — vol. 51, num. 51 (2022). https://abmproceedings.com.br/ptbr/article/influence-of-slag-composition-on-the-desulphurization-process-in-the-ladle-furnace

— Anjos PQ. Viskositas: Viscosity Prediction of Multicomponent Chemical Systems. arXiv. 2022;2208.01440. https://doi.org/10.48550/arXiv.2208.01440

— Anjos PQ, Quaresma LA, Machado MLP. Linear Modeling of the Glass Transition Temperature of the system SiO₂-Na₂O-CaO. Anais do Contecc 2022: ISSN 2358117-4, Ano 8, Volume 1. https://www.confea.org.br/midias/uploads-imce/Contecc%202022/MecMetal/LINEAR%20MODELING%20OF%20THE%20GLASS%20TRANSITION%20TEMPERATURE%20OF%20THE%20SYSTEM%20SiO2-Na2O-CaO.pdf

— Anjos PQ, Quaresma LA, Machado MLP. Artificial neural networks for predicting the viscosity of lead-containing glasses. XIII ECTM (2022). https://even3.blob.core.windows.net/anais/515621.pdf

— Anjos PQ, Quaresma LA, Machado MLP. Linear modeling and Feature selection of Break Temperature in multicomponents Slags. 24° CBECiMat. https://www.cbecimat.com.br/anais/PDF/Is23-001.pdf

— Anjos PQ, Quaresma LA, Machado MLP. Development of Non-Linear Equations for Predicting Electrical Conductivity in Silicates. Iron & Steel Technology, v. June, p. 82, 2024 (AISTech 2023 - Accepted and Presented). https://imis.aist.org/store/detail.aspx?id=pr-pm0624-3

— Anjos PQ, Quaresma LA, Machado MLP. Viscosity Prediction of Silica Refractories using Artificial Neural Networks. 51º Seminário de Redução de Minérios e Matérias-Primas — vol. 51, num. 51 (2023). https://abmproceedings.com.br/ptbr/article/viscosity-prediction-of-silica-refractories-using-artificial-neural-networks

— Anjos PQ, Quaresma LA, Machado MLP. Semi-Empirical Modeling of the Liquidus Temperatura of Blast Furnace Slag. Anais do Contecc 2023: ISSN 2358117-4, Ano 9, Volume 1. https://www.confea.org.br/eventos/contecc/contecc-2023/mecanica-metalurgica

— Anjos PQ, Grillo FF, Machado MLP, Quaresma LA. Modelagem de Propriedades Físicas de Escórias de Siderurgia por meio de Redes Neurais Parte 1: Temperatura Liquidus. 52º Seminário de Redução de Minérios e Matérias-Primas — vol. 52, num. 52 (2024). https://abmproceedings.com.br/ptbr/article/modelagem-de-propriedades-fsicas-de-escria-de-siderurgia-por-meio-de-redes-neurais-parte-1-temperatura-liquidus

— Anjos PQ, Grillo FF, Machado MLP, Quaresma LA. Modeling Physical Properties of Steel Slag based on Neural Networks Part 2: Glass Transition Temperature. 53º Seminário de Aciaria, Fundição e Metalurgia de Não-Ferrosos — vol. 53, num.53 (2024). https://abmproceedings.com.br/ptbr/article/modeling-physical-properties-of-steel-slag-based-on-neural-networks-part-2-glass-transition-temperature

— Anjos PQ, Machado MLP. Simulation-Informed Artificial Neural Networks for Calculating Electrical Resistivity of low alloyed Cu: Cases CuCrZr and CuAgCr. 77º Congresso Anual da ABM - Internacional — vol. 77, num.77 (2024). https://abmproceedings.com.br/ptbr/article/simulation-informed-artificial-neural-networks-for-calculating-electrical-resistivity-of-low-alloyed-cu-cases-cucrzr-and-cuagcr

Certificates

Experience

Data Analyst — Shinagawa Refractories | 08/2022 - 07/2024

○ Analysis of products, processes and projects with data-based decision making. Use of different techniques for selection, optimization and continuous business improvement. Statistical and industrial plant monitoring of the implementation of products and processes.

Researcher Assistant — Federal Institute of Espírito Santo | 08/2017 - 12/2021

○ Analysis and presentation of experimental data, monitoring with control and quality of processes and products and development of innovation and continuous improvement projects.

Research and Development (R&D) Intern — ArcelorMittal Tubarão | 01/2020 - 05/2020 and 09/2021 - 01/2022

○ Development of mathematical models for product description and control and laboratory analysis to determine different materials. Use of programming language for knowledge of process variables.

Projects

Viskositas (Proprietary)

• Viskositas is a model capable of predicting the viscosity of multicomponent systems, with up to 19 different chemical species, with varying viscosity and operating temperature for the metallurgical and refractory industry.

Viskositas Academic (Free)

• Free version of Viskositas software capable of predicting the viscosity of CaO-SiO₂-MgO-Al₂O₃-MnO-FeO-CaF₂-Na₂O systems at different process temperatures with statistical evaluation superior to classical equations and commercial software.

Prediction of physical properties of glasses using the Monte Carlo method (in progress...)

• Development of numerical models through artificial neural networks for numerical simulations through the Monte Carlo method for the discovery of new glasses.

Break Temperature Modeling (Free)

• Mathematical modeling of the break temperature (TBr, or solification temperature) of multicomponent slags through linear regression with regularization.