Search results for: Goncalo%20Maia%20Da%20Costa

Authors: Yizhen Zhao, Adam S. Z. Belloum, Goncalo Maia Da Costa, Zhiming Zhao

Abstract:

Machine learning has evolved from an area of academic research to a real-word applied field. This change comes with challenges, gaps and differences exist between common practices in academic environments and the ones in production environments. Following continuous integration, development and delivery practices in software engineering, similar trends have happened in machine learning (ML) systems, called MLOps. In this paper we propose a framework that helps to streamline and introduce best practices that facilitate the ML lifecycle in an industrial setting. This framework can be used as a template that can be customized to implement various machine learning experiment. The proposed framework is modular and can be recomposed to be adapted to various use cases (e.g. data versioning, remote training on cloud). The framework inherits practices from DevOps and introduces other practices that are unique to the machine learning system (e.g.data versioning). Our MLOps practices automate the entire machine learning lifecycle, bridge the gap between development and operation.

Keywords: cloud computing, continuous development, data versioning, DevOps, industrial setting, MLOps

Procedia PDF Downloads 234

Authors: Daniel Barros, Carlos Mota, Raul Fangueiro, Pedro Rosa, Gonçalo Domingos, Alfredo Passanha, Norberto Almeida

Abstract:

The main aim of the work was to compare the ballistic performance of developed composites using different types of fiber woven fabrics [0,90] and different layers orientation (Angle-ply). The ballistic laminate composites were developed using E-glass, S-glass and aramid fabrics impregnated with thermosetting epoxy resin and using different layers orientation (0,0)º and (0,15)º. The idea of the study is to compare the ballistic performance of each laminate produced by studying the velocity loss of the fragment fired into the laminate surface. There are present some mechanical properties for laminates produced using the different types of fiber, where tensile, flexural and impact Charpy properties were studied. Overall, the angle-ply laminates produced using orientations of (0,15)º, despite the slight loss of mechanical properties compared to the (0,0)º orientation, presents better ballistic resistance and dissipation of energy, for lower ballistic impact velocities (under 290 m/s-1). After treatment of ballistic impact results, the S-Glass with (0,15)º laminate presents better ballistic perforce compared to the other combinations studied.

Keywords: ballistic impact, angle-ply, ballistic composite, s-glass fiber, aramid fiber, fabric fiber, energy dissipation, mechanical performance

Procedia PDF Downloads 181