Logo des Repositoriums

Auflistung nach Schlagwort "Tool Qualification"

1 - 2 von 2
  • Konferenzbeitrag
    Modeling and Safety-Certification of Model-based Development Processes
    (Modellierung 2018, 2018) Slotosch, Oscar; Abu-Alqumsan, Mohammad
    In this paper, we describe a two-step approach to show evidence for compliance with safety standards within certification efforts for model-based development projects that share some commonalities (i.e. using the same metamodel). The approach is based on modeling model-based development processes in combination with the requirements imposed on them by safety standards. Besides the typical benefits of model-based approaches (modularity, rigor, formalization and simulation), we use the combined hierarchic processes-requirements model in order to automatically generate formalized descriptions of processes, standard compliance report and verification check-lists. The process description can be used to introduce new team members to the deployed development processes. As a concrete example of the proposed approach, we present representative parts of the Validas model-based tool qualification process that has been fully modeled and certified based on the automatically generated documents by TÜV SÜD
  • Konferenzbeitrag
    Tool Qualification Aspects in ML-Based Airborne Systems Development
    (Software Engineering 2023 Workshops, 2023) Dmitriev, Konstantin; Kaakai, Fateh; Ibrahim, Mohamad; Durak, Umut; Potter, Bill; Holzapfel, Florian
    Machine Learning (ML) technology can provide the best results in many highly complex tasks such as computer vision and natural language processing and quickly evolving further. These unique ML capabilities and apparent potential can enable the next epoch of automation in airborne systems including single pilot or even autonomous operation of large commercial aircraft. The main problems to be solved towards ML deployment in commercial aviation are safety and certification, because there are several major incompatibilities between ML development aspects and traditional design assurance practices, in particular traceability and coverage verification issues. In this paper, we study the qualification aspects of tools used for development and verification of ML-based systems (ML tools) and propose mitigation measures for some known ML verification gaps through ML tools qualification. In particular, we review the DO-330 and DO-200B tool classification approach with respect to ML-specific workflows and propose to extend the tool qualification criteria for ML data management and ML model training tools.