**5. Conclusions**

The design process is iterative, and the number of approximations in the case of a complex UAV object can be significant. Nowadays, CAD systems are commonly used to model the geometric form. In each of these approximations, it is necessary to generate a new geometric model, which is laborious and may lead to errors and inconsistencies. Automating the generation of a geometric model in the CAD system using generative modelling can significantly accelerate this process. Such generative models can be used both in the case of iterative improvement of the structure by designers and the application of optimization algorithms. The article describes improving a very unusual HALE UAV structure, where subsequent analyses are usually preceded by a labor-intensive rebuilding of the geometric model. Such an operation can be supported by using a generative model in the form of structured modules that enable structural modifications which are not understood in most low-fidelity verification methods of a parametric mesh but are in a multielement engineering model in the CAD system. The proposed solution does not eliminate the methods and models mentioned above—it perfectly complements them, as it allows for remodeling of a complex engineering structure and several engineering verifications that go far beyond general verification methods. In this way, the FEM analysis is performed not only on the general support structure but also on a highly verified design, including technological, assembly and general engineering relations.

The most important contributions of the paper are:


In future works, it is necessary to improve the design processes with the use of generative modelling, and in particular for further automation and integration with numerical verification methods and tools. Work will be carried out to extend the range of generative models to include less typical design solutions. Depending on needs, the generative models developed as part of the research will also be transferred to other CAD tools. Improvements of the design procedures for unusual classes of flying objects, such as HALE UAVs, are also required.

**Author Contributions:** Conceptualization, W.S. and A.J.; methodology, W.S. and A.J.; software, A.J.; validation, W.S. and A.J.; formal analysis, W.S. and A.J.; investigation, W.S. and A.J.; resources, A.J.; data curation, W.S. and A.J.; writing—original draft preparation, W.S. and A.J.; writing—review and editing, W.S. and A.J.; visualization, W.S. and A.J.; supervision, W.S.; project administration, W.S.; funding acquisition, W.S. All authors have read and agreed to the published version of the manuscript.

**Funding:** The APC was funded by the Rector's grant. Silesian University of Technology gran<sup>t</sup> number 10/060/RGP18/0102.

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** Restrictions apply to the availability of these data. Data was obtained from SkyTech eLab LLC and are available from the owners with the permission of SkyTech eLab LLC.

**Acknowledgments:** The authors would like to express their thanks to SkyTech eLab LLC for providing the data for research, moreover, we would like to thank the engineering staff and students who performed the calculations and analyses, in particular Mateusz W ˛asik, Nikodem Ciomperlik and Michał Simon.

**Conflicts of Interest:** The authors declare no conflict of interest.
