WCSE

Exploring the Adoption of Machine Learning Based Manufacturing Methods in the UK’s Aerospace Manufacturing Sector: a Post Covid-19 Perspective

Abstract— Machine learning (ML) is a branch of artificial intelligence which requires the application of data and algorithms to analyse information, identify patterns and learn from experiences. Despite various challenges, ML has proved to be a powerful tool contributing to various aspects of society, specifically in the manufacturing sector through operational optimisation, quality control, design, maintenance, and inventory management etc. Although ML is playing an increasingly important role in the aerospace sector, it faces adoption challenges specifically due to its high rate of maturity being asynchronous to the aerospace sector’s rate of adaptability, specifically during times of technology disruption. This investigation applies a qualitative research design through two case studies and expert interviews to understand the various elements contributing to the dynamics of adoption of ML based manufacturing processes in the UK’s aerospace manufacturing sector. The findings indicate a general recognition about the benefits of ML based manufacturing processes, however, there are business, organisational and technical challenges which need addressing to encourage adoption. The findings are envisaged to create a mutual appreciation of challenges faced between the aerospace manufacturing sector and the ML community to further future adoption practices.

Index Terms— machine learning, aerospace, manufacturing, technology adoption

Salime Mascarenas Assad
Prometheus Group
Kushwanth Koya
The Information School, The University of Sheffield

[Download]

Cite: Salime Mascarenas Assad, Kushwanth Koya, "Exploring the Adoption of Machine Learning Based Manufacturing Methods in the UK’s Aerospace Manufacturing Sector: a Post Covid-19 Perspective", 2025 the 15th International Workshop on Computer Science and Engineering (WCSE 2025), pp. 267-276, Jeju Island, South Korea, June 28-30, 2025.