Promising results using NLP and machine learning to automate variability and reuse analysis at Bombardier Transportation
VARA, an automated requirements analysis solution developed at RISE Research Institutes of Sweden in collaboration with Mälardalen University and Bombardier Transportation in the ITEA XIVT project, can already reduce the process of software reuse analysis by at least 20 days with a prediction accuracy of around 82% as industrial evaluations at Bombardier show.
Many industrial companies don’t produce a single product but rather a series of products that are, for instance, tailored and customised for different markets, regions and customers. As the number of such products grows, the ability to reuse and adapt existing features and components across different products and projects becomes a key factor in improving production efficiency and reducing the time to market. In this context, identifying which previously implemented features and components can be selected for reuse in a new product is of utmost importance, yet not trivial in large industrial systems. Variability-Aware requirements Reuse Analysis (VARA) is a solution based on natural language processing (NLP) and machine learning developed in the scope of the ITEA project XIVT that can automatically analyse existing projects and recommend implemented features that can be candidates for reuse to realise new products. Its application and evaluation on Bombardier’s Propulsion and Controls (PPC) systems has already shown promising results as the manual process of reuse analysis can now be done automatically in a matter of minutes instead of a couple of weeks for complex systems.
The ITEA project XIVT, consisting of partners from Sweden, Germany, Turkey, Canada and Portugal, targets specific challenges of testing highly-configurable variant-intensive industrial systems. Within the XIVT project, a method and toolchain will be defined for testing such systems in the automotive, railway, telecommunication, and industrial production domains. VARA is one of the solutions in the XIVT project that are developed towards optimising the overall testing process of variant-intensive industrial systems.
More information
Related events
ToCaMS workshop at ICST 2020 conference
ITEQS workshop at ICST 2020 conference
