Design Engineering Assistant for the Early Design of Space Missions

Summary: Space missions development takes years and traditionally starts with a feasibility study phase where experts consider several design options, trade-offs and eventually take decisions that will impact the rest of the mission life cycle. To make these first design decisions, experts rely both on their implicit knowledge (i.e. past experiences, network) and on the available explicit knowledge (i.e. past reports, publications, datasheets, books, etc.). The former type of knowledge represents a substantial amount of unstructured data, which is today underutilized and too time-consuming to explore during the limited timeframe of a  feasibility study. A solution is to design an Expert System (ES) to support the initial study input estimation, assist experts by answering queries related to previous design decisions or push them to explore new design options. Such an effort is led since January 2018 by two PhD students, Audrey Berquand and Francesco Murdaca, at the University of Strathclyde within the Intelligent Computational Engineering (ICE) lab, under the supervision of Dr. Annalisa Riccardi. The project is done in collaboration with the European Space Agency (ESA) and industrial partners: Airbus, RHEA and satsearch.
The Design Engineering Assistant (DEA) project aims to enhance the productivity of Human experts by providing them with new insights on large amount of data accumulated in the field of space mission design. Natural Language processing, Machine Learning, Knowledge Management and Human-Machine Interaction (HMI) methods are leveraged to develop the ES. The DEA will convert the accumulated unstructured data into structured data and store them into a knowledge graph that can be traversed by an inference engine to provide reasoning and deductions. Information will be extracted from the knowledge graph via a smart querying engine tool to provide reliable and relevant knowledge summaries to the Human experts. The HMI will be reinforced by a human-to-machine feedback loop allowing experts to continuously contribute to the DEA learning process.

Timeframe: January 2018 – December 2020

People: Audrey Berquand, Francesco Murdaca, Annalisa Riccardi

Partners: ESA, Airbus, RHEA, Satsearch