The last five years have seen a rise in AI for commercial enterprises, and now the technology could transform how space missions are designed. A new study of the The University of Strathclyde’s Intelligent Computational Engineering Laboratory is leveraging AI techniques to create a design engineering assistant for the early design of space missions.
Every space mission traditionally starts with a feasibility study, where experts consider several design options and discuss some of the aspects that will impact the rest of the mission lifecycle. To make these first design decisions, engineers need to process huge amounts of information from different sources in a very short period, which often becomes an impossible task.
The design engineering assistant aims to structure a large amount of data, answer queries related to previous design decisions, and offer new design options to explore.
To do that, the study is using the latest natural language processing, machine learning, knowledge management and human-machine interaction techniques to structure the data and store them into a knowledge graph that can be traversed by an inference engine to provide reasoning and deductions.
Information is then extracted from the knowledge graph via a smart querying engine tool to provide reliable and relevant knowledge summaries to the experts. The human-machine interaction will be reinforced by a human-to-machine feedback loop allowing experts to contribute to the learning process of the design engineering assistant.
The study is being 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), Airbus, RHEA Group and Citysearch.
The initial results of this project will be presented at SECESA 2018 in Glasgow, United Kingdom, from 26th to 28th of September.