Towards an artificial intelligence based design engineering assistant for the early design of space missions

Audrey Berquand, Francesco Murdaca, Annalisa Riccardi, Tiago Soares, Sam Gerené, Norbert Brauer, Kartik Kumar

Research output: Contribution to conferencePaper

1 Citation (Scopus)

Abstract

This paper describes a solution to enhance Knowledge Management (KM) and Reuse at the early stages of space mission design in the frame of Concurrent Engineering (CE) studies via the implementation of an Expert System (ES). CE is a centralized engineering approach which significantly accelerates and increases the reliability of space mission feasibility assessment by having experts work concurrently, thus enhancing the communication flow. An ES is an AI-based agent capturing Human expertise in a computer program. There are many examples of ES being successfully implemented in the aeronautical, agricultural, legal or medical fields. To assess the feasibility of a mission, experts rely both on their implicit knowledge (i.e., past experiences, network, etc.) and on available explicit knowledge (i.e., past reports, publications, datasheets, books, etc.). This latter type of knowledge represents a substantial amount of unstructured data, continuously increasing over the past decades. The amount of information has become highly time consuming to search through within the limited timeframe of a feasibility study and is therefore often underutilised. A solution is to convert this data into structured data and store them into a Knowledge Graph (KG) that can be traversed through an inference engine to provide reasoning and deductions. Information is extracted from the KG via a querying module from a User Interface (UI) supporting the Human-Machine Interaction (HMI). The Design Engineering Assistant (DEA), the ES for space mission design, aims to enhance the productivity of experts by providing them with new insights on large amount of data accumulated in the field of space mission design. Not only will it act as a Knowledge Engine (KE) but, integrated to the design environment, it could play a much more active part into the design process, advising the Human experts on design iterations. This paper introduces the proposed integration of an Artificial Intelligence (AI) agent into the CE process, the preliminary architecture of the tool and identified challenges. The study will also present the outcomes of a set of experts interviews carried out at the European Space Research and Technology Center (ESTEC) of ESA in July-August 2018, to define the DEA requirements following a User-centred approach.

Conference

Conference69th International Astronautical Congress
Abbreviated titleIAC 2018
CountryGermany
CityBremen
Period1/10/185/10/18

Fingerprint

Artificial intelligence
Expert systems
Concurrent engineering
Space research
Inference engines
Knowledge management
User interfaces
Computer program listings
Productivity
Communication

Keywords

  • expert systems
  • space mission design
  • concurrent engineering
  • artificial intelligence
  • knowledge graph

Cite this

Berquand, A., Murdaca, F., Riccardi, A., Soares, T., Gerené, S., Brauer, N., & Kumar, K. (2018). Towards an artificial intelligence based design engineering assistant for the early design of space missions. Paper presented at 69th International Astronautical Congress, Bremen, Germany.
Berquand, Audrey ; Murdaca, Francesco ; Riccardi, Annalisa ; Soares, Tiago ; Gerené, Sam ; Brauer, Norbert ; Kumar, Kartik. / Towards an artificial intelligence based design engineering assistant for the early design of space missions. Paper presented at 69th International Astronautical Congress, Bremen, Germany.11 p.
@conference{6fe65cd5277f42efb2a5b67968d8c6b5,
title = "Towards an artificial intelligence based design engineering assistant for the early design of space missions",
abstract = "This paper describes a solution to enhance Knowledge Management (KM) and Reuse at the early stages of space mission design in the frame of Concurrent Engineering (CE) studies via the implementation of an Expert System (ES). CE is a centralized engineering approach which significantly accelerates and increases the reliability of space mission feasibility assessment by having experts work concurrently, thus enhancing the communication flow. An ES is an AI-based agent capturing Human expertise in a computer program. There are many examples of ES being successfully implemented in the aeronautical, agricultural, legal or medical fields. To assess the feasibility of a mission, experts rely both on their implicit knowledge (i.e., past experiences, network, etc.) and on available explicit knowledge (i.e., past reports, publications, datasheets, books, etc.). This latter type of knowledge represents a substantial amount of unstructured data, continuously increasing over the past decades. The amount of information has become highly time consuming to search through within the limited timeframe of a feasibility study and is therefore often underutilised. A solution is to convert this data into structured data and store them into a Knowledge Graph (KG) that can be traversed through an inference engine to provide reasoning and deductions. Information is extracted from the KG via a querying module from a User Interface (UI) supporting the Human-Machine Interaction (HMI). The Design Engineering Assistant (DEA), the ES for space mission design, aims to enhance the productivity of experts by providing them with new insights on large amount of data accumulated in the field of space mission design. Not only will it act as a Knowledge Engine (KE) but, integrated to the design environment, it could play a much more active part into the design process, advising the Human experts on design iterations. This paper introduces the proposed integration of an Artificial Intelligence (AI) agent into the CE process, the preliminary architecture of the tool and identified challenges. The study will also present the outcomes of a set of experts interviews carried out at the European Space Research and Technology Center (ESTEC) of ESA in July-August 2018, to define the DEA requirements following a User-centred approach.",
keywords = "expert systems, space mission design, concurrent engineering, artificial intelligence, knowledge graph",
author = "Audrey Berquand and Francesco Murdaca and Annalisa Riccardi and Tiago Soares and Sam Geren{\'e} and Norbert Brauer and Kartik Kumar",
year = "2018",
month = "10",
day = "1",
language = "English",
note = "69th International Astronautical Congress, IAC 2018 ; Conference date: 01-10-2018 Through 05-10-2018",

}

Berquand, A, Murdaca, F, Riccardi, A, Soares, T, Gerené, S, Brauer, N & Kumar, K 2018, 'Towards an artificial intelligence based design engineering assistant for the early design of space missions' Paper presented at 69th International Astronautical Congress, Bremen, Germany, 1/10/18 - 5/10/18, .

Towards an artificial intelligence based design engineering assistant for the early design of space missions. / Berquand, Audrey; Murdaca, Francesco; Riccardi, Annalisa; Soares, Tiago; Gerené, Sam ; Brauer, Norbert ; Kumar, Kartik.

2018. Paper presented at 69th International Astronautical Congress, Bremen, Germany.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Towards an artificial intelligence based design engineering assistant for the early design of space missions

AU - Berquand, Audrey

AU - Murdaca, Francesco

AU - Riccardi, Annalisa

AU - Soares, Tiago

AU - Gerené, Sam

AU - Brauer, Norbert

AU - Kumar, Kartik

PY - 2018/10/1

Y1 - 2018/10/1

N2 - This paper describes a solution to enhance Knowledge Management (KM) and Reuse at the early stages of space mission design in the frame of Concurrent Engineering (CE) studies via the implementation of an Expert System (ES). CE is a centralized engineering approach which significantly accelerates and increases the reliability of space mission feasibility assessment by having experts work concurrently, thus enhancing the communication flow. An ES is an AI-based agent capturing Human expertise in a computer program. There are many examples of ES being successfully implemented in the aeronautical, agricultural, legal or medical fields. To assess the feasibility of a mission, experts rely both on their implicit knowledge (i.e., past experiences, network, etc.) and on available explicit knowledge (i.e., past reports, publications, datasheets, books, etc.). This latter type of knowledge represents a substantial amount of unstructured data, continuously increasing over the past decades. The amount of information has become highly time consuming to search through within the limited timeframe of a feasibility study and is therefore often underutilised. A solution is to convert this data into structured data and store them into a Knowledge Graph (KG) that can be traversed through an inference engine to provide reasoning and deductions. Information is extracted from the KG via a querying module from a User Interface (UI) supporting the Human-Machine Interaction (HMI). The Design Engineering Assistant (DEA), the ES for space mission design, aims to enhance the productivity of experts by providing them with new insights on large amount of data accumulated in the field of space mission design. Not only will it act as a Knowledge Engine (KE) but, integrated to the design environment, it could play a much more active part into the design process, advising the Human experts on design iterations. This paper introduces the proposed integration of an Artificial Intelligence (AI) agent into the CE process, the preliminary architecture of the tool and identified challenges. The study will also present the outcomes of a set of experts interviews carried out at the European Space Research and Technology Center (ESTEC) of ESA in July-August 2018, to define the DEA requirements following a User-centred approach.

AB - This paper describes a solution to enhance Knowledge Management (KM) and Reuse at the early stages of space mission design in the frame of Concurrent Engineering (CE) studies via the implementation of an Expert System (ES). CE is a centralized engineering approach which significantly accelerates and increases the reliability of space mission feasibility assessment by having experts work concurrently, thus enhancing the communication flow. An ES is an AI-based agent capturing Human expertise in a computer program. There are many examples of ES being successfully implemented in the aeronautical, agricultural, legal or medical fields. To assess the feasibility of a mission, experts rely both on their implicit knowledge (i.e., past experiences, network, etc.) and on available explicit knowledge (i.e., past reports, publications, datasheets, books, etc.). This latter type of knowledge represents a substantial amount of unstructured data, continuously increasing over the past decades. The amount of information has become highly time consuming to search through within the limited timeframe of a feasibility study and is therefore often underutilised. A solution is to convert this data into structured data and store them into a Knowledge Graph (KG) that can be traversed through an inference engine to provide reasoning and deductions. Information is extracted from the KG via a querying module from a User Interface (UI) supporting the Human-Machine Interaction (HMI). The Design Engineering Assistant (DEA), the ES for space mission design, aims to enhance the productivity of experts by providing them with new insights on large amount of data accumulated in the field of space mission design. Not only will it act as a Knowledge Engine (KE) but, integrated to the design environment, it could play a much more active part into the design process, advising the Human experts on design iterations. This paper introduces the proposed integration of an Artificial Intelligence (AI) agent into the CE process, the preliminary architecture of the tool and identified challenges. The study will also present the outcomes of a set of experts interviews carried out at the European Space Research and Technology Center (ESTEC) of ESA in July-August 2018, to define the DEA requirements following a User-centred approach.

KW - expert systems

KW - space mission design

KW - concurrent engineering

KW - artificial intelligence

KW - knowledge graph

UR - https://www.iac2018.org/

M3 - Paper

ER -

Berquand A, Murdaca F, Riccardi A, Soares T, Gerené S, Brauer N et al. Towards an artificial intelligence based design engineering assistant for the early design of space missions. 2018. Paper presented at 69th International Astronautical Congress, Bremen, Germany.