Siyuan Ji
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Siyuan Ji has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Charles E. Dickerson
Loughborough University
7 shared publications - Michael J. de C. Henshaw
Loughborough University, Loughborough, United Kingdom
6 shared publications - Amal Elsokary
Loughborough University, Loughborough, United Kingdom
4 shared publications - Hayato Ishida
Loughborough University, Loughborough, United Kingdom
4 shared publications C. Ates
2 shared publications- Catherine White
BT Research, Ipswich, United Kingdom
2 shared publications
Latest Publications
- Open Access
- 31 October 2026
- Published by Elsevier in Digital Engineering
- Vol. 12
Digital engineering for quantum communication networks: A systematic review of models, simulators, and testbeds
- 31 October 2026
- Published by Elsevier in Digital Engineering
- Vol. 12
Open AccessDigital engineering for quantum communication networks: A systematic review of models, simulators, and testbeds
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1190-1194
Anchoring Co-Design on the Engineered Quantum System: A Model-Based Approach
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1190-1194
Open AccessAnchoring Co-Design on the Engineered Quantum System: A Model-Based Approach
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1205-1214
Model-Driven Digital Twin Framework for Quantum Networks
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1205-1214
Open AccessModel-Driven Digital Twin Framework for Quantum Networks
- Open Access
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1185-1189
A Framework for Managing the Models of Engineered Quantum Systems
- 4 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1185-1189
Open AccessA Framework for Managing the Models of Engineered Quantum Systems
- Open Access
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 504-510
Models as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
Programmatic access to machine-readable models such as SysML v2 is often treated as sufficient for AI participation in systems engineering. It is only a precondition. The remaining work lies in the data architecture around the model. An AI reader querying a structurally complete model encounters absent derivation chains, untagged epistemic status, missing provenance, and unreachable evidence. Faced with these gaps, the AI reader fills them from training data, which lies outside the governed record. We test on the public Apollo 11 SysML v2 reconstruction, exemplary by current practice. We name the missing property epistemic adequacy and offer it as a candidate data-architecture pattern in two halves. Read-side adequacy lets derivation, status, and provenance answer a query the model would otherwise leave to inference; write-side admissibility gates an AI contribution before it enters the record. The property decomposes into five criteria. Four sit on the read side, evidenced by the case and convergent literature; the fifth sits on the participation side, advanced as a hypothesis for future test. The architecture space spans an inline metadata extension to a substrate-native multi-model store, and over that space we propose the Governed-Query Architecture Framework, governing agent participation through the viewpoint conventions engineers already use. We state the reframing in falsifiable form: the epistemic layer stands only if it outperforms a retrieval-augmented baseline on the same model.
- 3 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 504-510
Open AccessModels as Governed Interfaces for AI-Native MBSE: Read-Side Adequacy and Write-Side Admissibility
Programmatic access to machine-readable models such as SysML v2 is often treated as sufficient for AI participation in systems engineering. It is only a precondition. The remaining work lies in the data architecture around the model. An AI reader querying a structurally complete model encounters absent derivation chains, untagged epistemic status, missing provenance, and unreachable evidence. Faced with these gaps, the AI reader fills them from training data, which lies outside the governed record. We test on the public Apollo 11 SysML v2 reconstruction, exemplary by current practice. We name the missing property epistemic adequacy and offer it as a candidate data-architecture pattern in two halves. Read-side adequacy lets derivation, status, and provenance answer a query the model would otherwise leave to inference; write-side admissibility gates an AI contribution before it enters the record. The property decomposes into five criteria. Four sit on the read side, evidenced by the case and convergent literature; the fifth sits on the participation side, advanced as a hypothesis for future test. The architecture space spans an inline metadata extension to a substrate-native multi-model store, and over that space we propose the Governed-Query Architecture Framework, governing agent participation through the viewpoint conventions engineers already use. We state the reframing in falsifiable form: the epistemic layer stands only if it outperforms a retrieval-augmented baseline on the same model.
- Open Access
- 5 September 2025
- Published by Wiley in Systems Engineering
- Vol. 29 (1) , 20-33
MBSE Co‐Pilot: A Research Roadmap
As the complexity of engineered systems continues to increase, Model‐Based Systems Engineering (MBSE) methodologies, languages, and tools are increasingly insufficient to meet the demands of modern systems engineering. This paper proposes a research roadmap for the development of an AI‐driven machine, referred to as MBSE Co‐Pilot, designed to augment MBSE activities, not only to address the demand for technical advancement in MBSE, but also to better facilitate the adoption of MBSE for organizations transitioning into digital engineering. The MBSE Co‐Pilot leverages advances in Artificial Intelligence (AI) technologies, including but not limited to Natural Language Processing, Machine Learning, and Computer Vision, to support model development, model management, and model comprehension.
- 5 September 2025
- Published by Wiley in Systems Engineering
- Vol. 29 (1) , 20-33
Open AccessMBSE Co‐Pilot: A Research Roadmap
As the complexity of engineered systems continues to increase, Model‐Based Systems Engineering (MBSE) methodologies, languages, and tools are increasingly insufficient to meet the demands of modern systems engineering. This paper proposes a research roadmap for the development of an AI‐driven machine, referred to as MBSE Co‐Pilot, designed to augment MBSE activities, not only to address the demand for technical advancement in MBSE, but also to better facilitate the adoption of MBSE for organizations transitioning into digital engineering. The MBSE Co‐Pilot leverages advances in Artificial Intelligence (AI) technologies, including but not limited to Natural Language Processing, Machine Learning, and Computer Vision, to support model development, model management, and model comprehension.
- Open Access
When BIM Meets MBSE: Building a Semantic Bridge for Infrastructure Data Integration
The global infrastructure industry is faced with increasing system complexity and requirements driven by the Sustainable Development Goals, technological advancements, and the shift from Industry 4.0 to human-centric 5.0 principles. Coupled with persistent infrastructure investment deficits, these pressures necessitate improved methods for efficient requirements management and validation. While digital twins promise transformative real-time decision-making, reliance on static unstructured data formats inhibits progress. This paper presents a novel framework that integrates Building Information Modelling (BIM) and Model-Based Systems Engineering (MBSE), using Linked Data principles to preserve semantic meaning during information exchange between physical abstractions and requirements. The proposed approach automates a step of compliance validation against regulatory standards explored through a case study, utilising requirements from a high-speed railway station fire safety system and a modified duplex apartment digital model. The workflow (i) digitises static documents into machine-readable MBSE formats, (ii) integrates structured data into dynamic digital models, and (iii) creates foundations for data exchange to enable compliance validation. These findings highlight the framework’s ability to enhance traceability, bridge static and dynamic data gaps, and provide decision-making support in digital twin environments. This study advances the application of Linked Data in infrastructure, enabling broader integration of ontologies required for dynamic decision-making trade-offs.
Open AccessWhen BIM Meets MBSE: Building a Semantic Bridge for Infrastructure Data Integration
The global infrastructure industry is faced with increasing system complexity and requirements driven by the Sustainable Development Goals, technological advancements, and the shift from Industry 4.0 to human-centric 5.0 principles. Coupled with persistent infrastructure investment deficits, these pressures necessitate improved methods for efficient requirements management and validation. While digital twins promise transformative real-time decision-making, reliance on static unstructured data formats inhibits progress. This paper presents a novel framework that integrates Building Information Modelling (BIM) and Model-Based Systems Engineering (MBSE), using Linked Data principles to preserve semantic meaning during information exchange between physical abstractions and requirements. The proposed approach automates a step of compliance validation against regulatory standards explored through a case study, utilising requirements from a high-speed railway station fire safety system and a modified duplex apartment digital model. The workflow (i) digitises static documents into machine-readable MBSE formats, (ii) integrates structured data into dynamic digital models, and (iii) creates foundations for data exchange to enable compliance validation. These findings highlight the framework’s ability to enhance traceability, bridge static and dynamic data gaps, and provide decision-making support in digital twin environments. This study advances the application of Linked Data in infrastructure, enabling broader integration of ontologies required for dynamic decision-making trade-offs.
- Open Access
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Systems Engineering
- Vol. 1, 81-93
BSafeML: A Model-Based Hazard Management Technique for Safety-Critical Systems Development
Effective management of hazards is at the heart of achieving acceptable safety for any safety-critical system. With the recent advancement in model-based systems engineering, various hazard management techniques have been proposed as means to transition from a document-based paradigm, such as hazard logs implemented in a relational database to a model-based paradigm with standardized modeling languages. However, a review of the state-of-the-art has shown that existing methods do not provide sufficient traceability to integrate hazard management with other system lifecycle activities. To address this gap, a new model-based hazard management technique, BSafeML, is developed. BSafeML is a UML profile, and a pro- cedure, extending the existing SysML and SafeML profiles with language for modeling the behavior of hazards and mitigations. BSafeML integrates structural and behavioral views of hazards, supporting traceability and semantic consistency over them and with the wider system-of-interest. Specific behaviors supported by BSafeML include accident sequences and ordered action of safety functions. BSafeML is evaluated in a case study of a waste package emplacement system in the context of geological disposal of radioactive waste. A hazard log, including a range of hazard types, is converted to model-based format with BSafeML. The evaluation is further supported by a stakeholder survey that revealed mostly positive attitudes towards the safety function modeling by BSafeML.
- 17 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Systems Engineering
- Vol. 1, 81-93
Open AccessBSafeML: A Model-Based Hazard Management Technique for Safety-Critical Systems Development
Effective management of hazards is at the heart of achieving acceptable safety for any safety-critical system. With the recent advancement in model-based systems engineering, various hazard management techniques have been proposed as means to transition from a document-based paradigm, such as hazard logs implemented in a relational database to a model-based paradigm with standardized modeling languages. However, a review of the state-of-the-art has shown that existing methods do not provide sufficient traceability to integrate hazard management with other system lifecycle activities. To address this gap, a new model-based hazard management technique, BSafeML, is developed. BSafeML is a UML profile, and a pro- cedure, extending the existing SysML and SafeML profiles with language for modeling the behavior of hazards and mitigations. BSafeML integrates structural and behavioral views of hazards, supporting traceability and semantic consistency over them and with the wider system-of-interest. Specific behaviors supported by BSafeML include accident sequences and ordered action of safety functions. BSafeML is evaluated in a case study of a waste package emplacement system in the context of geological disposal of radioactive waste. A hazard log, including a range of hazard types, is converted to model-based format with BSafeML. The evaluation is further supported by a stakeholder survey that revealed mostly positive attitudes towards the safety function modeling by BSafeML.
- Open Access
- 24 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Systems Engineering
- Vol. 1, 26-37
Requirements Rationalization and Synthesis Enabled by Model Synchronization
In the international standard for system and software engineering ISO/IEC/IEEE 15288: 2015, the output of the stakeholder needs and the business or mission analysis technical processes are transformed into a technical view of the system by the system requirements definition process. In model-based systems engineering, functional needs can be modeled by use case diagrams. Intended outcomes of system requirements definition include resolution of disagreement about requirements, explicit agreement between stakeholders, and traceability. However, stakeholder needs are often elicited in a siloed manner and may be inconsistent. The lack of mathematically based systematic approaches for requirements definition poses a challenge to model-based transformation of needs into a technical view of the system that achieves agreement between stakeholders. This paper specifies and demonstrates mathematical frameworks for rationalizing and synthesizing functional needs that have been captured through an elicitation process. Benefits of this approach include but are not limited to supporting rigorous identification and resolution of disagreements and facilitating systematic analysis of change impact to achieve stakeholder agreement all with minimal intervention by the system engineers.
- 24 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of Systems Engineering
- Vol. 1, 26-37
Open AccessRequirements Rationalization and Synthesis Enabled by Model Synchronization
In the international standard for system and software engineering ISO/IEC/IEEE 15288: 2015, the output of the stakeholder needs and the business or mission analysis technical processes are transformed into a technical view of the system by the system requirements definition process. In model-based systems engineering, functional needs can be modeled by use case diagrams. Intended outcomes of system requirements definition include resolution of disagreement about requirements, explicit agreement between stakeholders, and traceability. However, stakeholder needs are often elicited in a siloed manner and may be inconsistent. The lack of mathematically based systematic approaches for requirements definition poses a challenge to model-based transformation of needs into a technical view of the system that achieves agreement between stakeholders. This paper specifies and demonstrates mathematical frameworks for rationalizing and synthesizing functional needs that have been captured through an elicitation process. Benefits of this approach include but are not limited to supporting rigorous identification and resolution of disagreements and facilitating systematic analysis of change impact to achieve stakeholder agreement all with minimal intervention by the system engineers.
- Open Access
Requirements Rationalization and Synthesis enabled by Model Synchronization
In the international standard for system and software engineering ISO/IEC/IEEE 15288: 2015, the output of the stakeholder needs and the business or mission analysis technical processes are transformed into a technical view of the system by the system requirements definition process. In model-based systems engineering, functional needs can be modeled by use case diagrams. Intended outcomes of system requirements definition include resolution of disagreement about requirements, explicit agreement between stakeholders, and traceability. However, stakeholder needs are often elicited in a siloed manner and may be inconsistent. The lack of mathematically based systematic approaches for requirements definition poses a challenge to model-based transformation of needs into a technical view of the system that achieves agreement between stakeholders. This paper specifies and demonstrates mathematical frameworks for rationalizing and synthesizing functional needs that have been captured through an elicitation process. Benefits of this approach include but are not limited to supporting rigorous identification and resolution of disagreements and facilitating systematic analysis of change impact to achieve stakeholder agreement all with minimal intervention by the system engineers.
Open AccessRequirements Rationalization and Synthesis enabled by Model Synchronization
In the international standard for system and software engineering ISO/IEC/IEEE 15288: 2015, the output of the stakeholder needs and the business or mission analysis technical processes are transformed into a technical view of the system by the system requirements definition process. In model-based systems engineering, functional needs can be modeled by use case diagrams. Intended outcomes of system requirements definition include resolution of disagreement about requirements, explicit agreement between stakeholders, and traceability. However, stakeholder needs are often elicited in a siloed manner and may be inconsistent. The lack of mathematically based systematic approaches for requirements definition poses a challenge to model-based transformation of needs into a technical view of the system that achieves agreement between stakeholders. This paper specifies and demonstrates mathematical frameworks for rationalizing and synthesizing functional needs that have been captured through an elicitation process. Benefits of this approach include but are not limited to supporting rigorous identification and resolution of disagreements and facilitating systematic analysis of change impact to achieve stakeholder agreement all with minimal intervention by the system engineers.