Unassigned · 2026-10-01
An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
Hadiza Umar Yusuf, Khouloud Gaaloul
AI-assisted summary based on the paper. Consult the linked source for methods and limitations. Benchmark numbers appear after editor verification.
TL;DR
The authors report an empirical study comparing traditional vs AI-enabled Simulink controllers using a literature-derived taxonomy of 10 structural categories and 9 functional roles, analyzing 62 real-world models and surveying 13 practitioners. They identify three architectural tensions: subsystem organization dominates (68–72% footprint), AI-enabled controllers use discrete dynamics and user-defined abstraction not present in AI literature, and constraint enforcement blocks largely disappear in AI-enabled models, reducing traceability.
Why it matters
The paper provides an architectural lens for cross-paradigm comparison in Simulink controller design. By contrasting literature descriptions with what appears in real-world Simulink models—and checking with practitioners—it highlights where architectural documentation and safety expectations diverge between traditional and AI-enabled controllers, motivating paradigm-aware MBSE tool support for safety assurance and verification traceability.
Method
- Builds a literature-derived taxonomy of ten structural categories (C1–C10) and nine functional roles (L1–L9) for Simulink controller architecture.
- Analyzes 62 open-source Simulink models (traditional vs AI-enabled) using block extraction and category detection at the controller-subsystem level; computes coverage, mean normalized presence, and model-level prevalence.
- Corroborates patterns via an anonymous survey with 13 practitioners on 12 representative Simulink models using dominance/essentiality ratings and open-ended justification.
Limitation
External validity may not generalize beyond Simulink or to other domains (e.g., power systems), and the 13-participant sample may not capture the full range of industrial expertise.
Abstract (from arXiv)
Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace analytically derived control laws, this occurs without a systematic understanding of how controller architectures differ or remain similar across paradigms. We address this gap with an empirical study of traditional and AI-enabled Simulink controllers, guided by a literature-derived taxonomy of ten structural categories and nine functional roles. The study analyzes 62 real-world models spanning 8 controller types and 10 application domains, and surveys 13 practitioners, identifying three architectural tensions. First, subsystem organization dominates all controller structures regardless of paradigm, occupying 68-72% of controller footprint, while core control logic occupies minimal space. Second, AI-enabled controllers rely heavily on discrete dynamics and user-defined abstraction, categories largely absent from AI literature, exposing a gap between described and implemented architectures. Third, constraint enforcement blocks largely disappear from AI-enabled models despite practitioner expectations. This reveals a misalignment where safety mechanisms shift from explicit structure to implicit training-time artifacts, breaking traceability.
Related papers
- Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance
- A Decade of Learning-Based Control: From Theoretic Foundations to Practical Deployment
- Physical AI: Concepts, Techniques, and Challenges
- Mind the Execution Gap: Action-Semantic Mismatch in World-Model Control
- CyberWorld: World Models for Sample-Efficient Autonomous Cyber Defense
Publication record
Bibliographic evidence describes where and when a record appeared. It does not validate scientific claims.
First public release: 2026-09-29 · Indexed by Pub-AI: 2026-10-01 UTC
An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
Preprint posted: 2026-09-29 · Original record ↗
- arxiv
- 2609.38504
Explicit source versions (1)
- v1 · 2026-09-29
- Preprint available
Source date: 2026-09-29 · First detected: 2026-10-25 UTC · Historical baseline
Source evidence (1)
- Official evidence ↗ · atom:published (official metadata)
Abstract · arxiv
Effective AI adoption in cyber-physical systems (CPS) depends on embedding design knowledge into engineering practice. Yet as AI-enabled components increasingly replace analytically derived control laws, this occurs without a systematic understanding of how controller architectures differ or remain similar across paradigms. We address this gap with an empirical study of traditional and AI-enabled Simulink controllers, guided by a literature-derived taxonomy of ten structural categories and nine functional roles. The study analyzes 62 real-world models spanning 8 controller types and 10 application domains, and surveys 13 practitioners, identifying three architectural tensions. First, subsystem organization dominates all controller structures regardless of paradigm, occupying 68-72% of controller footprint, while core control logic occupies minimal space. Second, AI-enabled controllers rely heavily on discrete dynamics and user-defined abstraction, categories largely absent from AI literature, exposing a gap between described and implemented architectures. Third, constraint enforcement blocks largely disappear from AI-enabled models despite practitioner expectations. This reveals a misalignment where safety mechanisms shift from explicit structure to implicit training-time artifacts, breaking traceability.