Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines

Eduardo de Conto; Blaise Genest; Arvind Easwaran; Nicholas Ng; Shweta Menon

cs.SEAug 19, 2026

Building real-time digital twin instances with Function+Data Flow: user evaluation and extension for iterative pipelines

Authors: Eduardo de Conto, Blaise Genest, Arvind Easwaran, Nicholas Ng, Shweta Menon

Organizations: College of Computing and Data Science, Nanyang Technological University, 50 Nanyang Avenue, Singapore, 639798, Singapore. · CNRS, IPAL Lab, France.

Abstract

Digital twins (DTs) increasingly leverage artificial intelligence (AI) and machine learning (ML) pipelines, both to build real-time DTs from high-fidelity simulations and to instantiate them with historical data. However, engineering these pipelines remains largely ad-hoc: pipelines are hard to specify, validate, and reuse, with scarce dedicated tooling. Function+Data Flow (FDF) addresses this by defining a visual domain-specific language (DSL) that represents functions (ML models) explicitly, enabling their composition and reuse. We implemented FDF in DesCartes Builder, an integrated modeling environment supporting FDF-based DT synthesis and validation. In this paper, we report on an empirical user study evaluating whether FDF and DesCartes Builder can make AI-based DT development more accessible and reliable. Participants implemented a representative real-time DT prototype within DesCartes Builder, and we measured perceived usability and feature adequacy through quantitative and qualitative measures. Our results indicate that DesCartes Builder and FDF achieve a good level of usability across a broad range of potential users, and particularly for the intended audience of domain experts. The study additionally surfaces concrete strengths and areas for improvement of both the tool and the underlying FDF framework. Informed by these findings, we propose H-FDF, a Hierarchical extension of FDF supporting iterative and modular pipelines, enabling the formal specification of more complex DT pipelines such as dual training. Our findings suggest that integrated, model-driven platforms are a promising direction to transform AI-based DT engineering into a disciplined modeling practice.

Figures & tables

Figure 1: Summary of DT engineering phases. FDF De Conto et al. (2024) and DesCartes Builder de Conto et al. (2025) focus on the second and third phases of fast DT learning ( Φ 2 ) and DT instantiation ( Φ 3 )

Figure 2: Pipeline to design a real-time DT prototype for material strain prediction (extracted from De Conto et al. (2024) )

Figure 3: Minimal FDF pipeline implemented in DesCartes Builder . The number next to the ports indicates a possible inferred implicit type

Figure 4: Example of FDF’s implicit type warning as implemented in DesCartes Builder when attemping to connect y to the function reduce that expects an inputs with same implicit type as X in the FDF pipeline of Fig. 3

Panel of Figure 5 — Figure 5: Comparison of FDF pipeline in DesCartes Builder (top) and equivalent KNIME pipeline (bottom)

Figure 6: Depiction of the DesCartes Builder architecture

Figure 7: DesCartes Builder user interface showing the canvas ( C 1 ) , the library selector ( C 2 ) , and the parameter editor ( C 3 ) . A simplified implementation of the material strain prediction real-time DTP (Fig. 2 ) is displayed. It uses a split_data block to partition displacement ( displ ) and plastic strain ( eps ) into training ( _train ) and test ( _test ) sets. The Trainer then learns a function predict from ( displ_train , eps_train ), which a Processor then applies to displ_test to estimate eps_p . Last, a score box compares eps_p against the test data eps_test , outputting metrics such as NMRSE and $R^{2}$ . The function predict is exported to constitute a real-time DTP.

Figure 8: Implementation of the material strain reduced-order model (ROM). It uses two Coder boxes to learn the dimensionality reduction basis, two Processors to obtain the reduced displacement ( displ_red ) and reduced strain ( eps_red ), and a Trainer to learn a surrogate model from displ_red to eps_red . Evaluation is performed using a score and a sensitivity_analysis Processor box (adapted from de Conto et al. (2025) )

Figure 9: Testing pipeline for the material strain ROM

Panel of Figure 10 — Figure 10: Validation results for the material strain prediction use case

ID	Short label (positive only)
$Q_{1}$	Intended frequency of use
$Q_{2}$	System simplicity
$Q_{3}$	Ease of use
$Q_{4}$	User independence
$Q_{5}$	Functions well integrated
$Q_{6}$	Design consistency

Table 1: Questionnaire for DesCartes Builder usability (based on the SUS questionnaire Brooke (1996) )

Panel of Figure 11 — Figure 11: Participant demographics in the DesCartes Builder user study

Figure 12: Box plot with the normalized SUS score (0 - 100 scale, higher = better). Black line: median (72.5); dark red cross (

\times

): mean score (68.9); dashed line: unnaceptable score (50)

Tool	SUS Score	Reference
Simulink	76.4	Ferrari et al. (2021)
UPPAAL	61.7	Ferrari et al. (2021)
Excel	56.5	Kortum and Bangor (2013)
Extremo	70.0	Mora Segura, Ángel and De Lara, Juan and Wimmer, Manuel (2024)
DesCartes Builder	68.9	De Conto et al. (2024) ; de Conto et al. (2025)

Table 2: Mean SUS Scores for selected tools

Figure 13: Normalized SUS item scores (0-10 scale, higher = better). Error bars: standard deviation; diamonds: medians; dashed line: unacceptable score (5.0)

Group ( $n$ )	Mean (SD)	95% CI
Technical (15)	72.8 (12.1)	[66.1, 79.5]
Low-technical (10)	63.0 (17.9)	[50.2, 75.8]
Total (25)	68.9 (15.2)	[62.6, 75.2]
Note: Welch’s $t(14.4)=1.52,p=0.15,d=0.67$ .

Table 3: SUS scores for subgroups

Figure 14: Participant feedback on specific DesCartes Builder features

Figure 15: Visual syntax for the Module box. The Module box encapsulates a subpipeline executed upon its invocation from a higher-level Module

Panel of Figure 16 — Figure 16: Example of a H-FDF pipeline $P_{1},P_{2},\hier$

Panel of Figure 17 — Figure 17: Dual Training pipeline

Panel of Figure 18 — Figure 18: Comparison of FDF pipeline in DesCartes Builder (top) and equivalent KNIME pipeline (bottom)

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

ID	Short label (positive only)	Full SUS item (positive/negative version)
$Q_{1}$	Intended frequency of use	I think that I will use DesCartes Builder rather than other methods.
$Q_{2}$	System simplicity	I found DesCartes Builder unnecessarily complex.
$Q_{3}$	Ease of use	I thought DesCartes Builder was easy to use.
$Q_{4}$	User independence	I think that I would need the support of a technical person to be able to use DesCartes Builder .
$Q_{5}$	Functions well integrated	I found the various functions in DesCartes Builder were well integrated.
$Q_{6}$	Design consistency	I thought there was too much inconsistency in DesCartes Builder .

Appendix

Table 4: Complete questionnaire for DesCartes Builder usability (based on the SUS questionnaire Brooke (1996) )

Model-Driven Engineering

See all 8 papers

High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics
Sep 15, 2026Diana A. BistrianNeural Surrogate Modeling Reduced-Order Modeling
University Politehnica Timisoara, Department of Electrical Engineering and Industrial Informatics, Romania
ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations
Aug 20, 2026Naveen Venkat, Yuchen Qiu, Tianyi Peng +2Digital Twins User Simulation
Columbia University · Columbia Business School
DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models
Oct 13, 2026Kérian Fiter, Angelica Portocarrero, Bentley OakesDigital Twins
Département de Génie Informatique et Génie Logiciel, Polytechnique Montréal, 2500, chemin de Polytechnique, Montréal, H3T 1J4, Québec, Canada · Facultad de Ingeniería y Ciencias Básicas, Universidad Autónoma de Occidente, Carrera 25 #115-85, Santiago de Cali, 760030, Colombia

Sep 15, 2026J/K move · Enter open · S save

High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics

Diana A. Bistrian

University Politehnica Timisoara, Department of Electrical Engineering and Industrial Informatics, Romania

Neural Surrogate Modeling Reduced-Order Modeling Digital Twins Computational Fluid Dynamics

Open paper AskPDF arXiv

The purpose of this paper is the identification of high-fidelity digital twin data models from numerical code outputs by non-intrusive techniques (i.e., not requiring Galerkin projection of the governing equations onto the reduced modes basis). In this paper the author defines the concept of the digital twin data model (DTM) as a model of reduced complexity that has the main feature of mirroring the original process behavior. The significant advantage of a DTM is to reproduce the dynamics with high accuracy and reduced costs in CPU time and hardware for settings difficult to explore because of the complexity of the dynamics over time. This paper introduces a new framework for creating efficient digital twin data models by combining two state-of-the-art tools: randomized dynamic mode decomposition and deep learning artificial intelligence. It is shown that the outputs are consistent with the original source data with the advantage of reduced complexity. The DTMs are investigated in the numerical simulation of three shock wave phenomena with increasing complexity. The author performs a thorough assessment of the performance of the new digital twin data models in terms of numerical accuracy and computational efficiency.

Abstract

Model-Driven Engineering

Explore similar work

High-Fidelity Digital Twin Data Models by Randomized Dynamic Mode Decomposition and Deep Learning with Applications in Fluid Dynamics

ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations

DTScribe: Generating Models for Digital Twin Reporting using Local Large Language Models