Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin

Osimone Imhogiemhe; Yoann Jus; Hubert Lejeune; Saïd Moussaoui

cs.LGFeb 25, 2026

Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin

Authors: Osimone Imhogiemhe, Yoann Jus, Hubert Lejeune, Saïd Moussaoui

Organizations: LS2N, LS2N - équipe SIMS, Nantes Univ - ECN · Nantes Univ., Centrale Nantes LS2N, CNRS UMR 6004 F-44000 Nantes, France · Cetim · Fluid & Sealing Technologies CETIM Nantes, France

Abstract

The real-time supervision of production processes is a common challenge across several industries. It targets process component monitoring and its predictive maintenance in order to ensure safety, uninterrupted production and maintain high efficiency level. The rise of advanced tools for the simulation of physical systems in addition to data-driven machine learning models offers the possibility to design numerical tools dedicated to efficient system monitoring. In that respect, the digital twin concept presents an adequate framework that proffers solution to these challenges. The main purpose of this paper is to develop such a digital twin dedicated to fault detection and diagnosis in the context of a thermal-hydraulic process supervision. Based on a numerical simulation of the system, in addition to machine learning methods, we propose different modules dedicated to process parameter change detection and their on-line estimation. The proposed fault detection and diagnosis algorithm is validated on a specific test scenario, with single one-off parameter change occurrences in the system. The numerical results show good accuracy in terms of parameter variation localization and the update of their values.

Figures & tables

Fig. 1: Photo of the closed hydraulic loop

Fig. 2: The CAD of the closed hydraulic loop

Fig. 3: The 1D model of the closed hydraulic loop on Simcenter Flomaster software

Parameter	Description	Value
$\theta_{1}$	Head loss of piping section 1 ”Loss1” (-)	4.5
$\theta_{2}$	Head loss of piping section 3 ”Loss3” (-)	1.17
$\theta_{3}$	Head loss of heat exchanger ”Lossx” (-)	10.35
$\theta_{4}$	Tank pressure ”P $\_$ Tank” (bar)	3
$\theta_{5}$	Pump rated head ”HMT”(m)	229
$\theta_{6}$	Pump rated flow ”Debit”( $m^{3}/h$ )	15.3

TABLE I: Nominal Values of the Component Vector

Fig. 4: The simplified monitoring principle using the DT

Fig. 5: The FDD Algorithm

Fig. 6: Example of a single perturbation scenario

	Truth
Classification	$\theta_{1}$	$\theta_{2}$	$\theta_{3}$	$\theta_{4}$	$\theta_{5}$ $\&$ $\theta_{6}$
$\theta_{1}$	5139	2	115	0	564
$\theta_{2}$	0	5702	141	0	157
$\theta_{3}$	9	25	5639	0	327
$\theta_{4}$	0	0	0	5699	0
$\theta_{5}$ $\&$ $\theta_{6}$	17	0	379	0	11304

TABLE II: Confusion Matrix of the Fault Localization

	Truth
Classification	$\theta_{1}$	$\theta_{2}$	$\theta_{3}$	$\theta_{4}$	$\theta_{5}$ $\&$ $\theta_{6}$
$\theta_{1}$	88.3 $\%$	0.03 $\%$	1.98 $\%$	0.00 $\%$	9.69 $\%$
$\theta_{2}$	0.00 $\%$	95.03 $\%$	2.35 $\%$	0.00 $\%$	2.62 $\%$
$\theta_{3}$	0.15 $\%$	0.42 $\%$	93.98 $\%$	0.00 $\%$	5.45 $\%$
$\theta_{4}$	0.00 $\%$	0.00 $\%$	0.00 $\%$	100.00 $\%$	0.00 $\%$
$\theta_{5}$ $\&$ $\theta_{6}$	0.15 $\%$	0.00 $\%$	3.24 $\%$	0.00 $\%$	96.62 $\%$

TABLE III: Accuracy Matrix of the Fault Localization

Fig. 7: Evolution of single fault occurrences

Fig. 8: Estimation Error of the SVR model

Fault Detection

Fault detection identifies abnormal behavior in machines, sensors, infrastructure, software, and autonomous systems before it causes harm or disruption.

See all 104 papers

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing
Jul 20, 2026Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria +3Neural Surrogate Modeling Concept Drift
Department of Mechanical Engineering, Northwestern University · Department of Industrial Engineering and Management Science, Northwestern University
Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning
May 7, 2026Umme Mahbuba Nabila, Paul Seurin, Linyu Lin +1Surrogate Modeling Sparse Identification of Nonlinear Dynamics
Department of Nuclear Engineering and Radiological Sciences, University of Michigan, Ann Arbor, MI 48109, United States · Nuclear Science & Technology Division, Idaho National Laboratory, Idaho Falls, ID 83415, United States · Department of Computer Science and Engineering, University of Michigan, Ann Arbor, MI 48109, United States
FacProcessTwin: An LLM-Based System for Process Twin Development
Jun 16, 2026Yash Pulse, Yong-Bin Kang, Abhik Banerjee +1Manufacturing Human-in-the-Loop AI
Swinburne University of Technology Melbourne, Australia

Jul 20, 2026J/K move · Enter open · S save

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing

Yi-Ping Chen, Ying-Kuan Tsai, Vispi Karkaria, Seul Lee+2

Department of Mechanical Engineering, Northwestern University · Department of Industrial Engineering and Management Science, Northwestern University

Neural Surrogate Modeling Concept Drift Online Continual Learning Digital Twins

Open paper AskPDF arXiv

Digital Twins rely on surrogate models to mirror physical systems in real time, yet these models can degrade as operating conditions evolve, a phenomenon known as concept drift. Maintaining surrogate fidelity under drift, particularly when models must also capture aleatoric uncertainty, remains an open challenge. Existing adaptive frameworks lack principled mechanisms for detecting when updates are needed, for efficiently adapting models from limited streaming data, and for certifying that updates genuinely improve predictive performance. Here we present an adaptive Digital Twin framework that integrates a Fisher score--based multivariate drift detector, Low-Rank Adaptation (LoRA) for parameter-efficient continual learning, and a Mann--Whitney

U

test for online statistical validation. The framework monitors surrogate-model confidence via Fisher score vectors, triggers targeted fine-tuning of fewer than 1% of model parameters upon drift detection, and statistically certifies predictive improvement before deploying the updated surrogate. Applied to a stochastic linear system and a directed energy deposition additive manufacturing process as case studies, the framework successfully detects distributional shifts with short delays and restores both predictive accuracy and uncertainty quantification under abrupt and incremental drift. These results establish a statistically rigorous and computationally tractable pathway for sustaining the trustworthiness of neural-network--based Digital Twins throughout their operational life cycle.

Abstract

Fault Detection

Explore similar work

A Continual Validation, Updating, and Decision-Making Framework for Self-Adaptive Digital Twins via Robust Model Predictive Control: A Case Study in Additive Manufacturing

Physics-based Digital Twins for Integrated Thermal Energy Systems Using Active Learning

FacProcessTwin: An LLM-Based System for Process Twin Development