Flowcean - Model Learning for Cyber-Physical Systems

Maximilian Schmidt; Swantje Plambeck; Markus Knitt; Hendrik Rose; Goerschwin Fey; Jan Christian Wieck; Stephan Balduin

cs.LGMar 12, 2026

Flowcean - Model Learning for Cyber-Physical Systems

Authors: Maximilian Schmidt, Swantje Plambeck, Markus Knitt, Hendrik Rose, Goerschwin Fey, Jan Christian Wieck, Stephan Balduin

Organizations: Hamburg University of Technology, Hamburg, Germany · Fraunhofer — Center for Maritime Logistics and Services CML, Hamburg, Germany · OFFIS — Institute for Information Technology, Oldenburg, Germany

Abstract

Effective models of Cyber-Physical Systems (CPS) are crucial for their design and operation. Constructing such models is difficult and time-consuming due to the inherent complexity of CPS. As a result, data-driven model generation using machine learning methods is gaining popularity. In this paper, we present Flowcean, a novel framework designed to automate the generation of models through data-driven learning that focuses on modularity and usability. By offering various learning strategies, data processing methods, and evaluation metrics, our framework provides a comprehensive solution, tailored to CPS scenarios. Flowcean facilitates the integration of diverse learning libraries and tools within a modular and flexible architecture, ensuring adaptability to a wide range of modeling tasks. This streamlines the process of model generation and evaluation, making it more efficient and accessible.

Figures & tables

Panel of Figure 1 — Figure 1: Abstract workflow of data-driven modeling

Panel of Figure 2 — Figure 2: Component-view of the concepts, showing the three steps of data-driven modeling (A to C) extended by an evaluation (D to F)

Panel of Figure 3 — Figure 3: Flowchart for the variants of learning strategies

Module	Existing Implementations
Environment	Loader for CSV, JSON, Parquet, YAML, ROS bag Interfaces to Polars and PyTorch data sets ODE environment
Transform	Explode Select Sliding window Standardize
Learner	External interface via gRPC Neural network lightning learner Linear regression Regression tree
Model	PyTorch model scikit-learn model gRPC model
Metric	Regression: Max error, Mean absolute error, Mean squared error, R2 score Classification: Accuracy, Precision, Recall, F-beta score

Table 1: Existing implementations of Flowcean modules

Panel of Figure 4 — Figure 4: Non-linear water tank system with inflow $bV(t)$ , water level $x$ and resulting outflow $a\sqrt{x}$

$V$	$x$
1	10
\cellcolor highlightcolor!302	\cellcolor highlightcolor!3020
\cellcolor highlightcolor!303	\cellcolor highlightcolor!3030
\cellcolor highlightcolor!304	\cellcolor highlightcolor!3040
5	50

Figure 5: Pivot time series of

V

and

x

to extract a trace of bounded history with 3 time steps

Panel of Figure 6 — Figure 6: Modules of the case study implemented in Flowcean composing the learning and evaluation pipeline.

	Runtime [ms]	MAE	MSE
Regression Tree	$15.5$	$0.0206$	$0.0006$
Multi-layer perceptron	$813$	$0.0639$	$0.0054$

Table 2: Predictive performance of learned models

Cyber-Physical Systems

Cyber-Physical Systems (CPS) study networked computation and control interacting with physical processes, from factories and power grids to robots and vehicles.

See all 85 papers

IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems
Jun 4, 2026John S. Baras, Sai Sandeep Damera, Ryan Matheu +2Cyber-Physical Systems Model-Based Systems Engineering
Institute for Systems Research, University of Maryland, College Park, MD, USA
SMSI: System Model Security Inference: Automated Threat Modeling for Cyber-Physical Systems
Apr 26, 2026RoÝah Radaideh, Ali KhreisCyber-Physical Systems Cybersecurity
School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada
LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems
Sep 29, 2026Ziyan An, John Stankovic, Meiyi MaCyber-Physical Systems Time Series Forecasting
Department of Computer Science Vanderbilt University Nashville, TN · Department of Computer Science University of Virginia Charlottesville, VA

Jun 4, 2026J/K move · Enter open · S save

IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems

John S. Baras, Sai Sandeep Damera, Ryan Matheu, Clinton Enwerem+1

Institute for Systems Research, University of Maryland, College Park, MD, USA

Cyber-Physical Systems Model-Based Systems Engineering

Open paper AskPDF arXiv

Autonomous cyber-physical systems (CPS) sit at the intersection of Model-Based Systems Engineering (MBSE) and data-driven Machine Learning and Artificial Intelligence (ML/AI), yet no integrated Systems Engineering (SE) methodology natively spans both. We address this gap with IDDMBSE, an Integrated Data-Driven and Model-Based Systems Engineering methodology that extends the rigorous MBSE V-process with a data-driven loop at every step, anchored in SysML, the autonomy stack, and a hybrid model-based plus data-driven trade-off architecture. We instantiate IDDMBSE as an interoperable, open-source tool chain: PERFECT, which maps SysML system architectures to executable ROS autonomy stacks for scalable performance evaluation; TRADES-X, which decomposes design-space exploration into a model-based optimization stage followed by a data-driven evaluation stage; and VERITAS, which combines formal, data-driven, and runtime verification into a single assurance workflow. We demonstrate IDDMBSE on a Trusted Autonomous Ground Robot across its development lifecycle, spanning sensor-suite selection, risk-sensitive path planning, behavior-tree task verification, conformal-prediction-based robust perception, and assured multi-robot coordination, all exercised in a contested-terrain Isaac Sim test range that we release with the tool chain. We close by sketching how IDDMBSE is being re-formulated on SysML v2 / KerML foundations to enable language-native composability and tighter ML/AI integration.

Abstract

Cyber-Physical Systems

Explore similar work

IDDMBSE: Integrating Data-Driven and Model-Based Systems Engineering for Trusted Autonomous Cyber-Physical Systems

SMSI: System Model Security Inference: Automated Threat Modeling for Cyber-Physical Systems

LogiC-Diff: Embedding Security Properties Into AI-Enabled Cyber-Physical Systems