Welcome to the Documentation of HAI-CPPS v2.2

The Hamburg AI Benchmark for Cyber-Physical Production Systems (HAI-CPPS) is a benchmark for evaluating AI methods in anomaly detection, diagnosis, reconfiguration, and planning for modular cyber-physical process plants.

HAI-CPPS comprises ten process-plant topologies with increasing complexity. The v2.2 campaign contains 350 recordings: 160 healthy and 190 recordings with one enabled fault proxy in one module. Each fault has persistent and temporary variants paired with a seed-matched healthy test control.

HAI-CPPS process plant

HAI-CPPS includes:

  • OpenModelica simulation models

  • Published benchmark datasets

  • Validated generation, export, and release checks

  • A parallel campaign launcher with per-topology manifests and frozen generation source

The release separates online measurements and recorded controller commands from simulator-derived oracle states and offline metadata. You can also simulate a custom topology or module and obtain a raw OpenModelica CSV.

Note

HAI-CPPS extends the Benchmark for Diagnosis, Reconfiguration, and Planning (BeRfiPl). You can access the previous version here: BeRfiPl Benchmark

Contents:

When using the HAI-CPPS benchmark, please use the following citation:

@data{Ehrhardt2025HAICPPSDATASET,
doi = {10.21227/5ewb-cn40},
url = {https://dx.doi.org/10.21227/5ewb-cn40},
author = {Jonas Ehrhardt and Lukas Moddemann and Alexander Diedrich and Oliver Niggemann},
publisher = {IEEE Dataport},
title = {HAI-CPPS: The Hamburg AI Benchmark for Cyber-Physical Production Sytems},
year = {2025} }

When using the HAI-CPPS benchmark, please also cite the HAI-CPPS paper:

@INPROCEEDINGS{Moddemann2025HAICPPS,
  author={Moddemann, Lukas and Ehrhardt, Jonas and Diedrich, Alexander and Niggemann, Oliver},
  booktitle={2025 IEEE 30th International Conference on Emerging Technologies and Factory Automation (ETFA)},
  title={The HAI-CPPS Benchmark: Evaluating AI Capabilities Across Hybrid Data Spaces},
  year={2025},
  pages={1-8},
  doi={10.1109/ETFA65518.2025.11205680}}

When using the original benchmark (BeRFiPl) please cite:

@INPROCEEDINGS{Ehrhardt2022BERFIPL,
  author={Ehrhardt, Jonas and Ramonat, Malte and Heesch, René and Balzereit, Kaja and Diedrich, Alexander and Niggemann, Oliver},
  booktitle={2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA)},
  title={An AI benchmark for Diagnosis, Reconfiguration & Planning},
  year={2022},
  pages={1-8},
  organization = {IEEE},
  doi={10.1109/ETFA52439.2022.9921546}}

HAI-CPPS was developed at the Chair of Informatics in Mechanical Engineering at Helmut-Schmidt-University.

hsu imb