Fault Diagnosis Toolbox is a Python package for the analysis and design of fault diagnosis systems for dynamic systems, primarily described by differential algebraic equations. Key features of the toolbox are extensive support for structural analysis of large-scale dynamic models, fault isolability analysis, sensor placement analysis, and code generation in C/C++ and Python. The toolbox is an adaptation of our Matlab toolbox that can be downloaded from https://faultdiagnosistoolbox.github.io.
The toolbox is freely available under an MIT license.
The documentation is available at readthedocs.
For a quick introduction, see the use case where an industrial size example, an automotive engine, is analyzed, C-code for residual generators is generated, and the resulting diagnosis system is evaluated on test-cell measurements from our engine laboratory.
The toolbox is available on pip and can be installed as:
pip install faultdiagnosistoolbox
If you use this toolbox in your research, please cite
Erik Frisk, Mattias Krysander, and Daniel Jung. "A Toolbox for Analysis and Design of Model Based Diagnosis Systems for Large Scale Models" (https://doi.org/10.1016/j.ifacol.2017.08.504), IFAC World Congress. Toulouse, France, 2017.
and any relevant papers of ours. See a list of key references for details.