diff --git a/README.md b/README.md index 5346a8318e0a231ae4959ece6fdfb88087b8ab5b..fb2826013422ce14fcb9bd8bdb26dc2ab15b3863 100644 --- a/README.md +++ b/README.md @@ -4,11 +4,11 @@ Material for 2-day course in diagnostics and prognostics, ## Module 1: Diagnostics [[slides](Slides/diagnostics.pdf)] Some material for further reading: -* For an introduction to structural methods for diagnosis, see chapter: "Structural analysis" in the book "_Diagnosis and fault-tolerant control_", Blanke, M., Kinnaert, M., Lunze, J., Staroswiecki, M., Springer, 2006. -* For an introduction to the fault diagnosis toolbox we recommend the following paper. It includes references to works implemented in the toolbox."_A Toolbox for Analysis and Design of Model Based Diagnosis Systems for Large Scale Models_", Erik Frisk, Mattias Krysander, and Daniel Jung (2017). In: IFAC World Congress. Toulouse, France. -* Test selection using a random forest classifier is described in: "_Residual Selection for Consistency Based Diagnosis Using Machine Learning Models_", Erik Frisk, and Mattias Krysander (2018). In: IFAC SafeProcess. Warszaw, Poland. -* How to combine data-driven and model-based techniques for fault diagnosis is described in "_Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation_", Daniel Jung, Kok Yew Ng, Erik Frisk, and Mattias Krysander (2018). -In: Control Engineering Practice, 80:146-156. +* For an introduction to structural methods for diagnosis, see chapter: "_Structural analysis_" in the book "[_Diagnosis and fault-tolerant control_](https://www.springer.com/gp/book/9783642071362)", Blanke, M., Kinnaert, M., Lunze, J., Staroswiecki, M., Springer, 2006. +* For an introduction to the fault diagnosis toolbox we recommend the following paper. It includes references to works implemented in the toolbox."[_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)", Erik Frisk, Mattias Krysander, and Daniel Jung (2017). In: IFAC World Congress. Toulouse, France. DOI: https://doi.org/10.1016/j.ifacol.2017.08.504 +* Test selection using a random forest classifier is described in: "[_Residual Selection for Consistency Based Diagnosis Using Machine Learning Models_](https://doi.org/10.1016/j.ifacol.2018.09.547)", Erik Frisk, and Mattias Krysander (2018). In: IFAC SafeProcess. Warszaw, Poland. DOI: https://doi.org/10.1016/j.ifacol.2018.09.547 +* How to combine data-driven and model-based techniques for fault diagnosis is described in "[_Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation_](https://doi.org/10.1016/j.conengprac.2018.08.013)", Daniel Jung, Kok Yew Ng, Erik Frisk, and Mattias Krysander (2018), Control Engineering Practice, 80:146-156. DOI: https://doi.org/10.1016/j.conengprac.2018.08.013 + ## Module 2: Prognostics [[slides](Slides/prognostics.pdf)] Some material for further reading: