This dataset contains simulations of a complex, large-scale chemical plant proposed by Downs and Vogel (1993). As described by Reinartz, Kulahci and Ravn (2021):

The process involves the production of two liquid product components G and H from four gaseous reactants A, C, D and E with an additional inert B and a byproduct F. The reaction system consists of four exothermic and irreversible reactions which are described by,

\begin{equation} \begin{cases} A(g) + C(g) + D(g) \rightarrow G(liq)&\text{(Product 1)}\ A(g) + C(g) + E(g) \rightarrow H(liq)&\text{(Product 2)}\ A(g) + E(g) \rightarrow F(liq)&\text{(Byproduct)}\ 3D(g) \rightarrow F(liq)&\text{(Byproduct)} \end{cases} \end{equation}

The analysis and simulations were done by Reinartz, Kulahci and Ravn (2021), who published the complete dataset online. In this context. Different simulations correspond to different types of faults, and operation conditions, Montesuma et al (2023) used these simulations to compose a Cross-Domain Fault Diagnosis problem.

References

Downs, J.J., Vogel, E.F., 1993. A plant-wide industrial process control problem. Comput. Chem. Eng. 17 (3), 245–255. doi:10.1016/0098-1354(93)80018-I.

Christopher Reinartz, Murat Kulahci, and Ole Ravn. An extended tennessee eastman simulation dataset for faultdetection and decision support systems. Computers & Chemical Engineering, 149:107281, 2021

Montesuma, E. F., Mulas, M., Mboula, F. N., Corona, F., & Souloumiac, A. (2023). Multi-Source Domain Adaptation for Cross-Domain Fault Diagnosis of Chemical Processes. arXiv preprint arXiv:2308.11247.