Augmented and Cloud Computing With Chemical Process Simulators

ABSTRACT Methodology Mathematica provides unique symbolic and machine learning tools for developing and solving mathematical models that make it attractive for engineering applications. Chemical engineers frequently have a need to update process design software with custom unit operation models. This paper shows two new methods to connect Mathematica to chemical process simulators, including a local PC‐based connection and a cloud‐based connection. Both methods are discussed in detail using an illustrative example of a membrane separation process. We also demonstrate how the connection between Mathematica and Excel facilitates spreadsheet calculations while enabling the connection with the process simulator software. Furthermore, all methods shown here are model‐independent and can be implemented with any equation‐based model or with machine‐learning models when adequate training data is available. Results Our results show that Mathematica can be connected to chemical process simulators such as CHEMCAD or Aspen Plus. The performance of the methods was evaluated by direct comparison to standard models that already exist in the literature and in the process simulator software. To date, we have experimented with multicomponent flash, well‐mixed membrane calculations and machine‐learning models. However, any model that can be functionalized in Mathematica can be connected to the process simulator. Conclusion This paper demonstrates that Mathematica can be connected to chemical process simulators such as CHEMCAD and Aspen Plus. This is important because of the symbolic mathematics and machine‐learning tools available in Mathematica. The software can be connected using a local connect with Mathematica Link for Excel, or a cloud‐based connection using Wolfram Cloud Connector. Both methods are relatively easy to implement and are particularly exciting for research and design of new process models, or if one wishes to use CHEMCAD with proprietary models.