Software

This tool contains functionality for chemical engineering knoweldge graph project where we mine literature data and store the results in a knoweldge graph.

The Digitization Companion (DigiCo) is a cutting-edge, AI-powered tool designed to automatically digitize and analyze engineering diagrams. Our primary focus is on Piping and Instrumentation Diagrams (P&IDs), transforming them from static documents into intelligent, editable, and data-rich assets. Our mission is to eliminate the tedious and error-prone process of manual digitization, saving you time and resources.

Neural networks are increasingly used as surrogate models and decision-support methods in engineering. However, their predictions often fail to satisfy physical, operational, or safety-related constraints.

Prediction of combustion-related properties of (oxygenated) hydrocarbons is an important and challenging task for which quantitative structure-property relationship (QSPR) models are frequently employed.

The combination of data-driven modelling with mechanistic model components, reduces the data demand and enables extrapolation of data-driven models.

​The repository "optimization-over-KANs" provides resources for deterministic global optimization over trained Kolmogorov-Arnold Networks (KANs). It includes Mixed-Integer Nonlinear Programming (MINLP) formulations implemented in Pyomo, Python scripts for training Multilayer Perceptrons (MLPs) using TensorFlow, and optimization routines for trained MLPs utilizing OMLT. The repository also offers the necessary code and data to reproduce the results presented in the associated research paper.

Machine Learning models for Optimization (MeLOn) is toolbox that integrates machine-learning models into optimization problems.

Smart, machine-readable Piping and Instrumentation Diagram (P&ID) data is key to unlocking innovation in the process industry, especially for emerging applications like Generative Artificial Intelligence (GenAI) - see examples of GenAI for the process industry. pyDEXPI helps enable this by making the DEXPI standard accessible and usable in Python.

This tool contains functionality for the conversion between PFD-graphs/P&ID-graphs and SFILES 2.0 strings. In the paper, we describe the structure of the graphs, notation rules of the SFILES 2.0, and the conversion algorithm.

With this package, you can generate mixed-integer linear programming (MIP) models of trained artificial neural networks (ANNs) using the rectified linear unit (ReLU) activation function. At the moment, only TensorFlow sequential models are supported. Interfaces to either the Pyomo or Gurobi modeling environments are offered.