Search

Process Intelligence Research Group
Process Intelligence Research Group
  • Research
    Research projects Publications Software
  • Education
    Teaching Learning resources Exchange programs
  • Industry
  • Join us
  • About
    Team Alumni Values Contact

Software

Graph Neural Network Tool for Predicting Physico-Chemical Properties of Molecules

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.

Graph Neural Network Tool for Predicting Physico-Chemical Properties of Molecules
HybridML: Open source platform for hybrid modeling

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

HybridML: Open source platform for hybrid modeling
reluMIP

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.

reluMIP
SFILES 2.0 - an extended text-based flowsheet representation

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.

SFILES 2.0 - an extended text-based flowsheet representation
The MeLOn toolbox: Machine Learning Models for Optimization

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

The MeLOn toolbox: Machine Learning Models for Optimization
  • Home
  • Research
  • Teaching
  • Industry
  • Team

Process Intelligence Research group © A.Schweidtmann, L.Stops, G.Vogel, Q.Gao 2022

Cite
Copy Download