Mixed Integer (Non-) Linear Programming Formulations of Graph Neural Networks

Recently, ReLU neural networks have been modelled as constraints in mixed integer linear programming (MILP) enabling surrogate-based optimisation in various domains as well as efficient solution of machine learning verification problems. However, previous works have been limited to multilayer perceptrons (MLPs). The Graph Convolutional Neural...

Data-Driven Transportation Planning for a Large Manufacturing Plant: Analysis and development of a planning support tool for the internal transportation at Tata Steel IJmuiden

Planning the on-site transportation of large manufacturing sites is a complex process. Currently these plans are made based on the on-site logistics constraints rather than on KPIs. Research has been focused on either analysis of system parameters or generally on KPIs, but lacks the combination of both on real-life cases. This gap is closed by...

Development and Validation of Short-term Mine Planning Optimization Algorithms for a Sublevel Stoping Operation with Backfilling