High-dimensional, unsupervised cell clustering for computationally efficient engine simulations with detailed combustion chemistry

► Reduction of the computational efforts due to chemistry in CFD modeling. ► A new bounding-box-constrained k-means clustering algorithm is presented. ► Unsupervised cluster center initialisation based on grid-like domain decomposition. ► Local clustering accuracy is guaranteed by the bounding-box constraint. ► 3-4 Times reduction in overall CPU times is achieved.