(2014); detailed in this discussion is a variant called simplex self-directing evolutionary optimisation (SSDEVOP). To commence an SSDEVOP, a starting centroid is selected, around which a simplex is constructed (Figure 54) according to criteria defined in Spendley et al. (1962). The vertices of this simplex comprise the set-points of the first three runs of the experiment. Each run is tested once, and the ‘worst’ run is identified. Figure 54—Starting centroid and simplex in SSDEVOP. The coordinates of this ‘worst’ run are then reflected across the simplex, to generate the setpoints of the fourth run (Figure 55). Figure 55—Generation of second simplex in SSDEVOP. This workflow repeats, with the ‘worst’ run of the second simplex identified. These coordinates are then reflected across the second simplex to generate the set points for the 5th run. These results are then assessed against the remaining vertices of this new, third simplex (not shown). Variable 2 → Variable 1 → 'Worst' run Variable 2 → Variable 1 → Set points for 4th run
RkJQdWJsaXNoZXIy MTM0Mzk2