In order to reduce the CO₂ emission and cost of binders used in cemented paste backfill (CPB) technology, new blended binders with a large amount of fly ash (FA) were fabricated. Different doses of quicklime and calcium sulfoaluminate cement (CṠA) were used as mineral accelerators to improve the early workability of CPB. The effects of CṠA and quicklime on flowability, compressive strength, pore structure, hydration heat, and hydration evolution were investigated experimentally. The results showed that the addition of quicklime and CṠA reduced the spread diameter of the fresh backfill and improved the mechanical performance of the hardened CPB. With increasing quicklime and CṠA, the cumulative hydration heat of the blended binder distinctly increased in the first 6 h. CṠA improved the initial hydration by increasing the reactivity, and quicklime increased the hydration rate by activating FA. The blended binder (15% quicklime + 10% CṠA) with the lowest CO₂ emission and cost had potential application in filling technology.

Foam-cemented paste backfill (FCPB) has become a trend to solve the problem of roof-contacted filling. In order to solve the time-consuming and labor-intensive disadvantages when a large number of uniaxial compressive strength (UCS) tests needed, a hybrid artificial intelligence model was proposed for FCPB strength prediction, which combines random forest (RF) algorithm and grid search optimizer (GSO). Moreover, the effects of foaming agents on cement hydration and pore characteristics were studied. The results showed that GSO can effectively tune the hyper-parameters of the proposed GSO-RF model and the developed model is an efficient and accurate method to predict the UCS for FCPB. Though the foaming agent will not change the influence trend of cement-tailings ratio, solid content and curing time, the influence degree will be weakened by the foaming agent. The ranking of the relative importance of influencing variables is: cement-tailings ratio > curing time > foaming agent dosage > solid content. In addition, the foaming agent has no significant effect on the hydration of cement. The foaming agent mainly changes the strength by changing the pore characteristics (especially the large pore volume). This research provided guidance for developing UCS prediction model for FCPB.