A machine learning model to predict unconfined compressive strength of alkali-activated slag-based cemented paste backfill

The unconfined compressive strength(UCS)of alkali-activated slag(AAS)-based cemented paste backfill(CPB)is influenced by multiple design parameters.However,the experimental methods are limited to understanding the relationships between a single design parameter and the UCS,independently of each other.Although machine learning(ML)methods have proven efficient in understanding relationships between multiple parameters and the UCS of ordinary Portland cement(OPC)-based CPB,there is a lack of ML research on AAS-based CPB.In this study,two ensemble ML methods,comprising gradient boosting regression(GBR)and random forest(RF),were built on a dataset collected from literature alongside two other single ML methods,support vector regression(SVR)and artificial neural network(ANN).The results revealed that the ensemble learning methods outperformed the single learning methods in predicting the UCS of AAS-based CPB.Relative importance analysis based on the bestperforming model(GBR)indicated that curing time and water-to-binder ratio were the most critical input parameters in the model.Finally,the GBR model with the highest accuracy was proposed for the UCS predictions of AAS-based CPB.

Effect of magnesia on properties and microstructure of alkali-activated slag cement

The effect of magnesia bumt at 800-950℃ on the properties, especially the shrinkage, of alkali-activated slag cement （AASC.） was experimentally studied. Experimental results show that, although adding 4%-8% lightly-burnt magnesia may shorten the setting time and slightly reduce the compressive strength of AASC, it c, an remarkably reduce the shrinkage of AASC. The results also show that the setting time of AASC with a certain amount of magnesia increases with the buming temperature, and that the flexural and compressive strengths of AASC decrease with the increase of the additive amount of magnesia. Generally, the adverse effect of magnesia decreases with the increase of the burning temperature：, and the shrinkage-reducing effect of magnesia increases with the additive amount of magnesia. X-ray diffraction （XRD） and scanning electron microscopy （SEM） analyses show that some magnesia particles in the hardened AASC paste at a 28-d age remained unhydrated, and that the compactness decreased a little as magnesia was added. We can also conclude that magnesia bumt at 850-950℃ can be used to reduce the shrinkage of AASC only when its additive amount does not exceed 8%; otherwise, the setting time may be too short, and the flexural and compressive strengths may severely decrease.

The Influence of Free Water Content on Dielectric Properties of Alkali Active Slag Cement Paste

The dielectric performance of alkali activated slag （AAS） cement paste was investigated in the frequency range of 1 to 1000 MHz. The experimental results showed the unstable dielectric properties of harden paste were mostly influenced by the fraction of free water in paste or absorbed water from ambient, but not including hydration water and microstructure. The free water was completely eliminated by heat treatment at 105 ℃ about 4 hours, and then its dielectric loss was depressed; but with the exposure time in air increasing, the free water adsorption in ambient air made the dielectric property of harden cement paste to be bad. The temperature and relative humidity of environment was the key factors of free water adsorption; hence, if the influence of free water on dielectric constant was measured or eliminated, the cement-based materials may be applied in humidity sensitive materials or dielectric materials domains.

Mechanical properties and durability of alkali-activated steel slag-blastfurnace slag cement

Alkali-activated cement(AAC)is either clinker-less or free,and it is also environmentally friendly due to its low carbon footprint and wide range sources.Industrial wastes,like steel slag and blastfurnace slag,usually have latent hydraulic reactivity,and can be used as precursors of AAC.Both clinkerless and clinker-free AAC were prepared from the mixture of steel slag and blastfurnace slag by using water glass as an activator,and four different recipes which satisfied the strength requirement of 42.5R Portland cement were obtained.Each recipe of AAC exhibited better resistance to sulfate attack and frost attack than Portland cement.AAC showed huge drying shrinkage,but it was equivalent to that of Portland cement as steel slag content increased to 40%.The AAC also had quite low risk of alkali-aggregate reaction.Microstructure analysis showed that the major products were calcium silicate hydrate(C–S–H),calcium aluminosilicate hydrate(C–A–S–H)and zeolite-like phases.Ettringite was also detected in the binder when gypsum was contained in the precursors.

碱矿渣水泥混凝土研究进展及其发展前景

碱矿渣水泥是一种具有高强度、高耐久性、大幅度利用工业废料的新型建筑材料;基于大量文献材料综述了这种水泥的研究和应用情况。

-20℃条件下碱矿渣水泥性能研究

本文研究了碱矿渣水泥对温度的适用性,确定碱矿渣水泥-20℃条件下临界受冻强度,并选用无机盐类防冻剂对其负温下性能进行改性。试验结果表明:-10℃时,碱矿渣水泥已经不能正常水化硬化;-20℃条件下,碱矿渣水泥的临界受冻强度为3 MPa;采用三种无机盐防冻剂对碱矿渣水泥负温性能进行改性,对其负温下强度有着明显提高作用,以NaNO3提高强度最高。