Search

In view of the problem that the water gushing problem of deep coal mine roadway seriously affects the safety of coal mine construction, and the common cement grout is difficult to seal up the tiny rock cracks, the micron-grade fly ash is used to replace part of superfine cement, polycarboxylate superplasticizer and nano-CaCO3 admixture are used to improve the performance of composite slurry. The results show that the slurry properties vary with the water-cement ratio, and are negatively correlated with the initial viscosity, hardened rate and strength, while positively correlated with fluidity. The appropriate addition of nano-CaCO3 made the strength slightly improved, but the viscosity, fluidity and hardened rate did not change significantly. The addition of micron-grade fly ash reduces the viscosity, hardened rate and strength, and appropriately improves the fluidity. The polycarboxylate superplasticizer was positively correlated with fluidity and negatively correlated with stone rate, but had little effect on viscosity and strength. The change of slurry viscosity with time can be divided into two stages: stable period and rising period. The viscosity change rate of stable period does not exceed 15.5%.

The problem of water seepage through sandstone micro-fractures in deep well is one of key factors influencing normal production. With the method of single factor sensitivity analysis, this paper is to tell us how to affect the seepage of micro-fractures by roughness, fracture opening, confining pressure and seepage pressure by self-developed micro-fracture triaxial stress seepage mechanism model test system. Simultaneously, numerical simulation is used to study the seepage process of micro-fractures in sandstone, and explain the evolution process of hydraulic fracture under water pressure. The results show that the factors that affect the seepage of micro-fractures from strong to weak are osmotic pressure, roughness, fracture opening and confining pressure; the evolution process of hydraulic fracture propagation under water pressure can be divided into the stress accumulation stage and the stable expansion stage of micro-fractures.

Forest fire risk prediction is essential for building a forest fire defense system. Ensemble learning methods can avoid the problem of difficult model selection for disaster susceptibility prediction and can significantly improve modeling accuracy. This study introduces a stacking ensemble learning model for predicting forest fire risks in Yunnan Province by integrating various data types, such as meteorological, topographic, vegetation, and human activity factors. A total of 70,274 fire points and an equal number of randomly selected nonfire points were used to develop the model, with 70% of the data allocated for training and the remaining 30% for testing. The stacking model combined four diverse machine learning methods: random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multilayer perceptron (MLP). We evaluated the model's predictive performance using metrics like accuracy, area under the characteristic curve (AUC), and fire density (FD). The results demonstrated that the stacking fusion model exhibited remarkable accuracy with an AUC of 0.970 on the test set, significantly surpassing the performance of individual machine learning models, which had AUC values ranging from 0.935 to 0.953. Furthermore, the stacking fusion model effectively captured the maximum fire density in extremely high susceptibility areas, demonstrating enhanced generalization capabilities. [ABSTRACT FROM AUTHOR]

Abstract. Consumers may incur deliberation costs in learning about their valuations for new products. When the deliberation cost is not trivial, the retailer may set a low price to inhibit [...]

Periodic itemset patterns (PIPs) are widely used in predicting the occurrence of periodic events. However, extensive redundancy arises due to a large number of patterns. Mining skyline periodic itemset patterns (SPIPs) can reduce the number of PIPs and guarantee the accuracy of prediction. The existing SPIP mining algorithm uses FP-Growth to generate frequent patterns (FPs), and then identify SPIPs from FPs. Such separate steps lead to a massive time consumption, so we propose an efficient bit-based approach named BitSPIM to mine SPIPs. The proposed method introduces efficient bitwise representations and makes full use of the data obtained in the previous steps to accelerate the identification of SPIPs. A novel cutting mechanism is applied to eliminate unnecessary steps. A series of comparative experiments were conducted on various datasets with different attributes to verify the efficiency of BitSPIM. The experiment results demonstrate that our algorithm significantly outperforms the latest SPIP mining approach. [ABSTRACT FROM AUTHOR]