Predicting the strength evolution of fiber-reinforced cement mortar under freeze-thaw cycles plays an important role in engineering stability evaluation. In this study, the microscopic pore distribution characteristics of fiber-reinforced cement mortar were obtained by using nuclear magnetic resonance (NMR) technology. The change trend of T₂ spectrum curve and porosity cumulative distribution curve showed that the freeze-thaw resistance of cement mortar increased first and then decreased with the fiber content. The optimal fiber content was approximately 0.5%. By conducting mechanical experiments, it is found that the uniaxial compressive strength (UCS) of the samples exhibited the ‘upward convex’ evolution trends with freeze-thaw cycles due to cement hydration, and based on fractal theory, the negative correlation between UCS and D_min was established. Eventually, a freeze-thaw strength prediction model considering both porosity and pore distribution was proposed, which could accurately predict the strength deterioration law of cement-based materials under freeze-thaw conditions.

A series of three‐dimensional finite element analyses were performed to study the behavior of piles in sloping ground under undrained lateral loading conditions. The analyses have been conducted for slopes with different angles and two loading directions. The obtained results show that as the slope increases, it can cause greater lateral displacement and internal force of the pile. In addition, the increase of the slope ratio will cause the position of the maximum bending moment and soil resistance zero point of the pile to move downward, further increasing the pile deflection. Furthermore, when the pile distance from slope crest B < 7D, the displacement and internal force development of the pile under toward loading is more obvious. When the pile distance from the slope crest exceeds 7D, the effect of loading direction on the pile can be neglected.

The response of laterally loaded piles installed near the crest of clay slopes is analysed. Three-dimensional finite element analyses are presented for piles at various distances from a slope crest and for different pile shape. The results of these analyses are used to study the variation of the pile displacement, the bending moment of the pile and the soil resistance in relation to pile to slope distance and pile shape. The obtained results show that the proximity of slope significantly affects the lateral load capacity of the piles but not significantly when the piles are placed at 7D (where D is pile diameter) or greater from the slope crest. Furthermore, the lateral soil resistance on the ground surface for circular piles is larger than that for rectangular piles at the same lateral load in level ground. The decrease rate of lateral soil resistance on the ground surface for circular piles gets faster as the slope ratio and load level increase.

The automatic discrimination of rock fracture and blast events is complex and challenging due to the similar waveform characteristics. To solve this problem, a new method based on the signal complexity analysis and machine learning has been proposed in this paper. First, the permutation entropy values of signals at different scale factors are calculated to reflect complexity of signals and constructed into a feature vector set. Secondly, based on the feature vector set, back‐propagation neural network (BPNN) as a means of machine learning is applied to establish a discriminator for rock fracture and blast events. Then to evaluate the classification performances of the new method, the classifying accuracies of support vector machine (SVM), naive Bayes classifier, and the new method are compared, and the receiver operating characteristic (ROC) curves are also analyzed. The results show the new method obtains the best classification performances. In addition, the influence of different scale factor q and number of training samples n on discrimination results is discussed. It is found that the classifying accuracy of the new method reaches the highest value when q = 8–15 or 8–20 and n = 140.