Destruction pattern analysis of building materials subjected to fire provide the basis for strengthening, restoring the bearing capacity, and optimizing the function of the building structure. The surface cracking and fractal characteristics of calcium carbonate whisker-reinforced cement pastes subjected to high temperatures were studied herein. The test results showed that at 400 °C, the surface crack area, length, and fractal dimension of cement pastes specimen increases from 0 to 35 mm², 100 mm, and 1.0, respectively, due to the increase of vapor pressure. When the temperature is above 900 °C, the calcium carbonate whisker (CW) and other hydration products in the specimen begin to decompose, causing the surface crack area, length, and fractal dimension of the cement paste specimen to increase from 0 to 120 mm², 310 mm, and 1.2, respectively. Compared with the length and width of cracks, the area, and fractal dimension of cracks are less affected by the size and shape of specimen. This paper uses image processing methods to analyze the cracking patterns and fractal characteristics of specimens after high-temperature treatment. The aim is to elucidate the quantitative relationship between concrete material, temperature, and cracking characteristics, providing theoretical basis for structural evaluation after exposure to high temperature.

This paper proposes a structural damage detection method based on one-dimensional convolutional neural network (CNN). The method can automatically extract features from data to detect structural damage. First, a three-layer framework model was designed. Second, the displacement data of each node was collected under the environmental excitation. Then, the data was transformed into the interlayer displacement to form a damage dataset. Third, in order to verify the feasibility of the proposed method, the damage datasets were divided into three categories: single damage dataset, multiple damage dataset, and damage degree dataset. The three types of damage dataset can be classified by the convolutional neural network. The results showed that the recognition accuracy is above 0.9274. Thereafter, a visualization tool called “t-SNE” was employed to visualize the raw data and the output data of the convolutional neural network. The results showed that the feature extraction ability of CNN is excellent. However, there are many hidden layers in a CNN. The outputs of these hidden layers are invisible. In the last section, the outputs of hidden layers are visualized to understand how the convolutional neural networks work.

Owing to particle leanness, the standard Particle Filter (PF) algorithm is prone to the problem of reduced prediction accuracy when predicting fatigue crack propagation. An improved particle filter algorithm based on the optimization algorithm of beetle antenna search (IBAS-PF) for fatigue crack propagation in metals is proposed in this paper. The discrete Paris formula was used to establish the state equation of fatigue crack propagation, in which the uncertainty of material and crack propagation process were considered. Meanwhile, the characteristics of Lamb wave signals under different crack lengths were extracted to establish the observation equation. The sampling process of the PF algorithm was optimized based on the beetle antennae search algorithm to improve the particle diversity and the prediction accuracy. Compared with the standard PF algorithm, the improved BASO-PF algorithm has higher accuracy for metal fatigue crack propagation, as well as better state estimation ability.