The inflammability of asphalt road will promote fire spread in the tunnel and produce lots of toxic smoke. To improve the fire resistance of asphalt pavement, mineral powder flame retardants are generally replaced by flame retardants in equal amounts. In this study, the effects of the synergistic flame retardancy system of halloysite nanotubes (HNTs) and conventional flame retardants (CFR) on the flame retardancy performance and mechanism of asphalt were investigated. Firstly, the flame retardancy properties of the HNTs and CFR composite modified asphalt were investigated based on the Cleveland open cup method (COC), Limiting oxygen index meter (LOI), and Cone calorimeter tests (CCTs). Then, the flame retardancy mechanism of the modified asphalt was studied based on Thermogravimetric analyzer (TGA), Fourier-transform infrared (FTIR), and Scanning electron microscopy (SEM). The results show that adding HNTs could improve the flame retardancy of the CFR modified asphalt binder. When 1 wt % HNTs and 8 wt % CFR were used, the limiting oxygen index of asphalt increased by 40.1%, the ignition temperature increased by 40 °C, while the heat release rate, total heat release, the smoke production rate, total smoke release, and other parameters decreased with varying degrees. Based on TG, FTIR, and SEM, the targeted flame retardancy mechanism and synergistic effect of HNTs/CFR flame retardancy system were revealed and summarized as three stages: (1) Stage 1, aluminum hydroxide (ATH) absorbs heat through thermal decomposition and inhibits the decomposition of lightweight components in asphalt; (2) Stage 2, aluminum diethyl phosphate (ADP) decomposes and produces organic phosphoric acid, which catalyzes crosslinking and ring thickening of asphalt and the quenching effect of phosphorus free radicals to block the combustion; and (3) Stage 3, HNTs plays an important role in increasing the integrity and density of the barrier layer. In addition, the Al₂O₃ produced by the decomposition of ATH, the carbon layer formed by the ADP catalyzed pitch, and HNTs play a significant synergistic effect in the formation of the barrier layer. Thus, the combination of HNTs and CFR has been proved to be a prospective flame retardancy system for asphalt.

In this study, asphalt concrete specimens were subjected to a semicircle bending test at −10 °C to simulate the process of the development of cracks in asphalt concrete at low temperature. The acoustic emission parameters were collected during the test, the variation characteristics of acoustic emission parameters were analyzed, and the peakedness value was introduced to evaluate the damage of asphalt concrete. The dynamic evolution of fracture development was analyzed by periods with acoustic emission source location. The results indicate that the damage of asphalt mixtures shows an obvious brittle characteristic at low temperature, acoustic emission signals mainly originate from the crack damage caused by tensile stress, and the strength and number of signals can reflect the degree of crack development. Based on acoustic emission parameters and load curves, the cracking damage of asphalt concrete at low temperature in this study can be divided into three periods: a calm period, a stable development period, and a rapid fracture period. The crack point occurred and propagated upward rapidly in the rapid fracture period. During this period, acoustic emission parameters such as ringing count, acoustic emission energy, and amplitude increased suddenly; furthermore, the peakedness value reached its peak in this period and corresponded well with the low-temperature damage of asphalt concrete. Acoustic emission source location technology can track position of crack points and the propagation path of cracks, reflecting the dynamic evolution process of asphalt concrete crack damage at low temperature.

The accurate localization of an acoustic emission (AE) source is a vital aspect of AE nondestructive testing technology. A model of wave velocity attenuation caused by the extension of transmission distance is established to analyze the attenuation of AE wave velocities in concrete and thus improve the acoustic source localization accuracy from the perspective of modified velocity. In combination with the exhaustive and region localization methods, a region exhaustive localization method is established based on the modified wave velocity. The results indicate that the smaller the water–cement ratio, the larger the reference wave velocity, and the spatially dependent attenuation of wave velocity increase. Moreover, the larger the aggregate particle size, the larger the reference wave velocity, and the greater the attenuation of wave velocity with distance. For a propagation distance of 1000 mm, the AE wave velocity attenuation exceeds 50% compared with the AE velocity. The optimized localization method reduces the number of nodes calculated, thus improving the method’s accuracy when used for localization.

In order to improve the safety of the tunnel asphalt pavement in the event of a fire, and reduce the deterioration of the low temperature crack resistance of the asphalt by the flame retardant. The research uses aluminum hydroxide (ATH) as a smoke suppressant, diethyl aluminum hypophosphite (ADP) as a flame retardant, and halloysite nanotubes (HNTs) as a synergist to modified styrene-butadiene-styrene block copolymer (SBS) modified asphalt (MA). First, the content of ATH, ADP, and HNTs was used as the response variable. The physical properties (Penetration, Softening point, Ductility) and static flame retardant properties (Limiting oxygen index meter, Ignition point) of the asphalt modified by nanocomposite flame-retardant (HNTs-CFRMA) were the response variables. The response surface methodology was used to design the test, and regression models were established to analyze the influence of flame retardants on the performance of asphalt. Then, comprehensively considering the effects of physical properties and flame retardant properties, the normalized desirability function was used to perform a multi-objective optimization design on the components of the nanocomposite flame retardant modifier to obtain the best flame retardant formula. Finally, the rheological properties of MA, conventional flame-retardant modified asphalt (CFRMA), and HNTs-CFRMA were tested based on Dynamic shear rheometer, Multiple stress creep test, Force ductility tester, and Bending beam rheometer. The performance of flame-retardant and smoke suppression were tested by the Cone calorimeter tests. The result shows that ATH, ADP, and HNTs can enhance the high temperature performance of asphalt, reduce the penetration. The addition of HNTs can increase significantly the softening point and reduce the deteriorating effect of flame retardants on the low temperature performance of asphalt; the addition of ATH and HNTs can improve significantly the flame retardancy of asphalt. Based on the desirability function of power exponent, the formulation of the nanocomposite flame retardant with better physical properties and flame retardant properties is ATH:ADP:HNTs = 3:5:1, and the total content is 9 wt%. Nanocomposite flame retardants can improve obviously the high temperature rheological properties of asphalt. The rutting factor and the cracking factor of HNTs-CFRMA improve markedly, and the irrecoverable creep compliance is reduced, compared with MA and CFRMA. Nanocomposite flame retardant can make up for the deterioration of conventional flame retardants on asphalt’s low temperature performance. At the same time, it has better flame-retardant performance and smoke suppression performance.

To improve the safety of road tunnel pavement, the research established road tunnel pavement water seepage recognition models based on deep learning technology, and a water seepage area extraction model based on image processing technology to finally achieve accurate detection of water seepage on tunnel pavements. First, the deep learning models EfficientNet water seepage recognition model and MobileNet water seepage recognition model were built, the models were trained with the self-collected pavement seepage data set, and the F1 score was introduced to evaluate the accuracy and comprehensive performance of the two models in predicting different categories of water seepage characteristics. Then three grayscale processing methods, the cvtColor function, mean method and maximum method, six global threshold segmentation methods, Otsu thresholding method, THRESH_BINARY, THRESH_BINARY_INV, THRESH_TRUNC, THRESH_TOZERO and THRESH_TOZERO_INV, three filtering methods, namely Gaussian filtering, median filtering and morphological open operation, as well as small connected domain removal, were used to reduce the noise of the images. Finally, the seepage area image calculation method was proposed based on the processed images to predict the actual pavement seepage area. The results show that the recognition accuracy of the EfficientNet water seepage recognition model is 99.85% and 97.53% in the training and validation sets respectively, which is 2.85% and 0.76% higher than the 97% and 96.77% of the MobileNet model. The average F1 score of the EfficientNet model is 95.22%, which is 5.05% higher than that of the MobileNet model, for the four types of seepage feature images: point seepage, line seepage, surface seepage and no seepage. The cvtColor function for grayscale processing, THRESH_BINARY for threshold segmentation and a combination of median filtering and morphological open operation for image noise reduction can effectively extract the seepage features. The area calculation is performed by the seepage area image calculation method, and the average error between the predicted value and the actual seepage area is 8.30%, which can better achieve the accurate extraction of the seepage area.

In order to improve the traffic safety of the tunnel pavement and reduce the impact of water seepage on the pavement structure, a convolutional neural network (CNN) model is established based on image detection technology to realize the identification, classification and statistics of pavement seepage. First, compared with the MobileNet network model, the deep learning model EfficientNet network model was built, and the accuracy of the two models was analyzed for pavement seepage recognition. The F1 Score was introduced to evaluate the accuracy and comprehensive performance of the two models for different types of seepage characteristics. Then the three gray processing methods, six threshold segmentation methods, as well as three filtering methods were compared to extract water seepage characteristics of digital image. Finally, based on the processed image, a calculation method of water seepage area was proposed to identify the actual asphalt pavement water seepage. The result shows that the recognition accuracy of the EfficientNet network model in the training set and the validation set are 99.85% and 97.53%, respectively, and the prediction accuracy is 98.00%. The accuracy of pavement water seepage recognition and prediction is better than the MobileNet network model. Using the cvtColor function for gray processing, using THRESH_BINARY for threshold segmentation, and using a combination of median filtering and morphological opening operations for image noise reduction can effectively extract water seepage characteristics. The water seepage area calculated by the proposed method has a small difference with the actual water seepage area, and the effect is agreeable.