Study of entropy Weight-Grey theory-BP Network life prediction Model of unit silica fume concrete lining under the influence of carbonation-sulfate freeze-thaw cycle erosion

To address the challenges posed by tunnel construction in the alpine region, silica fume mixed concrete is commonly used as a construction material. The correlation between silica fume content and the lining life requires immediate investigation. In view of this phenomenon, the durability of unit lining concrete is predicted by analyzing three key indicators: carbonation depth, relative dynamic elastic modulus, and residual quality. This prediction is achieved by integrating the Entropy Weight Method, Grey theory life prediction model and BP artificial neural networks using data from tests and predictions of these indicators. Then, the Entropy Weight-Grey theory-BP Network Model is compared with other methods to analyze the predicted life. Finally, verify the scientificity of this model, and the optimum silica fume content of unit concrete lining is verified. The results showed, 1) The addition of silica fume will accelerate the carbonization of unit concrete lining, and slow down the freeze-thaw cycle and sulfate erosion. 2) The utilization of artificial neural networks is essential for enhancing the realism of the data, as it emphasizes the significance of silica fume content. 3) Silica fume content of 10% results in the longest life and is the most suitable for lining construction. 4) A comparison between single-factor and multi-factor predictions indicates that the multi-factor approach yields a longer maximum life. This improvement can be attributed to the inclusion of additional factors, such as freeze-thaw cycles and carbonation, which enhance the predicted life when employing these methods. In conclusion, the Entropy Weight-Grey Theory-BP Network life prediction Model is well-suited for tunnel lining in the alpine sulfate area of northwest China.