Instability Prediction Model of the Shield Tunnel Face Based on the Normal Cloud-PSM

Abstract

Considering the characteristics of fuzziness and randomness of shield tunnel face instability, normal cloud theory is introduced to establish an instability prediction model of the shield tunnel face based on the normal cloud-PSM (Product Scale Method). Geological, environmental, and tunnel influence factors are selected to set up a comprehensive evaluation index system. A three-dimensional numerical model is brought to determine the grading degree of each quantitative index. Then, the determination degree of the corresponding evaluation grade under each influencing factor is calculated using the normal cloud model. Finally, the product scale method is used to determine the index weight, calculate the comprehensive determination degree, and ascertain the instability risk level of the shield tunnel face according to the maximum membership degree principle. The prediction model is applied to predict the stability of the tunnel face of Chengdu Metro Line 18. The results of the instability prediction model of the shield tunnel face are essentially consistent with those of the fuzzy evaluation method and neural network method. The prediction results are also in good agreement with the real-world results. The prediction model should provide a new approach to the stability prediction of the shield tunnel face in the future.