Abstract
Surrounding rock squeezing deformation is a common and prominent hazard in tunnel engineering projects, which often induces the shield jamming disaster during the TBM tunneling process. Based on the 139 groups of historical squeezing deformation cases, this study developed a hybrid PCA-IWGO-PNN model for squeezing classification. According to the influencing factors and characteristics of squeezing deformation, the strength-stress ratio, tunnel burial depth, tunnel equivalent diameter, rock mass quality index, and support stiffness were selected to establish the prediction index system of squeezing level. Because the probabilistic neural network (PNN) requires that the input variables are independent, principal component analysis (PCA) was used to preprocess the original data to eliminate the correlation between prediction indexes and achieve dimensionality reduction. The spread coefficient was the critical hyper-parameter in the PNN, and the improved gray wolf optimization (IGWO) algorithm was used to realize its efficient automatic optimization. Then, the PNN model was applied to engineering practice. Only 1 of 20 test samples was misjudged, achieving the 95% prediction accuracy. Finally, the comparison analysis with the artificial neural network (ANN) model, support vector machine (SVM) model, and random forest (RF) model was conducted. Among them, the PNN model achieved the highest prediction accuracy, followed by the artificial neural network (85%), RF (85%), and SVM (80%). In addition, the PNN model had the fastest running speed, which only consumed 5.6350 s, while the running time of ANN, SVM, and RF was 8.8340, 6.2290, and 6.9260 s, respectively. The hybrid PCA-IWGO-PNN model developed in this research provides an effective method for surrounding rock squeezing classification, and it has superiorities in both prediction accuracy and running speed.
Highlights
In recent years, limited by the shallow resources, underground space development and tunnel engineering construction have ushered in a peak period (Zhu et al, 2019)
To accurately predict the squeezing levels, this study proposed a hybrid model of principal component analysis (PCA)-improved gray wolf optimization (IGWO)-Probabilistic neural network (PNN)
2) The spread coefficient has a significant influence on the PNN performance, and the IGWO optimization results indicate that when the spread coefficient is taken as 1.58, the fitness function converges to the global minimum (1.11)
Summary
In recent years, limited by the shallow resources, underground space development and tunnel engineering construction have ushered in a peak period (Zhu et al, 2019). TBM (tunnel boring machine) is widely used in deep-buried and ultra-long tunnels because of high excavation efficiency, low construction cost, and minor environmental disturbance (Liu et al, 2016) Most of these tunnels are located in areas with high seismic intensity, complex surface topography, and harsh geological conditions. Sun Y et al (Sun et al, 2018) proposed a multi-class support vector machine (SVM) method based on tunnel burial depth, tunnel diameter, rock quality index, and support stiffness to evaluate the squeezing level. Probabilistic neural network (PNN) has the advantages of simple structure, easy training, fast convergence speed, and robust fault tolerance, etc It can use a linear learning algorithm to realize the function of a nonlinear learning algorithm, and it has been widely applied to pattern classification problems such as fault diagnosis (Zhang et al, 2021c). This study established a hybrid squeezing level prediction model based on the PCA and PNN, and the hyper-parameter of PNN was automatically tuned by the improved gray wolf optimization (IGWO) algorithm
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
