Yangtze River Tunnel Research Articles

Development and verification of shield thrust vector self-adaptive control technology in soft soil strata

To solve the difficulty in automatically obtaining an effective total thrust vector relative to the shield posture adjustment requirements during self-driving in soft soil strata, a shield thrust vector self-adaptive control technology for shield machines was proposed. Subsequently, a large-scale model platform was established to simulate the straight-line advancement of the testing shield machine under dynamic loads, and the feasibility of steady shield driving was verified. The test results showed that: the actual total thrust force exhibited the same variation characteristics according to load force, while a relatively fixed difference of 1000 kN between the two caused by the system friction was observed. A quick recovery after an abrupt jump of the shield speed was discovered once there was a sudden, significant change in the load. The actual resultant moment of total thrust force effectively responded to the load force, and the shield postures were maintained well. Further, the driving speed and the horizontal stroke difference were controlled in the ranges of ±3 mm/min and ±5 mm of each set values, respectively. Subsequently, this technology was applied to the Wusongkou Yangtze River Tunnel project in Shanghai, and the on-site test results verified its feasibility in actual soft soil strata. The shield speed remained stable as the actual thrust forces shared the same changing low of the target values, and a fixed difference between the two was maintained to ensure the movement of the shield machine. The variation curves of the actual steering angles in both the horizontal and vertical directions coincided with those of the target steering angles because the resultant horizontal and vertical moments of the thrust force effectively responded to each steering requirement, which was executed with high quality.

Data reconstruction for tunnel structural health monitoring: An updated KNN model with gray relational analysis

Structural health monitoring (SHM) system is an important way to evaluate the tunnel structural performance. In practice, the missing data is inevitably induced in the SHM dataset, which may cause deviation or even misleading results of the data analysis, and hence, need to be accurately reconstructed. This study proposes a new KNN data reconstruction method based on a gray correlation measure (GRA-KNN). Compared to the traditional KNN, the GRA-KNN can measure the structural similarity of data better, and the pre-filling can make full use of the information of known data to estimate missing data. By comparing with the other five machine learning methods (i.e., Ridge Regression, Support Vector Regression, Multilayer Perceptron, RandomForest, and XGBoost), the imputation performance of this method is examined using two real-time SHM datasets from Nanjing Yangtze River tunnel and Hong Kong-Zhuhai-Macao Bridge Undersea Tunnel. Results show that the GRA-KNN method possesses a better performance and stronger robustness under a wide range of missing ratios from 10% to 90%, showing great potential in SHM data reconstruction. In particular, when the missing ratio is larger than 60%, the imputation error of the proposed method is the smallest compared to that of the other machine learning methods.

Numerical study of mechanical response of shield tunnel under vehicle collision

Shield tunnels account for an essential part of the urban highway system, which are more likely to encounter terrible traffic accidents during daily operation. There is a risk of collision between the errant vehicle and the shield tunnel when a traffic accident occurs. This paper establishes a refined numerical model of the shield tunnel based on the Wuhan Yangtze River Tunnel and the vehicle numerical model. Considering the four factors (vehicle weight, speed, collision angle, ground reaction coefficient), an orthogonal test scheme designing 9 simulation cases is proposed. During the collision, the dynamic responses (opening and dislocation of segment joints, stress, and plastic damage of shield tunnel lining) are studied. Results show that the anti-collision wall and segment lining are damaged to varying degrees, and bolts and reinforcement bars in the collision area reach their yield strength; meanwhile, segment joints appear to have irreversible opening and dislocation. According to the extremum difference analysis of orthogonal simulation results, vehicle weight and speed are the two leading factors in structural responses, the contribution degree of which is significantly larger than collision angle and ground reaction coefficient in structural responses.

A novel autoencoder for structural anomalies detection in river tunnel operation

Anomaly diagnosis is essential to prevent disasters and ensure long-term stable operation of tunnels. However, the diversity and scarcity of abnormal data make it difficult to identify outliers, especially to diagnose structural anomalies from poor-quality data. Therefore, an adaptive loss function improved autoencoder (AdaAE) model is proposed for anomaly detection, which is robust to poor-quality data and can accurately determine the anomaly source of river tunnel. To expand the abnormal dataset, numerical simulation of structure under extreme conditions and Gaussian noise are adopted to construct structural damage data and disturbance data respectively. The proposed model is then instantiated on the prepared dataset. Finally, the reliability and the advantage of the proposed model are verified by ablation study. The research results indicate that the detection ability of AdaAE model is greatly improved to that of the widely used methods. This model is suitable to poor quality dataset, and the accuracy to detect structural anomalies from pollution data sets is more than 90%. As a case study, the AdaAE model is applied to the Wuhan Yangtze River tunnel to detect anomalies of segment strain. This study would play a role in preventing structural diseases and promoting intelligent management during tunnel operation.

Study on Temperature Distribution along the Ultra-Long Underwater Tunnel: Based on the Long-Term Measured Results of the Shanghai Yangtze River Tunnel

Tunnels play a vital role in enhancing traffic flow and supporting public transportation systems. However, the discharge of polluted air and waste heat from vehicles passing through tunnels significantly raises the temperature inside, presenting challenges in terms of occupant comfort, tunnel safety, and infrastructure integrity. Therefore, ensuring proper temperature control is essential for their efficient operation. This study aims to investigate the phenomenon of temperature rise in ultra-long tunnels during normal operations, as limited research has been conducted in this area. The Shanghai Yangtze River Tunnel serves as a case study, utilizing temperature and air velocity data collected throughout the year (2021) from the management company. The analysis reveals that the temperature distribution near the tunnel exit is influenced by outdoor temperature fluctuations and traffic volume. The highest temperatures occur on 25 August (39.74 °C) during peak traffic hours. On-site measurements of tunnel temperature, humidity, and air velocity during winter and summer seasons yield the following results. During winter, the air temperature and wall temperature inside the tunnel experience significant increases along its length. The air temperature rises by approximately 11 °C from the entrance to the exit, while the wall temperature increases by about 15 °C. In contrast, during summer, the air temperature only rises by 2.7 °C, and the wall temperature increases by around 3 °C. Consequently, the humidity decreases along the tunnel, and this decrease is correlated with the magnitude of temperature increase. Furthermore, measurements of air velocity indicate that natural and traffic-induced winds contribute to the overall airflow inside the tunnel. A temperature data logger installed in the tunnel recorded temperature changes during the period of pandemic lockdown and subsequent recovery, spanning the spring and summer seasons. During the lockdown period, there was a relatively small increase in temperature along the tunnel, suggesting that vehicle heat dissipation is the primary factor contributing to temperature rise inside. Additionally, a method is proposed to predict the cross-sectional temperature of the tunnel using measured air velocities.

Full-scale experimental and theoretical study of an air leakage model and the applicable limit length for ceiling centralized smoke exhaust systems in tunnel fires

Based on the Jiangxinzhou Yangtze River Tunnel, this study investigated the air leakage of a ceiling-centralized smoke exhaust system through full-scale tests and theoretical analysis. The theoretical analysis established a functional relationship between the pressure of the exhaust vent and air leakage volume. The air leakage coefficient of the exhaust vent was defined. The exhaust vent air leakage coefficient, exhaust flue area, hydraulic diameter, resistance coefficient along the exhaust flue, and exhaust vent spacing were integrated to establish the exhaust flue air leakage coefficient. Through full-scale tests, the exhaust flue pressure and air volume distribution were analyzed under different opening schemes of the exhaust vent. A section-by-section calculation method was established for the applicable limit length and air leakage of the ceiling centralized smoke exhaust system. This study further established a simple calculation method for the applicable limit length of a ceiling centralized smoke exhaust system through theoretical analysis, which made the calculation simple and easy to perform and enabled the results to be calculated with a certain degree of accuracy.

Prediction of tunnel mechanical behaviour using multi-task deep learning under the external condition

ABSTRACT Accurate prediction of the future mechanical behaviour of the underground structure is important for the traffic system. However, the existing works mostly just predicted one type of property and failed to study the influence of different properties in the tunnel. Besides, most of them predicted future behaviours without considering the external influence of the environment like temperature and water pressure. In this paper, we propose a multi-task prediction model named MSTNet which combines different types of indicators and external factors for capturing the temporal and spatial characteristics in the tunnel. Firstly, we integrate time series of multiple indicators and build a deep learning algorithm based on a graph neural network and recurrent network to capture the temporal, spatial and external impacts in the tunnel. Then, we have a case study on the Wuhan Yangtze River tunnel which contains the comparison of different components in our model, the compared results between the single indicator and multiple indicators and the performance analysis among traditional models. From the experiment results, we could find that the ability of the MSTNet model is superior to other methods, whose capability achieved over 93% and 94% in strain variation and joint opening sensors on Pearson Correlation Coefficient (PCC) in the next 45 days, respectively.

Reusing Fine Silty Sand Excavated from Slurry Shield Tunnels as a Sustainable Raw Material for Synchronous Grouting

Using the Nanjing Dinghuaimen Yangtze River Tunnel project as a case study, we proposed a method to reuse the excavated silty-fine sand by adjusting the proportion of the waste sand to replace the commercial sand. This would address the issue of recycling the significant amount of waste sand generated when the slurry shield passes through the silty-fine sand stratum. Moreover, we have evaluated grout indicators such as density, fluidity, consistency, bleeding rate, volumetric shrinkage, setting time, and unconfined compressive strength and examined how the particle size and distribution of the sand affected the grout’s performance. The findings show that as the replacement ratio increases, the grout’s density, fluidity, consistency, and bleeding rate gradually increase; meanwhile, the volumetric shrinkage increases initially before decreasing; the setting time decreases gradually; the unconfined compressive strength initially decreases before increasing. The key factor altering the grout’s performance when the replacement ratio is less than 50% is the weakening of the adsorption effect of fine sand particles on water due to the increase in the sand’s fineness modulus. When it is greater than 50%, the particle size of the sand tends to be distributed nonuniformly and fine particles fill the voids between larger particles, thus contributing to the changes in grout properties.

Prediction for segment strain and opening of underwater shield tunnel using deep learning method

Predicting the future mechanical behaviors of tunnel structure is essential to prevent disasters and maintain the long-term stability. Due to the underwater shield tunnels are usually constructed in complicated geological conditions, it is a challenge for traditional models to accurately predict the future behaviors considering multiple influence factors comprehensively. In this study, a multi-learning model termed as GC-GRU was presented on the basis of deep learning algorithm to predict the future mechanical behaviors of tunnel structure, which was formalized on the structural health monitoring data obtained from the Wuhan Yangtze River tunnel. Based on GC-GRU, temporal dependencies of historical performance and the spatial correlations among different monitoring indicators were captured, and the segment strain and opening in next 45 days were predicted. In addition, a series of experiments were conducted to discuss the predictive capability of the presented model, including the comparison to single indictor prediction model and some widely used classical prediction models, such as GRU, LSTM, XGboost, LR, and RNN. The comparison results denoted that GC-GRU performed best among all models especially when the prediction time scale reaches 20 days. The predicted errors of GC-GRU deduce at least 0.02 mm and 8.62με for joint opening and segment strain respectively, and model learning capability improves 2.2% for both of them. Therefore, it is reliable to introduce GC-GRU model to predict the future mechanical behaviors of tunnel structure.

Analysis of Car-Following Behaviors under Different Conditions on the Entrance Section of Cross-River and Cross-Sea Tunnels: A Case Study of Shanghai Yangtze River Tunnel.

Compared to highway road tunnels, the entrance section of cross-river and cross-sea tunnels feature long and steep slopes. Along with a complicated traffic environment and harmful weather conditions, traffic congestion and rear-end crashes occur frequently during car-following in cross-river and cross-sea tunnels. It is necessary to examine the impact of traffic flow and weather conditions on car-following behavior at the entrance section of cross-river and cross-sea tunnels. To this end, this paper first extracted the vehicle speed data based surveillance video at the entrance of the Shanghai Yangtze River Tunnel. Moreover, the actual average speed under different traffic flow conditions was obtained through the clustering algorithm, which was used as the basis for setting the experimental parameters. Then, in the driving simulation experiment, three traffic flow conditions (free flow, congested flow, and jam flow) were set up in three weather conditions (sunny, rainy, and snowy), and a risk situation was set up in each condition. Distance headway, time headway, acceleration, lateral offset, and driver’s emergency response time were collected. Moreover, seven slopes of 2% to 5% were set, and the relationship of slope on longitudinal speed and lateral offset was analyzed. ANOVA and post-hoc analyses were applied. The result indicates that traffic flow conditions have a significant effect on the car-following behavior, while weather conditions mainly influence the time headway. Moreover, drivers tend to adopt more cautious driving behavior as the distance between the vehicle and the tunnel entrance decreases. The results also show that the slope of the cross-river and cross-sea tunnel entrance section has a major influence on vehicle speed.

Prediction for the future mechanical behavior of underwater shield tunnel fusing deep learning algorithm on SHM data

Predicting the future mechanical behavior of tunnel structure is vitally important to prevent accident disasters. However, in most of the existing models, the inadequate consideration for influencing factors reduced the final prediction accuracy. To this end, this study aims to develop an accurate prediction model considering the coupling effects of multiple influencing factors. First, the framework of model integrates the effects of Temporal, Spatial, and Load (TSL) dependencies is developed based on deep learning algorithm. Subsequently, TSL is formulated on the monitoring data obtained from the Wuhan Yangtze River tunnel and used to predict the mechanical behavior of this study case under an extreme condition. Through a series of experiments, the necessity of considering the coupling effects of multiple influencing factors is verified, and the parameter effects on model predictive capability are discussed. In addition, some commonly used prediction models, such as RNN, LSTM, Xgboost, SVR, LR, are selected as baselines to compare with TSL. Experimental results indicate that the predictive ability of TSL is superior among all models, whose accuracy improves 2.853% in next 15 days prediction. Therefore, it is essential to consider the couple effects of multiple factors, and the presented model is reasonable.

Identifying the outlier in tunnel monitoring data: An integration model

Structural health monitoring (SHM) system based on the Internet of Things is an important method to evaluate the safety of tunnel operation through the real-time monitoring data analysis. Identifying the outlier in SHM data is a non-trivial task but it is challenging for the tunnel engineers because the measurements are quite complicated with the characteristics of time series, unlabeled, high-dimensional, inter-correlations between variables, etc. To detect the outliers, an integration model is developed based on the independent data analysis from the Probabilistic, Proximity-Based (global), Proximity-Based (local), Linear Model and Outlier Ensembles. The model is examined with the shuttle data set in the University of California Irvine (UCI) database and its precision rate is up to 94.5%, highlighting the favorable performance in identifying the outliers. This method is thus applied to the outlier detection of the SHM data in the Nanjing Yangtze River tunnel. 6698 data sets collected from SHM are evaluated and 270 groups of outliers are identified effectively. By eliminating these outliers, comparisons between the proposed integrated model and the single model (i.e. IForest, ABOD, KNN, LOF) are further conducted to discuss the model performance based on the regression analysis. Results show that the integrated model is better than the single model and it possesses the great potential to detect the outliers in SHM system.

Developing a prediction model for segment joint opening in an underwater shield tunnel

The opening of segment joints is vital to structural stability and leakage prevention for the underwater shield tunnels and it is governed by many environmental variables, e.g., water pressure, earth pressure, and temperature. Identifying the key variables and selecting a reliable predictive model for the joint opening are challenging but important tasks but they are usually done according to subjective judgments. To develop a reliable predictive model, the Nanjing Yangtze River tunnel was introduced as a case study for field monitoring and theoretical analysis. First, the structural health monitoring system in this shield tunnel was used to construct a database of measurements including joint opening, water pressure, earth pressure, and temperatures in the escape layer and inside the segment. Then, Bayesian model class selection was conducted for the variable selection and model construction. Consequently, the water pressure and temperature inside the segment were identified as the input variables for joint opening evaluation. This two-parameter model was validated by using the measurement data. It is useful for the evaluation of similar projects in tunneling engineering.

Refined 3D modelling of spatial-temporal distribution of excess pore water pressure induced by large diameter slurry shield tunneling

Tunneling induced excess pore water pressure (EPWP) is crucial to face stability, time-dependent ground deformation and structural performance of tunnel lining. This paper numerically investigates the short-term spatial–temporal distribution of EPWP induced by large diameter slurry shield tunneling in saturated soils. A refined 3D finite element model is developed to consider the construction process including tunnel advance, segment installation, tail void grouting and grout material hardening. The commonly neglected shield conicity is fully considered in the refined modelling. The proposed fluid–solid coupled numerical model is well validated by the field monitoring data of Shanghai Yangtze River Tunnel after considering shield conicity. Temporal distribution of EPWP is equivalent to a certain spatial distribution in the longitudinal direction. Longitudinal distribution of EPWP is separated into five parts (Δua ~ Δue) induced by different construction process. The fives of EPWP are largely influenced by shield conicity induced overcut, soil compressibility, grouting pressure and tunnel diameter. The distribution of EPWP ahead of tunnel face is mainly determined by slurry support pressure and is hardly influenced by other factors.

Investigation on the data augmentation using machine learning algorithms in structural health monitoring information

Structural health monitoring system plays a vital role in smart management of civil engineering. A lot of efforts have been motivated to improve data quality through mean, median values, or simple interpolation methods, which are low-precision and not fully reflected field conditions due to the neglect of strong spatio-temporal correlations borne by monitoring datasets and the thoughtless for various forms of abnormal conditions. Along this line, this article proposed an integrated framework for data augmentation in structural health monitoring system using machine learning algorithms. As a case study, the monitoring data obtained from structural health monitoring system in the Nanjing Yangtze River Tunnel are selected to make experience. First, the original data are reconstructed based on an improved non-negative matrix factorization model to detect abnormal conditions occurred in different cases. Subsequently, multiple supervised learning methods are introduced to process the abnormal conditions detected by non-negative matrix factorization. The effectiveness of multiple supervised learning methods at different missing ratios is discussed to improve its university. The experimental results indicate that non-negative matrix factorization can recognize different abnormal situations simultaneously. The supervised learning algorithms expressed good effects to impute datasets under different missing rates. Therefore, the presented framework is applied to this case for data augmentation, which is crucial for further analysis and provides an important reference for similar projects.

Modified analytical solution of shield tunnel lining considering nonlinear bending stiffness of longitudinal joint

As discontinued segmental joint plays a great important role in the mechanical behavior of shield tunnel lining, design for the joint suffers much from the difficulty in selecting proper parameters i.e., reduction factor η, spring stiffness. The mechanical behavior of longitudinal joint is highly nonlinear and can be classified into four stages. A four stage analytical model for determining the joint bending stiffness is proposed considering the influence of bending moment and axial force. The proposed analytical model is verified by 3D FE model and experimental results of Shanghai Yangtze River Tunnel. An analytical full ring solution based on Lee’s model is proposed incorporating the nonlinear joint stiffness model. The modified analytical solution is compared with the Lee’s model and 3D FE model with a case study of metro tunnels. Compared to Lee’s model, the modified solution has a better prediction of bending moment distribution especially at tunnel invert while has a close prediction of axial force distribution. The proposed solution has a good agreement with FEM results in tunnel deformation including horizontal convergence and joint opening. The maximum prediction errors are 1.5 mm for horizontal convergence and 0.36 mm for joint opening compared to 3D FE model analysis.

Analysis of Local Damages Effect on Mechanical Responses of Underwater Shield Tunnel via Field Testing and Numerical Simulation

The investigation of concrete structural performance is crucial to maintain the stability of infrastructure. In order to assess structural stability, this work focuses on the development of an integrated framework to detect damaged conditions in the field and analyze their effect on mechanical performance through nondestructive testing (NDT) technology and numerical models. First, a ground penetrating radar (GPR) and an infrared camera work collaboratively to identify the damaged positions of the concrete structure, with parameters calibrated by laboratory experiments. Then, a finite element model is established to study structural mechanical performance based on field conditions and detected results. In addition, the influenced regions induced by local damage are studied under different boundary conditions. As a case study, the devised method was employed in the Nanjing Yangtze River tunnel for stability assessment and disaster prevention. The detected results of the damaged conditions agree well with the actual conditions in the field. Numerical results show that the circumferential stress component is more significant than that observed longitudinally. The effect of local damage on stress implies a positive correlation with the rise of water pressure, in which the maximum stress response to the variation of water level is 45KPa per meter.

Settlement behaviors investigation for underwater tunnel considering the impacts of fractured medium and water pressure

Settlement behavior plays an important role for the stability of underwater tunnel due to the different responses of fractured surrounding rock to external load. In contrast to the traditional analysis method based on continuum mechanics, the presented numerical model using improved hybrid finite element was performed to study the settlement behaviors of structure, and structural health monitoring system (SHMS) was introduced for field verification. The Nanjing Yangtze River tunnel, a typical underwater shield tunnel was selected as a case study for numerical simulation and real-time monitoring. First, an improved numerical model was developed on the basic of our previous research, which considers the impact of natural geological fractures on structure stability. Then, numerical investigation was applied to study the displacement of settlement under different boundary conditions. The differences between intact and fractured surrounding rock were discussed, which denote the response of fractured surrounding rock is significantly larger. To verify the numerical results, SHMS was employed in this project to monitor its mechanical behaviors. On the basis of the mass monitoring data, the analytical method was introduced to investigate the response of tunnel settlement to water pressure, which agreed well with the results obtained from the model of fractured surrounding rock.

Structural Monitoring and Performance Assessment of Shield Tunnels during the Operation Period, Based on Distributed Optical-Fiber Sensors

The weak parts of shield tunnels are not obvious, so it is urgently necessary to implement distributed monitoring based on an advanced sensing method. As the horizontal loads at both sides of the shield tunnel present a type of symmetric distribution, the deformation parameters under the vertical loads are often selected as the key monitored parameters, such as convergence, settlement, and seam opening. In this paper, the monitoring of the proposed deformation parameters is innovatively implemented with only one sensing technology, namely distributed optical-fiber strain sensing technology. First, the improved distributed optical-fiber sensors are introduced with the sensing performance. Second, a structural health monitoring (SHM) system for operational shield tunnels is proposed, including optical-fiber sensor installation, data logging and saving, key parameter analysis, and structural health assessment. The key monitoring theory and technology are also proposed. The proposed system has been verified by experiments at the Nanjing Yangtze River tunnel. In the experiments, the proposed optical-fiber sensors were installed on the surface of a selected tunnel ring, with a longitudinal span of approximately 90 m long. The experiments were conducted over 55 days to measure the distributed strain and temperature. Then the key parameters were obtained from the measurements, with which the structural health was assessed. The possibility that the shield tunnel SHM system can be constructed with the improved distributed optical-fiber sensors, monitoring theory, and technology is proven.

Safety Risk Analysis and Protective Control of Existing Pipelines Affected by Deep Pit Excavation in Metro Construction

Urban underground pipelines undertake many tasks closely related to people’s daily life and production, such as water supply, drainage, gas supply, and power supply. Metro projects are usually located in areas with dense underground pipelines; therefore, in the construction process of deep-foundation metro pit, some measures should be taken to protect the safety of underground pipelines. Under the engineering background of the Jiangbei foundation pit of the Wuhan Yangtze River Tunnel, the influence of soil disturbance caused by deep-foundation pit excavation is first simulated using the ABAQUS software on the displacement of underground pipelines and the dangerous area of underground pipelines is analyzed. Second, the most disadvantageous combination is analyzed for the risk factors of pipelines under the influences of multiple risk factors. Finally, a systematic additional partial reinforcement scheme (APRS) is proposed from the aspects of safety and economy to protect the safety of underground pipelines in the dangerous areas with greater risk. The results of measurement prove that the APRS is effective for pipeline protection and can provide reference for similar problems.