Boring Machine Research Articles

A residual denoising and multiscale attention-based weighted domain adaptation network for tunnel boring machine main bearing fault diagnosis

A residual denoising and multiscale attention-based weighted domain adaptation network for tunnel boring machine main bearing fault diagnosis

Estimating the penetration rate of tunnel boring machines via gradient boosting algorithms

The prediction of tunnel boring machine (TBM) performance from the rate of penetration (ROP) point of view has yet to draw a lot of attention since it is one of the main challenges for excavation with TBMs. This study examined six tunnels excavated with TBM to develop predictive models of the ROP estimation using five algorithms: Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine, Adaptive Boosting (AdaBoost), and CatBoost (categorical-features-include-GB). A dataset has been developed, including uniaxial compressive strength (UCS), Rock Type, the distance between planes of weakness (DPW), and thrust force (TF), and contains more than 575 data points for each parameter. The developed models showed that the XGBoost model outperformed the other models, followed by the CatBoost, according to seven different evaluation metrics used to rank the models when the models were modeled with the default values of the algorithm parameters. After tuning the hyperparameters, the GB model outperformed the others, while the other models remained relatively unchanged. By using the overall ranking according to the metrics and considering the parameter tuning time, XGBoost and CatBoost were presented as the two best models. SHAP (Shapley additive explanations: an explainable artificial intelligence tool) values and dependency plots showed that the TF has the highest impact on the ROP, followed by UCS, Rock Type, and DPW. It is concluded that the XGBoost and CatBoost models, with coefficients of determination of 0.9878 and 0.9682, respectively, may be used for estimating the TBM penetration rate for similar rock types.

MatDEM-based study of disc cutter force model in open TBM tunnels: Incorporating installation radius and synergistic effects

The prediction of rock cutting force is critical for tunnel boring machine performance and cutterhead design. This paper presents a novel model for rock cutting force prediction based on the Colorado School of Mines (CSM) model, which incorporates the installation position of disc cutters by introducing installation radius and synergistic effect factors. Linear cutting tests in the laboratory and large-scale rotary cutting simulations in MatDEM software were conducted to examine the impact of these factors. Results indicate that the normal and rolling forces increase and stabilize as the installation radius increases. The synergistic effect produces three force modes in a cutting circle, with mode α having the largest cutting force, mode β having a smaller force, and mode γ having the smallest force. The impact of installation radius and synergistic effect varies with rock-cutter parameters. Multiple regression analysis was used to determine the introduced factors. The proposed model was validated with rock strength and operation data from the Irtysh River conveyance project. The results demonstrate that the proposed model outperforms the CSM model in predicting cutting force in field conditions.

Dynamic reliability evaluation of TBM components in tunnel construction

The complex geological conditions in tunnels pose a huge challenge to the reliability of tunnel boring machine (TBM). However, existing reliability studies typically focus on core structures such as cutters and cutterheads, with less consideration given to the rest of the components that frequently fail. In this study, the reliability analysis and dynamic evaluation of TBM components with high failure rates are carried out relying on the Shanxi Central Yellow River Diversion Project. The life distribution and reliability variation characteristics of TBM components under different rock mass classes are investigated in terms of tunnelling time and tunnelling distance as two types of life data indexes. And the life index which is more suitable for the reliability evaluation of TBM components is identified by comparison. On this basis, a dynamic evaluation method for the reliability of TBM components under the condition of multi‐classes surrounding rock is proposed. This method can quickly evaluate the current reliability of TBM components and serve as the basis for preventive maintenance. The results of this study play a certain role in supplementing the reliability research of TBM and also provide a scientific basis for optimizing the design and maintenance strategy of TBM components.

Precise pose control of shaft boring machine considering the characteristic of stratum

The shaft boring machine (SBM) is innovatively applied to shaft engineering with depth and large diameter for the advantages of efficiency, adaptability, and safety. The manual and rough pose control of SBM blocks the improvement of engineering quality and efficiency. This article presents a precise pose control method for SBM considering the characteristics of strata. The kinematic model of SBM and the mechanical-hydraulic-rock coupled dynamic model of grippers actuator are established considering the characteristics of different surrounding rock, respectively. A test rig is established to validate these models. The stratum-adapted double-layer controller is designed for the pose control from the practical aspects, including the deviation and inclination of the SBM center. The upper layer devotes to the kinematic planning between pose and displacement of grippers. The linear active disturbance rejection control (LADRC) method is used to control each gripper in the lower layer. The compensation control strategy is proposed to improve the reliability of the system under the different strata conditions. The stratum-adapted property is validated with the simulation of different surrounding rock characteristics. The control test under hard rock condition is performed with the test rig. The results indicate that the displacement control error of the single gripper cylinder is less than 1.8%, and the corresponding control error of deviation and inclination angle of the SBM center is less than 2.1% and 2.3% respectively. The proposed method can cover the precise pose control under different strata conditions, and it can be applied in the shaft infrastructure construction practically.

TBM excavation of São Paulo Metro Line 6 South in heterogeneous ground in urban area

AbstractThe São Paulo Metro is expanding its network in the São Paulo Metropolitan Area inhabited by 21 million people. Metro Line 6 connects the north of the city to the existing metro network further South. The construction of Line 6 currently represents the largest infrastructure project in Latin America, combining the excavation of tunnel boring machine (TBM) and conventional tunnels, cut‐and‐cover stations and a number of deep emergency exit shafts. This paper presents the main features of the TBM tunnel excavated in the South stretch through the Tertiary soils of the São Paulo Basin and through the challenging Embu Complex, which consists of a mixture of fractured rock, saprolite and residual soils. The alignment runs under the dense urban grid of São Paulo under high‐rise buildings and other infrastructure, such as existing Metro lines.

Combining improved DFMEA with knowledge graph for component risk analysis of complex products

With the development of information technology in manufacturing, product lifecycle iteration is accelerating. Efficiently analyzing and identifying component risks is important to ensure the reliability of products. This paper proposes a new method that combines improved design failure mode and effect analysis (DFMEA) with the knowledge graph for component risk analysis of complex products. A risk evaluation knowledge graph is built for the risk identification and knowledge provision in the process of DFMEA. Graph analysis is used to identify to-be-evaluated objectives based on historical maintenance data, which helps designers avoid the heavy task of identification. The graph matrix of the historical evaluations is used to calculate the comprehensive weights. A Dempster-Shafer (DS) evidence fusion method based on comprehensive weight evaluation information is proposed for the effective fusion of evaluation evidence. As an alternative to the exact risk ranking, we offer a risk trade-off VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje) method for components classification that classifies components into different risk classes for different risk treatment measures. Finally, the proposed method is validated using a tunnel boring machine as an example, and comparison and sensitivity analyses are performed to demonstrate that the risk value shows a consistent and stable change with expert evaluation.

Risk Assessment of TBM Construction Based on a Matter-Element Extension Model with Optimized Weight Distribution

In order to effectively address the potential hazards associated with the construction of Phase II of the YE Water Supply Project’s KS tunnel in Xinjiang, this study employs the WBS-RBS (Work Breakdown Structure and Risk Breakdown Structure) method for risk identification. This approach aims to identify various risks that may arise during TBM (Tunnel Boring Machine) construction. To prevent incomplete risk factor identification resulting from subjective judgment, a risk index system is established based on the identification results. Subsequently, a matter-element extension model is utilized to quantify the risk factors within this index system, and comprehensive weights are determined using variable weight theory to assess construction risk levels. Importance analysis of each index is then conducted to identify those with significant impact on risk evaluation outcomes. Finally, by comparing actual engineering cases with other risk evaluation models, this paper verifies the reliability of its constructed risk assessment model and proposes measures for controlling potential risks based on these evaluations. The paper provides a clear definition of safety risks encountered during TBM construction and conducts comprehensive risk assessments as a valuable reference for research related to the tunnel boring machine construction period in tunnel engineering.

Development of Thrust, Torque, and Power Estimation Model, and Prediction Performance of Earth Pressure Balance Tunnel Boring Machine in Mixed-Face Strata

Development of Thrust, Torque, and Power Estimation Model, and Prediction Performance of Earth Pressure Balance Tunnel Boring Machine in Mixed-Face Strata

An approach for the design of dewatering systems: the case of an excavation for the construction of the assembly shaft of a tunnel boring machine

Robust approaches are needed for designing efficient dewatering systems of deep excavations below the water table to avoid unforeseen incidents (e.g., bottom instabilities in deep excavations and flooding, among others). This paper proposes a methodology, which integrates existing experiences, that was adopted to design the dewatering system of an excavation in the city of Barcelona (Spain). The approach consists of combining: (i) detailed geological and hydrogeological characterizations, (ii) numerical modelling for parameter estimation and drawdown predictions, and (iii) analytical assessment for stability evaluation and soil deformation predictions. The idea is that by combining a set of relatively easy to apply methods, it is possible to successfully solve a complex and risky problem. The methodology allows designing efficient dewatering systems, increasing safety and mitigating potential impacts of groundwater pumping. The most significant conclusion is that the most important step of the proposed approach is the hydrogeological characterization because it allows building realistic and representative numerical models to address most of the challenges associated to dewatering.

Probabilistic assessment of rockburst risk in TBM-excavated tunnels with multi-source data fusion

In recent years, tunnel boring machines (TBMs) have become extensively utilized in underground engineering projects. However, as a prevalent type of dynamic geological hazard, rockburst poses a serious threat to the safety of personnel, equipment, and property. To ensure the safe advancement of TBMs, we integrate the data of microseismic monitoring, TBM excavation, and surrounding rock and establish multiple probabilistic assessment models of rockburst risk using probabilistic ensemble learning and quantum particle swarm optimization. In order to identify the most optimal model for geological engineers, a comprehensive evaluation system is devised based on metrics like accuracy, Cohen’s kappa, and F1-score. This system provides a thorough assessment of the models’ global and local generalization performance. The results indicate that the classification and regression tree-extremely randomized trees (CART-ERT) hybrid model achieves the highest score, demonstrating superior generalization performance with an accuracy of 93.06% and a Cohen’s kappa of 0.9074. Moreover, the F1-scores for no rockburst, low rockburst, moderate rockburst, and strong rockburst are 0.9412, 0.9444, 0.9189, and 0.9189, respectively. Based on the operational framework of the CART-ERT hybrid model, a user-friendly graphical user interface (GUI) system is developed. This significantly enhances the practicality and deployability of the model. Through application in a TBM diversion tunnel project in Xinjiang, the on-site early-warning accuracy of rockburst with the GUI system reaches 90%. Notably, the GUI system maintains high early-warning sensitivity and reliability for high-intensity rockburst such as moderate and strong ones. Lastly, to enhance the model’s interpretability, a variable importance measure (VIM) analysis on 14 features extracted from three types of heterogeneous data is conducted to assess their contributions to the early warning of rockburst. We discover that the cumulative energy change rate of microseismic events exhibits the highest importance score, indicating its crucial role in rockburst early warning.

Multi-step real-time prediction of hard-rock TBM penetration rate combining temporal convolutional network and squeeze-and-excitation block

Accurate penetration rate prediction enhances rock-breaking efficiency and reduces disc cutter damage in tunnel boring machine (TBM) construction. However, this process faces significant challenges such as the high uncertainty of ground conditions and the complexity of maintaining optimal TBM operation in long and large tunnels. To address these challenges, we propose TCN-SENet++, a novel hybrid multistep real-time penetration rate prediction model that combines a temporal convolutional network (TCN) and a squeeze-and-excitation (SENet) block for aided tunneling. This study aims to demonstrate the application of TCN-SENet++, as well as other models such as RNN, LSTM, GRU, and TCN, for TBM penetration rate prediction. The model was developed using actual datasets collected from the Yin-Song diversion project. We employ a 30-s time step to predict the future time steps of the penetration rate (1st, 3rd, 5th, 7th, and 9th). The features that influence the penetration rate, such as the cutterhead torque, thrust, and cutterhead power, were considered. A comparative analysis using the mean absolute error and mean squared error revealed that the TCN-SENet++ model outperformed the other models, including RNN, LSTM, GRU, TCN, and TCN-SENet+. In comparison, TCN-SENet++ achieved average MSE reductions of 18%, 6%, 3%, 1%, and 2%, respectively. The TCN-SENet++ model demonstrated fewer errors in the new project, validating its effectiveness and suitability for real-time penetration rate prediction in TBM construction.

Multi-stream domain adversarial prototype network for integrated smart roller TBM main bearing fault diagnosis across various low rotating speeds

The well-being of tunnel boring machines (TBM) heavily relies on the health status of main bearings, significantly impacting both safety and operational efficiency. Investigating the operation monitoring and diagnosis algorithms of TBM main bearings in practical scenarios with limited fault data and real-time variations in low-speed heavy-load operating conditions poses a research challenge. To solve these issues, a novel domain-adversarial prototype network diagnostic algorithm with a multi-stream fusion feature encoder (MDAPN) based on smart roller monitoring data is proposed. In contrast to existing external vibration monitoring schemes for bearings, monitoring data from smart rollers can mitigate complex external interference and greatly shorten the transmission path of fault sources. The algorithm encompasses a multi-stream fusion feature encoder, domain discriminator, and prototype network classifier. Specifically, the multi-stream fusion feature encoder adopts the two-stream convolutional network to deeply extract the axial-radial fused features of rollers, incorporating shallow statistical feature information. Domain-invariant features are generated based on domain adversarial learning strategies, and the prototype network classifier reduces dependence on target domain samples. An integrated smart roller main bearing fault simulation testbed was built, conducting 6 sets of cross-domain experiments. The proposed method reached an average accuracy of 98.41 % under 5-shot, surpassing the baseline method by 6.57 % at least. This validates that the MDAPN based on smart roller state exhibits excellent fault recognition performance for the main bearing under varying operational conditions with scarce available samples.

Kinematics and spatial structure analysis of TBM gunite robot based on D–H parameter method

In modern tunnel construction, TBM (Tunnel Boring Machine) plays a very important role. In response to the needs of tunnel wall reinforcement and TBM automated construction for tunnel construction, a shotcrete mechanism mounted on the TBM is designed. In order to evaluate the kinematic performance of the mechanism, this paper studies the forward and inverse kinematics and spatial architecture of the TBM shotcrete robot. Firstly, based on the D–H parameter method, the number of joints and links is determined and structural analysis is performed to obtain the robot's forward kinematics equation, achieving the mapping between joint space and pose space. Then, by determining the joint variables, the mapping of the end tool in Cartesian space is achieved. Finally, based on the Monte Carlo random sampling method, the workspace of the robot is constructed, and its reachability and flexibility within the robot workspace are evaluated. The performance of the device is verified by building a prototype, which meets the requirements well. Through the research in this paper, it can provide theoretical basis and guidance for the design and control of the shotcrete robot.

Coupling process controlling data and numerical simulation in mechanised tunnelling

AbstractNowadays, both process data management and numerical analysis are necessary for decision‐making in a tunnel project from its early design stage to the construction phase. Traditional generation of simulation models largely depends on tunnel design and reports, which are error prone due to the involvement of manual intervention. This article presents the application of a digital workflow to efficiently transfer automatically acquired data from tunnel projects to computational simulations. The application workflow is developed and executed through a web‐based environment. Project data from the Victory Boogie Woogie tunnel is retrieved from the process controlling software PROCON via web services to generate numerical simulations for settlement predictions at different tunnel sections. The simulated results are validated using real measured settlements in the project to prove the quality of the simulation model. Different scenarios of applying operational steering parameters are then investigated, utilising the simulation model, which can be used to support the on‐site engineers as an assistance system to drive the tunnel boring machines. The work has been carried out within the framework of the transfer project T2 of the Collaborative Research Center “Interaction Modeling in Mechanized Tunneling” (SFB 837), which aims to implement and test a digital twin for process control under practical conditions in the tunnelling industry.

Research on Rock-Breaking Characteristics of Cutters and Matching of Cutter Spacing and Penetration for Tunnel Boring Machine

Tunnel boring machine (TBM) tunnel construction in composite strata relies heavily on understanding the rock-breaking characteristics of TBM cutters and optimizing cutter spacing and penetration. Utilizing a full-scale rock rotary cutting machine (RCM), this study conducted rock-breaking tests with disc cutters under varying rolling radii. An analysis of rock debris shape and cutter behavior provided insights into rock-breaking mechanisms. Two main types of rock fragments were identified, with both shear and compression failure observed during cutter–rock interactions. The influence of the rolling radius and cutter spacing on cutter forces was analyzed, along with numerical modeling using the particle flow method. Optimal cutter selection in soft–hard composite strata should prioritize cutter force, with the greatest force required in hard rock. Cutter force increases with penetration, while the force difference between cutters decreases with reduced cutter spacing. These findings offer practical guidance for efficient rock-breaking in composite geological formations during tunnel construction.

Research on Tunnel Boring Machine Tunnel Water Disaster Detection and Radar Echo Signal Processing

This study focused on the detection of water inrush in tunnels excavated by full-section hard rock tunnel boring machines (TBMs) and employed ground penetrating radar methods for conducting research on radar signal processing algorithms. The research demonstrates that conventional techniques are inadequate for eliminating the interference of TBM equipment on radar signal propagation. This study employs a radar antenna array method for signal transmission, utilizing a wavelet double-threshold filtering algorithm and wave propagation theory to suppress clutter. These methods exhibit strong signal reception capabilities and are effective in eliminating 13.1% of the direct wave components. The adoption of a novel, efficient radar signal imaging algorithm simplifies the imaging process. Results of verification indicate that the synthetic aperture algorithm, enhanced with cross-correlation calculation, yields the optimal imaging effect. This investigation, which was conducted in conjunction with the construction of a diversion tunnel in a specific region, has confirmed the applicability of the ground penetrating radar method for the detection of water inrush in TBM tunnels by conducting a comparative analysis of the direct wave removal algorithm and the integration of the optimal imaging algorithm. The innovative application of ground penetrating radar within TBM tunnels, along with a targeted technology to mitigate signal interference from metal equipment, has led to the selection of an appropriate algorithm for both signal processing and imaging. This approach offers a novel solution for the detection of water source disasters in TBM tunnels.

Optimizing cutter wear in TBM operations through numerical analysis of enhanced rock-cutting interaction

The inevitable wear and degradation of disc cutters during the rock-crushing process significantly impacts the efficacy, timeline, and cost-effectiveness of tunnel construction. Optimizing cutter arrangements and adjusting suitable excavation parameters are crucial to reducing cutter wear in Tunnel Boring Machine (TBM) operations. This study probes the interaction between disc cutters and rock, employing an enhanced Bonding model to more accurately depict the failure behavior of rock specimens. Numerical simulations of the rock-breaking process using two disc cutters were conducted, focusing on highly influential excavation parameters—penetration depth (3, 5, 7, 9 mm) and cutter arrangements—tip width (14, 17, 20, 23 mm) and cutter spacing (50, 65, 80, 95, 110 mm). These simulations analyzed the impact of various factors on cutter force, wear, specific energy of rock breaking, and crushing unit rock cutter wear. The results show that increased penetration depth leads to higher cutter force and wear, with specific energy and unit wear remaining low when penetration is less than 5 mm. A larger cutter tip width incurs higher forces and wear of the first cutter, but when the tip width exceeds 20 mm, the force and wear of the second cutter will be reduced. Optimal specific energy for rock breaking and unit wear of rock volume were identified within a cutter spacing range of 80 to 95 mm. These findings can facilitate the analysis of how excavation parameters and cutter arrangements affect wear behavior, offering superior construction recommendations.

Assessing cutter-rock interaction during TBM tunnelling in granite: Large-scale standing rotary cutting tests and 3D DEM simulations

The widespread utilisation of tunnel boring machines (TBMs) in underground construction engineering requires a detailed investigation of the cutter-rock interaction. In this paper, we conduct a series of large-scale standing rotary cutting tests on granite in conjunction with high-fidelity numerical simulations based on a particle-type discrete element method (DEM) to explore the effects of key cutting parameters on the TBM cutter performance and the distribution of cutter-rock contact stresses. The assessment results of cutter performance obtained from the cutting tests and numerical simulations reveal similar dependencies on the key cutting parameters. More specifically, the normal and rolling forces exhibit a positive correlation with penetration but are slightly influenced by the cutting radius. In contrast, the side force decreases as the cutting radius increases. Additionally, the side force shows a positive relationship with the penetration for smaller cutting radii but tends to become negative as the cutting radius increases. The cutter's relative effectiveness in rock breaking is significantly impacted by the penetration but shows little dependency on the cutting radius. Consequently, an optimal penetration is identified, leading to a low boreability index and specific energy. A combined Hertz-Weibull function is developed to fit the cutter-rock contact stress distribution obtained in DEM simulations, whereby an improved CSM (Colorado School of Mines) model is proposed by replacing the original monotonic cutting force distribution with this combined Hertz-Weibull model. The proposed model outperforms the original CSM model as demonstrated by a comparison of the estimated cutting forces with those from the tests/simulations. The findings from this work that advance our understanding of TBM cutter performance have important implications for improving the efficiency and reliability of TBM tunnelling in granite.

126 Size distribution and characterization of particulate matter generated during tunnel boring machine excavation

126 Size distribution and characterization of particulate matter generated during tunnel boring machine excavation