Cutter Consumption Research Articles

Real-time monitoring of disc cutter wear in tunnel boring machines: A sound and vibration sensor-based approach with machine learning technique

Large portions of the tunnel boring machine (TBM) construction cost are attributed to disc cutter consumption, and assessing the disc cutter's wear level can help determine the optimal time to replace the disc cutter. Therefore, the need to monitor disc cutter wear in real-time has emerged as a technical challenge for TBMs. In this study, real-time disc cutter wear monitoring is developed based on sound and vibration sensors. For this purpose, the microphone and accelerometer were used to record the sound and vibration signals of cutting three different types of rocks with varying abrasions on a laboratory scale. The relationship between disc cutter wear and the sound and vibration signal was determined by comparing the measurements of disc cutter wear with the signal plots for each sample. The features extracted from the signals showed that the sound and vibration signals are impacted by the progression of disc wear during the rock-cutting process. The signal features obtained from the rock-cutting operation were utilized to verify the machine learning techniques. The results showed that the multilayer perceptron (MLP), random subspace-based decision tree (RS-DT), DT, and random forest (RF) methods could predict the wear level of the disc cutter with an accuracy of 0.89, 0.951, 0.951, and 0.927, respectively. Based on the accuracy of the models and the confusion matrix, it was found that the RS-DT model has the best estimate for predicting the level of disc wear. This research has developed a method that can potentially determine when to replace a tool and assess disc wear in real-time.

Machine learning-based prediction model for disc cutter life in TBM excavation through hard rock formations

Replacing damaged or worn disc cutters is costly and time-consuming, which can significantly reduce the utilization and advance rate of tunnel boring machines (TBMs). Accurate prediction of disc cutter life is crucial for optimizing TBM operation in tunneling projects. This study introduces a machine-learning-based prediction model designed to forecast disc cutter wear, incorporating the analysis of each cutter’s travel length and the intervals between cutterhead interventions (CHI). The principle underlying the developed machine learning approach involves usage of multiple learning algorithms, ensemble learning methods, and a sophisticated analysis of these factors to identify patterns and relationships essential for effectively predicting wear rates. Employing CHI report data from the Daegok–Sosa tunneling project’s hard rock excavation, the model evaluates 15 wear-influencing factors, providing precise wear predictions. This study proposes the ensemble machine learning (ML) methods, namely Random Forest (RF) and Extreme Gradient Boosting (XGB), for accurate wear rate predictions and discern influential factors. The proposed model demonstrated exceptional prediction accuracy, as evidenced by a root mean square error of 0.049 mm for a single-ring excavation length. Notably, this model innovatively accounts for variable wear rates of cutters based on the individual cutter travel lengths as well as other geological and operational parameters. Furthermore, the predicted cutter consumption rate showed reasonable correspondence when compared to the actual CHI records. The proposed model is expected to improve existing disc cutter life prediction methods and reduce the cost and time for replacing damaged or worn disc cutters.

Effects of changing water content of clay-content rocks on field cutter consumption rate of roadheaders: a case study of porous ignimbrites

The changing formation characteristics during excavation can cause a higher cutter consumption rate (CCR) of mechanical excavators than theoretically estimated before the project begins. This study investigates the adhesive potential of clay-content porous ignimbrites in increasing water content and their effects on the CCR of roadheaders. For this purpose, the actual field CCR data of roadheaders were recorded for ten cold storage caverns (CSC) projects during the excavation in dry and wet conditions. Then, laboratory tests were carried out on the rock samples collected from project areas. CCRs of roadheaders were theoretically estimated based on the Cerchar abrasivity index of rocks using three different empirical models. The laboratory test results showed that increasing water content reduces the abrasivity and strength of the rocks. The theoretically estimated results also showed that CCR is to be less under saturated conditions. However, actual field data revealed higher CCRs for all CSC projects in wet conditions. Therefore, the adhesion potential of rocks in different water contents was analyzed, and positive relationships were obtained between the field CCR in wet conditions and the adhesion potentials of excavated rocks with 15%, 20%, and 25% water content. New equations were developed to estimate the CCR of roadheaders, especially in excavating rocks that have an adhesive potential to cutters, such as clay-content rocks. It has been concluded that for an accurate CCR estimation, more than theoretical calculations will be required, and changing formation conditions should also be analyzed in detail.

Improving Tunnel Boring Machine Tunneling Performance by Investigating the Particle Size Distribution of Rock Chips and Cutter Consumption

The construction environment of deep rock tunnels is complex, and effectively enhancing tunnel boring machine (TBM) tunneling efficiency is paramount. Increasing rock-breaking efficiency and minimizing cutter consumption are essential strategies for improving TBM tunneling efficiency. Selecting suitable tunneling parameters is crucial for enhancing rock-breaking efficiency and reducing cutter consumption. Existing research on the optimization of the ratio of maximum cutter spacing to penetration (Smax/P) based on field-measured data is limited, and few studies compare and analyze the relationship between SE, CI, and the Smax/P ratio separately. Consequently, this study determined optimal tunneling parameters for various types of surrounding rock and construction environments, aiming to more accurately optimize TBM tunneling performance during construction processes based on on-site construction data. This study conducted a comparative analysis of specific energy (SE) and the coarseness index (CI). Under both working conditions, the quadratic fitting coefficients of the CI are 4.2% and 10.6% higher than those of the SE, respectively, with the CI selected to represent the particle size distribution of rock chips. Finally, taking into account both the correlations between the CI and the ratio of maximum cutter spacing to penetration (Smax/P), as well as cutter consumption and the Smax/P ratio, an optimization method for the TBM tunneling parameter was established under both dry and saturated conditions. The research findings indicate that cutter consumption exhibits an exponential increase with a higher rock Cerchar Abrasivity Index (CAI); it initially decreases as the Smax/P ratio increases and subsequently increases in both dry and saturated conditions. Instead, the CI demonstrates an initial increase and subsequent decrease as the Smax/P ratio increases. Maximizing rock-breaking efficiency and minimizing cutter consumption are crucial for improving tunneling performance. In saturated conditions, the corresponding optimal Smax/P ratio ranges are 7.055–8.319 for soft rock, 8.606–8.931 for medium–hard rock, and 13.50–14.00 for hard rock, and these optimal ranges under dry conditions are 8.495–9.457, 10.972–12.169, and 16.5–17.5 for the same rock types. This study provides optimal Smax/P ratio ranges for TBM tunneling, thereby significantly enhancing tunneling efficiency.

Predicting advance rate and cutter life in TBM tunnelling using evolutionary algorithm

ABSTRACT Tunnelling with a Tunnel Boring Machine (TBM) offers several advantages over conventional tunnelling methods when covering long distances, particularly regarding time, safety, and environmental impact. Prior to starting a TBM project, performance analysis is a crucial stage necessary to inform the initial investment decision and project cost estimation. However, this analysis requires extensive fieldwork and laboratory studies. The Advance Rate (AR), calculated from the Utilization Factor (U) – the ratio of excavation time to total project time – is a widely accepted measure of TBM performance. Total project time encompasses various parameters, including boring time, cutter inspection and replacement times, and constant factors like re-gripping, service, and maintenance times. In this study, we employed analytical methods, statistical analysis, and genetic programming approaches to evaluate the AR and thus enhance TBM performance analysis. Gamma tests were conducted to identify interrelated parameters in TBM operations. The results from these tests showed that the Applied Force per Cutter (FN) and penetration values (together forming the Field Penetration Index or FPI) are useful in estimating cutter consumption. While FN can be determined through laboratory tests, its field determination is challenging. We have developed several charts and a function derived from genetic programming to estimate the AR of a TBM. The study demonstrated that this function, formulated using genetic programming, possesses strong predictive capability and can significantly improve TBM performance analysis.

Numerical investigation of temperature distribution on a tunnel boring machine disc cutter affected by geomechanically and excavation parameters

This study focuses on the thermal behavior of tunnel boring machines (TBMs) through an in-depth investigation into the temperature distribution of their disc cutters. Utilizing the differential quadrature method (DQM), the research conducts a comprehensive numerical analysis to assess the impact of excavation and geological parameters on disc cutter temperature and wear. The accuracy of the DQM model is validated against the finite difference method (FDM), demonstrating comparative results with reduced computational requirements. The findings indicate a significant correlation between disc cutter temperature and various factors, such as rotational speed, spacing, geological conditions, and material strength. Notably, increased spacing or cutter speed leads to higher temperatures and accelerated cutter wear. Moreover, geological factors, particularly rock strength, influence friction coefficients, affecting disc cutter temperatures significantly. For instance, even a slight increase in cutter spacing results in a substantial 65% rise in cutter consumption, underscoring the relevance of these findings for life cycle assessment (LCA) evaluations across diverse geological and environmental conditions in TBM operations.

Water saturation effects on rock abrasivity and TBM tunneling efficiency

Tunnel boring machine (TBM) tunneling efficiency is influenced by surrounding rocks, TBM design, and interaction between the TBM cutter and rocks. Using a case study from a water conveyance tunnel project located in northwestern China and involving five different lithologies (metamorphic andesite, sandstone, granite, quartz schist, and quartz diorite), this work investigates the water saturation effects on Cerchar abrasivity index (CAI) and its correlations with other physical and mechanical rock properties and TBM disc cutter and energy consumption. The results show that water saturation reduces CAI for all examined rocks except for the quartz diorite at the 90 % confidence level. CAI of saturated rocks (CAIsat) has statistically better correlations with weighted Mohs hardness value of rock minerals (Ha), equivalent quartz content (EQC), and uniaxial compressive strength (UCS), than CAI of dry rocks (CAIdry). The in-situ construction data analyses suggest that the average disc cutter consumption increases exponentially with the rise of CAI values in both dry and saturated conditions, and the water saturation effects significantly reduce the disc cutter consumption within medium-hard and hard surrounding rocks. Both disc cutter and specific energy consumption have a quadratic relationship with the ratio of the maximum cutter spacing to penetration depth (Smax/P), and water saturation can significantly shift the quadratic relationships. Optimal Smax/P ranges for minimizing the disc cutter and energy consumption are recommended for different rocks under dry and saturated conditions. The findings from this study can support estimating cutter and energy consumption with considerations of groundwater effects.

Effect of water saturation on Cerchar abrasivity index (CAI) of clay-rich rocks at different scratch lengths

Predicting the cutter consumption rate of mechanical excavators using the Cerchar abrasivity index (CAI) results is possible. However, changing operational parameters in the field may cause differences between the estimated cutter consumption rate based on CAI test results and the real cutter consumption rate observed in the field. One of the essential parameters in the field that affects the cutter consumption rate is the increase in the water content of the excavated rocks. In theory, an increase in the water content of rocks is expected to reduce their abrasivity. In addition, the prediction of cutter consumption rate is based solely on CAI test results conducted on dry surfaces. However, especially during the excavation of low-strength clay-rich rocks, the excavated rock material can adhere to the cutters and block them, leading to a higher cutter consumption rate than initially predicted. This study aims to analyze the rock-pin interaction in CAI tests conducted on wet surfaces of clay-rich rocks and investigate the effect of water saturation on CAI at different scratch lengths. CAI tests were conducted on dry and wet surfaces of 20 clay-rich rocks with low strength at 10, 30, 50, and 70 mm scratch lengths, respectively. The relationships between the CAI test results obtained on dry and saturated rock surfaces were statistically analyzed for each scratch length. A positive linear correlation was found between CAI values obtained on dry (CAIDry) and saturated surfaces (CAISat) at each scratch length. The percentage variations in CAI values at each scratch length were analyzed in detail. It was found that 90 % of samples have higher CAIDry than CAISat at 10 mm scratch length. However, it was observed that as the scratch length increased, the relationship between the CAI values obtained in dry and saturated conditions changed, and the proportion of samples with CAIDry higher than CAISat decreased to 65 %, 55 %, and 25 % at scratch lengths of 30 mm, 50 mm, and 70 mm, respectively. In CAI tests conducted on saturated surfaces, it was observed that the excavated rock material adhered to the test pins, and as the scratch length increased, the increase in CAISat values was considered to be due to this situation. This study revealed the importance of considering the adhesion potential of rocks to cutters at water-saturated conditions for the accurate prediction of cutter consumption in the excavation of clay-rich rocks.

Investigation of disc cutter wear during shield tunnelling in weathered granite: A case study

Wear characteristics of disc cutter can vary significantly during shield tunnelling in different geological formations. This paper presents a case study on disc-cutter wear experienced during earth pressure balance shield tunnelling of the Guang-Fo intercity railway in Guangzhou, China. During excavation of the 2.8 km tunnel, 149 cutter inspections were conducted and 1163 cutters were consumed. Cutter wear morphology and cutter consumption was investigated. Cost-effectiveness of cutter replacement under different ground conditions was evaluated regarding time consumption. Field data revealed that cutter consumption varied with ground conditions, cutter mounting radii, and boring parameters. During mixed ground tunneling, it was noticed that the tips of cutter rings had been sharpened. An approximate estimation of when to inspect cutters during tunnelling can be determined using the field penetration index. Cutter replacement in hard rock ground was more cost-effective than in other ground conditions. The wear data provided here can serve as a reference for future operations in similar geological conditions.

A study on predicting the wear of TBM disc cutters using Cerchar testing

Estimating the disc cutter wear life or change time is a critical part of performance prediction for the application of hard rock TBMs. This paper examines the disc cutter wear rate and the number of required discs during the excavation of the Kanisib (or Zab) tunnel based on the transpositioning concept. The study covers the disc changes due to the normal wear process, leaving out those replaced due to mechanical/bearing failures. This study also analyzes TBM field performance and actual cutter consumption using a method, specific mass loss per volume (SMLV) excavated. SMLV considers the wear mass of a disc cutter relative to the disc cutters replacement for a given volume of excavated rock. Generally speaking, the disc SMLV incorporates critical parameters, and a formula is introduced to calculate it from the rock properties. The new model can be utilized for estimating disc life for any disc cutter size, diameter, and tip width. The predictive model developed in this study allows for estimating cutter life based on the location of disc cutters on the cutterhead. The proposed model uses rock mass parameter, namely the rock quality designation (RQD), and rock material parameters measured in a laboratory, including rock abrasion and strength. Rock abrasion is estimated by Cerchar abrasivity index (CAI) or modified Cerchar abrasivity index (MCAI). Furthermore, a new approach to Cerchar indices has been used, which is based on the pin mass loss instead of pin tip flat size, and as a result, new indices called CAIML and MCAIML are introduced. The correlation between predicted and observed values shows that the proposed model for specific mass loss per volume can predict the normal wear of disc cutters. Furthermore, the Cerchar indices calculated using the pin mass loss offered better correlations with field data than those specified based on the diameter of the pin tip flat. Overall, MCAIML exhibited the best correlation with the field observations compared to the other Cerchar indices.

Rock cutting performance and wear characteristics of undercutting disc cutter: Based on experiment and DEM

The undercutting disc cutter used to break the hard rock bears a huge load and severe wear during rock fragmentation; however, the wear mechanism and law of the cutter are still unclear. The wear mechanism of the undercutting disc cutter was revealed by comparing and analyzing the three-dimensional topography of the cutter before and after the experiments. Based on the DEM, the numerical model of rock cutting using an undercutting disc cutter was established and the influence of factors such as structural and working parameters on the wear behavior of the cutter was studied. The results indicate that under the large contact force, the hard particles of rock are inset into the cutter tip and the material was spalled, resulting in the local pits; the furrows on the cutter face are not continuous and less deep because of the contact between the cutter face and the bottom rock free-face is discontinuous. The wear of the cutter is positively related to the cutting depth and tip width, and negatively to the cutting angle. The circular tip has better wear resistance than the flat tip, and the effect of the tip angle on the wear of the cutter is not significant. The index of cutter consumption ratio (CCR) is proposed, and combined with the specific energy, the recommended structural and working parameters of the cutter for improving the cutting performance and reducing cutter wear are provided.

A Numerical Investigation of the Effect of Disc Cutter Wear on Rock-Cutting Forces in Mechanized Tunnel Boring Machines

The wear of the disc cutter results in an increase in contact area with the rock, so when the wearing of the cutter exceeds its maximum limits, it should be replaced. However, this is not done on time because of cost concerns. Therefore, this study will investigate the effects of disc cutter wear on tunnel boring machine (TBM) operational parameters such as thrust force, torque, penetration rate, and specific energy as well as how it impacts advance rate and project time in hard rock TBMs. Finite-element modeling has been performed on 17″ disc cutters, calibrated with the results of linear cutting machine test (LCM). The wear values varied within the range of 0–20 mm and different penetration depths. Numerical results of normal cutting forces are compared with the previously suggested theoretical model, which shows good agreement. According to numerical models, normal and rolling forces are significantly increased as disc cutter wear increases. Increases in vertical and rolling forces are 130% and 75%, respectively. Changes in the side force on the disc cutters indicate that with the wear of the cutters, the result of the side forces is asymmetric and from the inside of the cutter. It causes the bearing system of the disc cutter to fail. The intensity of these asymmetric forces decreases as the installation radius of the disc cutter increases. Further, the wear of disc cutters significantly increases the specific excavation energy, resulting in a significant reduction in excavation efficiency. Finally, disc cutter consumption information for the Kani Sib water conveyance tunnel is also provided, which confirms the findings.

Study on disc cutter chipping of TBM based on field data and particle flow code simulation

Using tunnel boring machines to excavate high-strength intact rock masses is becoming more common. Due to the interactions between disc cutters and rocks, abnormal wear of disc cutters, especially cutter chipping, has become a common phenomenon. Existing research has mainly focused on normal wear of disc cutters without addressing abnormal wear cases. This study used the disc cutter consumption data of a tunnel project in China to investigate the abovementioned problem based on field research. According to the failure patterns and fracture surface characteristics, the cutter chipping patterns were mainly categorized into four types: granule chipping, patch chipping, primary collapse, and secondary collapse. To further simulate the evolution of disc cutter chipping, based on the linear plastic bond model, a new contact model called the modified plastic bond (MPB) model was proposed to solve the metal simulation problem in Particle Flow Code software. To this end, a set of uniaxial tensile and compressive tests were initially conducted to verify the applicability of the MPB model. Then, a series of three-dimensional rock-cutting simulation tests were conducted to reflect the evolutionary processes involved in each type of cutter chipping. The cutter chipping mechanism and morphological characteristics were classified and summarized in detail. The results revealed that the cutting speed and penetration growth led to a rising trend in the probability and intensity of the cutter chipping. The presence of initial defects also induced an adverse effect on the service life of the cutter. The results indicated suitable working conditions for the cutter and suggested ways to control tunneling parameters and avoid frequent cutter chipping cases.

Application of Soft Computing Techniques to Estimate Cutter Life Index Using Mechanical Properties of Rocks

The wear of cutting tools is critical for any engineering applications dealing with mechanical rock excavations, as it directly affects the cost and time of project completion as well as the utilization rate of excavators in various rock masses. The cutting tool wear could be expressed in terms of the life of the tool used to excavate rocks in hours or cutter per unit volume of excavated materials. The aim of this study is to estimate disc cutter wear as a function of common mechanical rock properties including uniaxial compressive strength, Brazilian tensile strength, brittleness, and density. To achieve this goal, a database of cutter life was established by analyzing data from 80 tunneling projects. The data were then utilized for evaluating the relationship between rock properties and cutter consumption by means of cutter life index. The analysis was based on artificial intelligence techniques, namely artificial neural networks (ANN) and fuzzy logic (FL). Furthermore, linear and non-linear regression methods were also used to investigate the relationship between these parameters using a statistical software package. Several alternative models are introduced with different input variables for each model, to identify the best model with the highest accuracy. To develop these models, 70% of the dataset was used for training and the rest, for testing. The estimated cutter life by various models was compared with each other to identify the most reliable model. It appears that the ANN and FL techniques are superior to standard linear and non-linear multiple regression analysis, based on the higher correlation coefficient (R2) and lower Mean square error (MSE).

Position-oriented process monitoring in milling of thin-walled parts

Improving machining performance of thin-walled parts is of great significance in aviation industry, since most aviation parts are characterized by large size, complex shape, and thin-walled structure. Machining process monitoring is the essential premise to improve the machining performance. In order to improve the machining quality and efficiency, this paper presents a position-oriented process monitoring model based on multiple data during milling process, and corresponding solution is provided. Through obtaining the internal data set of the numerical control (NC) system during machining, it is possible to correlate the cutting position with monitoring signals including cutting force, acceleration, and spindle power. Then, process optimization is realized to improve the machining quality and efficiency based on the monitoring results. Machining tests are conducted on aircraft structural part as well as blade part, and the experimental results show this method provides a significant insight into the machining process of thin-walled part and contributes to the process optimization. By using feedrate optimization, time consumption for the rough milling process of one titanium alloy part reduced from 19.1 h to 14.4 h and the number of cutter consumption dropped from 5 to 3. And according to the result of position-oriented process monitoring, the machining strategies were optimized to reduce vibration and avoid chatter, thereby improving the machining quality.

Cutter change time and cutter consumption for rock TBMs

This paper discusses common methodologies used in the prediction of cutter change time (the average time required for changing a cutter on the cutter head) and cutter consumption (the average number of cutters worn out for the excavation of 1000 cubic meter of rock) and highlights some potential pitfalls in the process. For this purpose, the prediction capabilities of these methods are discussed and their validity is examined using detailed data from many tunnels from around the world. The results of the statistical analyses and comparative studies show that in most cases, the NTNU model underestimates cutter change time. The average cutter change time is approximately 66 min for different cutter sizes and there is a minimal difference between corresponding values of the large versus small cutters. A new cutter change time model is also developed using a statistical analysis of a database of 50 TBM projects’ records based on the TBM penetration rate and quartz content of the rock. Analysis of the cutter consumption information of several tunnel projects has revealed that the available models for the estimation of this parameter require some revisions in the structure of their formulas. A new cutter consumption model is also developed based on a statistical analysis of a database of 135 TBM projects’ records. The results show the proposed new model’s estimates are in good agreement with the actual values with a high coefficient of determination (78%). The outcomes of this paper can improve rock TBMs’ performance and project planning evaluation especially for the early stage of a tunneling project.

A field parameters-based method for real-time wear estimation of disc cutter on TBM cutterhead

In hard rock TBM tunneling, the loss caused by disc cutter wear accounts for a large proportion of time and cost for the entire project. However, existing disc cutter wear prediction models mainly focus on predicting cutter consumption before construction and cannot predict the wear of each disc cutter. Moreover, the accurate rock parameters required in these models are challenging to obtain. Hence, these models are not capable of determining which cutter on cutterhead should be replaced during construction. To solve the problems mentioned above, this paper presents a novel field parameters-based method for estimating the wear of each disc cutter in real-time. The proposed method is implemented through the following steps. To begin with, a new health index is constructed and defined as the ratio of the rolling distance of a cutter in a small excavated section to its maximum rolling distance. Then, specific field parameters related to the new health index are analyzed and selected. Thereafter, the mapping model between the new health index and the specific field parameters is established based on a one-dimensional convolutional neural network. Finally, on the basis of the established model, the estimated health indices corresponding to all excavated sections of a disc cutter are accumulated to obtain its health status. The field data obtained from Mumbai metro tunnel was utilized to verify the effectiveness of the proposed method, which demonstrates that the proposed method can estimate the wear of each disc cutter in real-time with average accuracy as high as 87.8% on the test set. Therefore, the proposed method is capable of significantly reducing the time and cost of cutter inspection, replacement, and repair for TBM, thereby improve tunneling efficiency and reduce construction cost.

A Numerical Investigation of TBM Disc Cutter Life Prediction in Hard Rocks

There is a direct relationship between the efficiency of mechanized excavation in hard rocks and that of disc cutters. Disc cutter wear is an important effective factor involved in the functionality of tunnel boring machines. Replacement of disc cutters is a time-consuming and costly activity that can significantly reduce the TBM utilization and advance rate, and has a major effect on the total time and cost of the tunneling projects. When these machines bore through hard rocks, the cutter wear considerably affects the excavation process. To evaluate the performance of the cutters, first, it is essential to figure out how they operate the rock cutting mechanism; secondly, it is important to identify the key factors that cause the wear. In this work, we attempt to introduce a comprehensive numerical method for estimation of disc cutter wear. The field data including the actual cutter wear more than 1000 pieces and the geological parameters along the Kani-Sib transmission tunnel in the northwest of Iran are compiled in a special database that is subjected to a statistical analysis in order to reveal the genuine wear rule. The results obtained from the numerical method indicate that with an increase in the wear of disk cutter up to 25 mm, the applied normal and rolling forces can be multiplied by 2.9 and 2.7, respectively, and by passing the critical wear, the disk cutters lose their optimal performance. This method also shows that confining pressure will increase the wear of the disc cutter. By the proposed formulation, the cutter consumption rate can be predicted with a high accuracy.

Prediction of Disc Cutter Life During Shield Tunneling with AI via the Incorporation of a Genetic Algorithm into a GMDH-Type Neural Network

Abstract Disc cutter consumption is a critical problem that influences work performance during shield tunneling processes and directly affects the cutter change decision. This study proposes a new model to estimate the disc cutter life (Hf) by integrating a group method of data handling (GMDH)-type neural network (NN) with a genetic algorithm (GA). The efficiency and effectiveness of the GMDH network structure are optimized by the GA, which enables each neuron to search for its optimum connections set from the previous layer. With the proposed model, monitoring data including the shield performance database, disc cutter consumption, geological conditions, and operational parameters can be analyzed. To verify the performance of the proposed model, a case study in China is presented and a database is adopted to illustrate the excellence of the hybrid model. The results indicate that the hybrid model predicts disc cutter life with high accuracy. The sensitivity analysis reveals that the penetration rate (PR) has a significant influence on disc cutter life. The results of this study can be beneficial in both the planning and construction stages of shield tunneling.

Prediction model of wear rate of inner disc cutter of engineering in Yinsong, Jilin

Disc cutter consumption takes up a large part of the cost of TBM construction, and the analysis of the wear of disc cutters can provide design guidance for the cutter head and cutter arrangement in practice. Data analysis of the disc cutter wear capacity of engineering 6859 m in Yinsong, Jilin (the diameter of cutter head is 7,920 mm) shows that the wear capacity of the inner disc cutter (under the same cutter space) is linear to the position where the cutter is installed on the cutter head. Therefore, a formula for calculating the wear rate of the inner disc cutter is based on establishment of the disc cutter installation radius. In accordance with the slope coefficient (A) of the wear rate of the disc cutter, the influence of tuff and granite on it is analyzed at first, then the difference of seven different prediction model combinations of penetration (P), rock uniaxial compressive strength (UCS) and thrust (Fn) under single action and combination action are analyzed. Then, it shows that the single action based on P is the best with the R2 of 0.7156 and the wear rate of the inner disc cutter based on P and UCS is the best for combination action with the R2 of 0.726.