A method, system, apparatus, and medium for predicting a tunnel boring machine's rate of advance
Patent Information
- Application Number
- CN202410335922.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-22
- Publication Date
- 2026-10-23
AI Technical Summary
[0003]然而，由于隧道掘进机掘进性能不仅会受到隧道直径、地质条件以及设备状态等客观因素的影响，还与现场施工人员的管理水平、人工素质等主观因素密切相关，随着项目管理和施工技术进步、设备质量提高等因素影响，这给准确预测隧道掘进机实际掘进速度带来了重大挑战
[0043]本发明采集滚刀推力、刀盘转速用以预测掘进速度，由于采集到的数据会受到掘进现场不同围岩的等级的影响，因此本发明利用BQ法将获取掘进现场的不同围岩的等级从而将掘进现场划分为不同地层，由于不同的地层对应不同掘进数据的修正系数，因此可以根据不同的修正系数对获取的掘进数据进行修正以计算得到净掘进速度预测量。之后利用隧道掘进机利用率预测模型乘以净掘进速度预测量即可得到实际的掘进速度。解决了现有技术中，无法准确预测隧道掘进机实际掘进速度的问题。
Smart Images
Figure CN122966052A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of excavation technology, specifically relating to a method, system, device, and medium for predicting the tunneling speed of a tunnel boring machine. Background Technology
[0002] Full-face tunnel boring machines (TBMs) are highly efficient, shortening construction periods, especially in long-distance tunneling in stable surrounding rock. During construction, they generate less vibration and noise, minimizing impact on surrounding residents and structures. Furthermore, mechanized construction improves safety and reduces the number of workers required, significantly enhancing the safety and working environment. They have become the preferred construction method for long tunnels. With the rapid development of TBMs in my country, accurately predicting their actual tunneling speed has become crucial for project timeline estimation, cost budgeting, and method selection.
[0003] However, the tunneling performance of tunnel boring machines is not only affected by objective factors such as tunnel diameter, geological conditions and equipment condition, but also by subjective factors such as the management level and human quality of on-site construction personnel. With the advancement of project management and construction technology and the improvement of equipment quality, this poses a significant challenge to accurately predicting the actual tunneling speed of tunnel boring machines.
[0004] In short, existing technologies cannot accurately measure the tunnel boring machine's excavation speed. Summary of the Invention
[0005] To overcome the shortcomings of the existing technology, the present invention provides a method for predicting the tunneling speed of a tunnel boring machine.
[0006] To achieve the above objectives, the present invention provides the following technical solution:
[0007] A method for predicting the tunneling speed of a tunnel boring machine includes:
[0008] Acquire tunneling data of a tunnel boring machine during the excavation process, including cutterhead thrust and cutterhead rotation speed;
[0009] Obtain the different grades of surrounding rock at the tunneling site, and divide the tunneling site into different strata according to the surrounding rock grades; different strata correspond to different correction coefficients for cutterhead thrust and cutterhead rotation speed;
[0010] By using correction coefficients for cutterhead thrust and cutterhead rotation speed corresponding to different geological formations, the net tunneling speed prediction is obtained after reducing and correcting the cutterhead thrust and cutterhead rotation speed.
[0011] By multiplying the tunnel boring machine utilization rate prediction model by the net tunneling speed prediction, a tunnel boring machine actual tunneling speed prediction model is constructed. The actual tunneling speed prediction model is then used to predict the actual tunneling speed of the tunnel boring machine.
[0012] Furthermore, after acquiring the tunnel boring machine's excavation data, the excavation data is cyclically divided into excavation data for different stages of the excavation process, including:
[0013] The real-time operating data of the tunnel boring machine is filtered to remove invalid data during equipment maintenance and downtime.
[0014] The data for each stage are divided according to the criteria for identifying the empty-push section, the initial section, and the stable section, thus obtaining the tunneling data for the empty-push section, the initial section, and the stable section.
[0015] Furthermore, the criteria for distinguishing between the empty thrust segment, the initial segment, and the stable segment are as follows:
[0016] When the speed and torque of the cutter head increase from 0, it is the dry push stage;
[0017] When the cutterhead thrust and torque begin to increase rapidly, and the cutterhead thrust rapidly exceeds the frictional resistance threshold and the torque exceeds the no-load thrust torque threshold, it is the initial stage;
[0018] The torque value that appears most frequently is selected as the discrimination threshold Th. When the torque exceeds the discrimination threshold Th, it is considered to be in a stable segment.
[0019] Furthermore, the predicted net tunneling speed is:
[0020]
[0021] In the formula: PR is the net tunneling speed, P is the tunnel boring machine penetration depth, and N is the cutter head speed of the tunnel boring machine.
[0022] Furthermore, the tunnel boring machine utilization rate prediction model is constructed, and the formula for the tunnel boring machine utilization rate prediction model is as follows:
[0023] U=(24-t s ) / twenty four
[0024] t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10
[0025] In the formula: U is the equipment utilization rate, ts is the average daily downtime of the tunnel boring machine, and AR is the actual advance speed of the tunnel boring machine.
[0026] Furthermore, the formula for predicting the actual tunneling speed of the tunnel boring machine is as follows:
[0027]
[0028] In the formula, AR is the actual tunneling speed prediction model;
[0029]
[0030] U=(24-t s ) / twenty four
[0031] Among them, t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10 AR = PR × U, where U is the equipment utilization rate and ts is the average daily downtime of the tunnel boring machine.
[0032] Furthermore, the hob thrust and cutter head speed data are reduced and corrected using correction coefficients for the hob thrust and cutter head speed; the hob thrust correction formula (2) and the cutter head speed reduction and correction formula (3) are as follows:
[0033] F n =K F ×F nmax (2)
[0034] N=K N ×N max (3)
[0035]
[0036] When BQ > 550, the rock mass quality grade is Class I, and the cutter thrust reduction factor K is... F ∈(0.9,1.0); when BQ∈(451,550), the rock mass quality grade is II, and the cutter thrust reduction factor K F ∈(0.7,0.8); when BQ∈(351,450), the rock mass quality grade is III, and the cutter thrust reduction factor K F ∈(0.6,0.7); when BQ∈(251,350), the rock mass quality grade is IV, and the cutter thrust reduction factor K is... F ∈(0.4,0.6); BQ≤250, rock mass quality grade is V, cutter thrust reduction factor K F ∈(0.2,0.4);
[0037] When the rock mass integrity index K v >0.75, cutter head speed reduction factor K N =1.0; when the rock mass integrity index K v ∈(0.55, 0.75), cutter head speed reduction factor K N ∈(0.8, 0.9); when the rock mass integrity index Kv ∈(0.35, 0.55), cutter head speed reduction factor K N ∈(0.7, 0.8); when the rock mass integrity index K v ∈(0.15, 0.35), cutter head speed reduction factor K N ∈(0.6, 0.7); when the rock mass integrity index K v ≤0.15, cutter head speed reduction factor K N ∈(0.4, 0.5).
[0038] A system for predicting the tunneling speed of a tunnel boring machine, characterized in that it comprises:
[0039] The information acquisition module is used to acquire tunneling data of the tunnel boring machine during the excavation process, including cutterhead thrust and cutterhead rotation speed;
[0040] The net tunneling speed prediction module acquires the different grades of surrounding rock at the tunneling site and divides the tunneling site into different strata according to the surrounding rock grade. Different strata correspond to different correction coefficients for cutterhead thrust and cutterhead speed. Using the correction coefficients for cutterhead thrust and cutterhead speed corresponding to different strata, the net tunneling speed prediction is obtained after reducing and correcting the cutterhead thrust and cutterhead speed.
[0041] The calculation module is used to multiply the tunnel boring machine utilization rate prediction model by the net tunneling speed prediction amount to obtain the actual tunneling speed prediction model of the tunnel boring machine, and then use the actual tunneling speed prediction model of the tunnel boring machine to predict the actual tunneling speed of the tunnel boring machine.
[0042] The method for predicting the tunneling speed of a tunnel boring machine provided by this invention has the following beneficial effects:
[0043] This invention collects cutterhead thrust and cutterhead rotation speed to predict tunneling speed. Since the collected data is affected by the different rock grades at the tunneling site, this invention uses the BQ method to classify the tunneling site into different strata based on these rock grades. Because different strata correspond to different correction coefficients for the tunneling data, the acquired tunneling data can be corrected according to these coefficients to calculate the net tunneling speed prediction. Then, the actual tunneling speed is obtained by multiplying the net tunneling speed prediction by the tunnel boring machine utilization prediction model. This solves the problem in existing technologies that cannot accurately predict the actual tunneling speed of a tunnel boring machine. Attached Figure Description
[0044] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0045] Figure 1 This is a schematic diagram of a method for predicting the tunneling speed of a tunnel boring machine according to the present invention. Detailed Implementation
[0046] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.
[0047] This invention provides a method for predicting the tunneling speed of a tunnel boring machine, specifically as follows: Figure 1 As shown, it includes:
[0048] S1: Divide the tunneling data cyclically.
[0049] The tunneling data is divided into four cyclic segments: the empty push segment, the starting segment, the stable segment, and the stopping segment.
[0050] a: In the air-push section, the tunnel boring machine mainly relies on friction to do work, and the values of thrust and torque are relatively small.
[0051] b: In the initial stage, the cutterhead contacts the excavation face to cut in, the cutterhead rotation speed and advance speed increase, and the various control parameters change significantly.
[0052] c: In the stable section, compared with the initial section, the state of the rock mass and equipment does not change drastically, and the various parameters will not change significantly. Only a stable state with small fluctuations will occur. The stable section is the main process in the tunneling cycle.
[0053] S2, the BQ method was used to statistically analyze different surrounding rock grades at the site and obtain the distribution patterns of the main tunneling parameters in different strata. The main tunneling parameters include cutterhead torque, single cutter thrust, and penetration depth.
[0054] The BQ method formula (1) is:
[0055] BQ = 90 + 3R c +250K v (1)
[0056] The parameter distribution pattern is as follows:
[0057] a: The probability distribution of cutterhead torque, thrust, and penetration depth of tunnel boring machines under different rock conditions basically conforms to a normal distribution. As the rock grade increases, from Class II to Class V, the thrust of a single cutter gradually decreases.
[0058] b: When the surrounding rock is classified as Class V, the rock mass is extremely fragile. When the thrust of the equipment exceeds the friction of the shield, the cutter applies a slight thrust, and the rock mass can fall off. At this point, the penetration depth reaches the maximum limit.
[0059] c: As the rock mass's BQ value increases, its integrity and strength gradually increase. With increasing penetration depth, thrust and torque also gradually increase. When the rock mass's integrity is poor, its overall strength is more limited by its integrity. Conversely, when the rock mass's integrity is good, its excavability is more constrained by the rock's own strength. Therefore, with increasing BQ value, the rate of increase in thrust and torque shows a trend of initially slowing down and then accelerating.
[0060] d: When BQ > 500, the rock mass exhibits extremely high integrity, and the rock strength is also very high. Even under extremely high cutterhead thrust, it is difficult to penetrate to a great depth, and thrust becomes the main limiting factor for tunneling speed.
[0061] S3: Corrects the reduction of cutterhead thrust and cutterhead rotation speed to obtain the net tunneling speed prediction.
[0062] The hob thrust correction formula (2) and the cutter head speed reduction correction formula (3) are as follows:
[0063] F n =K F ×F nmax (2)
[0064] N=K N ×N max (3)
[0065]
[0066] The cutterhead thrust reduction factor KF can be determined based on the BQ value, while the cutterhead reduction factor can be determined based on the rock mass integrity index KV. Details are as follows:
[0067] When BQ > 550, the rock mass quality grade is Class I, and the cutter thrust reduction factor K is... F ∈(0.9,1.0); when BQ∈(451,550), the rock mass quality grade is II, and the cutter thrust reduction factor K F ∈(0.7,0.8); when BQ∈(351,450), the rock mass quality grade is III, and the cutter thrust reduction factor K F∈(0.6,0.7); when BQ∈(251,350), the rock mass quality grade is IV, and the cutter thrust reduction factor K is... F ∈(0.4,0.6); BQ≤250, rock mass quality grade is V, cutter thrust reduction factor K F ∈(0.2,0.4).
[0068] When the rock mass integrity index K v >0.75, the rock mass is very intact, and the cutterhead speed reduction factor K N =1.0; when the rock mass integrity index K v ∈(0.55, 0.75), the rock mass is relatively intact, and the cutterhead speed reduction factor K N ∈(0.8, 0.9); when the rock mass integrity index K v ∈(0.35, 0.55), the rock mass is relatively broken, and the cutterhead speed reduction factor K N ∈(0.7, 0.8); when the rock mass integrity index K v ∈(0.15, 0.35), rock mass fracture, cutterhead speed reduction factor K N ∈(0.6, 0.7); when the rock mass integrity index K v ≤0.15, rock mass is extremely fragmented, cutterhead speed reduction factor K N ∈(0.4, 0.5).
[0069] The formula for net tunneling speed (5) is as follows:
[0070]
[0071] S4: Classify and statistically analyze the downtime procedures of tunnel boring machines, and construct a prediction model for tunnel boring machine utilization rate.
[0072] The shutdown procedures for tunnel boring machines include: fixed procedures, shutdowns between tunneling cycles, fixed shutdown times affected by rock conditions, and shutdown procedures affected by both tunneling distance and rock conditions.
[0073] Fixed procedures include shift handover (T1), equipment maintenance (T2), tool inspection (T3), post-processing (T4), and other time (T5). Downtime between tunneling cycles includes step change time (T6). Fixed downtime affected by rock conditions includes troubleshooting (T7) and tool replacement (T8). Downtime procedures affected by both tunneling distance and rock conditions include support time (T9) and treatment of adverse geological conditions (T10).
[0074] The formula (6) for predicting the utilization rate of tunnel boring machines is as follows:
[0075] U=(24-t s ) / 24(6)
[0076] t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10 (7)
[0077] S5: Execute step S3 and construct a prediction model for the actual tunneling speed of the tunnel boring machine based on the tunnel boring machine utilization prediction model in S4;
[0078] The derivation of formula (9) for the prediction model of the actual tunneling speed of a tunnel boring machine is as follows:
[0079]
[0080] U=(24-t s ) / twenty four
[0081] t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10
[0082] AR = PR × U(8)
[0083] Substituting formulas (5), (6), and (7) into formula (8) yields:
[0084]
[0085] In the formula, AR is the actual tunneling speed prediction model.
[0086] The following are embodiments of the present invention:
[0087] This example primarily utilizes data from 20 sets of rock excavators in a water diversion project's tunnel boring machine (TBM) for testing and verification. The specific implementation process is as follows:
[0088] 1) The distribution of rock machine parameters for the water diversion project is shown in Table 1. The installation radius and the maximum linear velocity of the cutter are substituted into formula (4) to obtain the maximum rotation speed of the cutterhead. Based on the rock integrity index KV, the rock integrity is judged, and the cutterhead rotation speed reduction coefficient KN is obtained. Substituted into formula (3) to obtain the predicted value of the actual rotation speed of the cutterhead after reduction.
[0089] 2) Substitute the rock mass integrity coefficient KV and rock mass strength UCS into formula (1) to obtain the basic rock mass index BQ value. Based on the basic rock mass index BQ value, determine the rock mass quality grade and obtain the cutter thrust reduction coefficient KF. Substitute it into formula (2) to obtain the single cutter thrust prediction value.
[0090] 3) Substitute the predicted actual speed of the cutterhead after reduction and the penetration in Table 1 into formula (5) to obtain the net tunneling speed of the tunnel boring machine.
[0091] 4) Estimate the downtime T1-T10 of the tunnel boring machine based on geological conditions such as surrounding rock grade, compressive strength, and rock mass integrity index.
[0092] 5) Substitute the actual speed N of the tunnel boring machine cutterhead, the actual penetration depth P, and the downtime T1-T10 obtained above into formula (9) to obtain the prediction of the actual tunneling speed. The prediction results are shown in Table 2. The average error of the absolute value of the predicted actual tunneling speed is 12.63%, and the prediction results meet the engineering prediction requirements.
[0093] This invention predicts the actual tunneling speed of tunnel boring machines by preprocessing construction data and estimating equipment utilization, which is of great significance for the estimation of tunnel boring machine schedule, cost budget and construction method selection.
[0094] Table 1. Step-by-step range of rock machine parameter values for a certain water diversion project.
[0095]
[0096] Table 2. TBM tunneling speed prediction for a certain project.
[0097]
[0098] The above embodiments are merely preferred embodiments of the present invention, and the scope of protection of the present invention is not limited thereto. Any simple changes or equivalent substitutions of the technical solutions that can be obviously obtained by those skilled in the art within the scope of the technology disclosed in the present invention shall fall within the scope of protection of the present invention.
Claims
1. A method for predicting the tunneling speed of a tunnel boring machine, characterized in that, include: Acquire tunneling data of a tunnel boring machine during the excavation process, including cutterhead thrust and cutterhead rotation speed; Obtain the different grades of surrounding rock at the tunneling site, and divide the tunneling site into different strata according to the surrounding rock grades; different strata correspond to different correction coefficients for cutterhead thrust and cutterhead rotation speed; By using correction coefficients for cutterhead thrust and cutterhead rotation speed corresponding to different geological formations, the net tunneling speed prediction is obtained after reducing and correcting the cutterhead thrust and cutterhead rotation speed. By multiplying the tunnel boring machine utilization rate prediction model by the net tunneling speed prediction, a tunnel boring machine actual tunneling speed prediction model is constructed. The actual tunneling speed prediction model is then used to predict the actual tunneling speed of the tunnel boring machine.
2. The method for predicting the tunneling speed of a tunnel boring machine according to claim 1, characterized in that, After acquiring the tunnel boring machine's excavation data, the data is cyclically divided into different stages of the excavation process, including: The real-time operating data of the tunnel boring machine is filtered to remove invalid data during equipment maintenance and downtime. The data for each stage are divided according to the criteria for identifying the empty-push section, the initial section, and the stable section, thus obtaining the tunneling data for the empty-push section, the initial section, and the stable section.
3. The method for predicting the tunnel boring machine speed according to claim 2, characterized in that, The criteria for distinguishing between the empty thrust phase, the initial phase, and the stable phase are as follows: When the speed and torque of the cutter head increase from 0, it is the dry push stage; When the cutterhead thrust and torque begin to increase rapidly, and the cutterhead thrust rapidly exceeds the frictional resistance threshold and the torque exceeds the no-load thrust torque threshold, it is the initial stage; The torque value that appears most frequently is selected as the discrimination threshold Th. When the torque exceeds the discrimination threshold Th, it is considered to be in a stable segment.
4. The method for predicting the tunneling speed of a tunnel boring machine according to claim 1, characterized in that, The predicted net tunneling speed is: In the formula: PR is the net tunneling speed, P is the tunnel boring machine penetration depth, and N is the cutter head speed of the tunnel boring machine.
5. The method for predicting the tunneling speed of a tunnel boring machine according to claim 1, characterized in that, The tunnel boring machine (TBM) utilization rate prediction model is constructed, and the formula for the TBM utilization rate prediction model is as follows: U=(24-t s ) / 24 t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10 In the formula: U is the equipment utilization rate, ts is the average daily downtime of the tunnel boring machine, and AR is the actual advance speed of the tunnel boring machine.
6. The method for predicting the tunneling speed of a tunnel boring machine according to claim 1, characterized in that, The formula for predicting the actual tunneling speed of the tunnel boring machine is as follows: In the formula, AR is the actual tunneling speed prediction model; U=(24-t s ) / 24 Among them, t s =t1+t2+t3+t4+t5+t6+t7+t8+t9+t 10 AR = PR × U, where U is the equipment utilization rate and ts is the average daily downtime of the tunnel boring machine.
7. The method for predicting the tunneling speed of a tunnel boring machine according to claim 1, characterized in that, The correction coefficients for the hob thrust and cutter head speed are used to reduce and correct the hob thrust and cutter head speed data; the hob thrust correction formula (2) and the cutter head speed reduction correction formula (3) are as follows: F n =K F ×F nmax (2) N=K N ×N max (3) When BQ > 550, the rock mass quality grade is Class I, and the cutter thrust reduction factor K is... F ∈(0.9,1.0); when BQ∈(451,550), the rock mass quality grade is II, and the cutter thrust reduction factor K F ∈(0.7,0.8); when BQ∈(351,450), the rock mass quality grade is III, and the cutter thrust reduction factor K F ∈(0.6,0.7); when BQ∈(251,350), the rock mass quality grade is IV, and the cutter thrust reduction factor K is... F ∈(0.4,0.6); BQ≤250, rock mass quality grade is V, cutter thrust reduction factor K F ∈(0.2,0.4); When the rock mass integrity index K v >0.75, cutter head speed reduction factor K N =1.0; when the rock mass integrity index K v ∈(0.55, 0.75), cutter head speed reduction factor K N ∈(0.8, 0.9); when the rock mass integrity index K v ∈(0.35, 0.55), cutter head speed reduction factor K N ∈(0.7, 0.8); when the rock mass integrity index K v ∈(0.15, 0.35), cutter head speed reduction factor K N ∈(0.6, 0.7); when the rock mass integrity index K v ≤0.15, cutter head speed reduction factor K N ∈(0.4, 0.5).
8. A system for predicting the tunneling speed of a tunnel boring machine, characterized in that, include: The information acquisition module is used to acquire tunneling data of the tunnel boring machine during the excavation process, including cutterhead thrust and cutterhead rotation speed; The net tunneling speed prediction module acquires the different grades of surrounding rock at the tunneling site and divides the tunneling site into different strata according to the surrounding rock grade. Different strata correspond to different correction coefficients for cutterhead thrust and cutterhead speed. Using the correction coefficients for cutterhead thrust and cutterhead speed corresponding to different strata, the net tunneling speed prediction is obtained after reducing and correcting the cutterhead thrust and cutterhead speed. The calculation module is used to multiply the tunnel boring machine utilization rate prediction model by the net tunneling speed prediction amount to obtain the actual tunneling speed prediction model of the tunnel boring machine, and then use the actual tunneling speed prediction model of the tunnel boring machine to predict the actual tunneling speed of the tunnel boring machine.
9. A device for predicting the tunneling speed of a tunnel boring machine, characterized in that, include: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method for predicting the tunnel boring machine speed as described in any one of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method for predicting the tunnel boring machine speed as described in any one of claims 1 to 7.