TBM intelligent decision-making method and system considering uniaxial compressive strength

Abstract

The invention provides a TBM (Tunnel Boring Machine) intelligent decision-making method and system considering uniaxial compressive strength. The method comprises the following steps: acquiring point load strength data of corresponding rocks of a tunneling tunnel; obtaining cutterhead data when the TBM is tunneled; training the obtained point load intensity data and cutterhead data by using a recurrent neural network to obtain a corresponding relationship between the point load intensity of the rock and the tunneling load information cutterhead data; based on the corresponding relation of the two kinds of data, a TBM tunneling load prediction model is established, and to-be-predicted TBM tunneling cutterhead data under the point load strength of the corresponding rock is obtained; and according to the predicted cutterhead data of TBM tunneling of the stable section in the tunneling circulation, selecting tunneling control parameters based on a minimum energy consumption criterion or a shortest construction period criterion. According to the method, when the strength of the rock in front of the tunnel face changes, the tunneling control parameters adapting to lithology changes can be obtained through intelligent decision making, so that the tunneling control parameters are adjusted in time, and the abrasion of the cutter head is effectively reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel TBM construction, and in particular to a TBM intelligent decision-making method and system considering uniaxial compressive strength. Background Art

[0002] With the planning and construction of more and more underground projects such as tunnels, the excavation and driving technology of underground projects has developed rapidly. (Full Face Rock Tunnel Boring Machine, hereinafter referred to as TBM) is a large-scale underground engineering equipment used for hard rock tunnel excavation and driving. Different from the traditional construction method, TBM is a highly mechanized and automated large-scale tunnel excavation and lining complete set of equipment integrating mechanical, electronic, hydraulic, laser, control and other technologies. The cutterhead is driven by an electric motor (or electric motor-hydraulic motor) to rotate and the hydraulic cylinder is pushed. The cutter installed on the cutterhead breaks the rock, so that the tunnel section is formed in one time. It is a large-scale engineering machinery. Because of its high degree of automation, fast construction speed, labor saving, safety and economy, one-time formation, not affected by external climate, it can control ground subsidence during excavation, reduce the impact on ground buildings, and underwater underground construction does not affect ground traffic in water. TBM has become the most promising mechanical equipment for rock tunnel excavation.

[0003] The inventor found in the research that TBM has been widely used in various large-scale tunnel construction, but it still faces many technical problems that need to be solved. The strength information of the rock in front of the TBM construction needs to be obtained through a series of complex processes such as sampling at the corresponding position and testing; and the selection of TBM operating parameters often relies on human experience control, and it is difficult to make timely and effective adjustments under complex geological conditions. The optimization decision theory is not yet mature, so that the excavation load generated by the TBM does not meet the current geological conditions, resulting in problems such as TBM jamming, slow excavation speed or excessive machine wear. Summary of the invention

[0004] The purpose of the implementation method of this specification is to provide a TBM intelligent decision-making method considering uniaxial compressive strength, establish appropriate intelligent decisions based on the mapping relationship between rock strength information and tunnel TBM excavation load, and thus obtain appropriate excavation control parameters to guide excavation.

[0005] The embodiments of this specification provide a TBM intelligent decision-making method considering uniaxial compressive strength, which is achieved through the following technical solutions:

[0006] include:

[0007] Obtain the point load strength data of the corresponding rock during tunneling and the cutterhead data during TBM excavation;

[0008] The acquired point load strength data and cutterhead data are trained using a recurrent neural network to obtain the corresponding relationship between the point load strength of the rock and the excavation load information cutterhead data;

[0009] Based on the corresponding relationship between the above two types of data, a TBM excavation load prediction model is established to obtain the TBM excavation cutterhead data under the point load strength of the corresponding rock to be predicted;

[0010] According to the predicted cutterhead data of the TBM excavation in the stable section of the excavation cycle, the excavation control parameters are selected based on the minimum energy consumption criterion or the shortest construction period criterion.

[0011] A further technical solution is to obtain the strength information of the rock mass by using a point load test method: the point load strength data of the rock slag at the corresponding position is measured.

[0012] As a further technical solution, the cutterhead data during TBM excavation includes the cutterhead thrust F and the cutterhead torque T, and the cutterhead data is obtained from previous engineering cases or directly derived from the TBM excavation data.

[0013] A further technical solution is to use a recurrent neural network to train the acquired rock point load strength data and cutterhead data:

[0014] The obtained raw data is divided into three groups: training data set, debugging data set and verification data set;

[0015] The rock strength information in the training data set is used as the input layer, and the excavation load information is used as the output layer for training to obtain a pre-trained RNN model;

[0016] Then, the parameters of the RNN model obtained through training are fine-tuned by debugging the data in the dataset, and the parameters are corrected, and finally a fusion feedback model between rock strength information and tunneling load information is obtained;

[0017] Finally, the effectiveness of the RNN model is verified by using the data in the validation dataset;

[0018] In a further technical solution, the excavation control parameters include the propulsion speed of the TBM and the rotation speed of the cutterhead;

[0019] Minimum energy consumption criterion: the optimal excavation control parameters obtained under the control of this criterion are the combination of TBM propulsion speed and cutterhead speed that minimizes the energy consumption of the TBM under the construction requirements;

[0020] The shortest construction period criterion, the optimized excavation control parameters obtained under the control of this criterion are the combination of the fastest excavation speed and cutter head speed that meets the conditions of the TBM excavation rated load.

[0021] Further technical solutions, based on the minimum energy consumption criterion, the optimal formula for tunneling control parameters is:

[0022] ν=ν(F,T)

[0023] r=r(F,T)

[0024] W=[Fν(F,T)+2πTr(F,T)]t

[0025] Where F is the cutterhead thrust, T is the cutterhead torque, v is the TBM propulsion speed, r is the TBM cutterhead speed, and W is the work done by the excavation load.

[0026] Further technical solutions, based on the shortest construction period criterion, the optimal formula for excavation control parameters:

[0027] F 额 ≥F=F(ν,r)

[0028] T 额 ≥T=T(ν,r)

[0029] Where Frated is the rated thrust, Trated is the rated torque, F is the cutterhead thrust, T is the cutterhead torque, v is the TBM propulsion speed, and r is the TBM cutterhead speed.

[0030] A further technical solution is that when the propulsion speed v and the cutter head rotation speed r change, when the degree of change exceeds the allowable value, the excavation control parameters are readjusted.

[0031] The embodiments of this specification provide a TBM intelligent decision-making system considering uniaxial compressive strength, which is implemented through the following technical solutions:

[0032] include:

[0033] The data acquisition module is used to obtain the point load strength data of the corresponding rock in the tunnel and the cutterhead data during TBM excavation;

[0034] The model training module uses a recurrent neural network to train the acquired point load strength data and cutterhead data to obtain the corresponding relationship between the point load strength of the rock and the excavation load information cutterhead data;

[0035] The prediction model building module builds a TBM excavation load prediction model based on the corresponding relationship between the above two data, and obtains the TBM excavation cutter head data under the point load strength of the corresponding rock to be predicted;

[0036] The excavation control parameter selection module selects the excavation control parameters based on the predicted cutterhead data of the TBM excavation in the stable section of the excavation cycle and based on the minimum energy consumption criterion or the shortest construction period criterion.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] 1. The present invention provides a method for quickly obtaining rock strength information, avoiding the complicated coring and testing procedures. The rock strength information can be obtained by directly measuring the point load strength information of the rock slag produced by TBM excavation, thereby establishing a rock strength information database. The method is simple to operate, convenient to obtain samples, and quick in the testing process.

[0039] 2. The present invention provides a fusion of rock strength information and excavation load data based on a recurrent neural network (RNN) algorithm, thereby realizing the prediction of the two types of data. The recurrent neural network has stronger dynamic behavior and computing power, can process the connection between the previous and next data in the time series, and outputs the results that comprehensively consider the influence of the previous and next data. Compared with other machine learning and deep learning methods, it has very high accuracy.

[0040] 3. After the disclosure is equipped with this system, the TBM operator can choose one of the following intelligent decisions on excavation control parameters according to construction requirements: based on the minimum energy consumption criterion, the combination of propulsion speed v and cutterhead speed r can minimize the energy consumption of the TBM while meeting the construction requirements; based on the shortest construction period criterion, the combination of propulsion speed v and cutterhead speed r can enable the TBM to obtain the fastest excavation speed while meeting the machine's carrying capacity. This can adapt to TBM excavation under different rock conditions and different construction requirements.

[0041] 4. When the rock strength in front of the face changes, the present invention can obtain tunneling control parameters that adapt to the rock property changes through intelligent decision-making, thereby adjusting the tunneling control parameters in time, thereby effectively reducing cutterhead wear. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0043] Figure 1 A technical roadmap of a TBM intelligent decision-making method and system considering uniaxial compressive strength for implementing examples of the present disclosure;

[0044] Figure 2 The present invention discloses an RNN training process of a TBM intelligent decision-making method and system considering uniaxial compressive strength. DETAILED DESCRIPTION

[0045] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0046] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0047] Example 1

[0048] This embodiment discloses a TBM intelligent decision-making method considering uniaxial compressive strength. The problems addressed by this application are: how to quickly obtain rock strength information; how to adjust excavation control parameters in time when rock strength changes to reduce cutterhead wear; and how to realize intelligent decision-making of TBM operations under complex rock conditions is an urgent problem to be solved in current TBM construction technology.

[0049] Participate in the Figure 1 As shown, the overall technical solution of the specific implementation example of the present application is: first, during the TBM excavation process, the rock point load strength Is of the excavation tunnel is obtained through a point load test to achieve rapid acquisition of rock strength information, thereby establishing a rock strength database. At the same time, an excavation load database is established in combination with the TBM excavation load information; then, through the interaction between the cutter head and the rock mass of the TBM excavation, a fusion mutual feedback model between the two databases is established based on a recurrent neural network (RNN) algorithm model, and a prediction model for rock strength information is established to achieve prediction of the rock strength in front of the face; then, according to the reaction of the fusion mutual feedback model, the corresponding excavation load information is obtained in combination with the predicted rock strength information in front; finally, intelligent decision-making is made according to the principle of minimum energy consumption or the principle of shortest construction period, so as to obtain the most suitable excavation control parameters for construction under the rock mass strength.

[0050] The specific implementation steps are:

[0051] Step 1: Establish a rock strength information database and an excavation load information database. The rock strength information database can be directly obtained through the collection of previous engineering cases and field engineering tests. This field test acquisition method can abandon a series of cumbersome processes such as field geological sketches, coring, and uniaxial compression tests, and adopt a point load test method to quickly obtain rock strength information. The point load test does not require coring at the measured position. It only needs to test and measure the point load strength Is data of the rock slag at the corresponding position to obtain the strength data of the corresponding rock. This method is simple to operate, easy to obtain samples, and has a fast test process. The excavation load information database includes the cutterhead thrust F and the cutterhead torque T. There is a certain correspondence between the two and the rock strength. These data can be obtained from previous engineering cases or directly derived from TBM excavation data.

[0052] The excavation process of TBM is considered as a plurality of excavation cycles, each cycle includes a starting section, a stable section and a step-changing section, wherein the excavation parameters of the starting section gradually increase, and it is an important stage for observing the excavation status of TBM and selecting appropriate excavation control parameters. In the conventional operation method, the TBM operator continuously increases the given speed and the given rotation speed to make the cutterhead contact with the rock, and obtains the corresponding cutterhead thrust F, cutterhead torque T and other data after contact, thereby guiding the operator to adjust the excavation control parameters, and then obtain stable TBM excavation control parameters until the excavation cycle ends. Therefore, the excavation load information database is divided into the starting section data and the stable section data.

[0053] Step 2: Through the correspondence between the rock mass strength information database and the excavation load information database, a fusion mutual feedback model between the two databases is established. The fusion mutual feedback model can be judged according to the interaction between the cutterhead and the rock mass during the TBM excavation process. Through the obtained rock mass strength information database and the excavation load information database, the fusion mutual feedback model of the two databases is obtained by training using a recurrent neural network (RNN) algorithm model, thereby establishing a rock strength prediction model in front of the tunnel face and realizing the rock strength prediction in front of the tunnel face.

[0054] The correspondence between the rock strength information database and the excavation load information database is that when the rock strength changes, the excavation parameters generated by the corresponding TBM excavator will also change. There is a certain connection between the two. The above correspondence is established through deep learning. It is a prediction model obtained by training the data in the database using a recurrent neural network.

[0055] For details, see the attached Figure 2As shown, the fusion mutual feedback model is obtained by training the recurrent neural network (RNN) algorithm model. The recurrent neural network (RNN) adopts the back propagation algorithm, and its parameters are shared at all times of the network. Each gradient output depends not only on the calculation results of the current moment, but also on the calculation results of all previous moments. Before model training, the original data in the entire database is divided into three groups, namely, training data set, debugging data set and verification data set, with proportions of 70%, 20% and 10% respectively. During model training, the rock strength information in the training data set is used as the input layer, and the excavation load information is used as the output layer for training to obtain a pre-trained RNN model; then, the parameters of the RNN model obtained by training are fine-tuned by the data in the debugging data set. The accuracy of the model can be effectively improved by further parameter correction, and finally a fusion mutual feedback model between rock strength information and excavation load information is obtained; finally, the validity of the RNN model is verified by the data in the verification data set.

[0056] Step 3: The fusion mutual feedback model obtained by the recurrent neural network (RNN) model is used to predict the corresponding TBM excavation load parameters according to the predicted rock strength information. The fusion mutual feedback model can be obtained in the second step. According to the corresponding relationship between the two data in the fusion mutual feedback model, a TBM excavation load prediction model is established to predict the excavation load in the stable section of the excavation cycle, and obtain the TBM excavation load under the corresponding rock strength; TBM excavation load parameters include cutterhead thrust and cutterhead torque, both of which belong to load information. TBM excavation load parameters can reflect the interaction between the cutterhead and the rock mass, including the cutterhead thrust F and cutterhead torque T of the TBM.

[0057] Step 4: Based on the predicted TBM excavation load parameters of the stable section in the excavation cycle, combined with the construction requirements, the excavation control parameters are optimized and evaluated based on the minimum energy consumption criterion or the shortest construction period criterion, so as to complete the intelligent decision-making of the TBM excavation process. The TBM excavation load parameters are obtained through the excavation load prediction model in the third step, including the cutterhead thrust F and the cutterhead torque T; the TBM excavation control parameters include the TBM propulsion speed v and the cutterhead speed r. The intelligent decision-making of the TBM excavation process is to obtain the optimal combination of the TBM construction propulsion speed v and the cutterhead speed r to guide the construction. According to the needs of the project, the appropriate intelligent decision-making criteria can be selected: first, the minimum energy consumption criterion, the excavation control parameters obtained after optimization under the control of this criterion are the combination of the TBM propulsion speed v and the cutterhead speed r that meet the construction requirements with the minimum energy consumption; second, the shortest construction period criterion, the excavation control parameters obtained after optimization under the control of this criterion are the combination of the propulsion speed v and the cutterhead speed r with the fastest excavation speed under the conditions of meeting the TBM excavation rated load. TBM can excavate according to the excavation control parameters provided by the intelligent decision-making system.

[0058] 1) The minimum energy consumption criterion is the parameter optimization criterion for the minimum energy consumption of TBM under construction conditions. In addition to heat loss, the main energy consumption of TBM construction process is the work done by the cutter head thrust F and the cutter head torque T. The minimum energy consumption criterion is the case where the work done by the cutter head thrust and the cutter head torque is the minimum. The excavation load work expression is as follows:

[0059] W=(Fν+2πrT)t

[0060] The excavation load parameters and excavation control parameters are interrelated. The excavation load information prediction model obtained by the fusion feedback mechanism described above predicts the excavation load information, and then the excavation load work is estimated. The propulsion speed v and the cutterhead speed r are expressed as functions of the excavation load, and the excavation control parameter optimization formula based on the minimum energy consumption criterion is obtained:

[0061] ν=ν(F,T)

[0062] r=r(F,T)

[0063] W=[Fν(F,T)+2πTr(F,T)]t

[0064] Based on the minimum energy consumption criterion, while meeting load conditions such as rated cutterhead thrust and rated cutterhead torque, as well as construction requirements such as construction period, the excavation control parameters are optimized through the predicted excavation load information, and the combination of propulsion speed and cutterhead speed with the lowest energy consumption is established, thereby achieving intelligent decision-making.

[0065] 2) The shortest construction period criterion is the parameter optimization criterion for the fastest TBM excavation speed under the construction conditions. The excavation speed of the TBM construction is mainly related to the advancement speed v and the construction length m. The shorter the construction period, the faster the excavation speed, so the advancement speed v is greater. The calculation formula for excavation time is as follows:

[0066] t=m / v

[0067] The greater the cutterhead propulsion speed v, the greater the cutterhead thrust, and thus the greater the cutterhead torque. The excavation control parameters cannot be increased indefinitely. The propulsion speed v and the cutterhead speed r have certain limitations, that is, the excavation control parameters cannot exceed the rated thrust F 额 and rated torque T 额 According to the tunneling load information prediction model obtained by the fusion feedback mechanism described above, the tunneling control parameters are fine-tuned in combination with the shortest construction period criterion. The tunneling load is expressed as a function of the propulsion speed v and the cutterhead speed r, and the tunneling control parameter optimization formula based on the shortest construction period criterion is obtained:

[0068] F 额 ≥F=F(ν,r)

[0069] T 额 ≥T=T(ν,r)

[0070] Based on the shortest construction period criterion, while meeting load conditions such as rated thrust and rated torque and other construction requirements, the excavation control parameters are optimized through the predicted excavation load information, and the fastest excavation speed combination of propulsion speed and cutterhead speed is established, thereby achieving intelligent decision-making.

[0071] Through the established fusion feedback model, the rock strength information is predicted according to the excavation load information of the starting section of the excavation cycle. When the predicted rock strength data changes significantly with the subsequent data, the predicted excavation load parameters of the stable section of the excavation cycle will also change. Then, through the intelligent decision-making system, it is predicted that the advancement speed v and the cutterhead speed r will change. When the degree of change exceeds the allowable value, the system will automatically prompt the TBM operator to adjust the excavation control parameters, thereby effectively reducing cutterhead wear.

[0072] Example 2

[0073] In existing TBM construction, it is difficult to obtain rock strength information and it is impossible to obtain it quickly; and the selection of excavation parameters relies solely on human experience and control, and it is impossible to make timely adjustments to complex geological conditions, which causes damage to the cutterhead.

[0074] The embodiments of this specification provide a TBM intelligent decision-making system considering uniaxial compressive strength, which is implemented through the following technical solutions:

[0075] include:

[0076] The data acquisition module is used to obtain the point load strength data of the corresponding rock in the tunnel and the cutterhead data during TBM excavation;

[0077] The model training module uses a recurrent neural network to train the acquired point load strength data and cutterhead data to obtain the corresponding relationship between the point load strength of the rock and the excavation load information cutterhead data;

[0078] The prediction model building module builds a TBM excavation load prediction model based on the corresponding relationship between the above two data, and obtains the TBM excavation cutter head data under the point load strength of the corresponding rock to be predicted;

[0079] The excavation control parameter selection module selects the excavation control parameters based on the predicted cutterhead data of the TBM excavation in the stable section of the excavation cycle and based on the minimum energy consumption criterion or the shortest construction period criterion.

[0080] Implementation Example 3

[0081] The implementation mode of this specification provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the specific steps in implementation example 1 when executing the program.

[0082] Example 4

[0083] The implementation manner of this specification provides a computer-readable storage medium on which a computer program is stored, characterized in that when the program is executed by a processor, specific steps in implementation example 1 are implemented.

[0084] It is understood that, in the description of this specification, the description with reference to the terms "an embodiment", "another embodiment", "other embodiments", or "first to Nth embodiments" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, and material characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0085] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. For those skilled in the art, the present disclosure may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A TBM intelligent decision-making method considering uniaxial compressive strength, characterized in that: include: Obtain the point load strength data of the corresponding rock during tunneling and the cutterhead data during TBM excavation; The acquired point load strength data and cutterhead data are trained using a recurrent neural network to obtain the corresponding relationship between the point load strength of the rock and the excavation load information cutterhead data; Based on the corresponding relationship between the above two types of data, a TBM excavation load prediction model is established to obtain the TBM excavation cutterhead data under the point load strength of the corresponding rock to be predicted; According to the predicted cutterhead data of the TBM excavation in the stable section of the excavation cycle, the excavation control parameters are selected based on the minimum energy consumption criterion or the shortest construction period criterion.

2. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: The point load test method is used to obtain the strength information of the rock mass: the point load strength data of the rock slag at the corresponding position is measured to obtain the strength data of the corresponding rock. As a further technical solution, the cutterhead data during TBM excavation includes the cutterhead thrust F and the cutterhead torque T, and the cutterhead data is obtained from previous engineering cases or directly derived from the TBM excavation data.

3. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: The acquired point load intensity data and cutter head data are trained using a recurrent neural network: The obtained raw data is divided into three groups: training data set, debugging data set and verification data set; The rock strength information in the training data set is used as the input layer, and the excavation load information is used as the output layer for training to obtain a pre-trained RNN model; Then, the parameters of the RNN model obtained through training are fine-tuned by debugging the data in the dataset, and the parameters are corrected, and finally a fusion feedback model between rock strength information and tunneling load information is obtained; Finally, the effectiveness of the RNN model is verified by using the data in the validation dataset.

4. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: The excavation control parameters include the propulsion speed of the TBM and the rotation speed of the cutterhead; Minimum energy consumption criterion: the optimal excavation control parameters obtained under the control of this criterion are the combination of TBM propulsion speed and cutterhead speed that minimizes the energy consumption of the TBM under the construction requirements; The shortest construction period criterion, the optimized excavation control parameters obtained under the control of this criterion are the combination of the fastest excavation speed and cutter head speed that meets the conditions of the TBM excavation rated load.

5. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: Optimal formula for tunneling control parameters based on minimum energy consumption criterion: ν=ν(F,T) r=r(F,T) W=[Fν(F,T)+2πTr(F,T)]t Where F is the cutterhead thrust, T is the cutterhead torque, v is the TBM propulsion speed, r is the TBM cutterhead speed, and W is the work done by the excavation load.

6. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: Optimal formula for excavation control parameters based on the shortest construction period criterion: F 额 ≥F=F(ν,r) T 额 ≥T=T(ν,r) In the formula, F 额 is the rated thrust, T 额 is the rated torque, F is the cutter head thrust, T is the cutter head torque, v is the TBM propulsion speed, and r is the TBM cutter head speed.

7. The TBM intelligent decision-making method considering uniaxial compressive strength according to claim 1 is characterized in that: When the propulsion speed v and the cutter head speed r change, when the degree of change exceeds the allowable value, the excavation control parameters are readjusted.

8. A TBM intelligent decision-making system considering uniaxial compressive strength, characterized in that: include: The data acquisition module is used to obtain the point load strength data of the corresponding rock during tunneling and the cutterhead data during TBM excavation; The model training module uses a recurrent neural network to train the acquired point load strength data and cutterhead data to obtain the corresponding relationship between the point load strength of the rock and the excavation load information cutterhead data; The prediction model building module builds a TBM excavation load prediction model based on the corresponding relationship between the above two data, and obtains the TBM excavation cutter head data under the point load strength of the corresponding rock to be predicted; The excavation control parameter selection module selects the excavation control parameters based on the predicted cutterhead data of the TBM excavation in the stable section of the excavation cycle and based on the minimum energy consumption criterion or the shortest construction period criterion.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the specific steps of the TBM intelligent decision-making method considering uniaxial compressive strength described in any one of claims 1-7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the specific steps of a TBM intelligent decision-making method considering uniaxial compressive strength as described in any one of claims 1-7 are implemented.

Images