CN112733432B - A TBM tunneling control method and system under extremely complex geological conditions - Google Patents

Abstract

The invention discloses a tunneling control method and system for TBM under extremely complex geological conditions, comprising the following steps: establishing a TBM tunneling sample database, and establishing a TBM control decision-making model based on the dynamic interaction law between TBM tunneling parameters and rock mass mechanical parameters; obtaining TBM working status information, and evaluate the TBM health status; if the TBM health status is not optimal, the TBM control decision-making model adjusts the tunneling parameters and status, so that the TBM can excavate under the optimal health status.

Description

A TBM tunneling control method and system under extremely complex geological conditions

technical field

The invention belongs to the technical field of tunnel engineering, and in particular relates to a tunneling control method and system for a TBM under extremely complex geological conditions.

Background technique

The statements herein merely provide background information related to the present invention and do not necessarily constitute prior art.

In recent years, the construction of long TBM tunnels has shifted to remote areas. These areas are vast and have extremely complex geological conditions. There are complex geological hazards such as granite alteration zones, active fault zones, high ground pressure, and large-scale fracture zones. The rapid excavation of TBM has encountered unprecedented challenges. Problems such as slow excavation and frequent machine jams have plagued the construction progress of the project. Improving the excavation efficiency of TBM under extremely complex geological conditions is an inevitable requirement for major engineering construction.

The selection and control of tunneling parameters in TBM construction basically rely entirely on human experience to make judgments and adjustments. Some other TBM tunneling intelligent systems are improved on the matching of TBM tunneling parameters and rock mass state parameters, and some satisfactory results have been achieved. , but these methods are only applicable to the uniform distribution of rock mass mechanical parameters and relatively constant rock mass mechanical parameters. Extremely complex geological conditions have the following two characteristics:

1. The mechanical parameters of the rock mass are unevenly distributed. The simplest example is soft and hard interbedded rock mass, but under extremely complex geological conditions, various possible situations will appear in the distribution of mechanical parameters of the rock mass at the face, which leads to the fact that a certain rock mass at the face It is very inaccurate to determine the tunneling parameters of TBM by mechanical parameters, and it is likely to have negative effects.

Second, the mechanical parameters of the rock mass are not constant. Usually, the mechanical parameters of the rock mass of the tunnel face are relatively constant when the same rock formation is excavated. That is to say, when the lithology does not change greatly, the mechanical parameters of the rock mass are basically the same. However, under extremely complex geological conditions, the mechanical parameters of rock mass of the same lithology will change abruptly. For example, in the granite alteration zone, the mechanical parameters of rock mass may change from those close to those of granite to those after sandification. huge.

Under the above circumstances, it is particularly important to research and invent a TBM high-efficiency tunneling system suitable for extremely complex geological conditions.

Contents of the invention

In view of the deficiencies in the prior art, the object of the present invention is to provide a method and system for controlling tunneling of TBM under extremely complex geological conditions. The method fully improves the tunneling efficiency of TBM for extremely complex geological conditions.

In order to achieve the above object, the present invention is achieved through the following technical solutions:

In a first aspect, an embodiment of the present invention provides a method for controlling tunneling of a TBM under extremely complex geological conditions, including the following steps:

Establish a TBM excavation sample database, and establish a TBM control decision-making model based on the dynamic interaction law between TBM excavation parameters and rock mass mechanical parameters;

Obtain the TBM working status information and evaluate the TBM health status; if the TBM health status is not optimal, the TBM control decision-making model adjusts the tunneling parameters and status to make the TBM excavate in an optimal healthy status.

As a further technical solution, the data information of the TBM excavation sample database includes TBM excavation parameters and rock mass mechanics parameter information.

As a further technical solution, the process of obtaining the dynamic interaction law between TBM tunneling parameters and rock mass mechanical parameters is as follows:

By using the deep learning algorithm to analyze the relationship between the rock mass mechanical parameters and the TBM tunneling parameters during the TBM tunneling process, the dynamic interaction law between the TBM tunneling parameters and the rock mass mechanical parameters is established.

As a further technical solution, the process of obtaining mechanical parameters of rock mass is as follows:

The mechanical parameters of the rock mass are obtained through the rock mass database corresponding to the TBM excavation parameters; the mechanical parameters of the rock mass are obtained through the statistical analysis of the size distribution of the diameter of the muck particles through image acquisition; the mechanical parameters of the rock mass obtained by the two methods are analyzed by the artificial neural network The parameters are weighted and fused to obtain the real solution of the mechanical parameter distribution of the tunnel face rock mass.

As a further technical solution, the TBM working state information includes cutterhead thrust, cutterhead torque, penetration, and propulsion speed.

As a further technical solution, the TBM health status evaluation grades are divided into excellent, good, medium and poor:

The evaluation of TBM health status is carried out according to the set parameter threshold interval. If it is within the first set threshold interval, the evaluation grade is excellent; if it is within the second set threshold interval, the evaluation grade is good; if it is within the third set threshold interval, the evaluation grade is good; , the evaluation level is medium; if it is within the fourth set threshold interval, the evaluation level is poor.

As a further technical solution, if the health status of the TBM is good, the unit where the TBM has a problem is determined according to the TBM working status information, and the corresponding tunneling parameters are adjusted to obtain the optimal solution for the current TBM tunneling parameters and TBM status adjustment.

As a further technical solution, if the health status of the TBM is moderate or poor, control the TBM to stop the excavation, analyze various information, and continue the excavation after the problem is solved.

As a further technical solution, collect TBM excavation information, rock mass mechanical parameter information, grouting information, and slag image information, establish a TBM construction information database, and conduct deep learning training on the information of non-optimal health status of TBM, and re-fit the TBM The optimal solution of the relationship between the tunneling parameters and the rock mass mechanical parameters, and adjust the tunneling parameters of the TBM under the same conditions.

In the second aspect, the embodiment of the present invention also provides a TBM tunneling control system under extremely complex geological conditions, including:

The model establishment module is used to establish the TBM excavation sample database, and establishes the TBM control decision-making model according to the dynamic interaction law between the TBM excavation parameters and the rock mass mechanical parameters;

The state evaluation module is used to obtain TBM working state information and evaluate the TBM health state; if the TBM health state is not optimal, the TBM control decision model adjusts the tunneling parameters and state to make the TBM tunnel in an optimal healthy state.

The beneficial effects of the above-mentioned embodiments of the present invention are as follows:

The method of the present invention makes full use of the advantages of big data and intelligent platforms. On the one hand, various data of TBM construction can be collected and used as important data support for future TBM tunneling parameter adjustment. Intelligent; on the other hand, based on the cloud intelligent platform, various data during the TBM construction process are shared in real time to realize remote monitoring of the TBM construction process, and the health status of each part of the TBM can be transmitted to the mobile terminal of the relevant responsible person in real time, realizing real intelligence construction.

The method of the present invention proposes an acquisition mechanism for the distribution of rock mass mechanics parameters, combines the TBM dregs image acquisition technology with the TBM tunneling parameters and the interaction law of rock mass mechanics parameters, and uses an intelligent algorithm to combine the two, so that the TBM Real-time monitoring of mechanical parameter distribution of rock mass in front face. This method can ensure that the TBM automatically takes effective corresponding measures when it encounters extremely complex geological conditions, and prevents serious accidents such as TBM jamming.

Description of drawings

The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations to the present invention.

Fig. 1 is a schematic diagram of the principle of a tunneling control method according to one or more embodiments of the present invention;

In the figure: In order to show the position of each part, the mutual distance or size is exaggerated, and the schematic diagram is only for illustration.

Detailed ways

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be noted that the terminology used here is only for describing specific embodiments, and is not intended to limit exemplary embodiments according to the present invention. As used herein, unless the invention clearly states otherwise, the singular form is also intended to include the plural form. In addition, it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, their Indicate the presence of features, steps, operations, means, components and/or combinations thereof;

For the convenience of description, if the words "up", "down", "left" and "right" appear in the present invention, it only means that they are consistent with the directions of up, down, left and right in the drawings themselves, and do not limit the structure. It is for the convenience of describing the present invention and simplifying the description, but does not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.

Explanation of terms: if the terms "installation", "connection", "connection", "fixation" etc. appear in the present invention, they should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral body; It can be a mechanical connection, or an electrical connection, a direct connection, or an indirect connection through an intermediary, or an internal connection between two elements, or an interaction relationship between two elements. For those of ordinary skill in the art, In other words, the specific meanings of the above terms in the present invention can be understood according to specific situations.

As introduced in the background technology, the selection and control of tunneling parameters in TBM construction basically rely entirely on human experience to make judgments and adjustments. Some other TBM tunneling intelligent systems are improved on the matching of TBM tunneling parameters and rock mass state parameters , and achieved some satisfactory results, but these methods are only applicable to the case where the rock mass mechanical parameters are evenly distributed and the rock mass mechanical parameters are relatively constant. Once the TBM encounters extremely complex geological conditions, a series of major problems will appear. In order to solve the above technical problems, the present invention proposes a tunneling control method and system for TBM under extremely complex geological conditions.

Example 1:

In a typical implementation of the present invention, as shown in Figure 1, a high-efficiency excavation method for TBM under extremely complex geological conditions based on a cloud intelligent platform is proposed. The cloud intelligent platform is based on various deep learning and machine learning frameworks The advanced artificial intelligence cloud platform has powerful hardware resource management capabilities and efficient model development capabilities. With the big data information of TBM construction as data support, it can quickly and efficiently calculate the distribution of rock mass mechanical parameters in front of the tunnel face.

The steps of this method are:

Establish a TBM excavation sample database based on TBM excavation parameter information and rock mass mechanical parameter information, and combine high-definition muck image acquisition technology to obtain the true solution of the distribution of rock mass mechanical parameters on the tunnel face;

Establish TBM control decision-making model and TBM tunneling big data cloud intelligent platform of TBM online monitoring system, determine TBM tunneling parameters and working status according to rock mass mechanical parameter distribution and TBM health status, and send specific information to the smart terminal;

When the TBM health evaluation is not optimal, the cloud intelligence platform will conduct deep learning on relevant information, re-fit the relevant data, and add the updated information of the interaction rule as sample data to the sample database.

Among them, before establishing the TBM excavation sample database, TBM information collection is carried out, including the collection of TBM excavation parameters, TBM current working status information, rock mass mechanics parameter information, and adverse geological body information. These information constitute the basic information source of the TBM excavation cloud intelligent platform .

Through the collection of various information, the TBM excavation sample database is established, and at the same time, the dynamic interaction relationship between the rock mass mechanical parameters and the TBM excavation parameters during the TBM excavation process is obtained by using the deep learning algorithm, and the dynamic interaction law between the TBM excavation parameters and the rock mass mechanical parameters is established. , the TBM control decision-making model is established based on this, and the TBM control decision-making model can control and adjust the tunneling parameters.

It should be noted that the interaction law is not static. With the increase of TBM excavation distance, the sample database of the dynamic interaction relationship between TBM excavation parameters and rock mass mechanical parameters will gradually increase, and the deep learning algorithm will be based on more learning samples. The interaction law between rock mass mechanical parameters and TBM tunneling parameters is constantly adjusted to achieve the purpose of dynamic interaction.

In an optional embodiment, according to the TBM excavation database and the muck image acquisition technology, the real solution of the mechanical parameter distribution of the tunnel face rock mass is obtained through artificial neural network calculation.

Specifically, the collection of TBM excavation parameters is carried out through the TBM online monitoring system; the TBM online monitoring system has a collection terminal, and the collection terminal includes 10 sensors distributed in the TBM, 4 of which are located in the cutter head and the cutter head drive system. , 2 are located in the support system, 2 are located in the propulsion system, and 2 are located in the hydraulic and electrical control system. Through the setting of multiple sensors, the collection of TBM tunneling parameters can be realized.

The current working status information of the TBM is obtained through the information terminal that comes with the TBM. The TBM is equipped with a master control room, and the information terminal has a summary of the working status information of the TBM, including cutterhead thrust (F), cutterhead torque (T), penetration ( P), propulsion speed (R).

The rock mass mechanical parameter information is obtained through the real-time information collection terminal. The terminal obtains the rock mass mechanical parameter distribution in two ways, one is to judge the overall strength of the rock mass mechanical parameter through the rock mass database corresponding to the TBM excavation parameters, and the other is to judge the overall strength of the rock mass mechanical parameter through the high-definition dregs Image acquisition technology collects and analyzes the scale distribution of muck particle diameters to obtain the distribution of mechanical parameters of the rock mass at the face of the tunnel.

In a further implementation plan, the cloud intelligence platform realizes multiple functions of data collection, online monitoring, data analysis, decision-making, and information submission at the same time, truly realizing the intelligent and efficient excavation of TBM; its TBM online monitoring system will evaluate the health status of TBM , the evaluation grades are divided into four grades: excellent, good, medium, and poor. In the case of non-excellent, the cloud intelligence platform will conduct deep learning on relevant data and take corresponding countermeasures.

In this embodiment, the smart terminal includes various clients of the cloud platform, including a PC terminal and a smart phone terminal, and the relevant information of the cloud intelligent platform can be synchronized at all clients, and technicians with different authorizations and authentications have different operating rights, thereby Realize remote monitoring and control of TBM information; conduct human-computer interaction on various collected information and TBM decision-making suggestions.

In order to enable those skilled in the art to understand the technical solution of the present invention more clearly, the technical solution of the present invention will be described in detail below in conjunction with specific embodiments.

The present invention provides a TBM tunneling method under extremely complex geological conditions based on a cloud intelligent platform, and its specific implementation steps are:

Collect TBM excavation parameters and rock mass mechanical parameters information, and establish TBM excavation sample database, analyze the relationship between TBM excavation parameters and rock mass mechanical parameters (that is, TBM rock-machine relationship) by using deep learning algorithm, and establish TBM The dynamic interaction law between the tunneling parameters and the rock mass mechanical parameters, so as to establish the TBM control decision-making model, in order to adjust the tunneling parameters; in this step, the TBM tunneling parameters are obtained by monitoring the sensors installed in the TBM; Statistical analysis is carried out on the size distribution of the particle diameter of the muck, and classification is made according to the range of the current tunneling parameters of the TBM. Finally, the rock mass mechanical parameters of the current tunnel face are calculated based on the particle diameter distribution of the muck through the deep learning algorithm.

TBM rock-mechanical relationship and slag particle identification can obtain different rock mass mechanical parameters, because the TBM rock-mechanical relationship can predict the corresponding rock mass mechanical parameters, and slag particle identification can also obtain the corresponding rock mass mechanical parameters. The weight of the two methods is determined by the network, and the rock mass mechanical parameters obtained by the two methods are weighted and fused, and finally the real solution of the rock mass mechanical parameter distribution of the tunnel face is obtained.

According to the obtained real solution of the distribution of rock mechanics parameters, the cloud intelligent platform will automatically adjust the TBM tunneling parameters. The current health status is evaluated, and the evaluation grades are divided into excellent, good, medium, and poor, which are represented by green, yellow, orange, and red, respectively. The TBM online monitoring system has a data analysis terminal, which performs data processing, analysis, comparison and verification, and judges the current health status of the TBM through the results of data processing and analysis, and makes a health evaluation.

The evaluation of TBM health status is carried out according to the set parameter threshold interval. If it is within the first set threshold interval, the evaluation grade is excellent; if it is within the second set threshold interval, the evaluation grade is good; if it is within the third set threshold interval, the evaluation grade is good; , the evaluation level is medium; if it is within the fourth set threshold interval, the evaluation level is poor.

If the current health status of the TBM is excellent, there is no need to adjust the parameters.

If the health status of the TBM is good, the cloud intelligence platform will analyze the data of the TBM online monitoring system to determine which units of the TBM have problems, and adjust the relevant parameters to obtain the optimal solution for the current TBM tunneling parameters and TBM status adjustment. The prompt information will be sent to the PC and mobile terminals of the cloud intelligence platform to attract the attention of construction workers. Specifically, when the TBM status is good, the information terminal of the TBM tunneling system will prompt several working status information such as cutterhead thrust (F), cutterhead torque (T), penetration (P), and propulsion speed (R). The specific data of the parameters, and will prompt which parameter has a problem. The TBM control decision-making model will automatically adjust the corresponding tunneling parameters and status according to the data of the TBM tunneling system information terminal, and finally keep the health status of the TBM at "excellent". status.

The human-computer interaction interface will be displayed on the PC terminal and the mobile terminal, and the construction personnel can directly see the current health status of the TBM, and can view the specific parameters of each sensor of the TBM.

If the health status of the TBM is medium or poor, the TBM will stop the excavation, analyze the information, and summarize the reasons. The relevant information will be sent to the relevant personnel through the cloud intelligent platform. After the problem is solved, the TBM construction leader will issue an excavation order .

The cloud intelligence platform will collect all construction information, including excavation information, rock parameter information, grouting information, and slag image recognition information, etc., establish a TBM construction information database, and conduct deep learning training on the information of non-optimal health status of TBM, and re-design Combined with the optimal solution of the TBM rock-machine relationship, adjust the tunneling parameters of the TBM when encountering similar situations. Specifically, the cloud intelligence platform will automatically adjust the TBM excavation parameters to keep the state as "excellent". Every adjustment, whether it fails or succeeds, is a learning sample. As the number of samples increases, the cloud intelligence platform uses the deep learning framework The adjustment success rate of the established TBM control decision-making model will be higher and higher, so that the TBM will basically remain in the "optimal" state.

During the TBM excavation process, various data are collected and analyzed, data with obvious errors are eliminated, and suitable data samples are retained to form a large data sample library. The cloud intelligence platform adds a variety of functions on the basis of the existing TBM intelligence platform, such as judging TBM failures, adjusting related parameters, and sending prompt information to the PC and mobile terminals of the cloud intelligence platform. The cloud intelligence platform conducts data mining through various deep learning and machine learning frameworks.

Example 2:

This embodiment provides a TBM tunneling control system under extremely complex geological conditions, including:

The model establishment module is used to establish the TBM excavation sample database, and establishes the TBM control decision-making model according to the dynamic interaction law between the TBM excavation parameters and the rock mass mechanical parameters;

The state evaluation module is used to obtain TBM working state information and evaluate the TBM health state; if the TBM health state is not optimal, the TBM control decision model adjusts the tunneling parameters and state to make the TBM tunnel in an optimal healthy state.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (8)

1. A tunneling control method under extremely complex geological conditions of a TBM, is characterized in that, comprises the following steps: Establish a TBM excavation sample database, and establish a TBM control decision-making model based on the dynamic interaction law between TBM excavation parameters and rock mass mechanical parameters; Obtain the TBM working status information and evaluate the TBM health status; if the TBM health status is not optimal, the TBM control decision-making model adjusts the tunneling parameters and status, so that the TBM can excavate under the optimal health status; The process of obtaining the dynamic interaction law between TBM tunneling parameters and rock mass mechanical parameters is as follows: By using the deep learning algorithm to analyze the relationship between the rock mass mechanical parameters and the TBM tunneling parameters during the TBM tunneling process, the dynamic interaction law between the TBM tunneling parameters and the rock mass mechanical parameters is established; The process of obtaining mechanical parameters of rock mass is as follows: The mechanical parameters of the rock mass are obtained through the rock mass database corresponding to the TBM excavation parameters; the mechanical parameters of the rock mass are obtained through the statistical analysis of the size distribution of the diameter of the muck particles through image acquisition; the mechanical parameters of the rock mass obtained by the two methods are analyzed by the artificial neural network The parameters are weighted and fused to obtain the real solution of the mechanical parameter distribution of the tunnel face rock mass. 2. The tunneling control method of TBM under extremely complex geological conditions as claimed in claim 1, wherein the data information of the TBM tunneling sample database includes TBM tunneling parameters and rock mass mechanics parameter information. 3. The tunneling control method of TBM under extremely complex geological conditions according to claim 1, wherein the TBM working state information includes cutterhead thrust, cutterhead torque, penetration, and propulsion speed. 4. The tunneling control method under extremely complex geological conditions of TBM as claimed in claim 1, characterized in that, the TBM health status evaluation grades are divided into excellent, good, medium and poor: The evaluation of TBM health status is carried out according to the set parameter threshold interval. If it is within the first set threshold interval, the evaluation grade is excellent; if it is within the second set threshold interval, the evaluation grade is good; if it is within the third set threshold interval, the evaluation grade is good; , the evaluation level is medium; if it is within the fourth set threshold interval, the evaluation level is poor. 5. The tunneling control method of TBM under extremely complex geological conditions as claimed in claim 4, characterized in that, if the health status of the TBM is good, the unit where the TBM has a problem is determined according to the TBM working state information, and the corresponding tunneling parameters are adjusted to obtain the current TBM The optimal solution for tunneling parameters and TBM state adjustment. 6. The tunneling control method of TBM under extremely complex geological conditions as claimed in claim 4, characterized in that, if the health status of the TBM is medium or poor, the TBM is controlled to stop the tunneling, and the information is analyzed, and the problem continues after the problem is solved. excavation. 7. the tunneling control method under the extremely complex geological conditions of TBM as claimed in claim 4, is characterized in that, collect TBM tunneling information, rock mass mechanics parameter information, grouting information, muck image information, set up TBM construction information base, and Carry out deep learning training on the non-optimal health status information of TBM, re-fit the optimal solution of the relationship between TBM tunneling parameters and rock mass mechanical parameters, and adjust TBM tunneling parameters under the same conditions. 8. A TBM tunneling control system under extremely complex geological conditions, characterized in that it includes: The model establishment module is used to establish the TBM excavation sample database, and establishes the TBM control decision-making model according to the dynamic interaction law between the TBM excavation parameters and the rock mass mechanical parameters; The state evaluation module is used to obtain TBM working state information and evaluate the TBM health state; if the TBM health state is not optimal, the TBM control decision model adjusts the tunneling parameters and state, so that the TBM can excavate in an optimal healthy state; The process of obtaining the dynamic interaction law between TBM tunneling parameters and rock mass mechanical parameters is as follows: By using the deep learning algorithm to analyze the relationship between the rock mass mechanical parameters and the TBM tunneling parameters during the TBM tunneling process, the dynamic interaction law between the TBM tunneling parameters and the rock mass mechanical parameters is established; The process of obtaining mechanical parameters of rock mass is as follows: The mechanical parameters of the rock mass are obtained through the rock mass database corresponding to the TBM excavation parameters; the mechanical parameters of the rock mass are obtained through the statistical analysis of the size distribution of the diameter of the muck particles through image acquisition; the mechanical parameters of the rock mass obtained by the two methods are analyzed by the artificial neural network The parameters are weighted and fused to obtain the real solution of the mechanical parameter distribution of the tunnel face rock mass.

Images