Tunneling state monitoring method, system and equipment for TBM (Tunnel Boring Machine) and medium

Abstract

The invention discloses a TBM tunneling state monitoring method, system and device and a medium, and relates to the technical field of TBM tunnel geological recognition and cutterhead maintaining.A plurality of different types of accelerometers are arranged on a cutterhead of a TBM to obtain vibration data of the TBM; establishing independent response models for the vibration data and TBM heading machine operation data, cutterhead data, geological data and construction data to obtain a nonlinear relationship between the vibration data and each data parameter; meanwhile, a comprehensive response model is established according to the nonlinear relation so as to establish a mutual feedback mechanism between the vibration data and the influence factors, and the specific numerical range of each influence factor is calculated according to the vibration data, so that the tunneling state of the TBM is judged; a plurality of accelerometers designed by the invention are slightly influenced by the metal cutterhead, and meanwhile, the tunneling state of the TBM can be judged according to a mutual feedback mechanism between obtained vibration data and related data.

Description

Technical Field

[0001] The present invention relates to the technical field of TBM tunnel geological identification and cutterhead maintenance, and in particular to a TBM tunneling machine excavation state monitoring method, system, equipment and medium. Background Art

[0002] During TBM tunnel construction, especially for long-distance and deep tunnels, it is often difficult to fully identify the adverse geological conditions along the line in the early stage of construction, such as weak fracture zones, joint development zones, faults and karst fissures. These factors can easily lead to serious accidents such as landslides, water inrush and mud inrush during construction, posing a great threat to construction safety and may even cause casualties. On the other hand, it is difficult to monitor the cutter of the TBM cutterhead in real time during TBM operation, and the cutter is often damaged while the TBM continues to excavate, which greatly reduces the efficiency of TBM excavation and causes serious damage to the TBM cutterhead.

[0003] In addition, the rapid excavation speed of TBM requires that the identification of geological bodies must be fast, real-time and high-precision to adapt to the rapid changes in geological conditions in front of the face. At present, during the excavation process of TBM, the metal cutter head of the TBM will seriously interfere with electromagnetic detection. At the same time, the TBM occupies a large space in the face area, almost filling the entire tunnel section, which increases the difficulty of collecting geological data by electromagnetic detection. At present, the status of TBM is usually judged based on each data separately, which makes it difficult to judge through the relationship between TBM machine parameters and surrounding rock parameters, making it difficult to accurately obtain the real-time status information of the TBM. Summary of the invention

[0004] The embodiments of the present invention provide a method, system, device and medium for monitoring the excavation status of a TBM tunneling machine, which can solve the problem in the prior art that it is difficult to judge through the relationship between TBM machine parameters and surrounding rock parameters, and thus it is difficult to accurately obtain the real-time status information of the TBM tunneling machine.

[0005] The embodiment of the present invention provides a method for monitoring the excavation status of a TBM, comprising the following steps:

[0006] Obtain the cutterhead data of the TBM before the TBM starts to operate; obtain the geological data and construction data of the geological body to be mined by the TBM; obtain the vibration data of the TBM in the x, y and z dimensions during the operation of the TBM; obtain the operation data of the TBM during the operation of the TBM;

[0007] Determine the nonlinear response relationship between vibration data and operating data, the nonlinear response relationship between vibration data and cutterhead data, the nonlinear response relationship between vibration data and geological data, and the nonlinear response relationship between vibration data and construction data;

[0008] Determine the integrated response model of vibration data with operational data, cutterhead data, geological data and construction data;

[0009] According to each nonlinear response relationship and the comprehensive response model, the influencing factors of the vibration data are obtained; when the real-time vibration data changes, the change state of the real-time influencing factors is obtained; when the real-time influencing factors change, the change state of the real-time vibration data is obtained; and according to the mutual change state between the vibration data and the influencing factors, a mutual feedback mechanism between the vibration data and the influencing factors is formed; wherein the influencing factors include operation data, cutter head data, geological data and construction data;

[0010] According to the feedback mechanism between vibration data and influencing factors, the numerical range of each influencing factor is obtained through real-time vibration data to judge the excavation status of the TBM.

[0011] Preferably, the step of obtaining vibration data of the TBM in the x, y and z dimensional directions during the operation of the TBM includes:

[0012] Two MEMS accelerometers and two piezoelectric accelerometers are arranged at the same interval on the rear side of the TBM cutterhead. After the TBM starts running, the MEMS accelerometers and piezoelectric accelerometers collect vibration data at different positions of different cutterheads.

[0013] The vibration data includes: vibration signals in the three dimensions of x, y and z during the operation of the TBM, the time history of the acceleration value changing with time, the ring variance, the maximum acceleration of each ring, the root mean square acceleration of each ring, the crest factor and the skewness.

[0014] Preferably, the operation data, cutterhead data, geological data and construction data of the TBM are respectively:

[0015] The TBM operation data includes: the cutter head thrust, cutter head speed, cutter head torque, penetration, excavation speed, effective support force of the gripper and total thrust of the TBM;

[0016] The TBM cutterhead data includes: cutterhead replacement time, loss status, damage type and damage location;

[0017] The geological data of the TBM include: uniaxial compressive strength of rock, tensile strength of rock, wear resistance of rock, brittleness of rock, rock mass integrity coefficient, groundwater status and engineering geological conditions of surrounding rock;

[0018] The TBM construction data includes: construction progress, slag discharge data, advance forecast information, ambient temperature and ambient humidity.

[0019] Preferably, the determining of the nonlinear response relationship between the vibration data and the operation data, the nonlinear response relationship between the vibration data and the cutter head data, the nonlinear response relationship between the vibration data and the geological data, and the nonlinear response relationship between the vibration data and the construction data comprises:

[0020] A recurrent neural network model RNN is constructed, and the recurrent neural network model RNN is trained according to the vibration data and operation data, cutter head data, geological data and construction data of the TBM tunneling machine, respectively, to obtain response models of the vibration data and operation data, cutter head data, geological data and construction data;

[0021] In the response models corresponding to vibration data, operation data, cutterhead data, geological data and construction data, the Pearson correlation coefficient statistical method is used to calculate the correlation between each parameter variable of vibration data and each parameter variable of TBM operation data, each parameter variable of cutterhead data, each parameter variable of geological data and each parameter variable of construction data;

[0022] Based on the correlation and through the random forest machine learning model, the nonlinear response relationships between vibration data and operation data, vibration data and cutterhead data, vibration data and geological data, and vibration data and construction data are established.

[0023] Preferably, the forming of a feedback mechanism between vibration data and influencing factors includes:

[0024] According to the vibration and operation data of the TBM, the cutter head data, the geological data and the construction data, the recurrent neural network model RNN is trained to obtain a comprehensive response model;

[0025] According to the real-time operation data, cutterhead data, geological data and construction data of the TBM during operation, and the nonlinear response relationship between the vibration data of the TBM and the operation data, cutterhead data, geological data and construction data, the comprehensive response model is used to set the data with a threshold value higher than the set threshold value among the data of the characteristic parameters of the control vibration data as the influencing factors of the characteristic parameters of the control vibration data;

[0026] The influencing factors are part of the operating data, cutterhead data, geological data and construction data;

[0027] The interaction process between the vibration data characteristic parameters and the influencing factors during the operation of the TBM tunneling machine is obtained, and the interaction process is set as a feedback mechanism between the vibration data characteristic parameters and the influencing factors.

[0028] The embodiment of the present invention further provides a TBM tunneling machine excavation state monitoring system, comprising:

[0029] The vibration monitoring module is used to obtain the cutter head data of the TBM before the TBM starts to operate; obtain the geological data and construction data of the geological body to be mined by the TBM; obtain the vibration data of the TBM in the x, y and z dimensions during the operation of the TBM; obtain the operation data of the TBM during the operation of the TBM;

[0030] A deep learning module for determining the nonlinear response relationship between vibration data and operating data, the nonlinear response relationship between vibration data and cutterhead data, the nonlinear response relationship between vibration data and geological data, and the nonlinear response relationship between vibration data and construction data;

[0031] Determine the integrated response model of vibration data with operational data, cutterhead data, geological data and construction data;

[0032] According to each nonlinear response relationship and the comprehensive response model, the influencing factors of the vibration data are obtained; when the real-time vibration data changes, the change state of the real-time influencing factors is obtained; when the real-time influencing factors change, the change state of the real-time vibration data is obtained; and according to the mutual change state between the vibration data and the influencing factors, a mutual feedback mechanism between the vibration data and the influencing factors is formed; wherein the influencing factors include operation data, cutter head data, geological data and construction data;

[0033] The early warning module is used to determine the excavation status of the TBM by obtaining the numerical range of each influencing factor through real-time vibration data based on the mutual feedback mechanism between vibration data and influencing factors.

[0034] An embodiment of the present invention further provides an electronic device, including a memory and a processor;

[0035] The memory is used to store computer programs;

[0036] The processor is used to implement the steps of the TBM tunneling machine excavation status monitoring method as described above when executing the computer program stored in the memory.

[0037] An embodiment of the present invention further provides a computer-readable storage medium, characterized in that it is used to store a computer program, and when the computer program is executed by a processor, the steps of the TBM tunneling machine excavation status monitoring method as described above are implemented.

[0038] The embodiments of the present invention provide a method, system, device and medium for monitoring the excavation status of a TBM. Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0039] The present invention arranges a plurality of different types of accelerometers on the cutterhead of a TBM to obtain vibration data of the TBM, and establishes independent response models with the vibration data, TBM operation data, cutterhead data, geological data and construction data to obtain the nonlinear relationship between the vibration data and each data parameter; and simultaneously establishes a comprehensive response model according to the nonlinear relationship, in which the influencing factors of the characteristic parameters of the vibration data are obtained according to the nonlinear relationship, and a mutual feedback mechanism between the vibration data and the influencing factors is established, and according to the mutual feedback mechanism, the specific numerical range of each influencing factor can be inferred through the vibration data, so as to judge the excavation state of the TBM. Different from the traditional technology that obtains a series of data parameters to make judgments, the present invention first establishes a nonlinear response relationship between the vibration data of the TBM during operation and various data, and then finds the influencing factors in each data that control the characteristic parameters of the vibration data under the comprehensive response model based on the nonlinear response relationship corresponding to each data and the real-time operation data, so as to establish a feedback mechanism between the vibration data and the influencing factors, so that the specific numerical range of each influencing factor can be inferred only through the vibration data, thereby judging the excavation status, unlike the traditional technology that can only make judgments after a series of parameters and analysis.

[0040] Furthermore, the multiple different types of accelerometers provided in the present invention avoid the influence of static gravity and cover normal frequency and extremely low frequency in recording frequency, thereby being able to more comprehensively reflect the vibration condition of the TBM tunneling machine. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A schematic diagram of the overall process of a TBM tunneling machine excavation status monitoring method provided by an embodiment of the present invention;

[0042] Figure 2 A schematic diagram of the system principle of a TBM tunneling machine excavation state monitoring method and system provided by an embodiment of the present invention;

[0043] Figure 3 A schematic diagram of the system principle of a TBM tunneling machine excavation state monitoring method and system provided by an embodiment of the present invention;

[0044] Figure 4 A schematic diagram of an accelerometer arranged on a cutter head of a TBM tunneling machine excavation state monitoring method and system provided in an embodiment of the present invention;

[0045] Figure 5 A schematic diagram of electronic equipment of a TBM tunneling machine excavation status monitoring method and system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present invention, so the present invention is not limited by the specific embodiments disclosed below.

[0047] See also Figure 2 An embodiment of the present invention provides a method and system for monitoring the excavation status of a TBM tunneling machine, including a vibration monitoring module 100, a data processing module 200, a database module 300, a deep learning module 400 and an early warning module 500.

[0048] The vibration monitoring module 100 is equipped with two different types of accelerometers to collect vibration signals during the operation of the TBM; the vibration monitoring module 100 controls the opening and closing of the two different types of accelerometers, so that the accelerometers record static gravity before the TBM is operated, so as to eliminate the influence of static gravity in the vibration signals during the operation of the TBM, thereby ensuring the accuracy and reliability of the recorded vibration signals.

[0049] like Figure 3 As shown, the vibration monitoring module 100 includes a MEMS accelerometer module 101 and a piezoelectric accelerometer module 102; the MEMS accelerometer module 101 is used to measure static gravity and record the extremely low frequency vibration signal of the TBM, and the piezoelectric accelerometer module 102 cannot record extremely low frequency signals, but has higher sensitivity and measurement range; each module in the MEMS accelerometer module 101 and the piezoelectric accelerometer module 102 is provided with two accelerometers, so that when one accelerometer fails, the other accelerometer can work normally, and the data recorded by the two accelerometers can verify and complement each other.

[0050] Specifically, Figure 4 As shown, two groups of accelerometers provided in the vibration monitoring module 100 are placed behind the TBM cutterhead and distributed around the TBM cutterhead to monitor the TBM vibration in real time. There are a total of 4 accelerometer sensors distributed behind the TBM cutterhead, of which A and B are MEMS accelerometers, and C and D are piezoelectric accelerometers.

[0051] The data processing module 200 is used to digitally process and record the signals from the analog accelerometer; the data processing module 200 can convert the vibration signals collected by the two accelerometer modules, and record and analyze the converted vibration signals through Simulink software. The software has signal filtering and compression functions, and preliminarily outputs the vibration data of the TBM.

[0052] The data processing module 200 includes an analog-to-digital converter module 201 and a data recording module 202; the data processing module 200 can be provided with the analog-to-digital converter module 201 and the data recording module 202, the analog-to-digital converter module 201 is used to perform analog-to-digital conversion on the signal after the vibration monitoring module 100 measures the vibration signal, and then input the digitized signal into the data recording module 202, the data recording module 202 records and analyzes the vibration data through the Simulink software, and the vibration result obtained at this time is the vibration data during the operation of the TBM, and the data is input into the database module 300 for storage and can be called by the deep learning module 400 at any time.

[0053] The database module 300 is used to collect and store all relevant data information; it includes a TBM vibration data module 301 , a geological data module 302 , a TBM operation data module 303 , a cutterhead data module 304 and a construction data module 305 .

[0054] The TBM vibration data module 301 contained in the database module 300 includes the vibration signals in the three dimensions of x, y, and z during the operation of the TBM, the time history (i.e., the change of the acceleration value over time), the ring variance (i.e., the variance of the acceleration value per rotation of the TBM cutter head), the maximum acceleration (per ring), the root mean square acceleration (per ring), the crest factor, and the skewness; the geological data module 302 includes the uniaxial compressive strength of rock, the tensile strength of rock, the wear resistance of rock, the brittleness of rock, the integrity coefficient of the rock mass, the groundwater status, and the engineering geological conditions of the surrounding rock; the TBM operation data module 303 includes the cutter head thrust, the cutter head speed, the cutter head torque, the penetration, the excavation speed, the effective support force of the support shoe, and the total thrust; the cutter head data module 304 includes the cutter head replacement time, the damage status, the damage type, and the damage location; the construction data module 305 includes the construction progress, the slag discharge data, the advance forecast information, the ambient temperature, and the ambient humidity.

[0055] The deep learning module 400 is used to establish a response relationship between vibration data and other data; it includes a data analysis module 401 and a model updating module 402.

[0056] The data analysis module 401 included in the deep learning module 400 is used to establish separate response models for the vibration data, geological data, TBM operation data, cutter head data and construction data, and clarify the significant correlation between the vibration characteristics and the parameters of each data. The working state of the TBM and the geological conditions ahead can be characterized by the vibration data; on this basis, a comprehensive response model between the vibration data and each data is established, and characteristic parameters of the influence of each related data on the vibration data are established, and the influencing factors that control the vibration parameter characteristics and the feedback mechanism between each influencing factor are found, so that the abnormal factors in the operation process of the TBM can be judged in real time through the vibration data; as the TBM continues to operate, the accumulation of various data continues to increase, and the model update module 402 will correct the response model based on all the data and the actual engineering situation revealed by the TBM excavation, so that the response model is more accurate and more in line with the actual working conditions. At the same time, the data analysis module 401 will make a real-time judgment on the operation status of the TBM based on the latest response model and the latest vibration data.

[0057] The warning module 500 is used to issue a real-time warning for abnormal situations that occur during the operation of the TBM; it includes a bad geological warning module 501, a cutterhead replacement warning module 502 and a TBM status abnormality warning module 503.

[0058] The bad geological warning module 501 included in the warning module 500 is used to predict the distribution of bad geological bodies in front of the TBM face according to the response relationship model between vibration data, geological data and TBM operation data. When the relevant parameters of the vibration data exceed the set threshold, it can be judged that there is a bad geological body in front of the face. By coupling calculation with geological data and TBM operation data, the warning level of the bad geological body in front of the face is obtained and displayed; the cutterhead replacement warning module 502 judges the damage state of the cutterhead according to the response relationship model between vibration data and cutterhead data, and judges the specific position of the damaged cutterhead through the data obtained by accelerometers at four different positions, so as to realize the cutterhead replacement warning module 502. Real-time monitoring of the disc status. When the set vibration parameter exceeds the threshold, the cutter disc replacement warning module 502 will issue and display different levels of warning information according to the specific values; the TBM abnormal status warning module 503 will judge the overall situation of the TBM according to the comprehensive response model. When the vibration data is abnormal and does not meet the warning standards of the poor geological warning module 501 and the cutter disc replacement warning module 502, it will prompt that the TBM status is abnormal. According to the specific situation of the TBM shutdown inspection, the TBM abnormal status corresponding to the vibration abnormality is judged and entered into the database module 300. When the same vibration abnormality occurs subsequently, the TBM status can be accurately judged.

[0059] Based on the response relationship model between vibration data, geological data and TBM operation data, the distribution of unfavorable geological bodies in front of the tunnel face is predicted. Through coupling calculation with geological data and TBM operation data, the early warning level of the unfavorable geological bodies in front of the tunnel face is obtained and displayed. The early warning level is divided into four levels: safe, low risk, high risk and high risk.

[0060] The damage status of the cutter disc is determined based on the response relationship model between the vibration data and the cutter disc data. The specific location of the damaged cutter disc is determined through the data obtained from accelerometers at four different positions. The warning levels include no damage, slight damage, moderate damage, and severe damage.

[0061] The overall situation of the TBM is judged based on the comprehensive response model. When the vibration data is abnormal and does not meet the warning standards of geological warning and cutter head warning, it indicates that the TBM status is abnormal. The warning level is divided into four levels: no abnormality, slight abnormality, high abnormality, and severe abnormality.

[0062] like Figure 1 As shown, the specific operation monitoring method specifically includes the following steps:

[0063] Step 1: Collect geological data, cutterhead data and construction data and enter them into the database, and perform data collection checks on the vibration monitoring module.

[0064] Step 2: After the TBM starts running, the vibration monitoring module collects vibration data in real time, and the data processing module processes and analyzes the vibration data.

[0065] Step 3: The generated vibration data is entered into the database module, and the deep learning module begins to establish various response models and make a preliminary judgment on the TBM operating status.

[0066] Step 4: Through the continuous operation of the TBM, the established response model presents the results of the adverse geology and cutterhead status ahead based on the real-time collected vibration data.

[0067] Step 5: When an abnormality occurs, the actual situation of the abnormality is entered into the database module, and the deep learning module modifies the response model according to the actual situation.

[0068] Step 6: Establish a warning level based on the revised response model and issue warnings for corresponding abnormalities through vibration data.

[0069] The present invention arranges two types of acceleration sensors, which can collect the vibration signals of the TBM more accurately, while avoiding the influence of static gravity. The recording frequency covers normal frequency and extremely low frequency, avoiding the disadvantage of traditional solutions that do not record extremely low frequency vibrations. It can reflect the vibration conditions of the TBM more comprehensively, and the judgment made on this basis is more accurate.

[0070] The present invention realizes the comprehensive integration of vibration signals with geological detection, cutterhead monitoring and TBM status monitoring, breaking through the drawbacks of traditional methods in which the functions are not interconnected and implemented separately, greatly shortening the downtime of TBM, accelerating the construction efficiency of TBM and reducing construction costs.

[0071] The present invention adopts a deep learning method to establish a response model, and at the same time updates it in real time according to the actual engineering situation, avoiding the limitation of the traditional general model that it is "not suitable for local conditions", so that the established response model can effectively collect vibration signals in soil tunnels and rock tunnels and make accurate judgments.

[0072] like Figure 5 FIG. 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, including:

[0073] A memory 1 , a processor 2 , and a computer program stored in the memory 1 and executable on the processor 2 .

[0074] When the processor 2 executes the program, the steps of a method for monitoring the excavation status of a TBM tunneling machine provided in the above embodiment are implemented.

[0075] Electronic equipment also includes:

[0076] The communication interface 3 is used for communication between the memory 1 and the processor 2 .

[0077] The memory 1 is used to store computer programs that can be run on the processor 2.

[0078] The memory 1 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0079] If the memory 1, the processor 2 and the communication interface 3 are implemented independently, the communication interface 3, the memory 1 and the processor 2 can be connected to each other through a bus and communicate with each other; the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc.; the bus can be divided into an address bus, a data bus, a control bus, etc.; for the convenience of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0080] If the memory 1, the processor 2 and the communication interface 3 are integrated on a chip, the memory 1, the processor 2 and the communication interface 3 can communicate with each other through an internal interface.

[0081] The processor 2 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0082] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for monitoring the excavation status of a TBM, characterized in that: The following steps are involved: Obtain the cutterhead data of the TBM before the TBM starts to operate; obtain the geological data and construction data of the geological body to be mined by the TBM; obtain the vibration data of the TBM in the x, y and z dimensions during the operation of the TBM; Obtaining the operation data of the TBM during operation; Determine the nonlinear response relationship between vibration data and operating data, the nonlinear response relationship between vibration data and cutterhead data, the nonlinear response relationship between vibration data and geological data, and the nonlinear response relationship between vibration data and construction data; Determine the integrated response model of vibration data with operational data, cutterhead data, geological data and construction data; According to each nonlinear response relationship and the comprehensive response model, the influencing factors of the vibration data are obtained; when the real-time vibration data changes, the change state of the real-time influencing factors is obtained; when the real-time influencing factors change, the change state of the real-time vibration data is obtained; and according to the mutual change state between the vibration data and the influencing factors, a mutual feedback mechanism between the vibration data and the influencing factors is formed; wherein the influencing factors include operation data, cutter head data, geological data and construction data; According to the feedback mechanism between vibration data and influencing factors, the numerical range of each influencing factor is obtained through real-time vibration data to judge the excavation status of the TBM.

2. A TBM excavation state monitoring method according to claim 1, characterized in that: The step of obtaining the vibration data of the TBM in the x, y and z dimensional directions during the operation of the TBM includes: Two MEMS accelerometers and two piezoelectric accelerometers are arranged at the same interval on the rear side of the TBM cutterhead. After the TBM starts running, the MEMS accelerometers and piezoelectric accelerometers collect vibration data at different positions of different cutterheads. The vibration data includes: vibration signals in the three dimensions of x, y and z during the operation of the TBM, the time history of the acceleration value changing with time, the ring variance, the maximum acceleration of each ring, the root mean square acceleration of each ring, the crest factor and the skewness.

3. A TBM excavation state monitoring method according to claim 1, characterized in that: The operation data, cutterhead data, geological data and construction data of the TBM are respectively: The TBM operation data includes: the cutter head thrust, cutter head speed, cutter head torque, penetration, excavation speed, effective support force of the gripper and total thrust of the TBM; The TBM cutterhead data includes: cutterhead replacement time, loss status, damage type and damage location; The geological data of the TBM include: uniaxial compressive strength of rock, tensile strength of rock, wear resistance of rock, brittleness of rock, rock mass integrity coefficient, groundwater status and engineering geological conditions of surrounding rock; The TBM construction data includes: construction progress, slag discharge data, advance forecast information, ambient temperature and ambient humidity.

4. A TBM excavation state monitoring method according to claim 1, characterized in that: The determining of the nonlinear response relationship between the vibration data and the operation data, the nonlinear response relationship between the vibration data and the cutter head data, the nonlinear response relationship between the vibration data and the geological data, and the nonlinear response relationship between the vibration data and the construction data includes: A recurrent neural network model RNN is constructed, and the recurrent neural network model RNN is trained according to the vibration data and operation data, cutter head data, geological data and construction data of the TBM tunneling machine, respectively, to obtain response models of the vibration data and operation data, cutter head data, geological data and construction data; In the response models corresponding to vibration data, operation data, cutterhead data, geological data and construction data, the Pearson correlation coefficient statistical method is used to calculate the correlation between each parameter variable of vibration data and each parameter variable of TBM operation data, each parameter variable of cutterhead data, each parameter variable of geological data and each parameter variable of construction data; Based on the correlation and through the random forest machine learning model, the nonlinear response relationships between vibration data and operation data, vibration data and cutterhead data, vibration data and geological data, and vibration data and construction data are established.

5. A TBM excavation state monitoring method according to claim 1, characterized in that: The feedback mechanism between the vibration data and the influencing factors is formed, including: According to the vibration and operation data of the TBM, the cutter head data, the geological data and the construction data, the recurrent neural network model RNN is trained to obtain a comprehensive response model; According to the real-time operation data, cutterhead data, geological data and construction data of the TBM during operation, and the nonlinear response relationship between the vibration data of the TBM and the operation data, cutterhead data, geological data and construction data, the comprehensive response model is used to set the data with a threshold value higher than the set threshold value among the data of the characteristic parameters of the control vibration data as the influencing factors of the characteristic parameters of the control vibration data; The influencing factors are part of the operating data, cutterhead data, geological data and construction data; The interaction process between the vibration data characteristic parameters and the influencing factors during the operation of the TBM tunneling machine is obtained, and the interaction process is set as a feedback mechanism between the vibration data characteristic parameters and the influencing factors.

6. A TBM tunneling machine excavation status monitoring system, characterized in that: include: A vibration monitoring module is used to obtain the cutterhead data of the TBM before the TBM starts running; Obtain geological data and construction data of the geological body to be mined by the TBM; obtain vibration data of the TBM in the x, y and z dimensions during operation; Obtaining the operation data of the TBM during operation; A deep learning module for determining the nonlinear response relationship between vibration data and operating data, the nonlinear response relationship between vibration data and cutterhead data, the nonlinear response relationship between vibration data and geological data, and the nonlinear response relationship between vibration data and construction data; Determine the integrated response model of vibration data with operational data, cutterhead data, geological data and construction data; According to each nonlinear response relationship and the comprehensive response model, the influencing factors of the vibration data are obtained; when the real-time vibration data changes, the change state of the real-time influencing factors is obtained; when the real-time influencing factors change, the change state of the real-time vibration data is obtained; and according to the mutual change state between the vibration data and the influencing factors, a mutual feedback mechanism between the vibration data and the influencing factors is formed; wherein the influencing factors include operation data, cutter head data, geological data and construction data; The early warning module is used to determine the excavation status of the TBM by obtaining the numerical range of each influencing factor through real-time vibration data based on the mutual feedback mechanism between vibration data and influencing factors.

7. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer programs; The processor is used to implement the steps of a TBM tunneling machine excavation status monitoring method as described in any one of claims 1 to 5 when executing the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the steps of a method for monitoring the excavation status of a TBM tunneling machine as described in any one of claims 1 to 5.

Images