An adaptive planning method and equipment for tunnel boring machine cross-section cutting trajectory

Abstract

This invention discloses an adaptive planning method and device for the cross-section cutting trajectory of a tunneling machine. The method monitors the position coordinates of the tunneling machine in the roadway measurement coordinate system to ensure accurate transformation between the machine coordinate system and the roadway measurement coordinate system. It collects the position information of the cutting head to ensure accurate cutting head coordinates. The D-H method is used to calculate the position coordinates of the cutting head's center of gravity in the machine coordinate system, and the transformation between the roadway measurement coordinate system and the machine coordinate system is realized. Finally, a Long Short-Time Memory (LSTM) network is used for adaptive planning of the cross-section cutting trajectory. The cutting trajectory display system visualizes the cutting trajectory coordinates in real time, achieving safe, efficient, and reliable operation of the cutting operation. This invention significantly improves the automation level of tunneling machine cutting operations, reduces manual intervention, and enhances work efficiency and safety.

Description

Technical Field

[0001] This invention belongs to the field of tunneling machine cutting planning technology, specifically relating to an adaptive planning method and equipment for tunneling machine cross-section cutting trajectory. Background Technology

[0002] Cantilever roadheaders are integrated mechanized equipment that combines cutting, loading, traveling, and operation functions. They are mainly used for cutting underground rock, coal, or semi-coal-rock roadways of arbitrary cross-sections. Currently, geological hazards (roof falls, gas outbursts, water outbursts, etc.) and harsh working conditions (high temperature, high humidity, high dust, etc.) at the tunneling face seriously threaten the health of underground workers and restrict the safe and efficient operation of coal mine tunneling. Therefore, intelligent coal mining is the core technological support and inevitable path for the high-quality development of the coal industry. However, as an important part of intelligent tunneling operations, the cutting trajectory planning of roadheaders still suffers from problems such as unreasonable cutting trajectory planning and inability to adapt to complex working conditions. Summary of the Invention

[0003] The present invention aims to improve the automation level of tunneling machine cutting operations, reduce manual intervention, and improve work efficiency and safety.

[0004] The first objective of this invention is to provide the following technical solution: a multi-source data sampling method for tunneling machines under a time network framework, comprising: Acquire historical monitoring data of the tunnel boring machine's position and orientation, and calculate the historical coordinate data of the tunnel boring machine based on the historical monitoring data of the tunnel boring machine's position and orientation; An adaptive planning model for the cutting trajectory of a tunnel boring machine (TBM) is constructed based on an LSTM neural network, and the model is trained using historical coordinate data of the TBM. Real-time tunneling machine posture monitoring data is collected and the corresponding tunneling machine coordinate data is calculated. This data is then input into the trained adaptive planning model for the tunneling machine's cross-section cutting trajectory. The output coordinate data of the tunneling machine's cutting trajectory is used as the adaptive planning result for the tunneling machine's cross-section cutting trajectory.

[0005] Furthermore, when acquiring historical monitoring data of the tunnel boring machine's (TBM) posture, the historical monitoring data includes historical monitoring data of the machine's fuselage posture and historical monitoring data of the cutting head posture; among which, The inertial navigation device of the tunneling machine is used to acquire historical information on the heading angle, pitch angle and roll angle of the tunneling machine. The total station device of the tunneling machine is used to acquire historical data on the distance of the tunneling machine relative to the centerline of the roadway and the distance traveled, which are used as historical monitoring data of the machine's posture. Historical data on the displacement of the cutting arm's lifting, swinging, and telescopic cylinders are acquired using the multi-channel cylinder displacement sensors of the tunneling machine, serving as historical monitoring data for the cutting head's posture.

[0006] Furthermore, based on the tunneling machine's pose monitoring data, the tunneling machine's coordinate data is calculated, including: Construct a spatial coordinate system for tunnel measurement and a spatial coordinate system for the tunnel boring machine; The position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system are obtained. The position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system are calculated through coordinate system transformation and used as the coordinate data of the tunneling machine.

[0007] Furthermore, a spatial coordinate system for tunnel measurement and a spatial coordinate system for the tunnel boring machine are constructed, including: Construct a spatial coordinate system for tunnel measurement; wherein, the X-axis of the ideal spatial coordinate system coincides with the tunnel design centerline and points to the tunnel cross-section, the Z-axis points to the tunnel roof, and the plane formed by the X-axis and Y-axis is the tunnel floor plane; Construct a spatial coordinate system for the tunneling machine; the spatial coordinate system for the tunneling machine includes the coordinate system of the tunneling machine body, the coordinate system of the rotary table, the coordinate system of the lifting and rotating center, the coordinate system of the telescopic cylinder, and the coordinate system of the cutting head; The principle for establishing each coordinate system is as follows: the Z-axis of the coordinate system is consistent with the rotation axis of each joint, the Y-axis points to the next moving joint, and the X-axis is determined by the right-hand rule.

[0008] Furthermore, the position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system are obtained. The position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system are then calculated through coordinate system transformation, including: Initialize to ensure all devices and systems in the tunneling machine are in normal working order; Obtain the current coordinates of the center of gravity of the tunnel boring machine in the roadway measurement coordinate system. x 2, y 2, z 2); Obtain the displacement d1 of the boom lifting cylinder and the displacement of the swing cylinder of the tunneling machine. d 2. Displacement of telescopic hydraulic cylinder d Furthermore, based on the mechanical structure characteristics and parameters of the tunneling machine, the lifting and rotating angle α of the cutting arm and the horizontal rotation angle β of the cutting arm were calculated. Using the DH method, a position model of the cutting head center in the tunneling machine's body coordinate system is calculated based on the analysis methods of robotics. The coordinates of the cutting head's center of gravity in the body coordinate system are also obtained. x 1, y 1, z 1); By transforming the tunnel measurement coordinate system and the machine body coordinate system, the position coordinates (x, y, z) of the center of gravity of the tunneling machine's cutting head in the tunnel measurement coordinate system are calculated.

[0009] Furthermore, based on an LSTM neural network, an adaptive planning model for the tunnel boring machine's cross-section cutting trajectory is constructed, and the model is trained using historical coordinate data of the tunnel boring machine, including: A sample set was constructed using historical coordinate data of the center of gravity of the tunnel boring machine's cutting head in the roadway measurement coordinate system. The cutting head position coordinates were stored every 100ms, and all position coordinates were sorted in chronological order. x 1, y 1, z 1), x 2, y 2, z 2) ( x t , y t , z t ), where t represents the time series order, and the coordinates differ by 100ms in the time series; Using the cutting head position coordinates information from 3 seconds ago, plan (predict) the cutting trajectory for the next 500 milliseconds; construct a sample set, starting from sequence 1, with the position coordinates of sequences 1 to 30 (…). x 1, y 1, z 1), x 2, y 2, z 2) ( x 30 , y 30 , z 30 ) as feature data, ( x 31 , y 31 , z 31 (), x 32 , y 32 , z 32 ), ( x 35 , y 35 , z 35 Using this as label data, construct the first sample set; Starting from sequence 2, the position coordinates of sequence 2 to 31 are ( x 2, y 2, z 2), x 3, y 3, z 3) ( x 31 , y 31 , z 31 ) as feature data, ( x 32 , y 32 , z 32 (), x 33 , y 33 , z 33 ), ( x 36 , y 36 , z 36 Using this as label data, construct the second sample set; And so on, starting from sequence t, the coordinates of the positions from sequence t to t+30 ( x t , y t , z t (), x t+1 , y t+1 , z t+1 ), ( x t+30 , y t+30 , z t+30 ) as feature data, ( x t+31 , y t+31 , z t+31 ), x t+32 , y t+32 , z t+32 ), xt+35 , y t+35 , z t+35 Using the t-th sample set as label data; The sample set is divided into training, validation and test sets in a ratio of 98:1:1, and the divided sample set is normalized. Long Short-Term Memory (LSTM) networks introduce "gate" structures and "cell states"; the gate structure is used to control the inflow and outflow of information, and the cell state is used to store states for long-term storage. The forget gate formula is expressed as: in Weight matrix, It is a bias term. The hidden state of the previous moment, This is the current input. It is the sigmoid function; The input gate formula is expressed as: in , It is a weight matrix. , It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function, and tanh is the hyperbolic tangent function; Updated cell state formula: Among them, It is the output of the forget gate. It represents the cell state at the previous moment. It is the input gate value. It is a candidate value; The formulas for output gates and hidden states are expressed as follows: Among them is Weight matrix, It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function. It represents the current cell state, and tanh is the hyperbolic tangent function; The feature data and label data of the training set are input into the LSTM network for training, and the network is validated using the validation set data and tested using the test set data. Using real-time 3-second historical position coordinate data of the cutting head, the cutting trajectory of the cutting head is planned (predicted) over 500ms; the cutting arm cuts according to the planned trajectory, and the travel trajectory is input in real time to plan the trajectory of the cutting head, realizing adaptive planning of the cutting trajectory.

[0010] Furthermore, following the analytical methods of robotics, the DH method is used to calculate the position model of the cutting head center in the tunneling machine's body coordinate system. The position coordinates of the tunneling machine cutting head's center of gravity in the body coordinate system include: Using the DH method, the position model of the cutting head center in the tunneling machine's coordinate system is calculated according to the analysis method of robotics. The formula is expressed as: in, , , , , , Here are the structural parameters of the tunneling machine: α is the lifting and rotating angle of the cutting arm, β is the horizontal rotation angle of the cutting arm, and d is the extension and retraction amount of the cutting head telescopic cylinder. fuselage coordinate system O 0 X 0 Y 0 Z 0. Coordinate system for tunnel measurement O c X c Y c Z c The formula is obtained after three rotations and three translations: Wherein: the tunneling machine's heading angle is δ, its pitch angle is φ, and its roll angle is γ; the translations of the machine along the X, Y, and Z directions are respectively... , The DH method was used to calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the machine's coordinate system. x 1, y 1, z1) By transforming the roadway measurement coordinate system and the machine body coordinate system, the position coordinates (x, y, z) of the center of gravity of the tunneling machine cutting head in the roadway measurement coordinate system are calculated.

[0011] The second objective of this invention is to provide an adaptive planning device for the cross-section cutting trajectory of a tunnel boring machine, comprising: The data acquisition module is used to acquire historical monitoring data of the tunneling machine's posture and calculate historical coordinate data of the tunneling machine based on the historical monitoring data of the tunneling machine's posture. The model building module is used to build an adaptive planning model for the tunnel boring machine's cross-section cutting trajectory based on an LSTM neural network, and to train the adaptive planning model for the tunnel boring machine's cross-section cutting trajectory using historical coordinate data of the tunnel boring machine. The cutting planning module is used to collect real-time tunneling machine posture monitoring data and calculate the corresponding tunneling machine coordinate data, which is then input into the trained adaptive planning model for the tunneling machine cross-section cutting trajectory. The output of the model is the tunneling machine cutting trajectory position coordinate data as the adaptive planning result for the tunneling machine cross-section cutting trajectory.

[0012] A third objective of the present invention is to provide an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the method described above.

[0013] A fourth objective of this invention is to provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to perform the steps of the method according to the foregoing technical solution.

[0014] Compared with the prior art, the advantages of the present invention are: The adaptive planning method for the cutting trajectory of a tunneling machine (TBM) in this invention monitors the TBM's position coordinates in the roadway measurement coordinate system to ensure accurate transformation between the machine's coordinate system and the roadway measurement coordinate system. It also collects the cutting head's position information to ensure accurate cutting head coordinates. The DH method is used to calculate the center of gravity of the cutting head in the machine's coordinate system, and the transformation between the roadway measurement coordinate system and the machine's coordinate system is implemented. Finally, a Long Short-Time Memory (LSTM) network is used for adaptive planning of the cutting trajectory. The cutting trajectory display system visualizes the cutting trajectory coordinates in real time, enabling safe, efficient, and reliable operation of the cutting operation. This invention significantly improves the automation level of TBM cutting operations, reduces manual intervention, and enhances work efficiency and safety. Attached Figure Description

[0015] Figure 1A flowchart illustrating an adaptive planning method for the cross-sectional cutting trajectory of a tunneling machine provided by the present invention; Figure 2 A logical schematic diagram of an adaptive planning method for the cross-sectional cutting trajectory of a tunneling machine provided by the present invention; Figure 3 A schematic diagram illustrating the principle of the Long Short-Time Memory (LSTM) network in an adaptive planning method for tunnel boring machine cross-section cutting trajectory provided by this invention; Figure 4 A schematic diagram of the structure of an adaptive planning device for the cross-section cutting trajectory of a tunneling machine provided by the present invention; Figure 5 This is a schematic diagram of a non-transitory computer-readable storage medium storing computer instructions, provided by the present invention. Detailed Implementation

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] like Figure 1 and Figure 2 As shown: A multi-source data sampling method for tunneling machines under a time network framework, comprising: S110: Obtain historical monitoring data of tunneling machine position and orientation, and calculate historical coordinate data of tunneling machine based on the historical monitoring data of tunneling machine position and orientation.

[0018] When acquiring historical monitoring data of the tunnel boring machine's (TBM) posture, the historical monitoring data includes the historical monitoring data of the machine's fuselage posture and the historical monitoring data of the cutting head posture; among which... The inertial navigation device of the tunneling machine is used to acquire historical information on the heading angle, pitch angle and roll angle of the tunneling machine. The total station device of the tunneling machine is used to acquire historical data on the distance of the tunneling machine relative to the centerline of the roadway and the distance traveled, which are used as historical monitoring data of the machine's posture. Historical data on the displacement of the cutting arm's lifting, swinging, and telescopic cylinders are acquired using multi-channel hydraulic cylinder displacement sensors on the tunneling machine, serving as historical monitoring data for the cutting head's posture. Specifically, the multi-channel hydraulic cylinder displacement sensors include at least a cantilever lifting cylinder displacement sensor, a cantilever swinging cylinder displacement sensor, and a cantilever telescopic cylinder displacement sensor, which respectively collect historical data on the displacement of the tunneling machine's cutting arm lifting cylinder, swinging cylinder, and telescopic cylinder.

[0019] After acquiring the tunnel boring machine (TBM) pose monitoring data, the TBM coordinate data is calculated based on the TBM pose monitoring data, specifically including: Constructing the spatial coordinate system for tunnel measurement and the spatial coordinate system for the tunnel boring machine includes: Construct a spatial coordinate system for tunnel measurement; wherein, the X-axis of the ideal spatial coordinate system coincides with the tunnel design centerline and points to the tunnel cross-section, the Z-axis points to the tunnel roof, and the plane formed by the X-axis and Y-axis is the tunnel floor plane; Construct a spatial coordinate system for the tunneling machine; the spatial coordinate system for the tunneling machine includes the coordinate system of the tunneling machine body, the coordinate system of the rotary table, the coordinate system of the lifting and rotating center, the coordinate system of the telescopic cylinder, and the coordinate system of the cutting head; The principle for establishing each coordinate system is as follows: the Z-axis of the coordinate system is consistent with the rotation axis of each joint, the Y-axis points to the next moving joint, and the X-axis is determined by the right-hand rule.

[0020] Obtain the position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system. Then, calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system through coordinate system transformation. These coordinates are used as the tunneling machine's coordinate data. The specific steps include: Step 1: Initialization, ensuring all devices and systems (body posture monitoring system, cutting head posture monitoring system) are in normal working condition; Step 2: Obtain the current coordinates of the tunnel boring machine's center of gravity in the roadway measurement coordinate system using the machine's posture monitoring system. x 2, y 2, z 2); Step 3: Obtain the displacement d1 of the boom lifting cylinder and the displacement of the swing cylinder of the tunneling machine through the cutting head posture monitoring system. d 2. Displacement of telescopic hydraulic cylinder d Furthermore, based on the mechanical structure characteristics and parameters of the tunneling machine, the lifting and rotating angle α of the cutting arm and the horizontal rotation angle β of the cutting arm were calculated. Step 4: Using the DH method (a robotics analysis method), the position model of the cutting head center in the tunneling machine's coordinate system is calculated, as shown below: In the formula: , , , , , Here are the structural parameters of the tunneling machine: α is the lifting and rotating angle of the cutting arm, β is the horizontal rotation angle of the cutting arm, and d is the extension and retraction amount of the cutting head telescopic cylinder. Step 5: Fuselage Coordinate System O0 X 0 Y 0 Z 0. Coordinate system for tunnel measurement O c X c Y c Z c The result is obtained after three rotations and one translation, as shown below: Wherein: the tunneling machine's heading angle is δ, its pitch angle is φ, and its roll angle is γ; the translations of the machine along the X, Y, and Z directions are respectively... , Step 6: Use the DH method to calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the machine's coordinate system. x 1, y 1, z 1) By transforming the roadway measurement coordinate system and the machine body coordinate system, the position coordinates (x, y, z) of the center of gravity of the tunneling machine cutting head in the roadway measurement coordinate system are calculated.

[0021] S120: Based on LSTM neural network, construct an adaptive planning model for the tunnel boring machine's cross-section cutting trajectory, and train the adaptive planning model for the tunnel boring machine's cross-section cutting trajectory using historical coordinate data of the tunnel boring machine.

[0022] The model training process is as follows: A sample set was constructed using historical coordinate data of the center of gravity of the tunnel boring machine's cutting head in the roadway measurement coordinate system. The cutting head position coordinates were stored every 100ms, and all position coordinates were sorted in chronological order. x 1, y 1, z 1), x 2, y 2, z 2) ( x t , y t , z t ), where t represents the time series order, and the coordinates differ by 100ms in the time series; Using the cutting head position coordinates information from 3 seconds ago, plan (predict) the cutting trajectory for the next 500 milliseconds; construct a sample set, starting from sequence 1, with the position coordinates of sequences 1 to 30 (…). x 1, y 1, z 1), x 2, y 2, z 2) ( x 30 , y 30 , z 30 ) as feature data, ( x 31 , y 31 , z 31 (), x 32 , y 32 , z 32 ), ( x 35 , y 35 , z 35 Using this as label data, construct the first sample set; Starting from sequence 2, the position coordinates of sequence 2 to 31 are ( x 2, y 2, z 2), x 3, y 3, z 3) ( x 31 , y 31 , z 31 ) as feature data, ( x 32 , y 32 , z 32 (), x 33 , y 33 , z 33 ), ( x 36 , y 36 ,z 36 Using this as label data, construct the second sample set; And so on, starting from sequence t, the coordinates of the positions from sequence t to t+30 ( x t , y t , z t (), x t+1 , y t+1 , z t+1 ), ( x t+30 , y t+30 , z t+30 ) as feature data, ( x t+31 , y t+31 , z t+31 ), x t+32 , y t+32 , z t+32 ), x t+35 , y t+35 , z t+35 Using the t-th sample set as label data; The sample set is divided into training, validation and test sets in a ratio of 98:1:1, and the divided sample set is normalized. Long Short-Term Memory (LSTM) networks introduce "gate" structures and "cell states." Gate structures control the inflow and outflow of information, while cell states store information long-term. This allows LSTM to better capture dependencies in long sequences, as explained below. Figure 3 As shown.

[0023] The forget gate formula is expressed as: in Weight matrix, It is a bias term. The hidden state of the previous moment, This is the current input. It is the sigmoid function; The input gate formula is expressed as: in , It is a weight matrix. , It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function, and tanh is the hyperbolic tangent function; Updated cell state formula: Among them, It is the output of the forget gate. It represents the cell state at the previous moment. It is the input gate value. It is a candidate value; The formulas for output gates and hidden states are expressed as follows: Among them is Weight matrix, It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function. It represents the current cell state, and tanh is the hyperbolic tangent function; The feature data and label data of the training set are input into the LSTM network for training, and the network is validated using the validation set data and tested using the test set data. Using real-time 3-second historical position coordinate data of the cutting head, the cutting trajectory of the cutting head is planned (predicted) over 500ms; the cutting arm cuts according to the planned trajectory, and the travel trajectory is input in real time to plan the trajectory of the cutting head, realizing adaptive planning of the cutting trajectory.

[0024] S130: Collect real-time tunneling machine posture monitoring data and calculate the corresponding tunneling machine coordinate data, input it into the trained tunneling machine cross-section cutting trajectory adaptive planning model, and use the tunneling machine cutting trajectory position coordinate data output by the model as the tunneling machine cross-section cutting trajectory adaptive planning result.

[0025] like Figure 4 As shown, the present invention provides a multi-source data sampling device 400 for a tunneling machine under a time network framework, comprising: Data acquisition module 410 is used to acquire historical monitoring data of tunneling machine posture and calculate historical coordinate data of tunneling machine based on the historical monitoring data of tunneling machine posture; The model building module 420 is used to build an adaptive planning model for the tunneling machine's cross-section cutting trajectory based on an LSTM neural network, and to train the adaptive planning model for the tunneling machine's cross-section cutting trajectory using historical coordinate data of the tunneling machine. The cutting planning module 430 is used to collect real-time tunneling machine posture monitoring data and calculate the corresponding tunneling machine coordinate data, which is then input into the trained tunneling machine cross-section cutting trajectory adaptive planning model. The tunneling machine cutting trajectory position coordinate data output by the model is used as the tunneling machine cross-section cutting trajectory adaptive planning result.

[0026] To implement the embodiments, the present invention also proposes an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the method described above.

[0027] like Figure 5 As shown, the non-transitory computer-readable storage medium 900 includes a memory 910 for instructions and an interface 930, the instructions of which can be executed by a processor 920 to complete the method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0028] To implement the embodiments, the present invention also proposes a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the embodiments of the present invention.

[0029] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0030] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0031] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of the invention pertain.

[0032] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0033] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the described embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0034] Those skilled in the art will understand that all or part of the steps of the method described in the embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0035] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0036] The storage medium mentioned may be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the embodiments within the scope of the present invention.

Claims

1. An adaptive planning method for the cross-sectional cutting trajectory of a tunnel boring machine, characterized in that, include: Acquire historical monitoring data of the tunnel boring machine's position and posture, which includes historical monitoring data of the machine's fuselage position and posture and historical monitoring data of the cutting head position and posture; wherein... The inertial navigation device of the tunneling machine is used to acquire historical information on the heading angle, pitch angle and roll angle of the tunneling machine. The total station device of the tunneling machine is used to acquire historical data on the distance of the tunneling machine relative to the centerline of the roadway and the distance traveled, which are used as the historical monitoring data of the machine's posture. Historical data on the displacement of the lifting, swinging, and telescopic cylinders of the tunneling machine's cutting arm are acquired through the multi-channel cylinder displacement sensors of the tunneling machine, and used as historical monitoring data of the cutting head's posture. Based on the historical monitoring data of the tunnel boring machine's posture, the historical coordinate data of the tunnel boring machine is calculated, including: Construct a spatial coordinate system for tunnel measurement and a spatial coordinate system for the tunnel boring machine; Obtain the position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system. Calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system through coordinate system transformation, and use these as the tunneling machine's coordinate data. An adaptive planning model for the cutting trajectory of a tunnel boring machine (TBM) section is constructed based on an LSTM neural network, and the TBM section cutting trajectory adaptive planning model is trained using the historical coordinate data of the TBM. Real-time tunneling machine position and posture monitoring data is collected and the corresponding tunneling machine coordinate data is calculated. This data is then input into the trained adaptive planning model for the tunneling machine cross-section cutting trajectory. The output coordinate data of the tunneling machine cutting trajectory is used as the adaptive planning result for the tunneling machine cross-section cutting trajectory.

2. The adaptive planning method for tunnel boring machine section cutting trajectory according to claim 1, characterized in that, Constructing the spatial coordinate system for tunnel measurement and the spatial coordinate system for the tunnel boring machine includes: Construct a tunnel measurement spatial coordinate system; wherein, the X-axis of the ideal measurement spatial coordinate system coincides with the tunnel design centerline and points to the tunnel cross-section, the Z-axis points to the tunnel roof, and the plane formed by the X-axis and Y-axis is the tunnel floor plane; Construct a spatial coordinate system for the tunneling machine; wherein, the spatial coordinate system for the tunneling machine includes the coordinate system of the tunneling machine body, the coordinate system of the rotary table, the coordinate system of the lifting and rotating center, the coordinate system of the telescopic cylinder, and the coordinate system of the cutting head; The principle for establishing each coordinate system is as follows: the Z-axis of the coordinate system is consistent with the rotation axis of each joint, the Y-axis points to the next moving joint, and the X-axis is determined by the right-hand rule.

3. The adaptive planning method for tunnel boring machine cross-section cutting trajectory according to claim 2, characterized in that, Obtain the position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system. Then, calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system through coordinate system transformation, including: Initialize to ensure all devices and systems in the tunneling machine are in normal working order; Obtain the current coordinates of the center of gravity of the tunnel boring machine in the roadway measurement coordinate system. x 2, y 2, z 2); Obtain the displacement d1 of the boom lifting cylinder and the displacement of the swing cylinder of the tunneling machine. d 2. Displacement of telescopic hydraulic cylinder d Furthermore, based on the mechanical structure characteristics and parameters of the tunneling machine, the lifting and rotating angle α of the cutting arm and the horizontal rotation angle β of the cutting arm were calculated. Using the DH method, a position model of the cutting head center in the tunneling machine's body coordinate system is calculated based on the analysis methods of robotics. The coordinates of the cutting head's center of gravity in the body coordinate system are also obtained. x 1, y 1, z 1); By transforming the tunnel measurement coordinate system and the machine body coordinate system, the position coordinates (x, y, z) of the center of gravity of the tunneling machine's cutting head in the tunnel measurement coordinate system are calculated.

4. The adaptive planning method for tunnel boring machine section cutting trajectory according to claim 3, characterized in that, An adaptive planning model for the tunnel boring machine (TBM) section cutting trajectory is constructed based on an LSTM neural network. This model is trained using historical coordinate data of the TBM, including: A sample set was constructed using historical coordinate data of the center of gravity of the tunnel boring machine's cutting head in the roadway measurement coordinate system. The cutting head position coordinates were stored every 100ms, and all position coordinates were sorted in chronological order. x 1, y 1, z 1), x 2, y 2, z 2) ( x t , y t , z t ), where t represents the time series order, and the coordinates differ by 100ms in the time series; Using the cutting head position coordinates information from 3 seconds ago, plan the cutting trajectory for the next 500 milliseconds; construct a sample set, starting from sequence 1, with the position coordinates of sequences 1 to 30 (…). x 1, y 1, z 1), x 2, y 2, z 2) ( x 30 , y 30 , z 30 ) as feature data, ( x 31 , y 31 , z 31 (), x 32 , y 32 , z 32 ), ( x 35 , y 35 , z 35 Using this as label data, construct the first sample set; Starting from sequence 2, the position coordinates of sequence 2 to 31 are ( x 2, y 2, z 2), x 3, y 3, z 3) ( x 31 , y 31 , z 31 ) as feature data, ( x 32 , y 32 , z 32 (), x 33 , y 33 , z 33 ), ( x 36 , y 36 , z 36 Using this as label data, construct the second sample set; And so on, starting from sequence t, the coordinates of the positions from sequence t to t+30 ( x t , y t , z t (), x t+1 , y t+1 , z t+1 ), ( x t+30 , y t+30 , z t+30 ) as feature data, ( x t+31 , y t+31 , z t+31 (), x t+32 , y t+32 , z t+32 ), ( x t+35 , y t+35 , z t+35 Using the t-th sample set as label data; The sample set is divided into training, validation and test sets in a ratio of 98:1:1, and the divided sample set is normalized. Long Short-Term Memory (LSTM) networks introduce "gate" structures and "cell states"; the gate structure is used to control the inflow and outflow of information, and the cell state is used to store the state for a long time. The forget gate formula is expressed as: in Weight matrix, It is a bias term. The hidden state of the previous moment, This is the current input. It is the sigmoid function; The input gate formula is expressed as: in , It is a weight matrix. , It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function, and tanh is the hyperbolic tangent function; Updated cell state formula: Among them, It is the output of the forget gate. It represents the cell state at the previous moment. It is the input gate value. It is a candidate value; The formulas for output gates and hidden states are expressed as follows: Among them is Weight matrix, It is a bias term. It is the hidden state from the previous moment. This is the current input. It is the sigmoid function. It represents the current cell state, and tanh is the hyperbolic tangent function; The feature data and label data of the training set are input into the LSTM network for training, and the network is validated using the validation set data and tested using the test set data. Using real-time 3-second historical position coordinate data of the cutting head, the cutting trajectory of the cutting head is planned for 500ms; the cutting arm cuts according to the planned trajectory, and the travel trajectory is input in real time to plan the trajectory of the cutting head, so as to realize the adaptive planning of the cutting trajectory.

5. The adaptive planning method for tunnel boring machine section cutting trajectory according to claim 4, characterized in that, Using the DH method, a position model of the cutting head's center position in the tunneling machine's coordinate system is calculated based on robotic analysis. The coordinates of the cutting head's center of gravity in the machine's coordinate system include: Using the DH method, a robotic analysis approach, the position model of the cutting head's center position in the tunneling machine's coordinate system is calculated. The formula is as follows: in, , , , , , Here are the structural parameters of the tunneling machine: α is the lifting and rotating angle of the cutting arm, β is the horizontal rotation angle of the cutting arm, and d is the extension and retraction amount of the cutting head telescopic cylinder. fuselage coordinate system O 0 X 0 Y 0 Z 0 is measured from the roadway coordinate system O c X c Y c Z c The formula is obtained after three rotations and three translations: Wherein: the tunneling machine's heading angle is δ, its pitch angle is φ, and its roll angle is γ; the translations of the machine along the X, Y, and Z directions are respectively... , The DH method was used to calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the machine's coordinate system. x 1, y 1, z 1) By transforming the roadway measurement coordinate system and the machine body coordinate system, the position coordinates (x, y, z) of the center of gravity of the tunneling machine cutting head in the roadway measurement coordinate system are calculated.

6. An adaptive planning device for the cross-sectional cutting trajectory of a tunneling machine, characterized in that, include: The data acquisition module is used to acquire historical monitoring data of the tunneling machine's position and posture, which includes historical monitoring data of the machine's hull position and posture and historical monitoring data of the cutting head position and posture; wherein, The inertial navigation device of the tunneling machine is used to acquire historical information on the heading angle, pitch angle and roll angle of the tunneling machine. The total station device of the tunneling machine is used to acquire historical data on the distance of the tunneling machine relative to the centerline of the roadway and the distance traveled, which are used as the historical monitoring data of the machine's posture. Historical data on the displacement of the lifting, swinging, and telescopic cylinders of the tunneling machine's cutting arm are acquired through the multi-channel cylinder displacement sensors of the tunneling machine, and used as historical monitoring data of the cutting head's posture. Based on the historical monitoring data of the tunnel boring machine's posture, the historical coordinate data of the tunnel boring machine is calculated, including: Construct a spatial coordinate system for tunnel measurement and a spatial coordinate system for the tunnel boring machine; Obtain the position coordinates of the center of gravity of the tunneling machine's cutting head in the tunneling machine's spatial coordinate system and the position coordinates of the center of gravity of the tunneling machine's body in the ideal measurement spatial coordinate system. Calculate the position coordinates of the center of gravity of the tunneling machine's cutting head in the roadway measurement spatial coordinate system through coordinate system transformation, and use these as the tunneling machine's coordinate data. The model building module is used to build an adaptive planning model for the tunnel boring machine's cross-section cutting trajectory based on an LSTM neural network, and to train the adaptive planning model for the tunnel boring machine's cross-section cutting trajectory using the tunnel boring machine's historical coordinate data. The cutting planning module is used to collect real-time tunneling machine posture monitoring data and calculate the corresponding tunneling machine coordinate data, which is then input into the trained adaptive planning model of the tunneling machine cross-section cutting trajectory. The tunneling machine cutting trajectory position coordinate data output by the model is used as the adaptive planning result of the tunneling machine cross-section cutting trajectory.

7. An electronic device, comprising: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform each step of the method according to any one of claims 1-5.

Images