A method and system for predicting excavation efficiency during tunnel excavation

Abstract

The present invention discloses a method and system for predicting excavation efficiency during tunnel excavation, which relates to the technical field of tunnel excavation management, including deploying sensors to collect excavation equipment data, obtaining excavation equipment point cloud coordinates for optimization and then planning the excavation path; calculating the excavation distance and speed based on the excavation path, and predicting the excavation efficiency based on the excavation distance and speed; generating an excavation efficiency report for display, and storing it in a database. The present invention extracts point cloud data by collecting excavation equipment data and tunnel environment data, optimizes the point cloud data, plans the shortest excavation path based on the optimized point cloud data, reduces the workload of tunnel excavation, and predicts the excavation efficiency based on the shortest excavation path based on the Gaussian mixture model and global error, thereby improving the accuracy and flexibility of excavation prediction and helping to improve tunnel excavation efficiency.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel excavation management, and in particular to a method and system for predicting excavation efficiency during tunnel excavation. Background Art

[0002] Tunnel excavation technology plays a vital role in the fields of mine development, tunnel construction, etc. With the development of sensor technology, data processing technology and automatic control technology, modern excavation equipment can perform efficient excavation tasks in complex environments. Traditional excavation methods rely on manual operation, which is inefficient and has large errors. Nowadays, advanced excavation equipment collects operating status, environmental information and path data through sensors, and realizes partial automation. However, even in modern excavation systems, accurate prediction of excavation efficiency is still a technical difficulty. In the existing technology, although equipment data can be collected in real time through sensors, there are still deficiencies in how to use these data to optimize the excavation path and improve the accuracy of efficiency prediction. Most of the existing path planning methods rely on historical data and static models, and fail to fully integrate the real-time data of the equipment, resulting in insufficient flexibility and accuracy of excavation path planning. In addition, the prediction model of excavation efficiency usually does not consider the actual movement state of the equipment and the complexity of the tunnel environment, which makes the prediction result inaccurate. Summary of the invention

[0003] In view of the problems existing in the above-mentioned existing methods and systems for predicting excavation efficiency during tunnel excavation, the present invention is proposed.

[0004] Therefore, the problem to be solved by the present invention is that the flexibility and accuracy of tunneling path planning are insufficient, and the accuracy of tunneling efficiency prediction results is not high.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for predicting excavation efficiency during tunnel excavation, which includes deploying sensors to collect excavation equipment data, and obtaining the point cloud coordinates of the excavation equipment for optimization and then planning the excavation path; calculating the excavation distance and speed based on the excavation path, and predicting the excavation efficiency based on the excavation distance and speed; generating an excavation efficiency report for display, and storing it in a database.

[0006] As a preferred solution of the method for predicting excavation efficiency during tunnel excavation described in the present invention, the deployment of sensors to collect excavation equipment data refers to installing magnetic displacement sensors and inertial navigation sensors to obtain excavation equipment data, using laser scanning to obtain excavation tunnel environment data, and sending it to the control center for preprocessing.

[0007] As a preferred solution of the tunneling efficiency prediction method in the tunneling process of the present invention, wherein: the acquisition of the tunneling equipment point cloud coordinates for optimization and then planning the tunneling path refers to acquiring the tunneling equipment point cloud data through the tunneling equipment data , and obtain the excavation environment point cloud data through the excavation tunnel environment data ;

[0008] For device point cloud data Each point , through KD-tree in the environmental point cloud data The closest point in , calculation point and Point The Euclidean distance of and Point If the Euclidean distance is less than or equal to the distance threshold, then the point and Point Form a point pair. If the distance is greater than the threshold, the point and Point Point cloud data from device and environmental point cloud data Eliminate;

[0009] Initialize the rotation matrix R to the identity matrix and the translation vector T to 0;

[0010] Apply a rigid transformation to perform a preliminary registration of the device point cloud data using the rotation matrix R and the translation vector:

[0011]

[0012] in is the point in the device point cloud data after preliminary registration;

[0013] Calculate the points in the device point cloud data after preliminary registration and equipment point cloud data points Distance error , define the optimization goal for:

[0014]

[0015] Where n is the total number of points in the device point cloud data;

[0016] Update the rotation matrix R through SVD decomposition, use the gradient descent method to update the translation vector T, and iteratively calculate the optimization target E until the optimization target E is less than the iteration threshold, and then stop, outputting the calculated value when the iteration stops. , rotation matrix and translation vectors ,based on Update device point cloud data:

[0017]

[0018] in is the point in the updated device point cloud data, is the learning rate;

[0019] Get the target position of excavation , the shortest excavation path is generated using the shortest path algorithm based on the updated equipment point cloud data.

[0020] As a preferred scheme of the method for predicting excavation efficiency during tunnel excavation described in the present invention, wherein: the calculation of excavation distance and speed based on the excavation path refers to obtaining the shortest excavation path and then identifying the path turning point in the shortest excavation path, obtaining the coordinates of the path turning point, and regarding the line connecting two adjacent path turning points as an excavation section, calculating the distance of each excavation section, and monitoring the working time of the excavation equipment in real time, recording the excavation start time and excavation end time of the excavation equipment in the excavation section to calculate the excavation time, and calculating the excavation speed of the excavation equipment in each excavation section according to the excavation section distance and excavation time.

[0021] As a preferred solution of the method for predicting the excavation efficiency during tunnel excavation of the present invention, the method of predicting the excavation efficiency according to the excavation distance and speed includes:

[0022] Based on equipment point cloud data Calculate the covariance matrix , and extract the point cloud coordinates of each path point in the shortest excavation path, and calculate the current time path point of the excavation equipment in the shortest excavation path based on the excavation speed and excavation time of the previous excavation section , synchronize according to the device point cloud data Extract the current time coordinate point , based on the rotation matrix and translation vectors Constructing Gaussian mixture model to calculate preliminary tunneling efficiency :

[0023]

[0024] Where m is the number of path points, K is the number of Gaussian components, is the weight of the jth Gaussian component, is the probability density function of the Gaussian component fit;

[0025] Calculate the global error based on the device's current time coordinate point and the path target point :

[0026]

[0027] Calculate the total length L of the shortest path and based on the global error Adjust initial excavation efficiency Forming the final excavation efficiency :

[0028]

[0029] The final excavation efficiency will be calculated Send to Control Center.

[0030] As a preferred solution of the tunneling efficiency prediction method in the tunneling process of the present invention, the generating of the tunneling efficiency report for display means that the control center obtains the final tunneling efficiency Generate a tunneling efficiency report based on the shortest tunneling path and tunneling start time for display, and synchronously display the tunneling equipment data and the tunneling efficiency report.

[0031] As a preferred solution of the method for predicting excavation efficiency during tunnel excavation described in the present invention, the storage in the database refers to the control center generating the excavation efficiency report and excavation equipment data and storing them in the local database, and performing multiple cloud backups of the stored data through a distributed storage system, and regularly performing security checks on the data stored in the local database.

[0032] Another object of the present invention is to provide a tunneling efficiency prediction system during tunneling, which includes a data collection module for acquiring tunneling equipment data and tunneling tunnel environment data and sending them to a control center to extract point cloud data;

[0033] The optimized path module is used to optimize the point cloud data and plan the shortest excavation path based on the optimized point cloud data;

[0034] An efficiency prediction module is used to predict the excavation efficiency based on the distance of the shortest excavation path and the excavation speed;

[0035] The display storage module is used to generate a tunneling efficiency report based on the predicted tunneling efficiency, and store the tunneling efficiency report and tunneling equipment data in a database.

[0036] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned method for predicting excavation efficiency during tunnel excavation when executing the computer program.

[0037] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for predicting excavation efficiency during tunnel excavation.

[0038] The beneficial effects of the present invention are as follows: the present invention extracts point cloud data by collecting excavation equipment data and tunnel environment data, and optimizes the point cloud data, plans the shortest excavation path based on the optimized point cloud data, reduces the workload of tunnel excavation, and at the same time predicts the excavation efficiency based on the Gaussian mixture model and global error according to the shortest excavation path, thereby improving the accuracy and flexibility of excavation prediction and helping to improve tunnel excavation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 The figure is a flow chart of the method for predicting the excavation efficiency during tunnel excavation.

[0041] Figure 2 This is a structural diagram of the tunnel excavation efficiency prediction system during tunnel excavation. DETAILED DESCRIPTION

[0042] 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.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0045] Example 1

[0046] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a method for predicting the excavation efficiency during tunnel excavation. The method for predicting the excavation efficiency during tunnel excavation includes:

[0047] S1. Deploy sensors to collect tunneling equipment data and obtain the point cloud coordinates of the tunneling equipment for optimization and planning of tunneling paths;

[0048] Specifically, deploying sensors to collect tunneling equipment data means installing magnetic displacement sensors and inertial navigation sensors to obtain tunneling equipment data, using laser scanning to obtain tunneling tunnel environment data, and installing magnetic displacement sensors on lifting cylinders and rotary cylinders, for example, to detect the telescopic displacement data of the cylinders. Inertial navigation sensors include gyroscopes and accelerometers, which are used to obtain the posture data of tunneling equipment, such as heading angle, pitch angle, roll angle, and spatial position coordinates, so as to comprehensively analyze the tunneling status of the tunneling equipment and send it to the control center for preprocessing.

[0049] The main task of data preprocessing is to filter out noise, fill in missing data and perform data standardization. After preprocessing, the system can obtain accurate and standardized equipment status data and environmental data, laying a solid foundation for subsequent path optimization and tunneling efficiency prediction. Through data preprocessing, the system can detect the operating status of the equipment in real time, such as the displacement change of the cylinder, the posture adjustment of the equipment, etc., and then perform effective feedback control. For example, when the equipment posture is abnormal or the cylinder displacement is abnormal, the control center can make a judgment in advance through data analysis and remind the operator to take adjustment measures in time. This real-time feedback system can greatly improve the safety and work efficiency of the equipment. Based on the data collected by the sensor, the control center can plan the optimal tunneling path by analyzing the point cloud data. In this process, the system first models the tunneling state of the equipment through a Gaussian mixture model, and then combines the global error correction technology to ensure the optimality and accuracy of the path. In this way, the system can update the working status of the tunneling equipment in real time and dynamically adjust the path planning during the tunneling process.

[0050] Furthermore, obtaining the point cloud coordinates of the tunneling equipment for optimization and then planning the tunneling path refers to obtaining the point cloud data of the tunneling equipment through the tunneling equipment data. , and obtain the excavation environment point cloud data through the excavation tunnel environment data ;

[0051] For device point cloud data Each point , through KD-tree in the environmental point cloud data The closest point in , calculation point and Point The Euclidean distance of and Point If the Euclidean distance is less than or equal to the distance threshold, then the point and Point Form a point pair. If the distance is greater than the threshold, the point and Point Point cloud data from device and environmental point cloud data Eliminate;

[0052] Initialize the rotation matrix R to the identity matrix and the translation vector T to 0;

[0053] Apply a rigid transformation to perform a preliminary registration of the device point cloud data using the rotation matrix R and the translation vector:

[0054]

[0055] in is the point in the device point cloud data after preliminary registration;

[0056] Calculate the points in the device point cloud data after preliminary registration and equipment point cloud data points Distance error , define the optimization goal for:

[0057]

[0058] Where n is the total number of points in the device point cloud data;

[0059] Update the rotation matrix R through SVD decomposition, use the gradient descent method to update the translation vector T, and iteratively calculate the optimization target E until the optimization target E is less than the iteration threshold, and then stop, outputting the calculated value when the iteration stops. , rotation matrix and translation vectors ,based on Update device point cloud data:

[0060]

[0061] in is the point in the updated device point cloud data, is the learning rate;

[0062] Get the target position of excavation , the shortest excavation path is generated using the shortest path algorithm based on the updated equipment point cloud data.

[0063] By using KD-tree to quickly find the point in the environment point cloud that is closest to each point in the device point cloud and calculate the Euclidean distance between the two points, the difference between the device and environment point clouds can be effectively identified. Setting a distance threshold to eliminate points with large errors can ensure that the noise in the point cloud data is filtered out, thereby improving the accuracy of the registration. By setting the initial rotation matrix and translation vector, the rigid transformation can provide a basis for subsequent fine optimization. The rigid transformation maintains the overall shape of the device point cloud data and performs a preliminary alignment with the environment point cloud without affecting its internal structure. This lays the foundation for subsequent precise error calculation. With preliminary alignment, the device point cloud data can be accurately matched with the environment point cloud, reducing errors and improving adaptability to the environment. The rotation matrix is ​​continuously updated through SVD decomposition to ensure that the rotation angle of the device point cloud in space can accurately match the environment point cloud. SVD Decomposition can ensure that it is always an orthogonal matrix, thereby maintaining the characteristics of rigid transformation. By minimizing the translation error between the device point cloud and the environment point cloud, it ensures that the device point cloud can be accurately aligned with the environment point cloud in the translation direction. The gradient descent method has the characteristics of gradual convergence and can gradually approach the optimal solution in multiple iterations to ensure that the final translation error is minimized. After the registration optimization is completed, the system performs shortest path planning based on the updated device point cloud data. The shortest path algorithm is used to plan the optimal path from the current position of the device to the target position, ensuring that the device chooses the shortest and most effective path to work during the tunnel excavation process. In the actual excavation process, the tunnel environment may change, and the position and posture of the equipment may also be adjusted at any time. By acquiring device point cloud data and environment point cloud data in real time, and continuously performing error optimization and path replanning, the system can dynamically adjust the excavation path to ensure that the equipment is always in the optimal working state.

[0064] S2. Calculate the excavation distance and speed based on the excavation path, and predict the excavation efficiency based on the excavation distance and speed;

[0065] Specifically, calculating the excavation distance and speed based on the excavation path means obtaining the shortest excavation path and then identifying the path turning points in the shortest excavation path, obtaining the coordinates of the path turning points, regarding the line connecting two adjacent path turning points as an excavation section, calculating the distance of each excavation section, and monitoring the working time of the excavation equipment in real time, recording the excavation start time and excavation end time of the excavation equipment in the excavation section to calculate the excavation time, and calculating the excavation speed of the excavation equipment in each excavation section according to the excavation section distance and excavation time.

[0066] After obtaining the shortest excavation path, the turning points in the path are identified. The beneficial effect of this step is that the complex excavation path is simplified into several linear excavation segments through the path turning points. In traditional excavation path planning, the equipment usually makes continuous adjustments on the curved segments, which easily leads to path deviation and reduced excavation efficiency. By detecting and dividing the turning points, the present invention can optimize the path structure so that the equipment can complete the excavation operation in a more efficient manner. By calculating the distance of each excavation segment, the total length of the equipment traveling on each straight segment can be accurately evaluated. The distance calculation of the excavation segment is based on the Euclidean distance formula of the three-dimensional coordinate system, which can accurately reflect the actual moving distance of the equipment in space. By real-time monitoring of the working time of the excavation equipment, the start and end time of the equipment in each excavation segment is recorded. The excavation time is recorded by monitoring the timestamps of the start and stop of the equipment through sensors, ensuring that the excavation time is consistent with the actual operation of the equipment. By calculating the excavation speed section by section, the present invention can dynamically adjust the working parameters of the equipment to optimize efficiency. For example, when the speed of a certain excavation section is significantly lower than the average level, the system can analyze the cause and prompt the operator to make adjustments. The real-time calculation and feedback mechanism of the excavation speed greatly improves the flexibility of the equipment, ensuring that the equipment can maintain optimal efficiency under different working conditions. It can not only help monitor the working efficiency of the equipment, but also predict the changing trend of the excavation efficiency, providing a scientific basis for path planning and equipment maintenance. Especially in long-term operations, the change of speed section by section can reflect the working status of the equipment and environmental changes, which is convenient for real-time adjustment.

[0067] Further, the prediction of excavation efficiency based on excavation distance and speed includes:

[0068] Based on equipment point cloud data Calculate the covariance matrix , and extract the point cloud coordinates of each path point in the shortest excavation path, and calculate the current time path point of the excavation equipment in the shortest excavation path based on the excavation speed and excavation time of the previous excavation section , synchronize according to the device point cloud data Extract the current time coordinate point , based on the rotation matrix and translation vectors Constructing Gaussian mixture model to calculate preliminary tunneling efficiency :

[0069]

[0070] Where m is the number of path points, K is the number of Gaussian components, is the weight of the jth Gaussian component, is the probability density function of the Gaussian component fit;

[0071] Calculate the global error based on the device's current time coordinate point and the path target point :

[0072]

[0073] Calculate the total length L of the shortest path and based on the global error Adjust initial excavation efficiency Forming the final excavation efficiency :

[0074]

[0075] The final excavation efficiency will be calculated Send to Control Center.

[0076] The excavation efficiency is derived and solved based on a variety of models and algorithms. The introduction of technologies such as Gaussian mixture model (GMM), covariance matrix analysis, and global error correction allows the solution process of excavation efficiency to take into account the real-time dynamic performance of the equipment. These mathematical models can capture the subtle changes of the equipment during the excavation process. The excavation efficiency value integrates multiple key indicators of the equipment during operation, including the equipment's operating speed, excavation time, energy consumption, etc. Although only one value is output in the end, the calculation of this value is based on the contribution of each individual factor. Therefore, it represents the overall performance of the equipment during the working process.

[0077] The covariance matrix is ​​calculated based on the equipment point cloud data to extract the point cloud coordinates of each path point in the shortest excavation path. This process can help the system extract the optimal excavation path for the equipment from complex point cloud data. In the traditional excavation process, the path planning of the equipment often relies on the preset route and fails to make full use of the real-time data of the equipment for adjustment. By calculating the covariance matrix, the system can identify the spatial correlation between the path points and generate the shortest path, thereby significantly improving the efficiency and accuracy of excavation. The calculation of the covariance matrix can also capture the distribution characteristics of each path point in the equipment point cloud data, helping the system to better understand the geometric structure of the path points. In three-dimensional space, this information can be used It is used to optimize the planning and adjustment of the path, reduce the energy consumption and time loss caused by path deviation during the excavation process, and calculate the movement state of the equipment at the current path point based on the excavation speed and excavation time of the previous excavation section. This real-time calculation method based on historical data can dynamically track the working state of the equipment and ensure that the system always adjusts the excavation path according to the latest motion data. During the excavation process, the speed and time of the equipment are the key factors affecting efficiency. The calculation based on these factors can ensure that the working state of the equipment is consistent with the predetermined plan. The Gaussian mixture model regards the point cloud data of the equipment as a combination of multiple Gaussian components, so as to capture the local characteristics of the equipment during movement. In this model, the system The probability density function of the Gaussian component is calculated for each path point, and the posture and position of the equipment are adjusted by optimizing the rotation matrix and translation vector. The initial excavation efficiency is calculated by the Gaussian mixture model, which can make a more accurate assessment of the real-time status of the equipment. The Gaussian mixture model can capture the subtle changes in the path of the equipment during the excavation process and fit it through the probability model, making the calculation of excavation efficiency more precise and flexible. Compared with the traditional simple path length and time calculation, the present invention improves the accuracy of excavation efficiency prediction by introducing a complex probability model. The introduction of global error helps to reduce the cumulative error of the equipment in complex paths. By calculating the global error, the system can perform Fine-tuning ensures that the actual movement of the equipment always remains on the optimal path. The global error correction mechanism ensures that the efficiency of the equipment will not be greatly reduced during the excavation process due to environmental changes or deviations in the equipment itself. The final excavation efficiency depends not only on the correction of path length and global errors, but also on the combination of the equipment's real-time point cloud data and the calculation results of the Gaussian mixture model. Therefore, this efficiency prediction method based on multidimensional data and multiple models can greatly improve the accuracy and reliability of excavation efficiency prediction. Through this real-time feedback mechanism, the operator can monitor the operation of the equipment in real time, and adjust the equipment's operating parameters in time according to the feedback results to ensure that the equipment always maintains the best working condition.

[0078] S3, generating a tunneling efficiency report for display and storing it in a database;

[0079] Specifically, the excavation efficiency report is generated for display to indicate to the control center to obtain the final excavation efficiency Generate a tunneling efficiency report based on the shortest tunneling path and tunneling start time for display, and synchronously display the tunneling equipment data and the tunneling efficiency report.

[0080] The report is based on the final excavation efficiency of the equipment and is displayed in combination with the excavation path and time data. The excavation efficiency report can provide operators with a comprehensive overview of the equipment's working conditions, including key indicators such as the equipment's excavation speed, operating time, and shortest path completion. The generation of the report helps to improve the transparency of the excavation process and allows operators to clearly understand the performance of the equipment throughout the entire excavation process. Compared with traditional excavation efficiency calculations that only rely on path and time, the report generation process can integrate data from more dimensions, thereby improving the accuracy and practicality of the report.

[0081] Furthermore, storing in a database means that the control center generates excavation efficiency reports and excavation equipment data and stores them in a local database, and performs multiple cloud backups of the stored data through a distributed storage system, and regularly performs security checks on the data stored in the local database.

[0082] The excavation efficiency report and equipment data generated by the control center will first be stored in the local database. The data can be quickly accessed and managed without complex network transmission or remote calls. At the same time, the storage method of the local database can improve the speed of data reading and writing when the system processes data locally, ensuring that the system can process the operating data of the equipment in real time. The distributed storage system can improve data security and fault tolerance by storing data in multiple cloud nodes. Even if a cloud node fails, the system can restore data through other nodes to avoid the risk of data loss. Through multiple cloud backups, the system can realize redundant storage of data in different locations, especially the large amount of important data generated during the excavation process, such as the operating status of the equipment, efficiency reports, etc. Multiple backups can prevent data loss in the event of a network attack or hardware failure. In addition, cloud backup can also improve data persistence and availability, ensuring that data can be stored for a long time and restored at any time.

[0083] Example 2

[0084] Reference Figure 2 , which is the second embodiment of the present invention, is different from the previous embodiment and provides a system for predicting tunneling efficiency during tunneling, which includes:

[0085] Data collection module, used to obtain excavation equipment data and excavation tunnel environment data and send them to the control center to extract point cloud data;

[0086] The optimized path module is used to optimize the point cloud data and plan the shortest excavation path based on the optimized point cloud data;

[0087] An efficiency prediction module is used to predict the excavation efficiency based on the distance of the shortest excavation path and the excavation speed;

[0088] The display storage module is used to generate a tunneling efficiency report based on the predicted tunneling efficiency, and store the tunneling efficiency report and tunneling equipment data in a database.

[0089] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a method for predicting excavation efficiency during tunnel excavation when executing the computer program.

[0090] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for predicting excavation efficiency during tunnel excavation.

[0091] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0093] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0094] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for predicting tunneling efficiency during tunneling, characterized in that: include, Deploy sensors to collect tunneling equipment data and obtain the point cloud coordinates of the tunneling equipment for optimization and tunneling path planning; Calculate the excavation distance and speed based on the excavation path, and predict the excavation efficiency based on the excavation distance and speed; Generate tunneling efficiency reports for display and store them in the database; Deploying sensors to collect tunneling equipment data refers to installing magnetic displacement sensors and inertial navigation sensors to obtain tunneling equipment data, using laser scanning to obtain tunneling tunnel environment data, and sending it to the control center for preprocessing; The obtaining of the excavation equipment point cloud coordinates for optimization and then planning the excavation path refers to obtaining the excavation equipment point cloud data through the excavation equipment data. , and obtain the excavation environment point cloud data through the excavation tunnel environment data ; For device point cloud data Each point , through KD-tree in the environmental point cloud data The closest point in , calculation point and Point The Euclidean distance of and Point If the Euclidean distance is less than or equal to the distance threshold, then the point and Point Form a point pair. If the distance is greater than the threshold, the point and Point Point cloud data from device and environmental point cloud data Eliminate; Initialize the rotation matrix R to the identity matrix and the translation vector T to 0; Apply a rigid transformation to perform a preliminary registration of the device point cloud data using the rotation matrix R and the translation vector: in is the point in the device point cloud data after preliminary registration; Calculate the points in the device point cloud data after preliminary registration and equipment point cloud data points Distance error , define the optimization goal for: Where n is the total number of points in the device point cloud data; Update the rotation matrix R through SVD decomposition, use the gradient descent method to update the translation vector T, and iteratively calculate the optimization target E until the optimization target E is less than the iteration threshold, and then stop, outputting the calculated value when the iteration stops. , rotation matrix and translation vectors ,based on Update device point cloud data: in is the point in the updated device point cloud data, is the learning rate; Get the target position of excavation , based on the updated equipment point cloud data, the shortest excavation path is generated using the shortest path algorithm; The calculation of the excavation distance and speed based on the excavation path refers to obtaining the shortest excavation path, identifying the path turning point in the shortest excavation path, obtaining the coordinates of the path turning point, regarding the line connecting two adjacent path turning points as an excavation section, calculating the distance of each excavation section, and monitoring the working time of the excavation equipment in real time, recording the excavation start time and excavation end time of the excavation equipment in the excavation section to calculate the excavation time, and calculating the excavation speed of the excavation equipment in each excavation section according to the excavation section distance and excavation time; The prediction of excavation efficiency according to excavation distance and speed includes: Based on equipment point cloud data Calculate the covariance matrix , and extract the point cloud coordinates of each path point in the shortest excavation path, and calculate the current time path point of the excavation equipment in the shortest excavation path based on the excavation speed and excavation time of the previous excavation section , synchronize according to the device point cloud data Extract the current time coordinate point , based on the rotation matrix and translation vectors Constructing Gaussian mixture model to calculate preliminary tunneling efficiency : Where m is the number of path points, K is the number of Gaussian components, is the weight of the jth Gaussian component, is the probability density function of the Gaussian component fit; Calculate the global error based on the device's current time coordinate point and the path target point : Calculate the total length L of the shortest path and based on the global error Adjust initial excavation efficiency Forming the final excavation efficiency : The final excavation efficiency will be calculated Send to Control Center.

2. The method for predicting tunneling efficiency during tunneling as claimed in claim 1, characterized in that: The generating of the excavation efficiency report for display means that the control center obtains the final excavation efficiency Generate a tunneling efficiency report based on the shortest tunneling path and tunneling start time for display, and synchronously display the tunneling equipment data and the tunneling efficiency report.

3. The method for predicting tunneling efficiency during tunneling as claimed in claim 2, characterized in that: The storage in the database refers to the control center generating the excavation efficiency report and excavation equipment data and storing them in the local database, and performing multiple cloud backups of the stored data through a distributed storage system, and regularly performing security checks on the data stored in the local database.

4. A tunnel excavation efficiency prediction system in a tunnel excavation process according to any one of claims 1 to 3, characterized in that: include, Data collection module, used to obtain excavation equipment data and excavation tunnel environment data and send them to the control center to extract point cloud data; The optimized path module is used to optimize the point cloud data and plan the shortest excavation path based on the optimized point cloud data; An efficiency prediction module is used to predict the excavation efficiency based on the distance of the shortest excavation path and the excavation speed; The display storage module is used to generate a tunneling efficiency report based on the predicted tunneling efficiency, and store the tunneling efficiency report and tunneling equipment data in a database.

5. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of the method for predicting excavation efficiency during tunnel excavation according to any one of claims 1 to 3 are implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting excavation efficiency during tunnel excavation according to any one of claims 1 to 3 are implemented.

Images