Autonomous navigation and positioning method and system for tunneling equipment based on multi-source data

Abstract

The present application provides a method and system for autonomous navigation and positioning of tunneling equipment based on multi-source data, which relates to the field of inertial navigation technology. The method includes: connecting multi-source monitoring equipment, acquiring multi-source data sets, performing spatiotemporal alignment, and establishing a monitoring data network; docking a transparent geological model, integrating it with the monitoring data network to construct a virtual model; fitting the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, positioning the tunneling equipment, and performing tunneling path optimization search; performing posture and inertial analysis in the virtual model based on the planned path to obtain a path posture strategy; and performing operational navigation control of the tunneling equipment. This application solves the technical problem of difficulty in long-term navigation and positioning in complex environments due to the lack of autonomous navigation of tunneling equipment. By integrating multi-source monitoring and virtual models, accurate positioning of tunneling equipment in complex environments is achieved, thereby improving tunneling efficiency and safety.

Description

Technical Field

[0001] The present application relates to the field of inertial navigation technology, and in particular to an autonomous navigation and positioning method and system for tunneling equipment based on multi-source data. Background Art

[0002] Tunneling equipment is a large-scale mechanical device used for rock and soil excavation in engineering environments such as underground tunnels and mines. It includes various models, including roadheaders, bolters, continuous miners, shield machines, shuttle cars, anchor carriers, crushers, and more. Due to the complex operating environment of tunneling equipment, tunneling equipment operates for long periods in narrow and long coal mine tunnels, facing complex conditions such as satellite signal denial, closed tunnel environments, prolonged vibration, electromagnetic interference, high temperatures and humidity, insufficient light, and high dust concentrations. Tunneling equipment typically relies on a single navigation source, resulting in difficult navigation and positioning during long operations and low accuracy, affecting operational efficiency and safety.

[0003] In summary, the existing technology has a technical problem that the tunneling equipment lacks autonomous navigation, resulting in difficulty in long-term navigation and positioning in complex environments. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for autonomous navigation and positioning of tunneling equipment based on multi-source data, so as to solve the technical problem in the prior art that tunneling equipment lacks autonomous navigation, resulting in difficulty in long-term navigation and positioning in complex environments.

[0005] In view of the above problems, the present application provides an autonomous navigation and positioning method and system for tunneling equipment based on multi-source data.

[0006] In the first aspect, the present application provides an autonomous navigation and positioning method for tunneling equipment based on multi-source data, which is implemented by an autonomous navigation and positioning system for tunneling equipment based on multi-source data, wherein the autonomous navigation and positioning method for tunneling equipment based on multi-source data includes: connecting multi-source monitoring equipment, obtaining multi-source data sets, aligning the multi-source data sets in time and space, and establishing a monitoring data network; docking with a transparent geological model, obtaining geological information such as thickness, faults, water-rich area range, and tunnel surrounding rock stress, and fusing them with the monitoring data network to construct a virtual model, which is used to simulate tunneling scenarios; fitting the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, positioning the tunneling equipment through the virtual model, and performing tunneling path optimization search according to the positioning data combined with the real-time data of the monitoring data network to obtain a planned path; performing posture and inertia analysis in the virtual model based on the planned path to obtain a path posture strategy, which is used to describe the posture control parameters of the tunneling equipment in the planned path; and performing operation navigation control of the tunneling equipment according to the path posture strategy.

[0007] Optionally, the multi-source monitoring equipment includes: inertial navigation, lidar, visual navigation, and geomagnetic sensor.

[0008] Optionally, the acquisition timestamp, acquisition position center, acquisition range, and acquisition parameters of the multi-source monitoring device are identified; the multi-source data set is time-aligned according to the acquisition timestamp; the position center coordinates, acquisition direction, and acquisition distance relationship are determined according to the acquisition position center, acquisition range, and acquisition parameters; a standard coordinate system is established, and the coordinates of each monitoring data in the multi-source data set are projected according to the position center coordinates, acquisition direction, and acquisition distance relationship, and data space alignment is performed according to the coordinate relationship; and the monitoring data network is constructed according to the time alignment and data space alignment relationship.

[0009] Optionally, the center coordinates of the position are aligned with the center point coordinates of the standard coordinate system, and the acquisition coordinates are determined according to the acquisition direction and acquisition distance; the monitoring data is projected into the standard coordinate system according to the acquisition coordinates of the monitoring data to locate the coordinate relationship of the monitoring data.

[0010] Optionally, the size, shape, dimensions of each component, and connection structure of the tunneling equipment are collected to obtain physical structure parameters; the speed, power, operating characteristics, and morphological change characteristics of the tunneling equipment in the operating state are analyzed to obtain operating state parameters; a correlation relationship between the operating state parameters and the physical structure parameters is established; coordinate transformation is performed according to the positional relationship between the position center coordinates and the physical structure parameters to determine the coordinate alignment relationship of the tunneling equipment, and the physical structure parameters of the tunneling equipment are fitted into the virtual model; according to the correlation relationship between the operating state parameters and the physical structure parameters, the operating state parameters are fitted into the virtual model.

[0011] Optionally, based on the monitoring data of the geomagnetic sensor, geomagnetic interference characteristics are obtained; an influence relationship between geomagnetic interference and inertial navigation is established; inertial navigation data interference compensation is performed based on the geomagnetic interference characteristics and the influence relationship; and the inertial monitoring data corrected by interference compensation is imported into the monitoring data network.

[0012] Optionally, based on the excavation task requirement parameters and the excavation execution obstacle penalty parameters, a fitness evaluation function is constructed, and according to the fitness evaluation function, a path optimization search module is established by relying on the optimization algorithm processing logic, and the path optimization search module is added to the virtual model; the excavation task requirement parameters and the positioning data are used as input parameters, and the path optimization search module is activated to identify the passable and obstacle features in the virtual model according to the geological structure and monitoring data network, and the path with the highest evaluation of the excavation task requirement parameters and the excavation execution obstacle penalty parameters is obtained through iterative search, and the planned path is output.

[0013] Optionally, according to the planned path, path excavation environment characteristics are identified in the virtual model; the path excavation environment characteristics are constrained and parsed according to the physical structure parameters and the operating status parameters to obtain excavation constraint conditions; the path posture correspondence analysis is performed according to the excavation task requirement parameters and the excavation constraint conditions to obtain the posture control parameters of each path node; the posture control parameters of each path node are smoothly connected according to the planned path to obtain the path posture strategy.

[0014] Optionally, the operating state parameters are simulated according to the control range of the posture control parameters to obtain the morphological change characteristics; the impact effect on the path excavation environment characteristics is simulated according to the physical structure parameters and the morphological change characteristics; based on the excavation task requirement parameters and the geological impact characteristics, the environmental impact effect threshold is set; the impact effect is constrained according to the environmental impact effect threshold to obtain the constraint control range of the posture control parameters and the excavation constraint conditions.

[0015] In the second aspect, the present application also provides an autonomous navigation and positioning system for tunneling equipment based on multi-source data, which is used to execute the autonomous navigation and positioning method for tunneling equipment based on multi-source data as described in the first aspect, wherein the autonomous navigation and positioning system for tunneling equipment based on multi-source data includes: a data acquisition and alignment module, which is used to connect multi-source monitoring equipment, obtain multi-source data sets, align the multi-source data sets in time and space, and establish a monitoring data network; a virtual model construction module, which is used to connect to the transparent geological model, obtain thickness, faults, water-rich area range, tunnel surrounding rock stress geological information, and fuse it with the monitoring data network to construct a virtual model, and the virtual model The model is used to simulate the tunneling scenario; the excavation path planning module is used to fit the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, locate the tunneling equipment through the virtual model, and optimize the tunneling path search according to the positioning data combined with the real-time data of the monitoring data network to obtain the planned path; the posture strategy determination module is used to perform posture and inertia analysis in the virtual model based on the planned path to obtain the path posture strategy, and the path posture strategy is used to describe the posture control parameters of the tunneling equipment in the planned path; the operation navigation control module is used to perform operation navigation control of the tunneling equipment according to the path posture strategy.

[0016] One or more technical solutions provided in this application have at least the following beneficial effects:

[0017] By connecting multi-source monitoring equipment, multi-source data sets are obtained, and the multi-source data sets are aligned in time and space to establish a monitoring data network; the transparent geological model is connected to obtain geological information such as thickness, faults, water-rich area range, and tunnel surrounding rock stress, and the information is integrated with the monitoring data network to construct a virtual model, which is used to simulate the tunneling scene; the physical structure parameters and operating status parameters of the tunneling equipment are fitted to the virtual model, the tunneling equipment is positioned through the virtual model, and the tunneling path optimization search is performed according to the positioning data combined with the real-time data of the monitoring data network to obtain a planned path; based on the planned path, posture and inertia analysis are performed in the virtual model to obtain a path posture strategy, which is used to describe the posture control parameters of the tunneling equipment in the planned path; and the operation navigation control of the tunneling equipment is performed according to the path posture strategy. That is to say, by integrating multi-source navigation data and combining it with a transparent geological model, including stratum thickness, fault location, water-rich area range, and tunnel surrounding rock stress, a virtual model is constructed, and the physical structure parameters and operating status parameters of the tunneling equipment are input into the virtual model to achieve the positioning of the tunneling equipment. Based on the positioning data and real-time monitoring data, an optimized search for the tunneling path is performed. According to the obtained planned path, posture and inertia analysis are performed in the virtual model to obtain the path posture strategy, guiding the tunneling equipment to complete the tunneling task safely and efficiently, thereby improving the navigation and positioning accuracy of the tunneling equipment in complex environments, thereby improving tunneling efficiency and safety.

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0020] Figure 1 This is a flow chart of the autonomous navigation and positioning method for tunneling equipment based on multi-source data in this application;

[0021] Figure 2 This is a structural diagram of the autonomous navigation and positioning system for tunneling equipment based on multi-source data in this application.

[0022] Description of the accompanying drawings: data acquisition and alignment module 11, virtual model construction module 12, mining path planning module 13, posture strategy determination module 14, operation navigation control module 15. DETAILED DESCRIPTION

[0023] This application solves the technical problem in the prior art that long-term navigation and positioning of tunneling equipment is difficult in complex environments due to the lack of autonomous navigation of tunneling equipment by providing a method and system for autonomous navigation and positioning of tunneling equipment based on multi-source data. By integrating multi-source navigation data and combining it with a transparent geological model, including stratum thickness, fault location, water-rich area range, and tunnel surrounding rock stress, a virtual model is constructed. The physical structure parameters and operating status parameters of the tunneling equipment are input into the virtual model to achieve positioning of the tunneling equipment. Based on the positioning data and real-time monitoring data, an optimized search for the tunneling path is performed. According to the obtained planned path, posture and inertia analysis are performed in the virtual model to obtain a path posture strategy, which guides the tunneling equipment to complete the tunneling task safely and efficiently, thereby improving the navigation and positioning accuracy of the tunneling equipment in complex environments, thereby improving tunneling efficiency and safety.

[0024] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0025] For example 1, please refer to the attached Figure 1 The present application provides a method for autonomous navigation and positioning of tunneling equipment based on multi-source data. The method is executed by an autonomous navigation and positioning system for tunneling equipment based on multi-source data. The method specifically includes the following steps:

[0026] S100: Connecting multi-source monitoring devices, acquiring multi-source data sets, performing spatiotemporal alignment on the multi-source data sets, and establishing a monitoring data network.

[0027] Furthermore, the present application S100 includes:

[0028] The multi-source monitoring equipment includes: inertial navigation, laser radar, visual navigation, and geomagnetic sensor.

[0029] Furthermore, the present application further comprises the following steps:

[0030] Identify the acquisition timestamp, acquisition location center, acquisition range, and acquisition parameters of the multi-source monitoring device; perform time alignment on the multi-source data set according to the acquisition timestamp; determine the relationship between the location center coordinates, acquisition direction, and acquisition distance according to the acquisition location center, acquisition range, and acquisition parameters; establish a standard coordinate system, project the coordinates of each monitoring data in the multi-source data set according to the relationship between the location center coordinates, acquisition direction, and acquisition distance, and perform data space alignment according to the coordinate relationship; and construct the monitoring data network according to the time alignment and data space alignment relationship.

[0031] The center coordinates of the position are aligned with the center point coordinates of the standard coordinate system, and the acquisition coordinates are determined according to the acquisition direction and acquisition distance; the monitoring data is projected into the standard coordinate system according to the acquisition coordinates of the monitoring data to locate the coordinate relationship of the monitoring data.

[0032] Specifically, multi-source monitoring equipment such as inertial navigation, lidar, visual navigation and geomagnetic sensors are connected to the tunneling equipment. These devices each have different measurement principles and advantages. Inertial navigation uses an inertial measurement unit to measure the acceleration and angular velocity of an object, and obtains the position and attitude information of the object through integral calculation; lidar measures the distance between the tunneling equipment and the surrounding environment by emitting a laser beam and receiving the reflected signal, generating a three-dimensional environmental map; visual navigation uses a camera to capture images of the surrounding environment, and achieves positioning and map construction through feature point extraction and matching; geomagnetic sensors measure the strength and direction of the earth's magnetic field to assist in heading determination and combat inertial navigation drift.

[0033] The raw logs of inertial navigation, lidar, visual navigation, and geomagnetic sensors are parsed to determine the timestamp, corresponding installation center coordinates, sensing range, and internal parameters of each data entry. The acquisition timestamp is the precise time stamp of each sensor at the sampling moment; the acquisition center is the sensor's installation location on the tunneling equipment, serving as the spatial reference point for the data; the acquisition range is the spatial area that each sensor can effectively monitor; and the acquisition parameters are the sensor settings during the data acquisition process, such as resolution and frequency.

[0034] Time alignment synchronizes data from different devices based on their acquisition timestamps, ensuring that all data can be compared and analyzed within the same timeframe. Spatial alignment projects data from different devices into a unified coordinate system, ensuring that all data can be integrated and analyzed within the same spatial framework. By comparing and adjusting the data timestamps of each device, data from all sensors can be analyzed within a unified timeframe. Time synchronization algorithms (such as the Network Time Protocol (NTP)) are used to time-align multi-source datasets based on their acquisition timestamps, ensuring that all data is on the same timebase. Time synchronization algorithms align the times of different devices to a unified timebase. They transmit time synchronization messages across the network, comparing the times of different devices and adjusting them to match the unified timebase. For example, if the inertial navigation system's time is 50 milliseconds ahead of the lidar, the inertial navigation system's time is adjusted to synchronize with the lidar and other devices.

[0035] Based on the acquisition location center, acquisition range, and acquisition parameters, the location center coordinates, acquisition direction, and acquisition distance relationship of each monitoring device are determined. The location center coordinates are the coordinate values ​​of the acquisition location center; the acquisition direction is the direction of data acquisition, such as the scanning direction of a LiDAR or the field of view of a visual sensor; and the acquisition distance relationship is the distance relationship between the data acquisition point and the location center. This determines the maximum distance and range that the device can perceive and is used to describe the device's spatial detection capabilities.

[0036] Construct a standard coordinate system. Select a fixed coordinate system as the standard coordinate system. Usually, a known reference point is selected as the origin, and the coordinate system is constructed using preset coordinate axes (such as the X-axis, Y-axis, and Z-axis). Based on the center coordinates of each device, the position of each sensor is converted into coordinates in the standard coordinate system. Through coordinate transformation and adjustments such as rotation and translation, multiple monitoring devices can be aligned in space. The acquisition coordinates of each sensor data are determined based on the acquisition direction and acquisition distance. In other words, all sensor data are uniformly transformed into the standard coordinate system based on the coordinate points (acquisition coordinates) calculated according to their own center coordinates + direction + distance, and the three-dimensional position of each sensor data in the unified coordinate system is determined.

[0037] Based on the acquisition coordinates of the monitoring data, the data is projected into a standard coordinate system. Each sensor data point is placed in the standard coordinate system according to its acquisition coordinates, thus achieving spatial alignment of the monitoring data. For example, in the point cloud data scanned by the LiDAR, the X, Y, and Z coordinates of each point are calculated based on its position and orientation relative to the center coordinates of the location and projected into the standard coordinate system.

[0038] Combining the results of temporal and spatial alignment, a monitoring data network is constructed, linking the sensor data across time and space to form a complete data model. The monitoring data network is a collection of data formed by the alignment of multi-source sensor data. It represents the real-time location, posture, and environmental data of the device throughout the monitoring process. Temporal and spatial alignment ensures that sensor data from different devices can be compared and analyzed under unified standards, improving the efficiency and accuracy of data fusion.

[0039] S200: Connecting to the transparent geological model, obtaining geological information on thickness, faults, water-rich area, and tunnel surrounding rock stress, and integrating the information with the monitoring data network to construct a virtual model, which is used to simulate the tunneling scenario.

[0040] Specifically, the transparent geological model is a three-dimensional geological model created based on geological exploration data (such as drilling, seismic waves, and groundwater monitoring). It can display information such as underground structure, rock formations, faults, and hydrogeology. Through the transparent geological model, geological information such as the thickness of the excavation area, faults, the extent of water-rich areas, and the stress of the roadway surrounding rock can be obtained. Thickness refers to the thickness of the rock or mineral layer, which affects the difficulty of excavation and tool selection; faults refer to the fractures and displacements of underground rock formations, which may pose geological risks to excavation equipment; the extent of water-rich areas refers to areas with high groundwater content, which may affect excavation operations (such as the risk of water inrush); and the stress of the roadway surrounding rock indicates the pressure conditions around the underground rock formation, which affects the safety and stability of the excavation process.

[0041] This geological information is integrated with the monitoring data network. Using data fusion algorithms (such as Kalman filtering), real-time monitoring data and static geological information are effectively combined to create a dynamic virtual tunneling scenario. Kalman filtering is used to fuse data from different sources (such as sensor data and geological data) into a precise estimate. Monitoring data provides information on the position, attitude, and speed of tunneling equipment, while the transparent geological model provides detailed information on the underground environment. The combination of the two enables a better simulation of the tunneling process.

[0042] Using a digital twin model, geological information (such as rock formations, faults, water-rich areas, and surrounding rock stress) and a monitoring data network are integrated into a unified virtual environment to simulate tunneling equipment operating in various geological environments. The monitoring data network ensures consistent coordinate systems between the real and virtual worlds. All sensors and geological information can be mapped into the same standard coordinate system, ensuring a precise correspondence between the virtual and real-world tunneling scenarios. Simply put, geological information (such as rock formations, faults, and water-rich areas) is mapped into the virtual model to clearly represent the geological environment. The virtual model should be dynamically updated based on real-time monitoring data to reflect the movement of the tunneling equipment and environmental changes. Based on this constructed virtual model, tunneling scenarios are simulated, including planning optimal tunneling equipment paths, simulating equipment behavior in different geological environments, monitoring environmental changes during tunneling, and predicting potential risks.

[0043] By connecting to the transparent geological model and monitoring data network, the constructed virtual model can provide accurate excavation scenario simulation, thereby achieving more accurate navigation positioning and path planning, and improving the safety and efficiency of excavation operations.

[0044] S300: Fitting the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, positioning the tunneling equipment through the virtual model, and performing tunneling path optimization search according to the positioning data combined with the real-time data of the monitoring data network to obtain a planned path.

[0045] Furthermore, the present application S300 includes:

[0046] The size, shape, dimensions of each component, and connection structure of the tunneling equipment are collected to obtain physical structure parameters; the speed, power, operating characteristics, and morphological change characteristics of the tunneling equipment in the operating state are analyzed to obtain operating state parameters; a correlation relationship between the operating state parameters and the physical structure parameters is established; coordinate transformation is performed according to the positional relationship between the position center coordinates and the physical structure parameters, the coordinate alignment relationship of the tunneling equipment is determined, and the physical structure parameters of the tunneling equipment are fitted into the virtual model; the operating state parameters are fitted into the virtual model according to the correlation relationship between the operating state parameters and the physical structure parameters.

[0047] Specifically, static characteristics such as the size, shape, component dimensions, and connection structure of the tunneling equipment are acquired to determine the equipment's physical appearance and the relative positions of its components, i.e., its physical structural parameters. These parameters can typically be obtained from the equipment's factory specifications or laser measurement. During operation, the equipment's speed, power, operating characteristics, and morphological changes (such as inclination and posture changes during tunneling) are monitored to reflect the equipment's workload and motion state. For example, the equipment's behavior during acceleration or deceleration, or morphological changes caused by load changes during operation, can be monitored.

[0048] Establish a correlation between operating state parameters and physical structure parameters. Specifically, understand how the equipment's physical structure affects its operating state, and how the operating state in turn affects the equipment's physical structure. By combining operating state data (such as power, speed, and stress) collected during actual tunneling operations with the physical structure model, regression analysis is used to identify the mapping between physical structure and operating state. The relationship between the equipment's power consumption and physical structure parameters (such as size, shape, component dimensions, and connection structure) under different workloads is measured to understand the impact of the physical structure on power consumption.

[0049] Using historically collected physical structure data and operational status data, the dataset is divided into several subsets. Each subset is used as a test set, and the remaining subsets are used as training sets for model training and evaluation. The average model performance is ultimately calculated. The process of training a regression model is essentially a model fitting process, with the goal of optimizing model parameters (such as regression coefficients) by minimizing error. A set of regression coefficients is found that minimizes the difference between the model's predicted values ​​and the true values. The regression coefficients are randomly initialized, typically to zero. The training set is then used as input to the model to calculate predicted values, predicting the model's operational status parameters based on the physical structure parameters. The error between the predicted values ​​and the true values ​​is calculated using the mean squared error (MSE). The regression coefficients are continuously adjusted using a gradient descent algorithm to minimize the error. The above steps are repeated until the error reaches a minimum or the preset number of iterations is reached. Training is then terminated, resulting in the correlation between the operational status parameters and the physical structure parameters.

[0050] Based on the positional relationship between the center coordinates and the physical structural parameters, coordinate transformation is performed to convert the equipment's physical structural parameters into the standard coordinate system of the virtual model, ensuring that the digital model of the equipment aligns with other elements in the virtual scene (such as geological structures). Based on the geometric information contained in the physical structural parameters, the equipment's exact position in the virtual model is calculated, ensuring that the spatial relationship between the equipment in the virtual model and the actual equipment is consistent. For example, the center point of the tunneling equipment in the virtual model must be aligned with the center point of the actual equipment to ensure that the equipment's position in the virtual environment is consistent with the actual equipment. The physical structural parameters of the tunneling equipment (such as component dimensions and connection methods) are mapped to the virtual model to ensure that the virtual model reflects the actual equipment's appearance and the structural relationships between its components. For example, the tunneling equipment in the virtual model should have identical dimensions and positions to the actual equipment's components (such as the cutterhead and support arm).

[0051] Based on these relationships, operating state parameters (such as speed, power, and shape changes) are used to dynamically adjust the equipment state in the virtual model, accurately reflecting the dynamic behavior of the real equipment. For example, if the tunneling equipment encounters hard rock during operation, the virtual model will adjust its displayed power and speed based on the operating state parameters to reflect the equipment's behavior under actual operating conditions. By fitting physical structural parameters and operating state parameters into the virtual model, the actual operating state of the tunneling equipment can be accurately simulated, providing highly accurate operational simulation.

[0052] Furthermore, the present application further comprises the following steps:

[0053] According to the monitoring data of the geomagnetic sensor, the geomagnetic interference characteristics are obtained; the influence relationship between the geomagnetic interference and the inertial navigation is established; according to the geomagnetic interference characteristics and the influence relationship, the inertial navigation data interference compensation is performed; and the inertial monitoring data corrected by the interference compensation is imported into the monitoring data network.

[0054] Specifically, geomagnetic sensors collect monitoring data, including the strength and direction of the geomagnetic field, which can vary over time and location. The magnetic field strength vector (X, Y, Z) recorded by the geomagnetic sensors during tunneling is compared with a standard geomagnetic reference value to calculate the disturbance vector. The geomagnetic disturbance signature is a characteristic interference signal caused by variations in the geomagnetic field. These variations can be caused by underground mineral deposits, geological structures, or other factors.

[0055] The relationship between geomagnetic disturbances and inertial navigation systems (INS) is established. Inertial navigation systems use gyroscopes and accelerometers to measure angular velocity and acceleration, independently of external signals, to estimate position and attitude. However, these systems suffer from cumulative error drift, which can be further amplified by environmental disturbances, resulting in attitude drift and positioning errors. A mathematical mapping is established between geomagnetic disturbances (input) and inertial navigation errors (output) for error prediction and compensation. Geomagnetic monitoring data includes magnetic field strength along the X, Y, and Z axes. These magnetic field strengths are compared with standard geomagnetic reference values ​​in the absence of disturbances to identify anomalies. The attitude angles output by the INS are compared with the true reference values ​​to determine the navigation error. A mapping model is constructed using geomagnetic disturbances as input and inertial navigation errors as output. The model is trained and evaluated using training and validation sets divided into historically collected data. An additional test set is used for model validation under known geomagnetic disturbance conditions. Ultimately, this mapping model can be used to predict the potential errors of an INS under current geomagnetic disturbances.

[0056] Based on the established influence relationships and geomagnetic interference characteristics, interference compensation is performed on the inertial navigation data, adjusting or correcting the inertial navigation system output to eliminate or reduce the impact of geomagnetic interference. The compensated inertial navigation output (position, attitude, velocity, etc.) is imported into the established monitoring data network as effective monitoring data, where it is used together with other data sources such as vision and lidar to participate in virtual model reconstruction, path repositioning, and navigation control. For example, the measured geomagnetic values ​​are (35, 12, -25) μT, while the standard reference values ​​are (30, 10, -30) μT. The modulus calculated from the measured values ​​is approximately 44.67 μT, while the modulus calculated from the reference values ​​is approximately 43.59 μT, a difference of 1.08 μT. This indicates a significant change in the geomagnetic vector strength, indicating the presence of interference. Under these interference conditions, the inertial navigation system estimated the measured inertial navigation heading angle to be 76.5°, while the true inertial navigation heading angle measured by a high-precision external system was 73.0°. The inferred inertial navigation error was 3.5°, a target variable that needed to be predicted and compensated for by modeling the relationship between geomagnetic interference and inertial navigation error. Using a trained geomagnetic interference to inertial navigation error mapping model, with inputs based on these magnetic field fluctuation characteristics (such as a difference of 5, 2, 5 in each direction or a modulus fluctuation of 1.08), the regression model predicted an inertial navigation heading error of 3.4°, demonstrating the effectiveness of the mapping model. The original inertial navigation heading angle of 76.5° was corrected to 73.1° after compensation based on the predicted error, significantly reducing the error.

[0057] By sensing geomagnetic disturbances in real time, constructing a functional mapping between disturbances and navigation errors, and dynamically compensating inertial navigation data based on predicted errors, the problem of error accumulation of inertial navigation systems in complex environments is effectively solved, significantly improving the positioning accuracy and stability of tunneling equipment in the absence of external signals.

[0058] Furthermore, the present application further comprises the following steps:

[0059] Based on the excavation task requirement parameters and the excavation execution obstacle penalty parameters, a fitness evaluation function is constructed. According to the fitness evaluation function, a path optimization search module is established by relying on the optimization algorithm processing logic, and the path optimization search module is added to the virtual model. The excavation task requirement parameters and positioning data are used as input parameters, and the path optimization search module is activated to identify the passable and obstacle features in the virtual model according to the geological structure and monitoring data network. Through iterative search, the path with the highest evaluation of the excavation task requirement parameters and the excavation execution obstacle penalty parameters is obtained, and the planned path is output.

[0060] Specifically, tunneling mission requirement parameters include tunneling targets, tunneling speed, and tunneling efficiency, which guide the operation of tunneling equipment. Tunneling execution penalty parameters include obstacles, geological conditions, and safety restrictions, which are used to assess the feasibility and safety of tunneling paths. Tunneling execution penalty parameters are used to measure the impact of adverse conditions encountered along the path and are penalty-type parameters.

[0061] The fitness evaluation function is constructed based on the excavation task requirement parameters and the excavation execution obstacle penalty parameters, and the excavation target, speed, efficiency, obstacles, geological conditions, safety restrictions and other factors are comprehensively considered to evaluate the quality of the excavation path. Specifically, the task requirement target (such as target point, shortest time, lowest risk) is set, combined with the penalty coefficient of the obstacle area, the function form is designed and the parameters are preliminarily adjusted to obtain the fitness evaluation function. For example, the fitness evaluation function Where a and b are weight coefficients, determined based on actual needs or user-side confirmation. f(a) represents the tunneling task requirement parameters, such as tunneling target, tunneling speed, and tunneling efficiency. This parameter is typically determined based on different tunneling operations and is subject to actual conditions. f(b) is a penalty parameter, typically determined based on the faults, water-rich layers, and high-level areas corresponding to the tunneling operation, to evaluate the quality of the tunneling path.

[0062] A path optimization search module was established, using an optimization algorithm to search and optimize tunneling paths within the virtual model. This module was embedded as a plug-in within the virtual model architecture. Based on the tunneling task parameters and positioning data, the module was activated to perform a planned path search within the virtual model. Based on the geological structure and monitoring data network, passability and obstacle characteristics were identified. A batch of paths (individuals) were randomly generated. Each path consisted of a set of continuous 3D coordinate points. These paths typically required determining the presence of obstacles. If so, the path was modified to ensure the obstacle was circumvented. For each modified path, the cost was determined based on the geological data. Paths with high costs or near-impassable paths were eliminated to obtain the final feasible paths. Specifically, the geological structure can be clearly defined within the aforementioned virtual model to determine path passability and obstacle identification, thereby generating feasible paths. These paths are represented as point sequences, encoded as node numbers and directions.

[0063] Using the fitness evaluation function in the path optimization search module, the fitness of a batch of paths (individuals) is calculated, resulting in a fitness score for each path. Paths with high fitness are retained for the next generation, and the middle segments of every two paths are swapped to generate new paths. Nodes on some paths are fine-tuned or detoured to generate more new paths, which are used to update the original feasible paths. The fitness evaluation function is again used to calculate the fitness of the updated feasible paths, obtaining a fitness score for each path. This process is repeated until the maximum number of iterations is reached or the fitness converges. During each generation of optimization, poor paths are gradually eliminated, while good paths are retained and replicated. Among the multiple paths ultimately determined, the path with the highest fitness score is selected as the planned path. This path is the path with the highest evaluation of both the tunneling task requirement parameters and the tunneling execution obstruction penalty parameters.

[0064] By constructing a fitness evaluation function and a path optimization search module, the excavation path can be optimized and searched, which helps to improve the safety and efficiency of the excavation operation. This is because it comprehensively considers the excavation task requirement parameters and the excavation execution obstacle penalty parameters to search for the optimal excavation path.

[0065] S400: performing posture and inertia analysis in the virtual model based on the planned path to obtain a path posture strategy, wherein the path posture strategy is used to describe posture control parameters of the tunneling equipment in the planned path.

[0066] Furthermore, the present application S400 includes:

[0067] According to the planned path, path excavation environment characteristics are identified in the virtual model; constraint analysis is performed on the path excavation environment characteristics according to the physical structure parameters and the operating status parameters to obtain excavation constraint conditions; path posture correspondence analysis is performed according to the excavation task requirement parameters and the excavation constraint conditions to obtain posture control parameters of each path node; and the posture control parameters of each path node are smoothly connected according to the planned path to obtain the path posture strategy.

[0068] Furthermore, the present application further comprises the following steps:

[0069] The operating state parameters are simulated according to the control range of the posture control parameters to obtain the morphological change characteristics; the influence effect on the path excavation environment characteristics is simulated according to the physical structure parameters and the morphological change characteristics; the environmental influence effect threshold is set based on the excavation task requirement parameters and the geological influence characteristics; the influence effect is constrained according to the environmental influence effect threshold to obtain the constraint control range of the posture control parameters and the excavation constraint conditions.

[0070] Specifically, based on the finalized planned path, the corresponding path nodes are loaded into the virtual model, and the environmental characteristics surrounding each node are identified to obtain the path excavation environment characteristics. These characteristics include geological conditions, obstacles, spatial constraints, and other environmental characteristics at each node in the planned path. The attitude control parameters of the excavation equipment are then obtained, namely the allowable range of attitude adjustment for the excavation equipment, such as angle and speed.

[0071] The control range of the attitude control parameters is input into the virtual model to simulate the operating state parameters. The changes in the speed, acceleration, steering angle and other operating state parameters of the tunneling equipment caused by the changes in the attitude control parameters during operation are simulated to obtain the morphological change characteristics, that is, the change characteristics of the shape, position, etc. of the tunneling equipment during operation.

[0072] Combining physical structure parameters and morphological change characteristics, the impact of tunneling equipment on the path environment is simulated, and the physical structure parameters such as size, shape, and strength of the tunneling equipment, as well as the morphological change characteristics caused by changes in posture control parameters, are evaluated, and their impact on underground environments such as rocks, faults, and water bodies is evaluated.

[0073] The required parameters for the tunneling mission include tunneling targets, tunneling speed, and tunneling efficiency, which are used to guide the operation of tunneling equipment. Geological impact characteristics are the impact of geological conditions on tunneling operations, such as rock hardness and faults. Based on the required parameters for the tunneling mission and the geological impact characteristics, an environmental impact threshold is set, that is, the maximum allowable value of the environmental impact is set to ensure construction safety. The set threshold is used to limit the simulated environmental impact effect, and the range of attitude control parameters that meets the environmental impact threshold conditions is determined, thereby obtaining tunneling constraints to ensure that the impact of tunneling equipment on the environment during operation remains within a safe range while meeting mission requirements. The tunneling constraints are the final upper and lower limit ranges after further tightening the attitude control parameters under the environmental threshold constraints, which serve as the operational boundaries for safe and efficient tunneling.

[0074] Based on the required tunneling task parameters and tunneling constraints, each node on the planned path is analyzed for its attitude, obtaining the attitude control parameters for each node. Specifically, for each node, a steering vector is calculated along the path between two adjacent nodes, and the theoretical attitude parameters are decomposed. The theoretical attitude is compared with the tunneling constraints. If the upper limit is exceeded, the value is truncated at the boundary value. The final attitude control parameters are determined based on the operating status (e.g., switching to low-speed mode when the current torque is less than the required torque). The attitude control parameters for all nodes are collected and smoothly transitioned to avoid sudden changes. Interpolation algorithms or smoothing filtering techniques are used to smooth the attitude control parameters at each node, resulting in an overall attitude control strategy for the tunneling equipment along the planned path. An appropriate interpolation algorithm, such as spline interpolation, is selected based on the data characteristics and requirements to interpolate the attitude control parameters for the node. The interpolated data is smoothed using an appropriate smoothing filtering technique based on the noise level and data variation trends. The smoothed attitude control parameters are plotted on a graph to visually demonstrate the smoothing effect. The error before and after smoothing is calculated to evaluate the smoothing effect. According to error analysis and actual needs, adjust the parameters of the interpolation algorithm or smoothing filter to optimize the smoothing effect.

[0075] The path attitude strategy determines attitude control parameters for each path node, such as speed, acceleration, and steering angle, based on the planned path and the required parameters of the tunneling task. This ensures that the tunneling equipment can smoothly transition between various attitudes as it moves along the planned path, avoiding sudden acceleration, deceleration, or steering, thereby improving operational safety and efficiency. By identifying the characteristics of the tunneling environment, analyzing tunneling constraints, and deriving the path attitude strategy, precise control of the tunneling equipment is achieved, helping to improve the safety and efficiency of tunneling operations.

[0076] S500: Performing operation navigation control of the tunneling equipment according to the path posture strategy.

[0077] Specifically, based on the path attitude strategy, the attitude control parameters that should be adopted by the tunneling equipment during operation are determined, including parameters such as speed, acceleration, and steering angle at each path node. These attitude control parameters are then input into the tunneling equipment's control center to control its operating status. Based on the input attitude control parameters, the tunneling equipment's operating status, such as speed, acceleration, and steering angle, is adjusted to ensure that it operates according to the predetermined path and attitude strategy. By monitoring the tunneling equipment's operating status and position in real time, feedback and adjustments are provided to the control center to ensure that it always operates according to the predetermined path and attitude strategy. By performing operational navigation control of the tunneling equipment according to the path attitude strategy, precise control of the tunneling equipment can be achieved, guiding it to complete the tunneling task safely and efficiently.

[0078] In summary, the autonomous navigation and positioning method for tunneling equipment based on multi-source data provided by this application has the following beneficial effects:

[0079] By connecting multi-source monitoring equipment, multi-source data sets are obtained, and the multi-source data sets are aligned in time and space to establish a monitoring data network; the transparent geological model is connected to obtain geological information such as thickness, faults, water-rich area range, and tunnel surrounding rock stress, and the information is integrated with the monitoring data network to construct a virtual model, which is used to simulate the tunneling scene; the physical structure parameters and operating status parameters of the tunneling equipment are fitted to the virtual model, the tunneling equipment is positioned through the virtual model, and the tunneling path optimization search is performed according to the positioning data combined with the real-time data of the monitoring data network to obtain a planned path; based on the planned path, posture and inertia analysis are performed in the virtual model to obtain a path posture strategy, which is used to describe the posture control parameters of the tunneling equipment in the planned path; and the operation navigation control of the tunneling equipment is performed according to the path posture strategy. That is to say, by integrating multi-source navigation data and combining it with a transparent geological model, including stratum thickness, fault location, water-rich area range, and tunnel surrounding rock stress, a virtual model is constructed, and the physical structure parameters and operating status parameters of the tunneling equipment are input into the virtual model to achieve the positioning of the tunneling equipment. Based on the positioning data and real-time monitoring data, an optimized search for the tunneling path is performed. According to the obtained planned path, posture and inertia analysis are performed in the virtual model to obtain the path posture strategy, guiding the tunneling equipment to complete the tunneling task safely and efficiently, thereby improving the navigation and positioning accuracy of the tunneling equipment in complex environments, thereby improving tunneling efficiency and safety.

[0080] In the second embodiment, based on the same inventive concept as the tunneling equipment autonomous navigation and positioning method based on multi-source data in the first embodiment, the present application also provides a tunneling equipment autonomous navigation and positioning system based on multi-source data, please refer to the attached Figure 2 The autonomous navigation and positioning system for tunneling equipment based on multi-source data includes:

[0081] The data acquisition and alignment module 11 is used to connect multi-source monitoring equipment, obtain multi-source data sets, align the multi-source data sets in time and space, and establish a monitoring data network; the virtual model construction module 12 is used to connect to the transparent geological model, obtain geological information such as thickness, faults, water-rich area range, and tunnel surrounding rock stress, and integrate it with the monitoring data network to construct a virtual model, and the virtual model is used to simulate the tunneling scene; the excavation path planning module 13 is used to fit the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, locate the tunneling equipment through the virtual model, and optimize the tunneling path according to the positioning data combined with the real-time data of the monitoring data network to obtain the planned path; the posture strategy determination module 14 is used to perform posture and inertia analysis in the virtual model based on the planned path to obtain a path posture strategy, and the path posture strategy is used to describe the posture control parameters of the tunneling equipment in the planned path; the operation navigation control module 15 is used to perform operation navigation control of the tunneling equipment according to the path posture strategy.

[0082] Furthermore, the data acquisition and alignment module 11 in the autonomous navigation and positioning system for tunneling equipment based on multi-source data is further configured to:

[0083] The multi-source monitoring equipment includes: inertial navigation, laser radar, visual navigation, and geomagnetic sensor.

[0084] Furthermore, the data acquisition and alignment module 11 in the autonomous navigation and positioning system for tunneling equipment based on multi-source data is further configured to:

[0085] Identify the acquisition timestamp, acquisition location center, acquisition range, and acquisition parameters of the multi-source monitoring device; perform time alignment on the multi-source data set according to the acquisition timestamp; determine the relationship between the location center coordinates, acquisition direction, and acquisition distance according to the acquisition location center, acquisition range, and acquisition parameters; establish a standard coordinate system, project the coordinates of each monitoring data in the multi-source data set according to the relationship between the location center coordinates, acquisition direction, and acquisition distance, and perform data space alignment according to the coordinate relationship; and construct the monitoring data network according to the time alignment and data space alignment relationship.

[0086] Furthermore, the data acquisition and alignment module 11 in the autonomous navigation and positioning system for tunneling equipment based on multi-source data is further configured to:

[0087] The center coordinates of the position are aligned with the center point coordinates of the standard coordinate system, and the acquisition coordinates are determined according to the acquisition direction and acquisition distance; the monitoring data is projected into the standard coordinate system according to the acquisition coordinates of the monitoring data to locate the coordinate relationship of the monitoring data.

[0088] Furthermore, the excavation path planning module 13 in the tunneling equipment autonomous navigation and positioning system based on multi-source data is further configured to:

[0089] The size, shape, dimensions of each component, and connection structure of the tunneling equipment are collected to obtain physical structure parameters; the speed, power, operating characteristics, and morphological change characteristics of the tunneling equipment in the operating state are analyzed to obtain operating state parameters; a correlation relationship between the operating state parameters and the physical structure parameters is established; coordinate transformation is performed according to the positional relationship between the position center coordinates and the physical structure parameters, the coordinate alignment relationship of the tunneling equipment is determined, and the physical structure parameters of the tunneling equipment are fitted into the virtual model; the operating state parameters are fitted into the virtual model according to the correlation relationship between the operating state parameters and the physical structure parameters.

[0090] Furthermore, the excavation path planning module 13 in the tunneling equipment autonomous navigation and positioning system based on multi-source data is further configured to:

[0091] According to the monitoring data of the geomagnetic sensor, the geomagnetic interference characteristics are obtained; the influence relationship between the geomagnetic interference and the inertial navigation is established; according to the geomagnetic interference characteristics and the influence relationship, the inertial navigation data interference compensation is performed; and the inertial monitoring data corrected by the interference compensation is imported into the monitoring data network.

[0092] Furthermore, the excavation path planning module 13 in the tunneling equipment autonomous navigation and positioning system based on multi-source data is further configured to:

[0093] Based on the excavation task requirement parameters and the excavation execution obstacle penalty parameters, a fitness evaluation function is constructed. According to the fitness evaluation function, a path optimization search module is established by relying on the optimization algorithm processing logic, and the path optimization search module is added to the virtual model. The excavation task requirement parameters and positioning data are used as input parameters, and the path optimization search module is activated to identify the passable and obstacle features in the virtual model according to the geological structure and monitoring data network. Through iterative search, the path with the highest evaluation of the excavation task requirement parameters and the excavation execution obstacle penalty parameters is obtained, and the planned path is output.

[0094] Furthermore, the posture strategy determination module 14 in the tunneling equipment autonomous navigation and positioning system based on multi-source data is further configured to:

[0095] According to the planned path, path excavation environment characteristics are identified in the virtual model; constraint analysis is performed on the path excavation environment characteristics according to the physical structure parameters and the operating status parameters to obtain excavation constraint conditions; path posture correspondence analysis is performed according to the excavation task requirement parameters and the excavation constraint conditions to obtain posture control parameters of each path node; and the posture control parameters of each path node are smoothly connected according to the planned path to obtain the path posture strategy.

[0096] Furthermore, the posture strategy determination module 14 in the tunneling equipment autonomous navigation and positioning system based on multi-source data is further configured to:

[0097] The operating state parameters are simulated according to the control range of the posture control parameters to obtain the morphological change characteristics; the influence effect on the path excavation environment characteristics is simulated according to the physical structure parameters and the morphological change characteristics; the environmental influence effect threshold is set based on the excavation task requirement parameters and the geological influence characteristics; the influence effect is constrained according to the environmental influence effect threshold to obtain the constraint control range of the posture control parameters and the excavation constraint conditions.

[0098] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The autonomous navigation and positioning method for tunneling equipment based on multi-source data and the specific examples in Example 1 are also applicable to the autonomous navigation and positioning system for tunneling equipment based on multi-source data in this embodiment. Through the above detailed description of the autonomous navigation and positioning method for tunneling equipment based on multi-source data, those skilled in the art can clearly understand the autonomous navigation and positioning system for tunneling equipment based on multi-source data in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0099] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0100] Obviously, for those skilled in the art, several improvements and modifications can be made to the present application without departing from the principles of the present application, and these improvements and modifications also fall within the scope of protection of the present application.

Claims

1. An autonomous navigation and positioning method for tunneling equipment based on multi-source data, characterized in that: include: Connecting multi-source monitoring equipment, acquiring multi-source data sets, performing spatiotemporal alignment on the multi-source data sets, and establishing a monitoring data network; Connecting to the transparent geological model to obtain geological information on thickness, faults, water-rich areas, and stress of tunnel surrounding rocks, and integrating it with the monitoring data network to build a virtual model, which is used to simulate tunneling scenarios; Fitting the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, positioning the tunneling equipment through the virtual model, and performing tunneling path optimization search based on the positioning data combined with real-time data from the monitoring data network to obtain a planned path; Performing posture and inertia analysis in the virtual model based on the planned path to obtain a path posture strategy, wherein the path posture strategy is used to describe posture control parameters of the tunneling equipment in the planned path; Performing operation navigation control of the tunneling equipment according to the path posture strategy; The multi-source monitoring equipment includes: inertial navigation, laser radar, visual navigation, and geomagnetic sensor; According to the positioning data combined with the real-time data of the monitoring data network, the tunneling path optimization search is carried out to obtain the planned path. Previously, it also included: Obtaining a geomagnetic interference feature based on monitoring data from a geomagnetic sensor, wherein the geomagnetic interference feature is a disturbance vector calculated by comparing the magnetic field intensity vector recorded by the geomagnetic sensor during the tunneling process with a standard geomagnetic reference value; Establishing the influence relationship between geomagnetic interference and inertial navigation includes: using geomagnetic interference as input and inertial navigation error as output, constructing a mapping model, and training and validating the model using historically collected data; wherein the geomagnetic interference is an anomaly determined by comparing the magnetic field strength of the X, Y, and Z axes of geomagnetic monitoring data with a standard geomagnetic reference value in the absence of interference; and the inertial navigation error is a navigation error obtained by comparing the attitude angle output by the inertial navigation with a true reference value; performing inertial navigation data interference compensation according to the geomagnetic interference characteristics and the influence relationship; The inertial monitoring data corrected by the interference compensation is imported into the monitoring data network.

2. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 1, characterized in that: The multi-source datasets are temporally and spatially aligned to establish a monitoring data network, including: Identify the acquisition timestamp, acquisition location center, acquisition range, and acquisition parameters of the multi-source monitoring device; Time-aligning the multi-source datasets according to the acquisition timestamps; Determine the relationship between the position center coordinates, the acquisition direction, and the acquisition distance according to the acquisition position center, the acquisition range, and the acquisition parameters; Establishing a standard coordinate system, projecting the coordinates of each monitoring data in the multi-source data set according to the relationship between the position center coordinates, the acquisition direction, and the acquisition distance, and aligning the data space according to the coordinate relationship; The monitoring data network is constructed according to the time alignment and data space alignment relationship.

3. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 2, characterized in that: Projecting the coordinates of each monitoring data in the multi-source data set according to the relationship between the position center coordinates, the acquisition direction, and the acquisition distance includes: Aligning the center coordinates of the position with the center coordinates of the standard coordinate system, and determining the acquisition coordinates according to the acquisition direction and acquisition distance; The monitoring data is projected into the standard coordinate system according to the acquisition coordinates of the monitoring data to locate the coordinate relationship of the monitoring data.

4. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 3 is characterized in that: Fitting the physical structure parameters and operating state parameters of the tunneling equipment to the virtual model includes: Collect the size, shape, dimensions of each component, and connection structure of the tunneling equipment to obtain physical structural parameters; Analyzing the speed, power, operating characteristics, and morphological change characteristics of the tunneling equipment in an operating state to obtain operating state parameters; Establishing an association relationship between the operating state parameter and the physical structure parameter; performing coordinate transformation according to the positional relationship between the position center coordinates and the physical structural parameters, determining the coordinate alignment relationship of the tunneling equipment, and fitting the physical structural parameters of the tunneling equipment into the virtual model; According to the association relationship between the operating state parameters and the physical structure parameters, the operating state parameters are fitted into the virtual model.

5. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 1, characterized in that: Based on the positioning data combined with the real-time data of the monitoring data network, the tunneling path optimization search is carried out to obtain the planned path, including: Based on the excavation task requirement parameters and the excavation execution obstruction penalty parameters, a fitness evaluation function is constructed, a path optimization search module is established according to the fitness evaluation function and the optimization algorithm processing logic, and the path optimization search module is added to the virtual model; Taking the excavation task requirement parameters and positioning data as input parameters, the path optimization search module is activated to identify the passable and obstacle characteristics in the virtual model according to the geological structure and monitoring data network. Through iterative search, the path with the highest evaluation of the excavation task requirement parameters and the excavation execution obstacle penalty parameters is obtained, and the planned path is output.

6. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 4, characterized in that: Performing posture and inertia analysis on the virtual model based on the planned path to obtain a path posture strategy includes: identifying path excavation environment characteristics in the virtual model according to the planned path; Perform constraint analysis on the path excavation environment characteristics according to the physical structure parameters and the operating state parameters to obtain excavation constraint conditions; Analyze the path posture correspondence according to the excavation task requirement parameters and the excavation constraint conditions to obtain the posture control parameters of each path node; The posture control parameters of each path node are smoothly connected according to the planned path to obtain the path posture strategy.

7. The autonomous navigation and positioning method for tunneling equipment based on multi-source data according to claim 6, characterized in that: The excavation environment characteristics of the path are constrained and analyzed according to the physical structure parameters and the operating state parameters to obtain excavation constraint conditions, including: According to the control range of the attitude control parameters, the running state parameters are simulated to obtain the morphological change characteristics; Simulating the effects of the path excavation environment characteristics according to the physical structure parameters and morphological change characteristics; Set environmental impact thresholds based on tunneling task requirements and geological impact characteristics; The impact effect is constrained according to the environmental impact effect threshold, the constraint control range of the posture control parameter is obtained, and the excavation constraint condition is obtained.

8. The autonomous navigation and positioning system for tunneling equipment based on multi-source data is characterized by: Steps for implementing the method for autonomous navigation and positioning of tunneling equipment based on multi-source data as recited in any one of claims 1 to 7, wherein the autonomous navigation and positioning system for tunneling equipment based on multi-source data comprises: A data acquisition and alignment module is used to connect to multi-source monitoring equipment, obtain multi-source data sets, align the multi-source data sets in time and space, and establish a monitoring data network; A virtual model construction module is used to connect to the transparent geological model, obtain geological information such as thickness, faults, water-rich area range, and tunnel surrounding rock stress, and integrate it with the monitoring data network to construct a virtual model. The virtual model is used to simulate the tunneling scene; An excavation path planning module is used to fit the physical structure parameters and operating status parameters of the tunneling equipment to the virtual model, locate the tunneling equipment through the virtual model, and optimize the tunneling path according to the positioning data combined with the real-time data of the monitoring data network to obtain a planned path; a posture strategy determination module, configured to perform posture and inertia analysis in the virtual model based on the planned path to obtain a path posture strategy, wherein the path posture strategy is used to describe posture control parameters of the tunneling equipment in the planned path; The operation navigation control module is used to perform operation navigation control of the tunneling equipment according to the path posture strategy.

Images