Positioning method and system for driving and anchoring all-in-one machine in coal mine driving roadway

Abstract

The invention belongs to the technical field of coal mine tunneling equipment positioning, and provides a method and a system for positioning a tunneling and anchoring all-in-one machine in a coal mine tunneling roadway in order to solve the problems of error accumulation, environmental interference and system reliability existing in a traditional underground positioning mode. The method comprises the following steps: acquiring multi-source sensing data acquired by a multi-source sensor array deployed on a digging and anchoring all-in-one machine; performing time synchronization and space synchronization processing on the multi-source sensing data to obtain a fusion data set under a unified timestamp and a unified coordinate system; and inputting the fusion data set into an improved Kalman filtering framework for data fusion, performing distance correction by using a mahalanobis distance, and determining a real-time pose state of the driving and anchoring all-in-one machine according to a data fusion result and a distance correction result. According to the invention, the positioning precision, the system robustness and the reliability of the digging and anchoring all-in-one machine under extremely severe working conditions are obviously improved, and the inherent defects of large accumulative error, easiness in environmental interference and easiness in failure in a traditional single sensor positioning mode are effectively overcome.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of coal mine tunneling equipment positioning, and particularly relates to a coal mine tunneling roadway tunneling and anchoring integrated machine positioning method and system. BACKGROUND

[0002] The rapid tunneling of coal mine underground roadways is the premise of efficient coal mining, and with the advancement of intelligent construction of coal mines, the tunneling and anchoring integrated machine, as the core equipment for rapid tunneling of coal mine roadways, its autonomous positioning accuracy directly affects the tunneling efficiency, forming quality and operation safety. In the complex environment of coal mines, the current positioning technology in the coal mine tunneling roadway has technical bottlenecks, for example, the cumulative error problem of inertial navigation system, inertial navigation has become the mainstream positioning method in underground mines due to its small size and strong anti-interference, but the attitude solution error accumulates with time, especially in long-distance tunneling, the heading angle, pitch angle and other parameter deviations can reach several degrees, which seriously affects the roadway forming precision; single laser radar system is seriously interfered by dust and vibration and cannot adapt to the demand of continuous advancement; total station positioning has high accuracy but needs frequent manual intervention, which is difficult for coal mine workers to operate and difficult to meet the automation requirements; visual positioning is easily affected by low illumination and dust shielding in underground mines and has insufficient robustness when used alone. The defects in positioning technology eventually lead to the risk of positioning failure, such as support position deviation, roadway overbreak, and actual roadway coordinates not matching the design roadway coordinates.

[0003] In summary, there is an urgent need for a positioning method that integrates the advantages of multiple sensors and adapts to the dynamic environment of underground roadways to solve the problems of error accumulation, environmental interference and system reliability, and to provide high-precision pose data support for intelligent tunneling of tunneling and anchoring integrated machines. SUMMARY

[0004] The present application provides a coal mine tunneling roadway tunneling and anchoring integrated machine positioning method and system to solve at least one of the technical problems existing in the prior art.

[0005] According to a first aspect, a coal mine tunneling roadway tunneling and anchoring integrated machine positioning method comprises the following steps: S1: acquiring multi-source sensor array data collected by multi-source sensors deployed on the tunneling and anchoring integrated machine, the multi-source sensor data including point cloud data, millimeter wave ranging data and UWB ranging data; S2: performing time synchronization and space synchronization processing on the multi-source sensor data to obtain a unified timestamp and a unified coordinate system fusion data set; S3: inputting the fusion data set into an improved Kalman filter framework for data fusion, and performing distance correction using Mahalanobis distance, and determining the real-time pose state of the tunneling and anchoring integrated machine according to the data fusion result and the distance correction result.

[0006] Preferably, in step S2, the time synchronization specifically comprises: A master-slave synchronization network is constructed by using a PTP precise time protocol, an edge computing unit is taken as a master clock node, and a pulse signal is output; A multi-source sensor array is taken as a slave clock node, the pulse signal is received based on the slave clock node, and a timestamp is aligned through a hardware timestamp interception and a bias compensation algorithm; A periodic trigger signal consistent with a PLC control period of the integrated machine is sent out by using a hardware data acquisition trigger bus, and the multi-source sensor array completes data acquisition within a fixed time window after receiving the trigger signal.

[0007] Preferably, in step S2, the space synchronization specifically comprises: A rigid body transformation relationship between a global coordinate system and a local coordinate system of the multi-source sensor array is established; A global coordinate of a cooperative target in the global coordinate system is measured, and observation values of the cooperative target in the local coordinate system by sensors in the multi-source sensor array are synchronously acquired; According to the global coordinate, the observation values and the rigid body transformation relationship, a transformation matrix between the sensors and the global coordinate system is calibrated by using least squares optimization.

[0008] Preferably, a calculation formula of the least squares optimization is as follows: In the formula, R represents a rotation matrix in the rigid body transformation, ; ; T represents a translation variable in the rigid body transformation, ; X represents the global coordinate; Y represents the observation values.

[0009] Preferably, in step S3, the improved Kalman filtering framework specifically comprises: A state vector is constructed according to three-dimensional positions, three-dimensional velocities, unit quaternion attitudes and system errors contained in the fusion data set; A robust observation equation is set according to the state vector and Gaussian observation noise and non-Gaussian interference terms; The robust observation equation is distance-corrected by using Mahalanobis distance, a Kalman gain coefficient is adjusted according to a distance correction result, and the state vector is updated according to the adjusted Kalman gain coefficient.

[0010] Preferably, the method further comprises: The point cloud data is optimized by using an improved point cloud preprocessing algorithm to obtain point cloud data satisfying a preset condition; A visual interface is developed based on the Unity3D engine, the point cloud data meeting the preset conditions is reconstructed and dynamically rendered in three dimensions, and a digital twin scene of the underground tunneling working face is constructed based on the real-time pose state.

[0011] Preferably, the improved point cloud preprocessing algorithm is: In the formula, represents the total number of point clouds; represents the number of point sequences contained in the point cloud; represents the characteristic value of the point contained in the point cloud; represents the local mean value of the point cloud within the data acquisition range; represents the statistical threshold coefficient of the decision boundary; represents the local standard deviation of the point cloud.

[0012] In a second aspect, a positioning system for a tunneling and bolting integrated machine in a coal mine tunneling roadway can perform a positioning method for a tunneling and bolting integrated machine in a coal mine tunneling roadway as described in the first aspect and any preferred embodiment, comprising: An environment perception layer composed of a multi-source sensor array deployed in the tunneling and bolting integrated machine and its surrounding roadway, for collecting raw data of the roadway environment and the pose of the tunneling and bolting integrated machine; A data processing layer containing an edge computing device mounted on the tunneling and bolting integrated machine and a multi-source sensor data fusion processing system running thereon; this layer is used to receive the raw data uploaded by the environment perception layer, to achieve time synchronization of multi-sensor data through PTP precise time protocol and hardware data acquisition trigger bus, to achieve spatial synchronization through coordinate system calibration and rigid body transformation, and to perform fusion processing on the time and space synchronized data using an improved cubature Kalman filter algorithm, and finally to output the real-time pose state of the tunneling and bolting integrated machine; A display application layer composed of an industrial control computer, a display, an operation panel and a visual operation software of a remote control center, for receiving the real-time pose state sent by the data processing layer, for real-time display and monitoring through a three-dimensional visual interface, and for transmitting the real-time pose state to the control system of the tunneling and bolting integrated machine.

[0013] Preferably, the environment perception layer includes a multi-line laser radar, a millimeter wave ranging radar and a UWB positioning system; The multi-line laser radar is deployed in an asymmetric three-node mode with forward double radar cross-scan and backward single radar redundancy verification, for obtaining high-precision three-dimensional point cloud data of the tunneling working face; The millimeter wave ranging radar is deployed on both sides of the tunneling and bolting integrated machine and the front part of the machine body, for providing high-resolution distance information based on the FMCW frequency modulation continuous wave technology in a dusty environment to assist in pose calibration; The UWB positioning system is composed of fixed base stations arranged along the roadway and tags carried on the machine body, and distance measurement is performed by measuring signal flight time or time difference of arrival.

[0014] Compared with the prior art, the present application has the following advantages: The present application constructs a multi-source sensor array integrating multi-line laser radar, millimeter wave radar and UWB system, and combines hardware-level PTP precise time synchronization and coordinate system calibration technology to lay a precise space-time reference for multi-modal data fusion; at the same time, an improved cubature Kalman filtering algorithm is adopted, which introduces Mahalanobis distance for anomaly suppression, to intelligently filter out observation errors caused by non-Gaussian interference such as underground dust and vibration, thereby significantly improving the positioning accuracy, system robustness and reliability of the combined drilling and bolting machine in extremely harsh working conditions, effectively overcoming the inherent defects of large cumulative error, susceptibility to environmental interference and failure of traditional single sensor positioning methods; at the same time, the present application realizes intuitive visualization of positioning data through three-dimensional point cloud reconstruction and digital twin technology, not only greatly reducing the cognitive load and operation difficulty of the operator, but more importantly, providing indispensable high-precision pose data support for the autonomous navigation and autonomous cutting of the combined drilling and bolting machine, forming a complete technical closed loop from environmental perception, data processing to decision application, and effectively promoting the intelligent and unmanned transformation and upgrading of coal mine tunneling operations. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, a brief introduction will be given below to the drawings needed to be used in the embodiments, and obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0016] Figure 1 is a coal mine tunneling roadway combined drilling and bolting machine positioning method flowchart provided by the embodiment of the present application; Figure 2 is a coal mine tunneling roadway combined drilling and bolting machine positioning system structure diagram provided by the embodiment of the present application; Figure 3 is a deployment diagram of the environment perception layer of the combined drilling and bolting machine positioning system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0017] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0018] It should be noted that the structures, proportions, sizes, etc. shown in the drawings of the specification are only used to understand and read the disclosed content by those skilled in the art, and are not used to limit the conditions for implementing the present application, so they do not have technical significance. Any modification of structure, change of proportion relationship or adjustment of size, which does not affect the effects and purposes that can be achieved by the present application, should fall within the scope of the disclosed technical content of the present application. It should be noted that in the specification, relationship terms such as first and second are only used to distinguish one entity from another entity, and do not necessarily require or imply any actual relationship or order between the entities.

[0019] The present application provides an embodiment: As Figure 1 shown, the present application provides a positioning method for a tunneling and anchoring integrated machine in a coal mine tunneling roadway, comprising the following steps: S1: acquiring multi-source sensing data collected by a multi-source sensor array deployed on the tunneling and anchoring integrated machine, wherein the multi-source sensing data includes point cloud data, millimeter wave ranging data and UWB ranging data; S2: performing time synchronization and space synchronization processing on the multi-source sensing data to obtain a fusion data set under a unified timestamp and a unified coordinate system; S3: inputting the fusion data set into an improved Kalman filtering framework for data fusion, and performing distance correction using Mahalanobis distance, and determining a real-time pose state of the tunneling and anchoring integrated machine according to the data fusion result and the distance correction result.

[0020] Optionally, in step S2, the time synchronization specifically includes: constructing a master-slave synchronization network using PTP (Precision Time Protocol), taking an edge computing unit as a master clock node and outputting a pulse signal; taking a multi-source sensor array as a slave clock node, receiving the pulse signal based on the slave clock node, and performing timestamp alignment through a hardware timestamp interception and offset compensation algorithm; using a hardware data acquisition trigger bus to send a periodic trigger signal consistent with a PLC control period of the tunneling and anchoring integrated machine, and the multi-source sensor array completes data acquisition within a fixed time window after receiving the trigger signal.

[0021] In this embodiment, the importance of time synchronization in multi-source sensor data fusion in complex environment is to ensure the time consistency of different sensor data and avoid errors caused by data misplacement. For example, if the data of inertial navigation and millimeter wave ranging radar are not synchronized in time, the positioning accuracy will be affected during fusion. Spatial synchronization involves the unification of coordinate systems. The data of each sensor needs to be converted to the same coordinate system to be correctly fused. For example, if the data of laser radar and UWB ranging are not accurately calibrated in space, the position information will be deviated, resulting in positioning error.

[0022] In this embodiment, PTP precise time protocol is used to construct master-slave clock synchronization network. The master clock node is deployed at the edge computing unit of the data processing layer, outputs 1PPS (second pulse) signal, and the timestamp precision is ; the slave clock node is distributed in each sensor in the multi-source sensor array, and the timestamp alignment is realized through hardware timestamp interception and offset compensation algorithm. The clock deviation correction result is as follows: In the formula, represents the master clock signal; represents the slave clock signal; , , , all represent the message timestamp in PTP protocol; represents the transmission link delay compensation amount.

[0023] In this embodiment, a hardware data acquisition trigger bus is designed to ensure strict synchronization of multi-source sensor data acquisition. The trigger signal period is consistent with the PLC control period of the tunnel anchor integrated machine. After receiving the trigger signal, each sensor completes the acquisition of the corresponding data within the time window.

[0024] Optionally, the spatial synchronization specifically includes: establishing a rigid body transformation relationship between a global coordinate system and a local coordinate system of the multi-source sensor array; measuring a global coordinate of a cooperative target in the global coordinate system, and synchronously collecting observation values of the cooperative target in the local coordinate system by each sensor in the multi-source sensor array; and calibrating a transformation matrix between each sensor and the global coordinate system according to the global coordinate, the observation values and the rigid body transformation relationship, and by using least square optimization.

[0025] In this embodiment, the coordinate system of the multi-sensor is calibrated. First, the rigid body transformation relationship between the global coordinate system and the local coordinate system of each sensor is established, and the expression of the rigid body transformation relationship is as follows: ​ wherein, represents a rotation matrix, ; represents a translation variable, .

[0026] In the embodiment, a plurality of multi-sensor coplanar cooperative targets are arranged on the body of the anchor-excavation integrated machine, the coordinates of the cooperative targets in a global coordinate system are measured, the observation values of the cooperative targets in a local coordinate system by each sensor are synchronously collected, and the transformation matrix between each sensor and the global coordinate system is calibrated by solving a least squares optimization problem, and the least squares optimization expression is: wherein, represents a rotation matrix in a rigid body transformation, ; represents a translation variable in a rigid body transformation, ; represents a global coordinate; represents an observation value.

[0027] Optionally, in step S3, the improved Kalman filtering framework specifically includes: constructing a state vector according to the three-dimensional position, the three-dimensional velocity, the unit quaternion attitude and the system error contained in the fusion data set; setting a robust observation equation according to the state vector and Gaussian observation noise and non-Gaussian interference terms; performing distance correction on the robust observation equation by using Mahalanobis distance, adjusting the Kalman gain coefficient according to the distance correction result, and updating the state vector according to the adjusted Kalman gain coefficient.

[0028] In the embodiment, the state vector is defined as: wherein, represents a three-dimensional position; represents a three-dimensional velocity; represents a unit quaternion attitude, respectively represent the system error of the multi-line laser radar and the UWB positioning base station.

[0029] The robust observation equation is: wherein, represents a sensor observation model, including coordinate transformation and distortion compensation; represents Gaussian observation noise; represents a non-Gaussian interference term caused by dust and vibration.

[0030] In this embodiment, a Mahalanobis distance correction is introduced for the Euclidean distance, and its expression is as follows: In the formula, Represents the observation vector at time k; This represents the inverse of the covariance matrix of the observation noise.

[0031] At this point, it is necessary to adjust the Kalman gain coefficient K and the attenuation coefficient. To prevent oversuppression, the Kalman gain coefficient adjustment formula is as follows: In the formula, Indicates the prior Kalman gain; Represents the natural constant e An exponential function with base 0; Indicates the attenuation coefficient; This represents the 0.95 quantile of the chi-square distribution with respect to degrees of freedom.

[0032] The updated state vector is: In the formula, Indicates the first k The prior estimate of the state vector at time step; Indicates the first k The prior estimate of the observation vector at time step.

[0033] In this embodiment, the updated state vector contains information in multiple dimensions such as position, velocity, and attitude. The part corresponding to the three-dimensional position is the final three-dimensional spatial coordinate of the tunneling and anchoring machine. The whole process is a continuous iterative update and optimization of the state estimation. In the formula, Indicates the first k Prior estimates of the state covariance matrix at time step; The covariance matrix represents the observation noise.

[0034] Optionally, it also includes: optimizing the point cloud data using an improved point cloud preprocessing algorithm to obtain point cloud data that meets preset conditions; developing a visualization interface based on the Unity3D engine to perform three-dimensional reconstruction and dynamic rendering of the point cloud data that meets the preset conditions, and constructing a digital twin scene of the underground tunneling face based on the real-time pose state.

[0035] In this embodiment, due to the large amount of data of the point cloud data, dynamic display of all point cloud images has data delay and processor load problems, therefore, the improved radius filtering combined with statistical outlier elimination algorithm is adopted in the present application to eliminate the noise while retaining the effective point cloud. The point cloud preprocessing algorithm is: In the formula, represents the total number of point clouds; represents the number of point sequences contained in the point cloud; represents the characteristic value of the point contained in the point cloud; represents the local mean value of the point cloud in the data acquisition range; represents the statistical threshold coefficient of the determination boundary; represents the local standard deviation of the point cloud.

[0036] As shown in Figure 2 , a coal mine tunneling roadway tunneling and anchoring integrated machine positioning system, comprising: An environment perception layer composed of a multi-source sensor array deployed in the tunneling and anchoring integrated machine and its surrounding roadway, for collecting raw data of the roadway environment and the pose of the tunneling and anchoring integrated machine; A data processing layer containing an edge computing device mounted on the tunneling and anchoring integrated machine and a multi-source sensor data fusion processing system running thereon; this layer is used to receive the raw data uploaded by the environment perception layer, to realize time synchronization of multi-sensor data through PTP precise time protocol and hardware data acquisition trigger bus, to realize spatial synchronization through coordinate system calibration and rigid body transformation, and to adopt an improved cubature Kalman filter algorithm to fuse the data after time and space synchronization, and finally to output the real-time pose state of the tunneling and anchoring integrated machine; A display application layer composed of an industrial control computer, a display, an operation panel and a visual operation software of a remote centralized control center, for receiving the real-time pose state sent by the data processing layer, for real-time display and monitoring through a three-dimensional visual interface, and for transmitting the real-time pose state to the control system of the tunneling and anchoring integrated machine.

[0037] In this embodiment, the environment perception layer is the perception nerve ending of the entire positioning system, this layer constructs a heterogeneous multi-source sensor array composed of various sensors mounted on the tunneling and anchoring integrated machine and its supporting equipment, including multi-line laser radar, millimeter wave ranging sensor, UWB ranging system, etc., and its main task is to obtain multi-source sensor data collected by the multi-source sensor array deployed on the tunneling and anchoring integrated machine.

[0038] In this embodiment, the multi-source sensor array is a direct component of the environment perception layer, and is a data collection task performer of the tunneling-anchor integrated machine. The deployment position determines whether the collected environmental data is typical, characteristic, and usable. Therefore, the topology optimization of the main sensor deployment of the multi-source sensor array is performed. The specific deployment of the environment perception layer is shown in Figure 3 .

[0039] Multi-line laser radar: adopts asymmetric three-node deployment (forward double radar cross scanning, backward single radar redundancy verification), realizes high-precision three-dimensional point cloud data acquisition of the tunneling roadway working face environment; Millimeter wave ranging radar: based on FMCW frequency modulation continuous wave technology, working frequency band 76-81GHz, ranging resolution 3cm under dynamic working condition, deployed on both sides of the tunneling-anchor integrated machine and the front part of the machine body, auxiliary calibration of the tunneling-anchor integrated machine pose in the dust environment; UWB positioning system: the UWB positioning base station is deployed along the tunneling roadway spatial coordinate axis behind the tunneling-anchor integrated machine, and is matched with the UWB airborne tag to form a complete positioning system. The distance measurement with high precision is realized by measuring the time of flight or time difference of arrival of the UWB signal. The positioning accuracy can reach centimeter level. The tunneling-anchor integrated machine is located in the tunneling roadway working face. The spatial coordinates and pose are calculated by cooperating with the millimeter wave ranging radar, the inertial navigation system and the odometer in the tunneling-anchor integrated machine.

[0040] In this embodiment, the data processing layer is a part of the whole system, which is composed of independent edge computing devices and multi-source sensor data fusion processing system software carried on the tunneling-anchor integrated machine, and is used for receiving all data sent by the environment perception layer and analyzing, processing and fusing. Its main task is to complete the acquisition of multi-sensor data at the same time stamp through multi-modal data time and space synchronization algorithm. The multi-source heterogeneous data, three-dimensional spatial coordinates and roll angle, pitch angle, heading angle and other pose detection fusion calculation are performed. The positioning data results are summarized and communicated. The complete data of the tunneling-anchor integrated machine is uploaded to the display application layer.

[0041] The multi-source sensor data fusion algorithm built in the multi-source sensor data fusion processing system software significantly improves the positioning reliability and accuracy in the complex underground environment through the joint optimization of heterogeneous data in space-time alignment. Its core function is to improve the volume Kalman filter framework, to perform probability fusion of multi-source sensor data under the unified space-time reference, to dynamically weight the abnormal observation caused by dust vibration by using Mahalanobis distance, and to provide reliable positioning data for intelligent tunneling for the data conflict and credibility fluctuation problems of multi-sensor under extreme working conditions.

[0042] In this embodiment, the display application layer is the display and final operation terminal of the whole system, and all data access of the system is displayed here by remote control center industrial control computer, display, operation panel and anchor integrated machine remote control visualization operation software, which can be intuitively displayed for the staff in all directions to achieve the goal of efficient visualization of anchor integrated machine positioning. The final positioning result can be used in the further intelligent process technology of autonomous movement and autonomous cutting of the anchor integrated machine.

[0043] The data three-dimensional visualization construction of the display application layer is a full-process processing chain from the original environment information to the decision view and data, which is the top-level design link of the whole anchor integrated machine positioning system. Its core value lies in converting the underground multi-source sensing data into intuitive spatial cognition. In the complex working conditions of coal mines, traditional text data cannot represent the spatial relationship of roadway trend and device pose, and data three-dimensional visualization can dynamically reconstruct the tunnel face point cloud model and real-time map device pose through the fusion of computer graphics and industrial internet of things technology to build a digital twin system. The staff can quickly identify the positioning information of the anchor integrated machine through the digital twin information, and the positioning result can be tested in the process technology of autonomous movement and autonomous cutting of the anchor integrated machine. Finally, the three-dimensional point cloud interface and data visualization interface are developed based on the Unity3D environment mesh to realize data three-dimensional visualization.

[0044] The coal mine tunneling roadway anchor integrated machine positioning method and system provided by the embodiment of the present application realizes real-time positioning of the anchor integrated machine in the coal mine roadway, provides reliable positioning data, and solves the problems of difficult operation, large error and poor stability of the traditional positioning operation. Compared with the traditional single type sensor positioning method, the probability of single sensor failure in extreme working conditions such as dust, vibration and low illumination is reduced, the multi-sensor time and space synchronization and data fusion are used, the acquisition of anchor integrated machine positioning data is realized through software algorithm, and stable operation is realized, and the positioning accuracy is improved. In addition, the coal mine tunneling roadway anchor integrated machine positioning system and method provided by the present application provides valuable data resources for environmental analysis and map construction of coal mine underground anchor integrated machine operation, and also provides a basic condition for the development and application of subsequent intelligent functions such as autonomous movement and automatic cutting of the anchor integrated machine.

[0045] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A positioning method for a coal mine tunneling and anchoring integrated machine in a tunneling roadway, characterized in that, Comprising the following steps: S1: acquiring multi-source sensor array deployed on the integrated machine of tunneling and anchoring Collect multi-source sensor data, the multi-source sensor data includes point cloud data, millimeter wave ranging data and UWB ranging data; S2: time synchronization and space synchronization processing is carried out on the multi-source sensor data to obtain a unified timestamp and a fusion data set in a unified coordinate system; S3: inputting the fusion data set into an improved Kalman filtering framework for data fusion, and using Mahalanobis distance for distance correction, and determining the real-time pose state of the integrated machine of tunneling and anchoring according to the data fusion result and the distance correction result.

2. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 1, characterized in that, In step S2, the time synchronization specifically includes: A master-slave synchronization network is constructed by using PTP precise time protocol, an edge computing unit is used as a master clock node, and a pulse signal is output; The multi-source sensor array is used as a slave clock node, the pulse signal is received based on the slave clock node, and the timestamp is aligned through a hardware timestamp interception and offset compensation algorithm; A periodic trigger signal consistent with the PLC control period of the integrated machine of tunneling and anchoring is sent out by using a hardware data acquisition trigger bus, and the multi-source sensor array completes data acquisition within a fixed time window after receiving the trigger signal.

3. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 1, characterized in that, In step S2, the space synchronization specifically includes: A rigid transformation relationship between a global coordinate system and a local coordinate system of the multi-source sensor array is established; The global coordinates of a cooperative target in the global coordinate system are measured, and the observation values of the cooperative target in the local coordinate system by each sensor in the multi-source sensor array are synchronously collected; According to the global coordinates, the observation values, and the rigid transformation relationship, and by using least squares optimization, the transformation matrix between each sensor and the global coordinate system is calibrated.

4. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 3, characterized in that, The calculation formula of least squares optimization is: wherein represents the rotation matrix in the rigid body transformation, ; represents the translation variable in the rigid body transformation, ; represents the global coordinate; represents the observation.

5. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 1, characterized in that, In step S3, the improved Kalman filtering framework specifically includes: A state vector is constructed according to the three-dimensional position, the three-dimensional velocity, the unit quaternion attitude and the system error contained in the fusion data set; A robust observation equation is set according to the state vector and the Gaussian observation noise and the non-Gaussian interference term; Mahalanobis distance is used to correct the distance of the robust observation equation, the Kalman gain coefficient is adjusted according to the distance correction result, and the state vector is updated according to the adjusted Kalman gain coefficient.

6. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 1, characterized in that, Further comprising: An improved point cloud preprocessing algorithm is used to optimize the point cloud data to obtain point cloud data meeting a preset condition; A visual interface is developed based on a Unity3D engine, the point cloud data meeting the preset condition is three-dimensionally reconstructed and dynamically rendered, and a digital twin scene of the underground tunneling working face is constructed based on the real-time pose state.

7. The positioning method of the combined drilling and bolting machine in the coal mine tunneling roadway according to claim 6, characterized in that, The improved point cloud preprocessing algorithm is: In the formula, represents the total number of point clouds; represents the number of point sequences contained in the point cloud; represents the characteristic value of the point contained in the point cloud; represents the local mean value of the point cloud within the data acquisition range; represents the statistical threshold coefficient of the determination boundary; represents the local standard deviation of the point cloud.

8. A positioning system for a combined drilling and bolting machine in a coal mine tunneling roadway, capable of performing a positioning method for a combined drilling and bolting machine in a coal mine tunneling roadway according to any one of claims 1 to 7, characterized in that, Comprising: An environment perception layer composed of a multi-source sensor array deployed in the integrated machine of tunneling and anchoring and the surrounding roadway, for collecting original data of the roadway environment and the pose of the integrated machine of tunneling and anchoring; The data processing layer comprises an edge computing device carried on the combined drilling and bolting machine and a multi-source sensing data fusion processing system running thereon; the layer is used for receiving original data uploaded by the environment perception layer, achieving time synchronization of multi-sensor data through a PTP (PTP, Precision Time Protocol) precise time protocol and a hardware data acquisition trigger bus, achieving space synchronization through coordinate system calibration and rigid body transformation, and adopting an improved volume Kalman filtering algorithm to fuse and process the data after time and space synchronization, and finally outputting real-time pose states of the combined drilling and bolting machine; The display application layer is composed of an industrial control computer, a display, an operation panel and visual operation software of a remote centralized control center, is used for receiving real-time pose states sent by the data processing layer, performing real-time display and monitoring through a three-dimensional visual interface, and transmitting the real-time pose states to a control system of the combined drilling and bolting machine.

9. The positioning system of a combined excavating and bolting machine in a coal mine tunneling roadway according to claim 8, characterized in that, The environment perception layer comprises a multi-line laser radar, a millimeter wave ranging radar and a UWB positioning system; The multi-line laser radar is deployed in an asymmetric three-node mode of forward double-radar cross scanning and backward single-radar redundancy verification, and is used for acquiring high-precision three-dimensional point cloud data of a tunneling working face; The millimeter wave ranging radar is deployed on both sides of two sides of the combined drilling and bolting machine and a front part of the machine body, and is used for providing high-resolution distance information in a dust environment based on an FMCW (FMCW, Frequency Modulated Continuous Wave) frequency modulation continuous wave technology to assist in pose calibration; The UWB positioning system is composed of fixed base stations arranged along a roadway and tags carried on the machine body, and is used for measuring distance through signal flight time or time difference of arrival.

Images