Method and device for calculating deformation of coal mine tunnel

Abstract

The invention provides a coal mine tunnel deformation calculation method and device. The method comprises the following steps: acquiring source point cloud data and target point cloud data of a to-be-estimated tunnel; establishing an action set; any action factor is called from the action set, a deformation instruction is selected from the action factors to carry out pose adjustment on the source point cloud data and / or the target point cloud data, a metric value is calculated, and whether an optimal adjustment pose exists or not is determined based on the metric value; and repeating the above steps until the existence of the optimal adjustment pose is determined, and calculating the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data. The motion factors are called from the motion set, deformation instructions in the motion factors are applied to adjust the poses of the source point cloud data and the target point cloud data, and finally the optimal adjustment pose is found to calculate the deformation value of the roadway to be estimated, so that the registration precision can be improved, a local optimal solution is avoided, and the estimation accuracy of the roadway to be estimated is improved. And meanwhile, the device can adapt to complex underground working conditions, and flexibility and adaptability are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer vision technology, and in particular, to a method and device for calculating the deformation of a coal mine roadway. Background Art

[0002] With the continuous increase in the mining depth and the continuous expansion of the mining scale of coal mines, in order to ensure safe production and protect the ecological environment, etc., it is of great significance to realize the deformation monitoring of coal mine roadways. Traditional methods for monitoring the deformation of coal mine roadways include manual observation and measurement, convergence monitors, monitoring of the forces on bolts and cables, and detection of roof separation deformation by roof separation indicators. However, manual observation and measurement are greatly affected by human factors, and the measurement accuracy and efficiency are limited; methods such as convergence monitoring, bolt and cable force monitoring, and roof separation monitoring are difficult to comprehensively and real-time grasp the overall deformation status of the roadway. Due to the complex geological conditions of coal mines, it is difficult to accurately estimate the deformation of coal mine roadways using traditional and single monitoring methods. Summary of the Invention

[0003] The present disclosure aims to solve at least one of the technical problems in the related art to some extent.

[0004] To this end, one object of the present disclosure is to propose a method for calculating the deformation of a coal mine roadway.

[0005] The second object of the present disclosure is to propose a device for calculating the deformation of a coal mine roadway.

[0006] The third object of the present disclosure is to propose an electronic device.

[0007] The fourth object of the present disclosure is to propose a non-transitory computer-readable storage medium.

[0008] The fifth object of the present disclosure is to propose a computer program product.

[0009] To achieve the above object, an embodiment of the first aspect of the present disclosure provides a method for calculating the deformation of a coal mine roadway, including: obtaining source point cloud data and target point cloud data of the roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps; establishing an action set, the action set includes a plurality of action factors, the action factors include a plurality of deformation instructions, and the deformation instructions are arranged in the order of operations; randomly retrieving any action factor from the action set, selecting a deformation instruction from the action factor based on the order of operations to perform pose adjustment on the source point cloud data and / or the target point cloud data, and calculating the metric value of the deformation instruction after the pose adjustment, and determining whether there is an optimal adjustment pose based on all the metric values of the action factor; in response to the non-existence of an optimal adjustment pose, repeating the above steps of randomly retrieving any action factor from the action set and its subsequent steps until it is determined that there is an optimal adjustment pose, and calculating the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose.

[0010] According to an embodiment of the present disclosure, calculating the metric value of the deformation instruction after the pose adjustment includes: establishing a three-dimensional coordinate system based on the source point cloud data and the target point cloud data after the pose adjustment; projecting the source point cloud data and the target point cloud data in the directions perpendicular to the YOZ plane and the XOZ plane respectively to obtain the first source point cloud projection data of the source point cloud data projected on the YOZ plane and the second source point cloud projection data projected on the XOZ plane, and obtaining the first target point cloud projection data of the target point cloud data projected on the YOZ plane and the second target point cloud projection data projected on the XOZ plane; calculating the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data.

[0011] According to an embodiment of the present disclosure, calculating the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data includes: for the i-th point position in the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data respectively, calculating the first distance between the first source point cloud projection data of the i-th point position and the first target point cloud projection data of the i-th point position, and calculating the second distance between the second source point cloud projection data of the i-th point position and the second target point cloud projection data of the i-th point position; adding the first distance and the second distance, and taking the square root of the sum value to obtain the square root sum of the i-th point position; taking the average value of the square root sums of all point positions to calculate and obtain the metric value.

[0012] According to an embodiment of the present disclosure, determining whether there is an optimal adjustment pose based on all the metric values of the action factors includes: for the j-th deformation instruction in the action factors, obtaining a first metric value of the j-th deformation instruction and obtaining a second metric value of the (j - 1)-th deformation instruction; determining a reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value; and determining whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose based on the reward and punishment value.

[0013] According to an embodiment of the present disclosure, determining the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value includes: comparing the first metric value and the second metric value; in response to the first metric value being greater than the second metric value, determining the reward and punishment value to be a first reward and punishment value; or, in response to the first metric value being less than the second metric value, determining the reward and punishment value to be a second reward and punishment value; or, in response to the first metric value being equal to the second metric value, determining the reward and punishment value to be a third reward and punishment value.

[0014] According to an embodiment of the present disclosure, determining whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose based on the reward and punishment value includes: in response to the reward and punishment value being the third reward and punishment value, determining that the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose.

[0015] According to an embodiment of the present disclosure, calculating the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose includes: for the k-th point in the source point cloud data based on the optimal adjustment pose, selecting two comparison points with the closest distance to the k-th point from the target point cloud data based on the optimal adjustment pose; respectively calculating the comparison distance values between the k-th point and the two comparison points; calculating a candidate deformation value of the k-th point based on the two comparison distance values; and obtaining an average value of the candidate deformation values of all the points in the source point cloud data based on the optimal adjustment pose as the deformation value of the roadway to be estimated.

[0016] According to an embodiment of the present disclosure, the pose adjustment of the source point cloud data and / or the target point cloud data by selecting a deformation instruction from the action factors based on the operation sequence includes: obtaining a displacement instruction and a rotation instruction in the deformation instruction; performing a translation process on the source point cloud data and / or the target point cloud data based on the displacement instruction, and performing a rotation process on the source point cloud data and / or the target point cloud data based on the rotation instruction.

[0017] To achieve the above object, an embodiment of the second aspect of the present disclosure provides a coal mine roadway deformation calculation device, including: an acquisition module, configured to acquire source point cloud data and target point cloud data of a roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps; a construction module, configured to construct an action set, the action set including a plurality of action factors, the action factors including a plurality of deformation instructions, and the deformation instructions being arranged in an operation sequence; an adjustment module, configured to randomly retrieve any one of the action factors from the action set, select a deformation instruction from the action factors based on the operation sequence to perform pose adjustment on the source point cloud data and / or the target point cloud data, and calculate a metric value of the deformation instruction after the pose adjustment, and determine whether there is an optimal adjustment pose based on all the metric values of the action factors; a calculation module, configured to, in response to the non-existence of an optimal adjustment pose, repeat the above steps of randomly retrieving any one of the action factors from the action set and subsequent steps until it is determined that there is an optimal adjustment pose, and calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose.

[0018] To achieve the above object, an embodiment of the third aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to implement the coal mine roadway deformation calculation method as described in the embodiment of the first aspect of the present disclosure.

[0019] To achieve the above object, an embodiment of the fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the coal mine roadway deformation calculation method as described in the embodiment of the first aspect of the present disclosure.

[0020] To achieve the above object, an embodiment of the fifth aspect of the present disclosure provides a computer program product, including a computer program, where the computer program is used to implement the coal mine roadway deformation calculation method as described in the embodiment of the first aspect of the present disclosure when executed by a processor.

[0021] Thus, by retrieving action factors from the action set without replacement and applying the deformation instructions in these action factors to adjust the poses of the source point cloud data and the target point cloud data, the optimal adjustment pose can be finally found to calculate the deformation value of the roadway to be estimated, which can improve the registration accuracy, avoid local optimal solutions, and at the same time can adapt to the complex working conditions in the mine, enhancing flexibility and adaptability. Brief Description of the Drawings

[0022] Figure 1 is a schematic diagram of a coal mine roadway deformation calculation method according to an embodiment of the present disclosure; Figure 2 is a schematic diagram of another coal mine roadway deformation calculation method according to an embodiment of the present disclosure; Figure 3 is a schematic diagram of another coal mine roadway deformation calculation method according to an embodiment of the present disclosure; Figure 4 is a schematic diagram of another coal mine roadway deformation calculation method according to an embodiment of the present disclosure; Figure 5 is a schematic diagram of a coal mine roadway deformation calculation device according to an embodiment of the present disclosure; Figure 6 is a schematic diagram of an electronic device according to an embodiment of the present disclosure. Detailed Embodiments

[0023] The embodiments of the present disclosure will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present disclosure, but should not be construed as a limitation to the present disclosure.

[0024] In the technical solution of the present disclosure, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of relevant laws and regulations.

[0025] It should be noted that in the embodiments of the present application, some industry-existing solutions such as certain software, components, models, etc. may be mentioned. They should be regarded as exemplary, and their purpose is only to illustrate the feasibility in the implementation of the technical solution of the present application, but it does not mean that the applicant has already or necessarily used this solution.

[0026] In recent years, with the rapid progress of computer and artificial intelligence technologies, the powerful modeling ability of deep learning neural networks has been widely introduced into the research of coal mine roadway deformation monitoring and mine slope deformation monitoring. The coal mine roadway deformation monitoring method based on the deep learning VoxelNet model converts disordered point cloud data into high-dimensional feature data and calculates the roadway deformation using the Alphashape algorithm, solving the problems of poor accuracy and inability to continuously monitor the deformation of the entire roadway in traditional coal mine roadway deformation monitoring methods. The vision-based three-dimensional point cloud identifier and three-dimensional registration method realize the automatic extraction of the mine road contour and can perform mine deformation monitoring, etc. The mine slope deformation monitoring method based on the DBSCAN clustering algorithm mines the clustering of the three-dimensional radar data of the mine slope obtained, determines different types of slope deformation regions according to time and space attributes, and estimates the displacement deformation characteristics to judge the slope deformation degree, thus effectively giving more accurate monitoring and early warning results on the deformation degree of the slope, the damage scale and mode of the deformation region.

[0027] Figure 1 is a schematic diagram of a coal mine roadway deformation calculation method according to an embodiment of the present disclosure, as Figure 1 shown, the coal mine roadway deformation calculation method includes the following steps: S101, obtain the source point cloud data and the target point cloud data of the roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps.

[0028] The coal mine roadway deformation calculation method of the embodiments of the present application can be applied to scenarios such as coal mine roadway deformation monitoring and mine slope deformation monitoring research. The execution subject of the coal mine roadway deformation calculation of the embodiments of the present application can be the coal mine roadway deformation calculation device of the embodiments of the present application, and the coal mine roadway deformation calculation device can be set on an electronic device.

[0029] In the embodiments of the present disclosure, the point cloud data can be collected by a radar device set underground. The radar device can be of various types and is not limited here.

[0030] In the current technology, lidar scanning technology can quickly obtain the three-dimensional coordinates of the surface of the object to be measured, and the point cloud data has high accuracy and large density, and has been widely applied in many industries. Using lidar to scan the roadway to be estimated, quickly obtain the data of the roadway shape, and using the coal mine roadway deformation calculation method is not only fast and accurate, but also has little impact on production.

[0031] In actual operation, due to the complex underground geographical environment and production requirements, the roadway to be estimated is in a dynamic change. Therefore, the point cloud data collected for the roadway to be estimated at different timestamps may vary. By analyzing the differences between the point cloud data at different timestamps, the overall deformation of the roadway to be estimated can be estimated and analyzed.

[0032] It should be noted that the acquisition time of the source point cloud data is earlier than that of the target point cloud data. The source point cloud data and the target point cloud data are not aligned data. After aligning the source point cloud data and the target point cloud data, subsequent deformation analysis can be carried out.

[0033] In the embodiments of the present disclosure, after collecting point cloud data through a radar device, the point cloud data can also be preprocessed, which can improve data quality, reduce noise, and enhance feature extraction. The preprocessing can be various. For example, the point cloud data can be preprocessed by one or more of denoising, sampling, feature extraction, matching, etc.

[0034] S102, establish an action set. The action set includes multiple action factors, and each action factor includes multiple deformation instructions, and the deformation instructions are arranged according to the operation sequence.

[0035] It should be noted that the action factor is a complete action or step for adjusting the point cloud data. The adjustment can include rotation, displacement, deformation, etc. Each deformation instruction includes and only includes one action.

[0036] It should be noted that the action factor is generated by arranging the deformation instructions according to the operation sequence. The operation sequence can be pre-designed or randomly generated.

[0037] In the embodiments of the present disclosure, the action set can be randomly established. By setting the translation range and rotation angle range in advance, etc., multiple deformation instructions can be randomly generated, and then an action set can be established based on the randomly generated multiple deformation instructions. For example, the coordinate axis, axis, The translation ranges in the three directions of the axis can be set to , and , and deformation instructions are randomly generated from the above three coordinate ranges.

[0038] S103, randomly retrieve any action factor from the action set, select a deformation instruction from the action factor based on the operation sequence to perform pose adjustment on the source point cloud data and / or the target point cloud data, and calculate the metric value of the deformation instruction after pose adjustment. Determine whether there is an optimal adjustment pose based on all the metric values of the action factors.

[0039] It should be noted that the non-replacement callback extraction means that when selecting action factors from the action set, after each selection, the action factor is removed from the set or marked as used, so as to ensure that the selected action factor will not be called repeatedly in subsequent selections.

[0040] It should be noted that the metric value is an evaluation value used to evaluate whether the source point cloud data and / or the target point cloud data are aligned after the pose adjustment is performed on the source point cloud data and / or the target point cloud data through the deformation instruction.

[0041] In the embodiments of the present disclosure, there can be various methods for calculating the metric value of the deformation instruction after the pose adjustment, and no limitation is made here.

[0042] In a possible implementation manner, the source point cloud data and the target point cloud data after the pose adjustment can be compared to determine the displacement value between the corresponding points, and then the metric value of the deformation instruction after the pose adjustment can be calculated based on the displacement value.

[0043] In another possible implementation manner, the source point cloud data and the target point cloud data after the pose adjustment can also be calculated through a preset metric value algorithm to calculate and obtain the metric value of the deformation instruction after the pose adjustment based on the displacement value. It should be noted that the metric value algorithm is designed in advance and can be changed according to the actual design needs, and no limitation is made here.

[0044] In the embodiments of the present disclosure, the pose of the source point cloud data can be adjusted through the deformation instruction, the pose of the target point cloud data can also be adjusted through the deformation instruction, and the poses of the source point cloud data and the target point cloud data can also be adjusted simultaneously. No limitation is made here, and it can be specifically set according to the actual design needs.

[0045] In the embodiments of the present disclosure, after obtaining the metric value of the deformation instruction, the metric value can be processed based on a preset determination condition to determine whether the source point cloud data and the target point cloud data reach the optimal adjusted pose after the execution of the deformation instruction. It should be noted that when the source point cloud data and the target point cloud data reach the optimal adjusted pose, it can be considered at this time that the source point cloud data and the target point cloud data are already aligned or reach the expected alignment condition.

[0046] S104, in response to the non-existence of the optimal adjusted pose, repeat the above steps of non-replacement callback extraction of any action factor from the action set and its subsequent steps until it is determined that there is an optimal adjusted pose, and calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjusted pose.

[0047] In the embodiments of the present disclosure, first, source point cloud data and target point cloud data of the roadway to be estimated are obtained, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps. Then, an action set is established. The action set includes multiple action factors, and each action factor includes multiple deformation instructions arranged in the order of operation. Then, any action factor is randomly retrieved from the action set, and deformation instructions are selected from the action factor based on the order of operation to adjust the pose of the source point cloud data and / or the target point cloud data, and the metric value of the deformation instruction after the pose adjustment is calculated. Based on all the metric values of the action factors, it is determined whether there is an optimal adjusted pose. Finally, in response to the absence of an optimal adjusted pose, the above steps of randomly retrieving any action factor from the action set and its subsequent steps are repeated until it is determined that there is an optimal adjusted pose, and the deformation value of the roadway to be estimated is calculated based on the source point cloud data and the target point cloud data after the optimal adjusted pose. Thus, by randomly retrieving action factors from the action set and applying the deformation instructions in these action factors to adjust the pose of the source point cloud data and the target point cloud data, the optimal adjusted pose is finally found to calculate the deformation value of the roadway to be estimated, which can improve the registration accuracy, avoid local optimal solutions, and at the same time can adapt to the complex working conditions in the mine, enhancing flexibility and adaptability.

[0048] In the embodiments of the present disclosure, when selecting deformation instructions from the action factor based on the order of operation to adjust the pose of the source point cloud data and / or the target point cloud data, the displacement instruction and the rotation instruction in the deformation instruction can be obtained first, and then the source point cloud data and / or the target point cloud data are translated based on the displacement instruction, and the source point cloud data and / or the target point cloud data are rotated based on the rotation instruction.

[0049] In the above embodiments, to calculate the metric value of the deformation instruction after the pose adjustment, it can also be through Figure 2 For further explanation, the method includes: S201, establishing a three-dimensional coordinate system based on the source point cloud data and the target point cloud data after the pose adjustment.

[0050] S202, projecting the source point cloud data and the target point cloud data respectively in the direction perpendicular to the YOZ plane and the direction perpendicular to the XOZ plane to obtain the first source point cloud projection data of the source point cloud data projected on the YOZ plane and the second source point cloud projection data projected on the XOZ plane, and obtaining the first target point cloud projection data of the target point cloud data projected on the YOZ plane and the second target point cloud projection data projected on the XOZ plane.

[0051] S203, calculating the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data.

[0052] In an embodiment of the present disclosure, for the i-th point position in the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data respectively, the first distance between the first source point cloud projection data of the i-th point position and the first target point cloud projection data of the i-th point position is calculated, and the second distance between the second source point cloud projection data of the i-th point position and the second target point cloud projection data of the i-th point position is calculated. Then, the first distance and the second distance are added together, and the square root of the sum value is taken to obtain the square root sum of the i-th point position. Finally, the average value of the square root sums of all point positions is calculated to obtain the metric value.

[0053] In an embodiment of the present disclosure, the formula for calculating the metric value is:

[0054] Wherein, and respectively represent the first source point cloud projection data of the i-th point position and the first target point cloud projection data of the i-th point position, and represent the second source point cloud projection data of the i-th point position and the second target point cloud projection data of the i-th point position, represents the total number of corresponding points, represents the metric value.

[0055] In an embodiment of the present disclosure, a three-dimensional coordinate system is first established based on the source point cloud data and the target point cloud data after pose adjustment. Then, the source point cloud data and the target point cloud data are projected in the directions perpendicular to the YOZ plane and the XOZ plane respectively, so as to obtain the first source point cloud projection data of the source point cloud data projected on the YOZ plane and the second source point cloud projection data projected on the XOZ plane, and the first target point cloud projection data of the target point cloud data projected on the YOZ plane and the second target point cloud projection data projected on the XOZ plane. Finally, the metric value is calculated based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data. By projecting on two different planes (YOZ and XOZ), the differences between point clouds can be evaluated from multiple angles, providing a more comprehensive evaluation criterion. At the same time, the projection operation simplifies the three-dimensional problem into a two-dimensional problem, making the calculation more simple and efficient, especially obvious in the processing of large-scale point cloud data.

[0056] In the above embodiment, based on all the metric values of the action factors, it is determined whether there is an optimal adjustment pose, and it can also be further explained by Figure 3 The method includes: S301. For the j-th deformation instruction in the action factor, obtain the first metric value of the j-th deformation instruction and obtain the second metric value of the (j - 1)-th deformation instruction.

[0057] S302. Determine the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value.

[0058] In the embodiments of the present disclosure, the first metric value and the second metric value can be compared. In response to the first metric value being greater than the second metric value, determine that the reward and punishment value is the first reward and punishment value; or in response to the first metric value being less than the second metric value, determine that the reward and punishment value is the second reward and punishment value; or in response to the first metric value being equal to the second metric value, determine that the reward and punishment value is the third reward and punishment value.

[0059] In a possible implementation manner, the formula for determining the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value is:

[0060] represents the second metric value of the (j - 1)-th deformation instruction, represents the first metric value of the j-th deformation instruction, is the first reward and punishment value, is the second reward and punishment value, is the third reward and punishment value.

[0061] S303. Based on the reward and punishment value, determine whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose.

[0062] In the embodiments of the present disclosure, in response to the reward and punishment value being the third reward and punishment value, determine that the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose.

[0063] In the embodiments of the present disclosure, first, for the j-th deformation instruction in the action factor, obtain the first metric value of the j-th deformation instruction and obtain the second metric value of the (j - 1)-th deformation instruction. Then, determine the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value. Finally, based on the reward and punishment value, determine whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose. Thus, by introducing a reward and punishment mechanism to dynamically evaluate the effect of each deformation instruction and accordingly decide whether to accept the pose adjustment result brought by the current instruction, this not only improves the accuracy and efficiency of point cloud registration, but also enhances the robustness and adaptability of the system.

[0064] In the above embodiments, calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose, and can also pass through Figure 4Further explanation, the method includes: S401. For the k-th point in the source point cloud data after optimal adjustment of the pose, select two comparison points with the closest distance to the k-th point from the target point cloud data after optimal adjustment of the pose.

[0065] S402. Calculate the comparison distance values between the k-th point and the two comparison points respectively.

[0066] S403. Calculate the candidate deformation value of the k-th point based on the two comparison distance values.

[0067] In the embodiment of the present disclosure, after obtaining the two comparison distances, the two comparison distances can be calculated according to a preset algorithm to calculate and obtain the candidate deformation value of the k-th point. This algorithm can be changed according to actual design requirements.

[0068] In a possible implementation manner, after obtaining the two comparison distances, the average value of the two comparison distances can be calculated as the candidate deformation value of the k-th point.

[0069] S404. Calculate the average value of the candidate deformation values of all points in the source point cloud data after optimal adjustment of the pose as the deformation value of the roadway to be estimated.

[0070] In the embodiment of the present disclosure, first, for the k-th point in the source point cloud data after optimal adjustment of the pose, select two comparison points with the closest distance to the k-th point from the target point cloud data after optimal adjustment of the pose, then calculate the comparison distance values between the k-th point and the two comparison points respectively, then calculate the candidate deformation value of the k-th point based on the two comparison distance values, and finally calculate the average value of the candidate deformation values of all points in the source point cloud data after optimal adjustment of the pose as the deformation value of the roadway to be estimated. This method can effectively improve the accuracy and reliability of deformation estimation by carefully comparing the distance between each point in the source point cloud data and its two closest comparison points in the target point cloud data. At the same time, due to the use of local calculation methods, not only the robustness of the system is enhanced, but also the calculation efficiency is optimized.

[0071] Corresponding to the coal mine roadway deformation calculation methods provided in the above several embodiments, an embodiment of the present disclosure also provides a coal mine roadway deformation calculation device. Since the coal mine roadway deformation calculation device provided in the embodiment of the present disclosure corresponds to the coal mine roadway deformation calculation methods provided in the above several embodiments, the implementation manners of the above coal mine roadway deformation calculation methods are also applicable to the coal mine roadway deformation calculation device provided in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0072] Figure 5It is a schematic diagram of a coal mine roadway deformation calculation device according to an embodiment of the present disclosure. As shown in FIG. 5, the coal mine roadway deformation calculation device 500 includes: an acquisition module 510, a construction module 520, an adjustment module 530, and a calculation module 540.

[0073] The acquisition module 510 is configured to acquire source point cloud data and target point cloud data of the roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps.

[0074] The construction module 520 is configured to construct an action set, the action set includes a plurality of action factors, and the action factors include a plurality of deformation instructions, and the deformation instructions are arranged in the operation sequence.

[0075] The adjustment module 530 is configured to randomly retrieve any action factor from the action set, select a deformation instruction from the action factor based on the operation sequence to perform pose adjustment on the source point cloud data and / or the target point cloud data, and calculate the metric value of the deformation instruction after the pose adjustment, and determine whether there is an optimal adjustment pose based on all the metric values of the action factors.

[0076] The calculation module 540 is configured to, in response to the non-existence of an optimal adjustment pose, repeat the above steps of randomly retrieving any action factor from the action set and its subsequent steps until it is determined that there is an optimal adjustment pose, and calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose.

[0077] According to an embodiment of the present disclosure, calculating the metric value of the deformation instruction after the pose adjustment includes: establishing a three-dimensional coordinate system based on the source point cloud data and the target point cloud data after the pose adjustment; respectively projecting the source point cloud data and the target point cloud data in the directions perpendicular to the YOZ plane and perpendicular to the XOZ plane to obtain first source point cloud projection data projected by the source point cloud data on the YOZ plane and second source point cloud projection data projected on the XOZ plane, and obtaining first target point cloud projection data projected by the target point cloud data on the YOZ plane and second target point cloud projection data projected on the XOZ plane; calculating the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data.

[0078] According to an embodiment of the present disclosure, calculating a metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data includes: for the i-th point position in the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data respectively, calculating a first distance between the first source point cloud projection data of the i-th point position and the first target point cloud projection data of the i-th point position, and calculating a second distance between the second source point cloud projection data of the i-th point position and the second target point cloud projection data of the i-th point position; adding the first distance and the second distance, and taking the square root of the sum value to obtain the square root sum of the i-th point position; taking the average of the square root sums of all point positions to calculate and obtain the metric value.

[0079] According to an embodiment of the present disclosure, determining whether there is an optimal adjustment pose based on all metric values of the action factor includes: for the j-th deformation instruction in the action factor, obtaining a first metric value of the j-th deformation instruction, and obtaining a second metric value of the (j - 1)-th deformation instruction; determining a reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value; determining whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data based on the reward and punishment value is the optimal adjustment pose.

[0080] According to an embodiment of the present disclosure, determining a reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value includes: comparing the first metric value and the second metric value; in response to the first metric value being greater than the second metric value, determining the reward and punishment value as the first reward and punishment value; or, in response to the first metric value being less than the second metric value, determining the reward and punishment value as the second reward and punishment value; or, in response to the first metric value being equal to the second metric value, determining the reward and punishment value as the third reward and punishment value.

[0081] According to an embodiment of the present disclosure, determining whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data based on the reward and punishment value is the optimal adjustment pose includes: in response to the reward and punishment value being the third reward and punishment value, determining that the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose.

[0082] According to an embodiment of the present disclosure, calculating the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after optimal pose adjustment includes: for the k-th point in the source point cloud data after optimal pose adjustment, selecting two comparison points with the closest distance to the k-th point from the target point cloud data after optimal pose adjustment; respectively calculating the comparison distance values between the k-th point and the two comparison points; calculating the candidate deformation value of the k-th point based on the two comparison distance values; and obtaining the average value of the candidate deformation values of all points in the source point cloud data after optimal pose adjustment as the deformation value of the roadway to be estimated.

[0083] According to an embodiment of the present disclosure, selecting a deformation instruction from the action factors to perform pose adjustment on the source point cloud data and / or the target point cloud data based on the operation sequence includes: obtaining the displacement instruction and the rotation instruction in the deformation instruction; performing translation processing on the source point cloud data and / or the target point cloud data based on the displacement instruction, and performing rotation processing on the source point cloud data and / or the target point cloud data based on the rotation instruction.

[0084] To implement the above embodiments, an embodiment of the present disclosure also proposes an electronic device 600, Figure 6 which is a schematic diagram of an electronic device according to an embodiment of the present disclosure. As Figure 6 shown, the electronic device 600 includes: a processor 601 and a memory 602 communicatively connected to the processor. The memory 602 stores instructions executable by at least one processor. The instructions are executed by at least one processor 601 to implement the coal mine roadway deformation calculation method as in the embodiments of the present disclosure. Figures 1 - 4 embodiment.

[0085] To implement the above embodiments, an embodiment of the present disclosure also proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to implement the coal mine roadway deformation calculation method as in the embodiments of the present disclosure. Figures 1 - 4 embodiment.

[0086] To implement the above embodiments, an embodiment of the present disclosure also proposes a computer program product, including a computer program, which when executed by a processor implements the coal mine roadway deformation calculation method as in the embodiments of the present disclosure. Figures 1 - 4 embodiment.

[0087] It should be noted that personal information from users should be collected for legal and reasonable purposes and not shared or sold outside of such legal uses. In addition, such collection / sharing should be carried out after obtaining the informed consent of the user, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization including authorizing relevant user information before the user uses the function. In addition, any necessary steps should be taken to safeguard and secure access to such personal information data and ensure that others with access to the personal information data comply with their privacy policies and procedures.

[0088] This application is expected to provide embodiments where users can selectively block the use or access of personal information data. That is, this disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, the risk can be minimized by restricting data collection and deleting the data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of the user.

[0089] In the descriptions of the foregoing embodiments, the descriptions with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0090] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" can explicitly or implicitly include at least one of such features. In the description of this application, "a plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0091] Any process or method description shown in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a manner that is not shown or discussed in sequence, including in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by those skilled in the art to which the embodiments of this application belong.

[0092] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that contains, stores, communicates, propagates, or transports a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0093] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0094] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0095] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0096] The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present application.

Claims

1. A method for calculating the deformation of a coal mine roadway, characterized in that, Including: Obtain the source point cloud data and the target point cloud data of the roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps; Establish an action set, the action set includes multiple action factors, the action factors include multiple deformation instructions, and the deformation instructions are arranged according to the operation sequence; Randomly retrieve any action factor from the action set, select a deformation instruction from the action factor based on the operation sequence to perform pose adjustment on the source point cloud data and / or the target point cloud data, and calculate the metric value of the deformation instruction after the pose adjustment. Determine whether there is an optimal adjustment pose based on all the metric values of the action factor; In response to the absence of an optimal adjustment pose, repeat the above steps of randomly retrieving any action factor from the action set and its subsequent steps until it is determined that there is an optimal adjustment pose, and calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose.

2. The method according to claim 1, characterized in that, The calculating the metric value of the deformation instruction after the pose adjustment includes: Establish a three-dimensional coordinate system based on the source point cloud data and the target point cloud data after the pose adjustment; Project the source point cloud data and the target point cloud data respectively in the direction perpendicular to the YOZ plane and the direction perpendicular to the XOZ plane to obtain the first source point cloud projection data projected by the source point cloud data on the YOZ plane and the second source point cloud projection data projected on the XOZ plane, and obtain the first target point cloud projection data projected by the target point cloud data on the YOZ plane and the second target point cloud projection data projected on the XOZ plane; Calculate the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data.

3. The method according to claim 2, characterized in that, The calculating the metric value based on the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data includes: For the i-th point position in the first source point cloud projection data, the second source point cloud projection data, the first target point cloud projection data, and the second target point cloud projection data respectively, calculate the first distance between the first source point cloud projection data of the i-th point position and the first target point cloud projection data of the i-th point position, and calculate the second distance between the second source point cloud projection data of the i-th point position and the second target point cloud projection data of the i-th point position; Add the first distance and the second distance, and take the square root of the sum value to obtain the square root sum of the i-th point position; Take the average value of the square root sums of all point positions to calculate and obtain the metric value.

4. The method according to any one of claims 1 - 3, characterized in that, The determining whether there is an optimal adjustment pose based on all the metric values of the action factor includes: For the j-th deformation instruction in the action factor, obtain the first metric value of the j-th deformation instruction, and obtain the second metric value of the j-1-th deformation instruction; Determine the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value; Determine whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data based on the reward and punishment value is the optimal adjustment pose.

5. The method according to claim 4, characterized in that, The determining the reward and punishment value of the j-th deformation instruction based on the first metric value and the second metric value includes: Compare the first metric value and the second metric value; In response to the first metric value being greater than the second metric value, determine that the reward and punishment value is the first reward and punishment value; or, In response to the first metric value being less than the second metric value, determine that the reward and punishment value is the second reward and punishment value; or, In response to the first metric value being equal to the second metric value, determine that the reward and punishment value is the third reward and punishment value.

6. The method according to claim 5, characterized in that, The determining whether the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data based on the reward and punishment value is the optimal adjustment pose includes: In response to the reward and punishment value being the third reward and punishment value, determine that the pose after the j-th deformation instruction adjusts the pose of the source point cloud data and / or the target point cloud data is the optimal adjustment pose.

7. The method according to claim 1, characterized in that, The calculating the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjustment pose includes: For the k-th point in the source point cloud data after the optimal adjustment pose, select two comparison points with the closest distance to the k-th point from the target point cloud data after the optimal adjustment pose; Calculate the comparison distance values between the k-th point and the two comparison points respectively; Calculate the candidate deformation value of the k-th point based on the two comparison distance values; Obtain the average value of the candidate deformation values of all points in the source point cloud data after the optimal adjustment pose as the deformation value of the roadway to be estimated.

8. The method according to claim 1, characterized in that, The selecting a deformation instruction from the action factors to adjust the pose of the source point cloud data and / or the target point cloud data based on the operation sequence includes: Obtain the displacement instruction and the rotation instruction in the deformation instruction; Perform a translation process on the source point cloud data and / or the target point cloud data based on the displacement instruction, and perform a rotation process on the source point cloud data and / or the target point cloud data based on the rotation instruction.

9. A device for calculating the deformation of a coal mine roadway, characterized in that, Includes: An acquisition module, configured to acquire the source point cloud data and the target point cloud data of the roadway to be estimated, where the source point cloud data and the target point cloud data are collected in the roadway to be estimated at different timestamps; A building module, configured to build an action set, the action set includes a plurality of action factors, the action factors include a plurality of deformation instructions, and the deformation instructions are arranged according to the operation sequence; An adjustment module, configured to randomly select any action factor from the action set, select a deformation instruction from the action factor to adjust the pose of the source point cloud data and / or the target point cloud data based on the operation sequence, calculate the metric value of the deformation instruction after the pose adjustment, and determine whether there is an optimal adjustment pose based on all the metric values of the action factor; A calculation module, configured to, in response to the non-existence of an optimal adjusted pose, repeat the above steps of fetching any action factor and its subsequent steps from the action set without callback until it is determined that there is an optimal adjusted pose, and calculate the deformation value of the roadway to be estimated based on the source point cloud data and the target point cloud data after the optimal adjusted pose.

10. An electronic device, characterized in that, It includes a memory and a processor; Wherein, the processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the method according to any one of claims 1-8.

Images