Soil layer tunneling cutter damage state detection method
By constructing the monitoring position change sequence and structural confidence of the shield machine tool and cleaning the point cloud data, the interference problems caused by environmental factors and soil structure in the shield machine tool detection are solved, and the accuracy of damage detection is improved.
Patent Information
- Application Number
- CN202411448371.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-17
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-10-17
AI Technical Summary
In the prior art, in the tool damage detection of shield machine, due to environmental factors such as vibration and the soil structure of different working rings, different degrees of interference information exist in different parts of the point cloud data, making it difficult to accurately judge the damage to the tool, and reduce the The accuracy of the test results is achieved.
Point cloud data of the cutter plate and palm surface area of the shield machine is collected, and the monitoring position change sequence and structural confidence are constructed, and detection accuracy is improved through data cleaning. The specific methods include: constructing a monitoring position change sequence based on the displacement changes of point cloud data, analyzing the correlation degree through the DTW algorithm, hierarchical clustering to obtain structural confidence, and cleaning the data according to the confidence threshold.
Through the analysis of monitoring the correlation degree of change and structural confidence, the disturbed point cloud data is cleaned, the accuracy of the detection results is improved, the change relationship of three-dimensional position information is clarified, and the interference relationship representation of geological changes is enhanced.
Smart Images

Figure CN118967688A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to the technical field of image processing, and in particular to a method for detecting the damage state of a soil excavation tool. Background Art
[0002] As one of the important tools in tunnel excavation engineering, shield machine cutters are mainly used to excavate underground tunnels. It is necessary to detect the damage state of the cutter surface in a timely manner to ensure the production quality of shield machine cutters. Existing technologies usually use point cloud data to collect and characterize the cutter information on the surface of shield machine cutters, thereby performing damage detection on shield machine cutters through point cloud data technology.
[0003] The existing technology usually uses the PL-ICP algorithm to process point cloud data to identify and control the operating status of the shield machine. In the process, it will be affected by environmental factors such as vibration and the soil structure of the tunnel face in different operating segments, resulting in different degrees of interference information in different data points in the point cloud data of different parts of the shield machine tool, making it difficult to judge the damage of the shield machine tool, thereby reducing the accuracy of the detection results. Summary of the invention
[0004] The present invention provides a soil excavation tool damage state detection method to solve the existing problem that when a PL-ICP algorithm processes point cloud data to identify and control the operation state of a shield machine, it is affected by environmental factors such as vibration and soil structures of the face of different operating segments, resulting in different degrees of interference information at different data points in the point cloud data of different parts of the shield machine tool, making it difficult to judge the damage state of the shield machine tool.
[0005] A soil excavation tool damage state detection method of the present invention adopts the following technical scheme: The following steps are involved: Collecting point cloud data of the cutter head area and the tunnel face area of the shield machine in several monitoring frames, wherein the point cloud data includes a plurality of shield image points with three-dimensional spatial position information, and each shield image point corresponds to a data point in each monitoring frame; The shield machine cutterhead area and the tunnel face area are both recorded as a shield monitoring area. According to the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames, the shield monitoring position change degree sequence of each shield monitoring area is constructed; according to the correlation of the shield monitoring position change degree between the shield monitoring position change degree sequences of different shield monitoring areas, the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutterhead area is obtained; according to the difference between the shield monitoring position change degrees of different shield monitoring positions in the shield machine cutterhead area, the structural confidence of each shield image point in each monitoring frame is obtained; The shield machine data is cleaned according to the structural confidence of each shield image point.
[0006] Preferably, the method of constructing a shield monitoring position change degree sequence for each shield monitoring area according to the displacement change of corresponding data points between adjacent monitoring frames of the point cloud data of the same shield monitoring area includes the following specific methods: Preset a window preset side length ; For any shield monitoring area, any shield image point in the shield monitoring area is recorded as the target shield image point; for any monitoring frame in the shield monitoring area, the data point corresponding to the target shield image point in the monitoring frame is recorded as the target shield monitoring data point of the target shield image point; with the target shield monitoring data point as the center, the window size The window area is recorded as the neighborhood data point area of the target shield monitoring data point; the neighborhood data point areas of all target shield monitoring data points of the target shield image point are obtained; For any two adjacent target shield monitoring data points of the target shield image point, of the two target shield monitoring data points, the first target shield monitoring data point is recorded as the reference shield monitoring data point, and the second target shield monitoring data point is recorded as the marked shield monitoring data point; according to the change difference distance of the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point, the neighborhood change degree of the marked shield monitoring data point is obtained; According to the degree of neighborhood change, the degree of change of the shield monitoring position in the shield monitoring area in each monitoring frame is obtained; The sequence formed by all shield monitoring position change degrees in the shield monitoring area is recorded as the shield monitoring position change degree sequence in the shield monitoring area.
[0007] Preferably, the degree of neighborhood change of the marked shield monitoring data point is obtained according to the change difference distance of the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point, and the specific method includes: In the formula, Indicates the degree of change in the neighborhood of the marked shield monitoring data point; Represents the number of all data points in the neighborhood data point area of the reference shield monitoring data point; Indicates the number of all data points in the neighborhood data point area marking the shield monitoring data point; Indicates the neighborhood data point area of the reference shield monitoring data point. data point, and the neighboring data point area of the marked shield monitoring data point The Euclidean distance between the data points.
[0008] Preferably, the method of obtaining the shield monitoring position change degree of the shield monitoring area in each monitoring frame according to the neighborhood change degree includes the following specific methods: The cumulative sum of the neighborhood change degrees of the marked shield monitoring data points of all target shield image points is recorded as the cumulative sum of the monitoring frame neighborhood changes of the shield monitoring area in the monitoring frame; the cumulative sum of the monitoring frame neighborhood changes of the shield monitoring area in all monitoring frames is linearly normalized, and the normalized cumulative sum of the neighborhood changes of each monitoring frame is recorded as the shield monitoring position change degree.
[0009] Preferably, the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area is obtained according to the correlation of the shield monitoring position change degrees between the shield monitoring position change degree sequences of different shield monitoring areas, and the specific method includes: Preset a reference number of shield monitoring position change ; Record any shield monitoring position change degree in the shield machine cutter head area shield monitoring position change degree sequence as the target shield monitoring position change degree, and record the target shield monitoring position change degree on the left The shield monitoring position change degree and the target shield monitoring position change degree on the right The data segment composed of the change degrees of the shield monitoring positions is recorded as the neighborhood reference data segment of the change degree of the target shield monitoring position; Obtaining the shield area correlation value of each shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree; Any shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area is recorded as the first target shield monitoring position change degree; according to the shield area correlation value of the overall shield monitoring position change degree in the neighborhood reference data segment of the first target shield monitoring position change degree, the monitoring change correlation factor of the first target shield monitoring position change degree is obtained; In the shield monitoring position change degree sequence in the cutter head area of the shield machine, the product of the monitoring change correlation factor of the first shield monitoring position change degree and the monitoring change correlation factor of the second shield monitoring position change degree is recorded as the monitoring change correlation degree of the second shield monitoring position change degree; the product of the monitoring change correlation degree of the second shield monitoring position change degree and the monitoring change correlation factor of the third shield monitoring position change degree is recorded as the monitoring change correlation degree of the third shield monitoring position change degree; the product of the monitoring change correlation degree of the third shield monitoring position change degree and the monitoring change correlation factor of the fourth shield monitoring position change degree is recorded as the monitoring change correlation degree of the fourth shield monitoring position change degree; and so on, to obtain the monitoring change correlation degree of each shield monitoring position change degree.
[0010] Preferably, the specific method of obtaining the shield area association value of each shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree includes: Any shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree is recorded as the reference shield monitoring position change degree; the sequence number of the reference shield monitoring position change degree in the shield monitoring position change degree sequence in the shield machine cutter head area is recorded as the target sequence number; the shield monitoring position change degree in the shield monitoring position change degree sequence in the tunnel face area with the same sequence number as the target sequence is recorded as the control shield monitoring position change degree of the reference shield monitoring position change degree; the shield monitoring position change degree sequence in the shield machine cutter head area and the shield monitoring position change degree sequence in the tunnel face area are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the control shield monitoring position change degree and the reference shield monitoring position change degree, and record it as the shield area association value of the reference shield monitoring position change degree.
[0011] Preferably, the monitoring change correlation factor of the first target shield monitoring position change degree is obtained according to the shield area correlation value of the overall shield monitoring position change degree in the neighborhood reference data segment of the first target shield monitoring position change degree, including the specific method of: In the formula, The monitoring change correlation factor representing the change degree of the first target shield monitoring position; A neighborhood reference data segment representing the degree of change of the first target shield monitoring position; The first target shield monitoring position change degree in the neighborhood reference data segment The shield monitoring position change degree shield area correlation value; Represents an exponential function with a natural constant as its base.
[0012] Preferably, the structural confidence of each shield image point in each monitoring frame is obtained according to the difference between the change degrees of different shield monitoring positions in the cutter head area of the shield machine, and the specific method includes: In the shield monitoring position change degree sequence of the shield machine cutter head area, the absolute value of the difference between any two different shield monitoring position changes is used as the distance metric, and all shield monitoring position change degrees are hierarchically clustered to obtain several clusters. According to the shield machine cutterhead area The differences between the different shield monitoring position change degrees within the cluster to which the shield monitoring position change degree belongs, as well as the differences between the shield machine cutter head area The shield image point is The degree of neighborhood change in the frame monitoring frame is obtained by The shield image point is Structural confidence factor in frame monitoring frames; Get all the shield image points in the shield machine cutterhead area in the first The structure confidence factors in the frame monitoring frame are linearly normalized, and each normalized structure confidence factor is recorded as the structure confidence.
[0013] Preferably, the shield machine cutter head area is in the The differences between the different shield monitoring position change degrees within the cluster to which the shield monitoring position change degree belongs, as well as the differences between the shield machine cutter head area The shield image point is The degree of neighborhood change in the frame monitoring frame is obtained by The shield image point is The structure confidence factor in the frame monitoring frame includes the following specific methods: In the formula, Indicates the shield machine cutterhead area The shield image point is Structural confidence factor in frame monitoring frames; Indicates the number of all monitoring frames in the cutterhead area of the shield machine; Indicates The data point in The degree of neighborhood changes in the frame monitoring frame; Indicates the shield machine cutterhead area The number of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Indicates The shield monitoring position change degree belongs to the cluster The change of shield monitoring position; Indicates The mean value of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Represents the preset hyperparameters.
[0014] Preferably, the data cleaning of the shield machine according to the structural confidence of each shield image point includes the following specific methods: Preset a structure confidence threshold ; If the shield machine cutter head area The shield image point is The structure confidence in the frame monitoring frame is less than , the first The shield image point is The data points in the frame monitoring frame are replaced by the first The shield image point is Frame monitors the data points in the frame.
[0015] The beneficial effects of the technical solution of the present invention are: according to the displacement changes of corresponding data points of point cloud data of the same shield monitoring area between adjacent monitoring frames, a shield monitoring position change degree sequence of each shield monitoring area is constructed; according to the correlation of shield monitoring position change degrees between shield monitoring position change degree sequences, the monitoring change correlation degree of each shield monitoring position change degree is obtained; according to the difference between different shield monitoring position change degrees in the cutter head area of the shield machine, the structural confidence of each shield image point in each monitoring frame is obtained; according to the structural confidence of each shield image point, the shield machine data is cleaned; wherein the monitoring change correlation degree is used to describe the degree to which the point cloud data of the shield machine changes slowly with geological changes during actual operation, so that the point cloud data better represents the relationship disturbed by geological changes; the structural confidence degree is used to describe the drastic degree of corresponding image structure changes in the monitoring frame, so that the change relationship of the corresponding three-dimensional position information in the point cloud data is clearer; the present invention cleans the data points that are greatly disturbed in the point cloud data, thereby improving the accuracy of the detection results. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 The present invention is a flowchart of the steps of a soil excavation tool damage state detection method. DETAILED DESCRIPTION
[0018] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the method for detecting the damage state of a soil excavation tool proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.
[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
[0020] The specific scheme of the soil excavation tool damage state detection method provided by the present invention is described in detail below with reference to the accompanying drawings.
[0021] See also Figure 1 , which shows a flowchart of a method for detecting damage status of a soil excavation tool provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Collect point cloud data of the cutter head area and the tunnel face area of the shield machine in several monitoring frames.
[0022] It should be noted that the existing technology usually uses the PL-ICP algorithm to process point cloud data to identify and control the operating status of the shield machine. This process is affected by environmental factors such as vibration and the soil structure of the face of different operating segments, resulting in different degrees of interference in the point cloud data of different parts of the shield machine cutter, making it difficult to judge the damage of the shield machine cutter, thereby reducing the accuracy of the detection results.
[0023] Specifically, it is necessary to first collect the point cloud data and several monitoring frames of each shield monitoring area. The specific process is: the shield cutter area and the face area of the shield machine are both used as the shield machine monitoring area; the point cloud data of each shield machine monitoring area is obtained through three-dimensional laser, and each data point in the point cloud data of each shield monitoring area is recorded as a shield image point; taking any shield machine monitoring area as an example, in the shield machine historical monitoring frame database, every 5 seconds is taken as a monitoring frame, and several monitoring frames of the shield machine monitoring area in the past day are obtained; and several monitoring frames of each shield machine monitoring area are obtained. The time interval for recording the monitoring frames and the total time length for recording the monitoring frames can be determined according to the specific implementation situation.
[0024] It should be noted that the cutterhead area of the shield machine is mainly composed of the main beam, auxiliary beam, roller cutter, scraper, side scraper and super-excavation cutter; the face area is mainly composed of the working surface area when the shield machine is advancing; the point cloud data of each shield monitoring area contains multiple data points, each data point corresponds to a data point with three-dimensional spatial position information in each monitoring frame, and the three-dimensional spatial position corresponding to each data point in different monitoring frames is not always the same.
[0025] So far, the point cloud data of the cutter head area and the tunnel face area of the shield machine in several monitoring frames are obtained through the above method.
[0026] Step S002: construct a shield monitoring position change degree sequence for each shield monitoring area based on the displacement change of corresponding data points between adjacent monitoring frames of the point cloud data of the same shield monitoring area; obtain the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area based on the correlation of the shield monitoring position change degrees between the shield monitoring position change degree sequences of different shield monitoring areas; obtain the structural confidence of each shield image point in each monitoring frame based on the difference between different shield monitoring position change degrees in the shield machine cutter head area.
[0027] It should be noted that the image data related to the shield machine's operating environment mainly includes the point cloud data of the tool assembly structure in the shield machine's cutter head area and the point cloud data of the corresponding soil structure in the face area. The positions of different data points corresponding to the point cloud data will be affected by environmental factors such as vibration and the soil structure of the face in different operating segments, resulting in difficulty in judging the degree of wear on different data point positions in each shield monitoring area. When the position of the corresponding data point of the point cloud data changes within multiple monitoring frames, the position of the data point caused by wear will slowly change over time. Therefore, the structural confidence of each data point can be obtained in combination with the change characteristics of the structural points in the shield monitoring area, so as to achieve accurate cleaning of the data points and complete accurate visualization of the shield machine's tool and operating environment.
[0028] Preferably, in one embodiment of the present invention, according to the displacement change of corresponding data points of the point cloud data of the same shield monitoring area between adjacent monitoring frames, a shield monitoring position change degree sequence of each shield monitoring area is obtained, including the specific method of: Preset a window preset side length , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It can be determined according to the specific implementation situation; taking any shield monitoring area as an example, any shield image point in the shield monitoring area is recorded as the target shield image point; taking any monitoring frame of the shield monitoring area as an example, the data point corresponding to the target shield image point in the monitoring frame is recorded as the target shield monitoring data point of the target shield image point; taking the target shield monitoring data point as the center, the window size The window area is recorded as the neighborhood data point area of the target shield monitoring data point; the neighborhood data point area of all target shield monitoring data points of the target shield image point is obtained. Each target shield monitoring data point corresponds to a monitoring frame.
[0029] Furthermore, taking any two adjacent target shield monitoring data points of the target shield image point as an example, among these two target shield monitoring data points, the first target shield monitoring data point is recorded as the reference shield monitoring data point, and the second target shield monitoring data point is recorded as the marked shield monitoring data point. According to the change difference distance of the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point, the neighborhood change degree of the marked shield monitoring data point is obtained. As an example, the neighborhood change degree of the marked shield monitoring data point can be calculated by the following formula: In the formula, Indicates the degree of change in the neighborhood of the marked shield monitoring data point; Represents the number of all data points in the neighborhood data point area of the reference shield monitoring data point; Indicates the number of all data points in the neighborhood data point area marking the shield monitoring data point; Indicates the neighborhood data point area of the reference shield monitoring data point. data point, and the neighboring data point area of the marked shield monitoring data point The Euclidean distance between the data points. The acquisition of the Euclidean distance is a well-known technique and will not be described in detail in this embodiment.
[0030] It should be noted that It indicates the overall change degree of the data points in the corresponding neighborhood data point area between the marked shield monitoring data point and the reference shield monitoring data point; if the neighborhood change degree of the marked shield monitoring data point is greater, it means that the point cloud data of the shield monitoring area has changed more in the monitoring frame to which the marked shield monitoring data point belongs, which reflects that the appearance change of the monitoring objects in the shield monitoring area in the monitoring frame to which the marked shield monitoring data point belongs is more obvious.
[0031] Furthermore, the neighborhood change degree of the marked shield monitoring data points of all target shield image points is obtained; the cumulative sum of the neighborhood change degree of the marked shield monitoring data points of all target shield image points is recorded as the cumulative sum of neighborhood change of the shield monitoring area in the monitoring frame; the cumulative sum of neighborhood change of the shield monitoring area in all monitoring frames is linearly normalized, and the normalized cumulative sum of neighborhood change of each monitoring frame is recorded as the shield monitoring position change degree; the sequence composed of all shield monitoring position change degrees of the shield monitoring area is recorded as the shield monitoring position change degree sequence of the shield monitoring area; the shield monitoring position change degree sequence of each shield monitoring area is obtained. Each monitoring frame corresponds to a cumulative sum of neighborhood change of the monitoring frame.
[0032] It should be further explained that, for the face area, the shield monitoring position change degree sequence will form a phased change trend with the regional changes of the geological structure; and for the shield machine cutter head area, when the cutter head tool area is worn, it will show consistent directional changes in multiple stages, and the regional position change will continue to increase, but it will be affected by the changes in the face area and the environmental factors such as mud, resulting in the misjudgment of the wear position of the shield machine cutter head area; therefore, the correlation between the position change degrees of the two shield monitoring areas can be used to further analyze the credibility of the position change of the shield machine cutter head area.
[0033] Preferably, in one embodiment of the present invention, according to the correlation of shield monitoring position change degrees between shield monitoring position change degree sequences in different shield monitoring areas, the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area is obtained, and the specific method includes: Preset a reference number of shield monitoring position change , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It can be determined according to the specific implementation situation; taking any shield monitoring position change degree in the shield machine cutter head area shield monitoring position change degree sequence as an example, the left side of the shield monitoring position change degree The shield monitoring position change degree and the shield monitoring position change degree on the right The data segment composed of the shield monitoring position change degrees is recorded as the neighborhood reference data segment of the shield monitoring position change degree. In particular, if the number of shield monitoring position change degrees on either side of the shield monitoring position change degree does not meet the preset , then the actual number of shield monitoring position changes on the left and right sides of the shield monitoring position change is used as the basis to obtain the neighborhood reference data segment of the shield monitoring position change.
[0034] Furthermore, any shield monitoring position change degree in the neighborhood reference data segment of the shield monitoring position change degree is recorded as the reference shield monitoring position change degree; the sequence number of the reference shield monitoring position change degree in the shield monitoring position change degree sequence is recorded as the target sequence number; the shield monitoring position change degree in the shield monitoring position change degree sequence of the face area with the same sequence number as the target sequence is recorded as the comparison shield monitoring position change degree of the reference shield monitoring position change degree; the shield monitoring position change degree sequence of the shield machine cutter head area and the shield monitoring position change degree sequence of the face area are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the comparison shield monitoring position change degree and the reference shield monitoring position change degree, and record it as the shield area association value of the reference shield monitoring position change degree; the shield area association values of all shield monitoring position change degrees in the neighborhood reference data segment of the shield monitoring position change degree are obtained. The process of obtaining the DTW distance between two data according to two data sequences is a well-known content of the DTW (Dynamic Time Warping) dynamic time warping algorithm, which will not be described in detail in this embodiment.
[0035] Further, taking any shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area as an example, according to the shield area correlation value of the overall shield monitoring position change degree in the neighborhood reference data segment of the shield monitoring position change degree, the monitoring change correlation factor of the shield monitoring position change degree is obtained. As an example, the monitoring change correlation factor of the shield monitoring position change degree can be calculated by the following formula: In the formula, The monitoring change correlation factor representing the degree of change of the shield monitoring position; A neighborhood reference data segment representing the degree of change of the shield monitoring position; The first one in the neighborhood reference data segment representing the change of the shield monitoring position The shield monitoring position change degree shield area correlation value; represents an exponential function with a natural constant as the base, and the embodiment adopts Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can choose the inverse proportional function and the normalization function according to the actual situation. The monitoring change correlation factor of all shield monitoring position change degrees in the shield machine cutter head area is obtained.
[0036] It should be noted that if the monitoring change correlation factor of the shield monitoring position change is larger, it means that the point cloud data of the shield machine during actual operation changes more slowly with geological changes.
[0037] Furthermore, in the shield monitoring position change degree sequence in the cutter head area of the shield machine, the product of the monitoring change correlation factor of the first shield monitoring position change degree and the monitoring change correlation factor of the second shield monitoring position change degree is recorded as the monitoring change correlation degree of the second shield monitoring position change degree; the product of the monitoring change correlation degree of the second shield monitoring position change degree and the monitoring change correlation factor of the third shield monitoring position change degree is recorded as the monitoring change correlation degree of the third shield monitoring position change degree; the product of the monitoring change correlation degree of the third shield monitoring position change degree and the monitoring change correlation factor of the fourth shield monitoring position change degree is recorded as the monitoring change correlation degree of the fourth shield monitoring position change degree; the product of the monitoring change correlation degree of the fourth shield monitoring position change degree and the monitoring change correlation factor of the fifth shield monitoring position change degree is recorded as the monitoring change correlation degree of the fifth shield monitoring position change degree; and so on, to obtain the monitoring change correlation degrees of all shield monitoring position change degrees. It is particularly noted that after calculating the monitoring change correlations of all shield monitoring position change degrees, this embodiment defaults the monitoring change correlation factor of the first shield monitoring position change degree to the monitoring change correlation of the first shield monitoring position change degree.
[0038] Preferably, in one embodiment of the present invention, according to the difference between the change degrees of different shield monitoring positions in the cutter head area of the shield machine, the structural confidence of each shield image point in each monitoring frame is obtained, and the specific method includes: In the shield monitoring position change degree sequence of the shield machine cutter head area, the absolute value of the difference between any two different shield monitoring position changes is used as the distance metric, and all shield monitoring position change degrees are hierarchically clustered to obtain a number of cluster clusters. Each cluster cluster contains multiple shield monitoring position change degrees; in addition, the process of clustering according to the distance metric is a well-known content of the hierarchical clustering algorithm, which will not be repeated in this embodiment.
[0039] Further, according to the shield machine cutterhead area The differences between the different shield monitoring position change degrees within the cluster to which the shield monitoring position change degree belongs, as well as the differences between the shield machine cutter head area The shield image point is The degree of neighborhood change in the frame monitoring frame is obtained by The shield image point is The structural confidence factor in the frame monitoring frame. As an example, the first confidence factor in the shield machine cutter head area can be calculated by the following formula: The shield image point is Structural confidence factor in frame monitoring frame: In the formula, Indicates the shield machine cutterhead area The shield image point is Structural confidence factor in frame monitoring frames; Indicates the number of all monitoring frames in the cutterhead area of the shield machine; Indicates The data point in The degree of neighborhood changes in the frame monitoring frame; Indicates the shield machine cutterhead area The number of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Indicates The shield monitoring position change degree belongs to the cluster The change of shield monitoring position; Indicates The mean value of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Indicates the preset hyperparameters. In this embodiment, , used to prevent the denominator from being 0; Indicates taking the absolute value.
[0040] It should be noted that if the shield machine cutter head area The shield image point is The smaller the structure confidence factor in the frame monitoring frame, the The data point in The more dramatic the change in the corresponding image structure in the frame monitoring frame, the more The data point in The more frame monitoring the data information in the frame, the more it needs to be cleaned.
[0041] Further, all shield image points in the shield machine cutterhead area are obtained in the first The structure confidence factors in the frame monitoring frame are linearly normalized, and each normalized structure confidence factor is recorded as the structure confidence.
[0042] So far, the structural confidence of each shield image point in each monitoring frame is obtained through the above method.
[0043] Step S003: Clean the shield machine data according to the structural confidence of each shield image point.
[0044] Preferably, in another embodiment of the present invention, data cleaning of the shield machine is performed according to the structural confidence of each shield image point, and the specific method includes: Preset a structure confidence threshold , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. It can be determined according to the specific implementation situation; if the shield machine cutter head area The shield image point is The structure confidence in the frame monitoring frame is less than , the first The shield image point is The data points in the frame monitoring frame are replaced by the first The shield image point is The data points in the frame monitoring frame. The data points of each shield image point in all monitoring frames are used to construct a BIM model, and a visual inspection is performed according to the BIM model to obtain a visual inspection result. Among them, building a BIM model is a well-known technology, and the process of obtaining a visual inspection result according to the BIM model is a well-known content of the PL-ICP (Point-to-line Iterative Closest Point) point-to-line iterative closest point algorithm, which will not be repeated in this embodiment.
[0045] It is particularly noted that if the first The structural confidence of shield image points in the last monitoring frame is less than , directly the first The position information of the shield image points in the last monitoring frame is eliminated.
[0046] At this point, this embodiment is completed.
[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A method for detecting damage status of soil excavation tools, characterized in that: The method comprises the following steps: Collecting point cloud data of the cutter head area and the tunnel face area of the shield machine in several monitoring frames, wherein the point cloud data includes a plurality of shield image points with three-dimensional spatial position information, and each shield image point corresponds to a data point in each monitoring frame; The shield machine cutterhead area and the tunnel face area are both recorded as a shield monitoring area. According to the displacement changes of corresponding data points in the point cloud data of the same shield monitoring area between adjacent monitoring frames, the shield monitoring position change degree sequence of each shield monitoring area is constructed; according to the correlation of the shield monitoring position change degree between the shield monitoring position change degree sequences of different shield monitoring areas, the monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutterhead area is obtained; according to the difference between the shield monitoring position change degrees of different shield monitoring positions in the shield machine cutterhead area, the structural confidence of each shield image point in each monitoring frame is obtained; The shield machine data is cleaned according to the structural confidence of each shield image point; The method of constructing a shield monitoring position change sequence for each shield monitoring area according to the displacement change of corresponding data points between adjacent monitoring frames of the point cloud data of the same shield monitoring area includes the following specific methods: Preset a window preset side length ; For any shield monitoring area, any shield image point in the shield monitoring area is recorded as the target shield image point; for any monitoring frame in the shield monitoring area, the data point corresponding to the target shield image point in the monitoring frame is recorded as the target shield monitoring data point of the target shield image point; with the target shield monitoring data point as the center, the window size The window area is recorded as the neighborhood data point area of the target shield monitoring data point; the neighborhood data point areas of all target shield monitoring data points of the target shield image point are obtained; For any two adjacent target shield monitoring data points of the target shield image point, of the two target shield monitoring data points, the first target shield monitoring data point is recorded as the reference shield monitoring data point, and the second target shield monitoring data point is recorded as the marked shield monitoring data point; according to the change difference distance of the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point, the neighborhood change degree of the marked shield monitoring data point is obtained; According to the degree of neighborhood change, the degree of change of the shield monitoring position in the shield monitoring area in each monitoring frame is obtained; The sequence formed by all shield monitoring position change degrees in the shield monitoring area is recorded as the shield monitoring position change degree sequence in the shield monitoring area; The monitoring change correlation degree of each shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area is obtained according to the correlation between the shield monitoring position change degree sequences of different shield monitoring areas, and the specific method includes: Preset a reference number of shield monitoring position change ; Record any shield monitoring position change degree in the shield machine cutter head area shield monitoring position change degree sequence as the target shield monitoring position change degree, and record the target shield monitoring position change degree on the left The shield monitoring position change degree and the target shield monitoring position change degree on the right The data segment composed of the change degrees of the shield monitoring positions is recorded as the neighborhood reference data segment of the change degree of the target shield monitoring position; Obtaining the shield area correlation value of each shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree; Any shield monitoring position change degree in the shield monitoring position change degree sequence of the shield machine cutter head area is recorded as the first target shield monitoring position change degree; according to the shield area correlation value of the overall shield monitoring position change degree in the neighborhood reference data segment of the first target shield monitoring position change degree, the monitoring change correlation factor of the first target shield monitoring position change degree is obtained; In the shield monitoring position change degree sequence of the shield machine cutter head area, the product of the monitoring change correlation factor of the first shield monitoring position change degree and the monitoring change correlation factor of the second shield monitoring position change degree is recorded as the monitoring change correlation degree of the second shield monitoring position change degree; the product of the monitoring change correlation degree of the second shield monitoring position change degree and the monitoring change correlation factor of the third shield monitoring position change degree is recorded as the monitoring change correlation degree of the third shield monitoring position change degree; the product of the monitoring change correlation degree of the third shield monitoring position change degree and the monitoring change correlation factor of the fourth shield monitoring position change degree is recorded as the monitoring change correlation degree of the fourth shield monitoring position change degree; and so on, the monitoring change correlation degree of each shield monitoring position change degree is obtained; The structural confidence of each shield image point in each monitoring frame is obtained according to the difference between the change degrees of different shield monitoring positions in the cutter head area of the shield machine, and the specific method includes: In the shield monitoring position change degree sequence of the shield machine cutter head area, the absolute value of the difference between any two different shield monitoring position changes is used as the distance metric, and all shield monitoring position change degrees are hierarchically clustered to obtain several clusters. According to the shield machine cutterhead area The differences between the different shield monitoring position change degrees within the cluster to which the shield monitoring position change degree belongs, as well as the differences between the shield machine cutter head area The shield image point is The degree of neighborhood change in the frame monitoring frame is obtained by The shield image point is Structural confidence factor in frame monitoring frames; Get all the shield image points in the shield machine cutterhead area in the first The structure confidence factors in the frame monitoring frame are linearly normalized, and each normalized structure confidence factor is recorded as the structure confidence.
2. A soil excavation tool damage state detection method according to claim 1, characterized in that: The specific method of obtaining the neighborhood change degree of the marked shield monitoring data point according to the change difference distance of the data points in the corresponding neighborhood data point area between the reference shield monitoring data point and the marked shield monitoring data point is as follows: In the formula, Indicates the degree of change in the neighborhood of the marked shield monitoring data point; Represents the number of all data points in the neighborhood data point area of the reference shield monitoring data point; Indicates the number of all data points in the neighborhood data point area marking the shield monitoring data point; Indicates the neighborhood data point area of the reference shield monitoring data point. data point, and the neighboring data point area of the marked shield monitoring data point The Euclidean distance between the data points.
3. A soil excavation tool damage state detection method according to claim 1, characterized in that: The specific method of obtaining the shield monitoring position change degree of the shield monitoring area in each monitoring frame according to the neighborhood change degree is as follows: The cumulative sum of the neighborhood change degrees of the marked shield monitoring data points of all target shield image points is recorded as the cumulative sum of the monitoring frame neighborhood change of the shield monitoring area in the monitoring frame; The cumulative sum of the changes in the neighborhood of the shield monitoring area in all monitoring frames is linearly normalized, and the normalized cumulative sum of the changes in the neighborhood of each monitoring frame is recorded as the change degree of the shield monitoring position.
4. A soil excavation tool damage state detection method according to claim 1, characterized in that: The specific method of obtaining the shield area association value of each shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree includes: Any shield monitoring position change degree in the neighborhood reference data segment of the target shield monitoring position change degree is recorded as the reference shield monitoring position change degree; the sequence number of the reference shield monitoring position change degree in the shield monitoring position change degree sequence in the shield machine cutter head area is recorded as the target sequence number; The shield monitoring position change degree with the same sequence number as the target sequence in the shield monitoring position change degree sequence in the tunnel face area is recorded as the control shield monitoring position change degree of the reference shield monitoring position change degree; the shield monitoring position change degree sequence in the shield machine cutter head area and the shield monitoring position change degree sequence in the tunnel face area are input into the DTW dynamic time warping algorithm to obtain the DTW distance between the control shield monitoring position change degree and the reference shield monitoring position change degree, and recorded as the shield area association value of the reference shield monitoring position change degree.
5. A soil excavation tool damage state detection method according to claim 1, characterized in that: The monitoring change correlation factor of the first target shield monitoring position change degree is obtained according to the shield area correlation value of the overall shield monitoring position change degree in the neighborhood reference data segment of the first target shield monitoring position change degree, including the specific method of: In the formula, The monitoring change correlation factor representing the change degree of the first target shield monitoring position; A neighborhood reference data segment representing the degree of change of the first target shield monitoring position; The first target shield monitoring position change degree in the neighborhood reference data segment The shield monitoring position change degree shield area correlation value; Represents an exponential function with a natural constant as its base.
6. A soil excavation tool damage state detection method according to claim 1, characterized in that: The shield machine cutter head area is The differences between the different shield monitoring position change degrees within the cluster to which the shield monitoring position change degree belongs, as well as the differences between the shield machine cutter head area The shield image point is The degree of neighborhood change in the frame monitoring frame is obtained by The shield image point is The structure confidence factor in the frame monitoring frame includes the following specific methods: In the formula, Indicates the shield machine cutterhead area The shield image point is Structural confidence factor in frame monitoring frames; Indicates the number of all monitoring frames in the cutterhead area of the shield machine; Indicates The data point in The degree of neighborhood changes in the frame monitoring frame; Indicates the shield machine cutterhead area The number of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Indicates The shield monitoring position change degree belongs to the cluster The change of shield monitoring position; Indicates The mean value of all shield monitoring position change degrees in the cluster to which the shield monitoring position change degree belongs; Represents the preset hyperparameters.
7. A soil excavation tool damage state detection method according to claim 1, characterized in that: The shield machine data is cleaned according to the structural confidence of each shield image point, and the specific method includes: Preset a structure confidence threshold ; If the shield machine cutter head area The shield image point is The structure confidence in the frame monitoring frame is less than , the first The shield image point is The data points in the frame monitoring frame are replaced by the first The shield image point is Frame monitors the data points in the frame.
Citation Information
Patent Citations
PDC drill bit wear detection method and system based on multi-view three-dimensional reconstruction
CN117808794A
Large-diameter pressure steel pipe welding seam nondestructive testing method and system
CN118225999A
Method of making three dimension model and defect analysis using camera and laser scanning
KR1020150128300A
Cited By
Shield tunneling machine or TBM hob associated characteristic analysis wear method and system
CN120298845A
