External force determination system, external force determination method, and external force determination program

Abstract

To provide an external force determination system capable of accurately diagnosing whether or not a tunnel is receiving an external force that displaces the tunnel.SOLUTION: An external force determination system 1A comprises a 3D point cloud receiving unit 40 that receives data of a 3D point cloud that indicates a shape of a tunnel and is to be analyzed as an analysis 3D point cloud, a ground swelling analysis unit 10 that analyzes ground swelling of a road surface inside the tunnel based on the analysis 3D point cloud, a wall displacement analysis unit 20 that analyzes wall displacement, which is the displacement of an inner wall surface of the tunnel, based on the analysis 3D point cloud, and an external force determination unit 30 that extracts displacement points where the tunnel is displaced more than a reference value based on the ground swelling analysis results and the wall displacement analysis results, calculates the external force direction, which is the direction of the external force received by the tunnel, based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an external force determination system, an external force determination method, and an external force determination program that diagnose whether a tunnel is subjected to an external force. [Background technology]

[0002] In tunnel inspections according to the Ministry of Land, Infrastructure, Transport and Tourism guidelines, a soundness diagnosis is conducted after an on-site inspection. The soundness diagnosis involves an external force assessment to determine whether the tunnel is subject to external forces.

[0003] The tunnel integrity diagnosis system described in Patent Document 1 uses a deformation expansion diagram created based on defects such as cracks inside the tunnel extracted by an inspector to determine whether the defects are caused by external forces. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2005-207044 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, with the technology of Patent Document 1 mentioned above, there are cases where the measurement values ​​taken by the inspector contain large errors, and therefore the deformation development diagram may also contain large errors, resulting in the problem that it is difficult to accurately diagnose whether the tunnel is being subjected to an external force that is displacing the tunnel.

[0006] The present disclosure has been made in consideration of the above, and aims to provide an external force determination system that can accurately diagnose whether or not a tunnel is receiving an external force that causes the tunnel to be displaced. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems and achieve the object, the external force determination system of the present disclosure includes a 3D point cloud receiving unit that receives data of a 3D point cloud that indicates the shape of a tunnel and is to be analyzed as an analysis 3D point cloud. The external force determination system of the present disclosure also includes a ground swelling analysis unit that analyzes ground swelling of a road surface inside a tunnel based on the analysis 3D point cloud, and a wall displacement analysis unit that analyzes wall displacement, which is the displacement of the inner wall surface of the tunnel, based on the analysis 3D point cloud. The external force determination system of the present disclosure also includes an external force determination unit that extracts displacement points where the tunnel is displaced larger than a reference value based on the analysis results of the ground swelling and the wall displacement, calculates the external force direction, which is the direction of the external force that the tunnel receives, based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction. Effect of the Invention

[0008] The external force determination system according to the present disclosure has the effect of being able to accurately diagnose whether or not a tunnel is receiving an external force that causes the tunnel to be displaced. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing a configuration of an external force determination system according to a first embodiment. [Diagram 2] An example of a deformation development diagram [Diagram 3] FIG. 1 is a diagram showing an example of a contour diagram used by the external force determination system according to the first embodiment; [Figure 4] FIG. 1 is a diagram showing an example of a three-dimensional contour diagram generated by the external force determination system according to the first embodiment; [Diagram 5] FIG. 1 is a diagram showing an example of topographical and geological information used by the external force determination system according to the first embodiment; [Figure 6] 1 is a flowchart showing the procedure of an overall process executed by the external force determination system according to the first embodiment; [Figure 7] A flowchart showing a procedure for a swelling analysis executed by the external force determination system according to the first embodiment. [Figure 8] 1 is a flowchart showing a procedure for a wall displacement analysis executed by the external force determination system according to the first embodiment. [Figure 9] 1 is a flowchart showing a procedure for determining whether an external force is present, which is executed by the external force determination system according to the first embodiment; [Figure 10] FIG. 1 is a diagram for explaining a calculation process of a road surface model in the ground swelling analysis process executed by the external force determination system according to the first embodiment; [Figure 11] FIG. 1 is a diagram for explaining a swelling analysis process executed by the external force determination system according to the first embodiment and an example of a processing result. [Figure 12] FIG. 1 is a diagram for explaining a wall displacement analysis process executed by the external force determination system according to the first embodiment; [Figure 13] FIG. 1 is a diagram showing an example of a design drawing of a tunnel used when the external force determination system according to the first embodiment executes a wall displacement analysis process. [Figure 14] FIG. 1 is a diagram showing an example of a model cross section of a tunnel used when the external force determination system according to the first embodiment executes a wall displacement analysis process; [Figure 15] FIG. 1 is a diagram showing an example of tunnel deformation information generated by the external force determination system according to the first embodiment. [Figure 16] FIG. 11 is a block diagram showing a configuration of an external force determination system according to a second embodiment. [Figure 17] FIG. 13 is a diagram showing a configuration of a learning device included in an external force determination system according to a second embodiment. [Figure 18] FIG. 13 is a diagram for explaining a neural network used by a learning device according to a second embodiment. [Figure 19] 11 is a flowchart showing a procedure of a learning process executed by a learning device according to a second embodiment. [Figure 20] FIG. 13 is a diagram showing a configuration of an inference device included in an external force determination system according to a second embodiment. [Figure 21] 11 is a flowchart showing a procedure of an inference process executed by the inference device according to the second embodiment. [Figure 22]FIG. 1 is a diagram showing an example of the configuration of a processing circuit when the processing circuit included in the external force determination system according to the first and second embodiments is realized by a processor and a memory. [Figure 23] FIG. 1 is a diagram showing an example of a processing circuit in the external force determination system according to the first and second embodiments, in the case where the processing circuit is configured with dedicated hardware; DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] An external force determination system, an external force determination method, and an external force determination program according to embodiments of the present disclosure will be described in detail below with reference to the drawings.

[0011] Embodiment 1 FIG. 1 is a block diagram showing the configuration of an external force determination system according to a first embodiment. The external force determination system 1A is a computer that analyzes the displacement of a tunnel to be determined and executes an external force determination for the tunnel. The external force determination system 1A diagnoses whether or not the deformation of the tunnel is caused by an external force. The external force determination system 1A includes a ground swelling analysis unit 10, a wall displacement analysis unit 20, an external force determination unit 30, and a three-dimensional point cloud reception unit 40.

[0012] The swelling analysis unit 10, the wall displacement analysis unit 20, the external force determination unit 30, and the three-dimensional point cloud reception unit 40 may be connected via a network or the like, or may be realized as one computer.

[0013] The ground swelling analysis unit 10 analyzes the ground swelling of the road surface inside the tunnel (the ground swelling of the road surface where the tunnel is located). The ground swelling analysis unit 10 has a road surface extraction unit 11, a road surface center line calculation unit 12, a road surface model calculation unit 13, and a road surface difference calculation unit 14.

[0014] The wall displacement analysis unit 20 analyzes wall displacement, which is the displacement of the inner wall surface of a tunnel. The wall displacement analysis unit 20 has a wall extraction unit 21, a cross-sectional view reading unit 22, a central axis calculation unit 23, a cross-sectional difference calculation unit 24, a comparison wall reading unit 25, a 3D wall model calculation unit 26, and a time-dependent difference calculation unit 27.

[0015] The external force determination unit 30 executes an external force determination for the tunnel. Specifically, the external force determination unit 30 determines whether or not the tunnel is receiving an external force that displaces the tunnel. In other words, the external force determination unit 30 determines whether or not the displacement of the tunnel is caused by an external force.

[0016] Furthermore, when there is an external force that displaces the tunnel, the external force determination unit 30 analyzes the cause of the external force that displaces the tunnel (external force occurrence factor). In this way, the external force determination includes a process of determining the presence or absence of an external force and a process of analyzing the external force occurrence factor.

[0017] The external force determination unit 30 has a 3D analysis result superposition unit 31, a displacement location extraction unit 32, an external force direction calculation unit 33, a supplementary information reading unit 34, and an external force analysis unit 35. The supplementary information reading unit 34 has a deformation development view reading unit 341 and a topography and geological information reading unit 342.

[0018] The 3D point cloud receiving unit 40 receives point cloud data corresponding to the 3D shape of the tunnel (hereinafter referred to as 3D point cloud) from an external device such as a 3D point cloud storage device. The 3D point cloud is data indicating the shape of the tunnel, and is measured, for example, using a laser measuring device, a camera, etc. mounted on a vehicle, etc.

[0019] In addition, when the comparison target to be compared with the 3D point group of the analysis target is a 3D point group, the 3D point group receiving unit 40 receives the 3D point group of the comparison target from an external device such as a storage device for 3D point groups. Hereinafter, the 3D point group of the analysis target may be referred to as an analysis 3D point group. Also, the 3D point group of the comparison target may be referred to as a comparison 3D point group.

[0020] The analysis 3D point cloud corresponds to the shape of the current tunnel (the tunnel to be diagnosed this time), and the comparison 3D point cloud corresponds to the shape of the tunnel in the past (for example, 5 years ago). The 3D point cloud receiving unit 40 transmits the 3D point clouds to the road surface extraction unit 11 of the ground swelling analysis unit 10 and the wall surface extraction unit 21 of the wall surface displacement analysis unit 20.

[0021] The road surface extraction unit 11 extracts only a road surface three-dimensional point cloud, which is a three-dimensional point cloud of the road surface portion, from the analysis three-dimensional point cloud. The road surface extraction unit 11 transmits the road surface three-dimensional point cloud to the road surface center line calculation unit 12.

[0022] The road surface centerline calculation unit 12 calculates a road surface centerline, which is the center line of the road surface, based on the road surface three-dimensional point cloud. The road surface centerline calculation unit 12 transmits the road surface three-dimensional point cloud and the road surface centerline to the road surface model calculation unit 13.

[0023] The road surface model calculation unit 13 calculates a road surface model, which is a model of a normal road surface, based on the road surface center line and the road surface three-dimensional point cloud. The road surface model corresponds to the shape of the road surface estimated when the road surface is normal. The road surface model calculation unit 13 transmits the road surface three-dimensional point cloud and the road surface model to the road surface difference calculation unit 14.

[0024] The road surface difference calculation unit 14 calculates the three-dimensional swelling analysis result, which is the difference between the three-dimensional road surface point cloud and the road surface model. The difference between the three-dimensional road surface point cloud and the road surface model corresponds to the difference between the past shape and the current shape of the road surface. In other words, the difference between the three-dimensional road surface point cloud and the road surface model corresponds to the amount of displacement on the road surface. The three-dimensional swelling analysis result is the result of a three-dimensional analysis of swelling on the road surface, and includes information on the position (coordinates) within the tunnel where the difference between the three-dimensional road surface point cloud and the road surface model was detected. The road surface difference calculation unit 14 transmits the three-dimensional swelling analysis result to the three-dimensional analysis result superimposition unit 31 of the external force determination unit 30.

[0025] The wall displacement analysis unit 20 analyzes the wall displacement using the three-dimensional point cloud of the analysis target and the comparison target. The comparison target in the wall displacement analysis unit 20 is a wall model used to judge the presence or absence of an external force. The wall model as the comparison target corresponds to the shape of the inner wall surface of the tunnel estimated when the inner wall surface is normal. The comparison target in the wall displacement analysis unit 20 is a cross-sectional view or a three-dimensional point cloud of the tunnel. When the comparison target is a cross-sectional view, the wall model becomes a two-dimensional wall model, and when the wall model is a three-dimensional point cloud, the wall model becomes a three-dimensional wall model. Whether the wall model is a cross-sectional view that is a two-dimensional wall model or a three-dimensional wall model based on a comparison three-dimensional point cloud is set in advance in the external force judgment system 1A by a user (such as a tunnel manager).

[0026] The wall surface extraction unit 21 receives a three-dimensional point cloud of an analysis target from the three-dimensional point cloud receiving unit 40. In addition, the wall surface extraction unit 21 determines whether the wall surface model set by the user is a two-dimensional wall surface model or a three-dimensional wall surface model. When the comparison target is a three-dimensional point cloud, the wall surface extraction unit 21 receives the three-dimensional point cloud of the comparison target from the three-dimensional point cloud receiving unit 40.

[0027] In both cases where the comparison target is a three-dimensional point cloud or a cross-sectional view, the wall surface extraction unit 21 extracts a three-dimensional point cloud of the wall surface from the analysis three-dimensional point cloud. Hereinafter, the three-dimensional point cloud of the wall surface to be analyzed may be referred to as an analysis wall surface three-dimensional point cloud. The analysis wall surface three-dimensional point cloud is a point cloud obtained by extracting the three-dimensional point cloud of the wall surface from the analysis three-dimensional point cloud.

[0028] In addition, when the comparison target is a three-dimensional point cloud, the wall surface extraction unit 21 extracts a three-dimensional point cloud of the wall surface from the comparison three-dimensional point cloud. Hereinafter, the three-dimensional point cloud of the wall surface to be compared may be referred to as a comparison wall surface three-dimensional point cloud. The comparison wall surface three-dimensional point cloud is a point cloud obtained by extracting the three-dimensional point cloud of the wall surface from the comparison three-dimensional point cloud.

[0029] When the comparison object is a cross section, the wall surface extraction unit 21 transmits an analysis wall surface three-dimensional point cloud to the cross section reading unit 22. On the other hand, when the comparison object is a three-dimensional point cloud, the wall surface extraction unit 21 transmits the analysis wall surface three-dimensional point cloud and the comparison wall surface three-dimensional point cloud to the comparison wall surface reading unit 25.

[0030] When the comparison wall surface three-dimensional point cloud has already been calculated, the wall surface extraction unit 21 may receive the calculated comparison wall surface three-dimensional point cloud from an external device such as a storage device for analysis wall surface three-dimensional point cloud.

[0031] When the wall model is set to a cross section (two-dimensional wall model), the wall extraction unit 21 calculates a two-dimensional wall model from the analysis wall three-dimensional point cloud. The process of calculating the two-dimensional wall model from the analysis wall three-dimensional point cloud may be executed by an external device such as a two-dimensional wall model calculation device. The wall extraction unit 21 may also use a design drawing of a tunnel as the two-dimensional wall model. In this case, the wall extraction unit 21 reads the design drawing from an external device such as a design drawing storage device. When the comparison target is a cross section, the wall extraction unit 21 transmits the two-dimensional wall model to the cross section reading unit 22.

[0032] The cross-sectional view reading unit 22 reads the analytical wall surface three-dimensional point cloud and the two-dimensional wall surface model of the cross section of the tunnel from the wall surface extraction unit 21. The cross-sectional view reading unit 22 may read the calculated two-dimensional wall surface model from an external device such as a storage device for the two-dimensional wall surface model. The cross-sectional view reading unit 22 transmits the analytical wall surface three-dimensional point cloud and the two-dimensional wall surface model to the central axis calculation unit 23.

[0033] The central axis calculation unit 23 calculates the central axis of the tunnel cross section from the analysis wall surface three-dimensional point cloud. The central axis of the tunnel cross section is an axis parallel to the extension direction of the tunnel. The central axis of the tunnel cross section is an axis connecting the center positions of the cross-sectional shape when the tunnel is cut by a plane perpendicular to the extension direction. The center position of the cross-sectional shape of the tunnel is, for example, the position of the tunnel center on the spring line. The central axis calculation unit 23 transmits the analysis wall surface three-dimensional point cloud and the calculated central axis to the cross-section difference calculation unit 24.

[0034] The cross-sectional difference calculation unit 24 calculates the difference between the analysis wall surface three-dimensional point cloud and the two-dimensional wall surface model (wall surface displacement three-dimensional analysis result) while sliding the two-dimensional wall surface model along the central axis. The wall surface displacement three-dimensional analysis result includes information on the position (coordinates) in the tunnel where the difference between the analysis wall surface three-dimensional point cloud and the two-dimensional wall surface model was detected. The cross-sectional difference calculation unit 24 transmits the calculated wall surface displacement three-dimensional analysis result to the three-dimensional analysis result superimposition unit 31 of the external force determination unit 30.

[0035] The comparison wall surface reading unit 25 reads the analysis wall surface three-dimensional point cloud and the comparison wall surface three-dimensional point cloud from the wall surface extraction unit 21. The comparison wall surface reading unit 25 transmits the analysis wall surface three-dimensional point cloud and the comparison wall surface three-dimensional point cloud to the 3D wall surface model calculation unit .

[0036] The three-dimensional wall model calculation unit 26 calculates a three-dimensional wall model based on the comparison wall three-dimensional point cloud. The three-dimensional wall model calculation unit 26 transmits the analysis wall three-dimensional point cloud and the three-dimensional wall model to the temporal difference calculation unit 27.

[0037] The time difference calculation unit 27 calculates the wall displacement three-dimensional analysis result, which is the difference between the analysis wall surface three-dimensional point cloud and the three-dimensional wall surface model. The difference between the analysis wall surface three-dimensional point cloud and the three-dimensional wall surface model corresponds to the difference between the past shape and the current shape of the inner wall surface of the tunnel. In other words, the difference between the analysis wall surface three-dimensional point cloud and the three-dimensional wall surface model corresponds to the amount of displacement on the inner wall surface of the tunnel. The wall displacement three-dimensional analysis result is the result of a three-dimensional analysis of the wall displacement on the inner wall surface of the tunnel. The time difference calculation unit 27 transmits the calculated wall displacement three-dimensional analysis result to the three-dimensional analysis result superimposition unit 31 of the external force determination unit 30.

[0038] In this way, in the external force determination system 1A, when the wall model is a cross section, the wall displacement is analyzed by the wall extraction unit 21, the cross section reading unit 22, the central axis calculation unit 23, and the cross section difference calculation unit 24. Also, in the external force determination system 1A, when the wall model is a three-dimensional point cloud, the wall displacement is analyzed by the wall extraction unit 21, the comparison wall reading unit 25, the three-dimensional wall model calculation unit 26, and the temporal difference calculation unit 27.

[0039] The 3D analysis result superimposition unit 31 receives the 3D ground swelling analysis results sent from the road surface difference calculation unit 14. The 3D analysis result superimposition unit 31 also receives the 3D wall displacement analysis results sent from the cross-section difference calculation unit 24 or the time-dependent difference calculation unit 27. The 3D analysis result superimposition unit 31 superimposes the 3D wall displacement analysis results on the 3D ground swelling analysis results, and transmits the superimposition results to the displacement location extraction unit 32 and the supplementary information reading unit 34 as the 3D all-around analysis results.

[0040] The displacement location extraction unit 32 extracts locations (external force displacement locations) in the tunnel where displacement due to external force is suspected based on the 3D full circumference analysis result. That is, the displacement location extraction unit 32 extracts displacement locations (deformation locations) of the tunnel wall and displacement locations of the road surface. Examples of external force displacement locations extracted by the displacement location extraction unit 32 include cracks, bulges toward the outer surface, and bulges toward the inner surface. The displacement location extraction unit 32 extracts, as the external force displacement locations, displacement locations whose magnitude of displacement is greater than a reference value among the displacement locations included in the 3D full circumference analysis result. The displacement location extraction unit 32 may also integrate the displacement over the tunnel cross section at a certain width, for example, 50 cm, in the axial direction of the tunnel, and extract the cross section where the integrated value is greater than the reference value as the external force displacement location. The displacement location extraction unit 32 transmits the external force displacement locations to the external force direction calculation unit 33.

[0041] The external force direction calculation unit 33 calculates the external force direction, which is the direction of the external force that the tunnel receives, based on the correlation between the external force-induced displacement locations. For example, when two external force-induced displacement locations are located opposite each other across the central axis of the tunnel, the external force direction calculation unit 33 calculates the opposing direction as the external force direction. For example, when a crack location on the upper surface of the tunnel wall portion and a crack location on the road surface portion are located opposite each other, the external force direction calculation unit 33 calculates the direction perpendicular to the crack location from the outside of the tunnel as the external force direction.

[0042] Furthermore, the external force direction calculation unit 33 may calculate the outer side as the external force direction when the two externally-forced displacement points are bulges toward the outer surface side, and may calculate the inner surface as the external force direction when the two externally-forced displacement points are bulges toward the inner surface side. Furthermore, when the external force direction calculation unit 33 extracts externally-forced displacement points by integrating the displacements over the tunnel cross section at a certain width in the axial direction of the tunnel, it may calculate the direction of the external force at the cross section showing the maximum displacement in the axial direction as the external force direction.

[0043] In addition, when swelling occurs on the road surface inside the tunnel, the wall of the side of the tunnel is pushed toward the inner side of the tunnel, and the top of the tunnel is displaced toward the outer side. In this case, the displacement location extraction unit 32 extracts the top position of the tunnel as the external force displacement location, and the external force direction calculation unit 33 calculates the outer side at the top position of the tunnel as the external force direction.

[0044] Furthermore, the external force direction calculation unit 33 may calculate the direction of the external force occurring globally or locally based on the deformation directions of the two externally displaced portions. For example, when the bulging direction of the upper surface position of the tunnel wall portion and the bulging direction of the road surface portion are opposite directions, the external force direction calculation unit 33 calculates the bulging direction of the upper surface position and the bulging direction of the road surface portion as the external force direction.

[0045] Furthermore, the external force direction calculation unit 33 may calculate the external force direction based on the location of the external force-induced displacement and information on the topography and geology of the location where the tunnel is located (hereinafter referred to as topography and geological information). For example, if the location of the external force-induced displacement is located in a location where the ground is loose, the external force direction calculation unit 33 calculates the direction from the location of the external force-induced displacement toward the location where the ground is loose as the external force direction. The external force direction calculation unit 33 transmits the calculated external force direction to the external force analysis unit 35.

[0046] The deformation development map reading unit 341 judges whether or not a deformation development map corresponding to the 3D full circumference analysis result is known. In other words, the deformation development map reading unit 341 judges whether or not a deformation development map corresponding to the external force-induced displacement location is stored in an external device such as a database. The deformation development map is a map in which the deformation information recorded during the tunnel inspection is expanded, and includes information on the position of the deformation (cracks, etc.), information on the size of the deformation, etc. When the deformation is a crack, the size of the deformation is the size of the crack in the width direction and the size of the crack in the extension direction.

[0047] When a deformation development diagram corresponding to the 3D full circumference analysis result is known, the deformation development diagram reading unit 341 reads the deformation development diagram from a database etc. The deformation development diagram reading unit 341 transmits the deformation development diagram to the external force analysis unit 35.

[0048] In addition, the topography and geological information reading unit 342 judges whether the topography and geological information corresponding to the 3D full circumference analysis result is known or not. In other words, the topography and geological information reading unit 342 judges whether the topography and geological information corresponding to the external force displacement location is stored in an external device such as a database or not.

[0049] The topographical and geological information includes at least one of information on the strata of the natural ground in which the tunnel is formed, information on the location of faults in the natural ground, information on the landslide history of the natural ground, information on the geology of the natural ground, information on the construction method of the tunnel, and information on the cavity behind the tunnel lining.

[0050] When the topography and geological information corresponding to the 3D full circumference analysis result is known, the topography and geological information reading unit 342 reads the topography and geological information from a database etc. The topography and geological information reading unit 342 transmits the topography and geological information to the external force analysis unit 35.

[0051] The external force analysis unit 35 performs an external force determination and an analysis of the factors that caused the external force based on the information received from the external force direction calculation unit 33 and the supplementary information reading unit 34. The external force analysis unit 35 performs an external force determination based on the external force direction. The external force determination is a determination of whether or not the tunnel is receiving an external force that displaces the tunnel. The analysis of the factors that caused the external force to displace the tunnel is an analysis of the factors that caused the external force to occur.

[0052] In addition, when the external force analysis unit 35 receives a deformation development diagram from the deformation development diagram reading unit 341, it performs an external force determination and an analysis of the causes of the external force based on the deformation development diagram and the external force direction.

[0053] Furthermore, when the external force analysis unit 35 receives the topography and geological information from the topography and geological information reading unit 342, it performs an external force determination and an analysis of the cause of the external force based on the topography and geological information and the external force direction.

[0054] In addition, when the external force analysis unit 35 receives a deformation development map from the deformation development map reading unit 341 and receives topography and geological information from the topography and geological information reading unit 342, it performs an external force judgment based on the deformation development map, the topography and geological information, and the external force direction.

[0055] The result of the external force determination includes the result of the determination of the presence or absence of an external force and the result of the analysis of the cause of the external force. The result of the determination of the presence or absence of an external force includes information such as the position where the external force is occurring and the direction of the external force.

[0056] Here, a specific example of an external force occurrence factor will be described with reference to Figs. 2 to 5. Fig. 2 is a diagram showing an example of a deformation development diagram. Fig. 3 is a diagram showing an example of a contour diagram used by the external force determination system according to the first embodiment. The diagram on the upper side of Fig. 3 is a contour diagram 96 showing the state of deformation of the tunnel wall (arch section and side wall section) relative to the design value (reference value), the diagram on the lower side of Fig. 3 is a contour diagram 97 of the road surface section, and the diagram on the left side of Fig. 3 is a contour diagram 95 of the wall surface section. The wall surface section in the contour diagram 96 corresponds to the comparison result with the design cross section diagram, and the road surface section corresponds to the comparison result with the reference surface obtained from the point cloud, not the comparison result with the design drawing. In the contour diagrams 95 to 97 shown in Fig. 3, the displacement location is indicated by color coding according to the amount of displacement, color shading, etc.

[0057] As shown in Figure 2, the deformation development diagram 101 shows the position, shape, size, etc. of the cracks. From only this deformation development diagram 101 in Figure 2, it is not possible to know whether the cracks are caused by external forces or shrinkage, and it is also not possible to know the degree of deformation.

[0058] In the case of contour maps 95 to 97 shown in FIG. 3, it is easier to see the extent of the external force than in the deformation development map 101, but it is difficult to grasp the direction of the external force.

[0059] FIG. 4 is a diagram showing an example of a three-dimensional contour diagram generated by the external force determination system according to the first embodiment. The three-dimensional contour diagram 102 shown in FIG. 4 is an example of tunnel deformation information 57 described later. In the three-dimensional contour diagram 102, the three-dimensional ground swelling analysis result and the displacement at each position of the wall surface and road surface of the tunnel are superimposed. In other words, in the three-dimensional contour diagram 102, the analysis result of the ground swelling analysis and the analysis result of the wall displacement analysis are visualized in three dimensions. In the three-dimensional contour diagram 102, the displacement of the road surface and wall surface of the tunnel is shown by color coding according to the amount of displacement. In the three-dimensional contour diagram 102 shown in FIG. 4, external force directions Ef1 to Ef5 are shown.

[0060] The external force determination system 1A generates a three-dimensional contour map 102, which makes it easier to understand the directionality and extent of the deformation. In addition, the external force determination system 1A uses topographical and geological information, which makes it easier to understand the relationship between spring water, geology, and the deformation location.

[0061] Fig. 5 is a diagram showing an example of topography and geological information used by the external force determination system according to the embodiment 1. The topography and geological information 103 in Fig. 5 includes information on spring water during tunnel construction, geological information, information on the water drainage pilot tunnel 85, and the like.

[0062] The external force determination system 1A performs an external force determination and an analysis of the cause of the external force based on the three-dimensional contour diagram 102 shown in FIG. 4 and the topography and geological information 103 shown in FIG. 5. For example, the external force determination system 1A analyzes that the cause of the external force is earth pressure (expansive or composition earth pressure) based on the three-dimensional contour diagram 102 shown in FIG. 4 and the topography and geological information 103 shown in FIG. 5. The external force determination system 1A also analyzes that water is still springing from the shoulder of the tunnel, and this shoulder is deforming inward, but the target position of the invert is also deforming. The external force determination system 1A further analyzes that immediately after the construction of the lining concrete, water pressure pushing inward acts on the waterproof sheet, and deformation occurs during the weak material age of the concrete. The external force determination system 1A also analyzes that immediately after the deformation, spring water occurs in the joint due to the damage of the waterproof sheet in the joint, and the deformation converges due to the drainage effect of the spring water. The external force determination system 1A then analyzes that the inward deformation of the mating portion between the pavement surface and the spring water point has progressed.The external force determination system 1A also analyzes that the cause of the progression of this deformation is the action of composition earth pressure or expansive earth pressure caused by water circulating in the ground below the roadbed.

[0063] The external force analysis unit 35 outputs the external force determination result to an external device such as a display device, etc. In response to this, the external force analysis unit 35 causes the external force determination result to be displayed on the display device or the like.

[0064] The ground swelling analysis unit 10 may calculate the ground swelling three-dimensional analysis result using a three-dimensional point cloud measured in the past, like the wall displacement analysis unit 20. In this case, the road surface difference calculation unit 14 calculates the ground swelling three-dimensional analysis result based on the analysis three-dimensional point cloud and the comparison three-dimensional point cloud.

[0065] Next, a procedure of an external force determination process by the external force determination system 1A will be described below. Fig. 6 is a flowchart showing the procedure of the overall process executed by the external force determination system according to the first embodiment.

[0066] The three-dimensional point cloud receiving unit 40 of the external force determination system 1A reads in the three-dimensional point cloud of the tunnel from an external device (step S10). The ground swelling analysis unit 10 of the external force determination system 1A performs a ground swelling analysis of the road surface on which the tunnel is installed based on the three-dimensional point cloud (step S20). In addition, the wall displacement analysis unit 20 of the external force determination system 1A performs a wall displacement analysis of the tunnel based on the three-dimensional point cloud (step S30). Note that the external force determination system 1A may perform the process of step S20 and the process of step S30 in any order.

[0067] The external force determination unit 30 of the external force determination system 1A determines the external force in the tunnel based on the analysis result of the swelling of the road surface (the swelling three-dimensional analysis result) and the analysis result of the displacement of the inner wall surface of the tunnel (the wall displacement three-dimensional analysis result). The external force determination unit 30 executes an external force determination for the tunnel (step S40). Specifically, the external force determination unit 30 executes an external force determination for the tunnel and an analysis of the causes of the external force.

[0068] In addition, the ground swelling analysis unit 10 may compare a tunnel construction drawing, which describes the transverse gradient and longitudinal gradient of the road surface for each joint, with the three-dimensional road surface point cloud, and analyze the ground swelling based on the comparison result.

[0069] Next, the processing procedures of each of the processes of the ground swelling analysis, the wall displacement analysis, and the external force determination will be described. Fig. 7 is a flowchart showing the processing procedures of the ground swelling analysis executed by the external force determination system according to the first embodiment.

[0070] The road surface extraction unit 11 receives the analysis three-dimensional point cloud from the three-dimensional point cloud receiving unit 40. The road surface extraction unit 11 extracts a road surface three-dimensional point cloud, which is a three-dimensional point cloud of the road surface portion, from the analysis three-dimensional point cloud (step S21). The road surface extraction unit 11 transmits the road surface three-dimensional point cloud to the road surface centerline calculation unit 12.

[0071] The road surface center line calculation unit 12 calculates a road surface center line, which is the center line of the road surface, based on the road surface three-dimensional point cloud (step S22). The road surface center line calculation unit 12 transmits the road surface three-dimensional point cloud and the road surface center line to the road surface model calculation unit 13.

[0072] The road surface model calculation unit 13 calculates a road surface model, which is a model of a normal road surface, based on the road surface center line and the road surface three-dimensional point cloud (step S23). The road surface model calculation unit 13 transmits the road surface three-dimensional point cloud and the road surface model to the road surface difference calculation unit 14.

[0073] The road surface difference calculation unit 14 calculates the three-dimensional road swelling analysis result, which is the difference between the three-dimensional road surface point cloud and the road surface model (step S24). The road surface difference calculation unit 14 transmits the three-dimensional road swelling analysis result to the three-dimensional analysis result superimposition unit 31 of the external force determination unit 30.

[0074] 8 is a flowchart showing a procedure of a wall displacement analysis process executed by the external force determination system according to the embodiment 1. The wall surface extraction unit 21 extracts an analysis wall surface three-dimensional point cloud, which is a three-dimensional point cloud of a wall surface portion, from the analysis three-dimensional point cloud (step S31).

[0075] The wall surface extraction unit 21 determines whether the wall surface model to be compared is a cross-sectional view or a three-dimensional point cloud (step S32). When the wall surface model is a cross-sectional view, the wall surface extraction unit 21 calculates a two-dimensional wall surface model from the analysis wall surface three-dimensional point cloud. On the other hand, when the wall surface model is a three-dimensional point cloud, the wall surface extraction unit 21 extracts a comparison wall surface three-dimensional point cloud from the comparison target three-dimensional point cloud.

[0076] When the wall model is to be a cross-sectional view (step S32, cross-sectional view), the cross-sectional view reading unit 22 reads the analysis wall three-dimensional point cloud and the two-dimensional wall model which is a cross-sectional view to be compared from the wall extraction unit 21 (step S33). The cross-sectional view reading unit 22 transmits the analysis wall three-dimensional point cloud and the two-dimensional wall model to the central axis calculation unit 23.

[0077] The central axis calculation unit 23 calculates the central axis of the tunnel cross section based on the analysis wall surface three-dimensional point cloud (step S34). The central axis calculation unit 23 transmits the analysis wall surface three-dimensional point cloud and the calculated central axis to the cross-section difference calculation unit 24.

[0078] The cross-sectional difference calculation unit 24 calculates the difference (wall displacement 3D analysis result) between the analysis wall 3D point cloud and the cross-sectional view (2D wall model) while sliding the cross-sectional view, which is the 2D wall model, along the central axis (step S35). The cross-sectional difference calculation unit 24 transmits the calculated wall displacement 3D analysis result to the 3D analysis result superimposition unit 31 of the external force determination unit 30.

[0079] When the wall surface model is a three-dimensional point cloud (step S32, three-dimensional point cloud), the comparison wall surface reading unit 25 reads the analysis wall surface three-dimensional point cloud and the comparison wall surface three-dimensional point cloud from the wall surface extraction unit 21 (step S36). The comparison wall surface reading unit 25 transmits the comparison wall surface three-dimensional point cloud and the analysis wall surface three-dimensional point cloud to the three-dimensional wall surface model calculation unit 26.

[0080] The three-dimensional wall surface model calculation unit 26 calculates a three-dimensional wall surface model based on the comparative wall surface three-dimensional point cloud (step S37). The three-dimensional wall surface model calculation unit 26 transmits the analytical wall surface three-dimensional point cloud and the three-dimensional wall surface model to the temporal difference calculation unit 27.

[0081] The temporal difference calculation unit 27 calculates the difference between the analysis wall surface three-dimensional point group and the three-dimensional wall surface model (the wall surface displacement three-dimensional analysis result) (step S38). The temporal difference calculation unit 27 transmits the calculated wall surface displacement three-dimensional analysis result to the three-dimensional analysis result superimposition unit 31 of the external force determination unit 30.

[0082] 9 is a flowchart showing a processing procedure of external force determination executed by the external force determination system according to the embodiment 1. The three-dimensional analysis result superimposition unit 31 receives the three-dimensional road swelling analysis result sent from the road surface difference calculation unit 14. The three-dimensional analysis result superimposition unit 31 also receives the three-dimensional wall displacement analysis result sent from the cross-section difference calculation unit 24 or the time-dependent difference calculation unit 27.

[0083] The 3D analysis result superimposition unit 31 superimposes the 3D analysis result (step S41). Specifically, the 3D analysis result superimposition unit 31 superimposes the wall displacement 3D analysis result on the floor swelling 3D analysis result. The 3D analysis result superimposition unit 31 transmits the superimposition result to the displacement location extraction unit 32 as the 3D 3D circumferential analysis result.

[0084] The displacement location extraction unit 32 extracts external force-induced displacement locations (locations suspected of being displaced by an external force) of the wall surface and road surface in the tunnel based on the 3D full circumference analysis result (step S42). The displacement location extraction unit 32 transmits the external force-induced displacement locations to the external force direction calculation unit 33.

[0085] The external force direction calculation unit 33 calculates the external force direction from the correlation between the external force-induced displacement points (step S43). The external force direction calculation unit 33 transmits the calculated external force direction to the external force analysis unit .

[0086] The deformation development plan reading unit 341 judges whether or not there is a deformation development plan corresponding to the external force displacement location (step S44). If there is a deformation development plan corresponding to the external force displacement location (step S44, Yes), the deformation development plan reading unit 341 reads the deformation development plan from a database or the like (step S45). The deformation development plan reading unit 341 transmits the deformation development plan to the external force analysis unit 35.

[0087] On the other hand, if there is no deformation development diagram (step S44, No), the deformation development diagram reading unit 341 does not read the deformation development diagram from the database etc. In other words, if there is no deformation development diagram, the deformation development diagram reading unit 341 does not execute the process of step S45.

[0088] The topography and geological information reading unit 342 also determines whether there is topography and geological information corresponding to the external force displacement location (step S46). If there is topography and geological information corresponding to the external force displacement location (step S46, Yes), the topography and geological information reading unit 342 reads the topography and geological information from a database or the like (step S47). The topography and geological information reading unit 342 transmits the topography and geological information to the external force analysis unit 35.

[0089] On the other hand, if there is no topography and geological information (step S46, No), the topography and geological information reading unit 342 does not read the topography and geological information from a database, etc. In other words, if there is no topography and geological information, the topography and geological information reading unit 342 does not execute the process of step S47.

[0090] The external force analysis unit 35 executes an external force determination based on the information received from the external force direction calculation unit 33 and the supplementary information reading unit 34 (step S48). The external force analysis unit 35 performs an external force determination based on, for example, a deformation development map, topographical and geological information, and an external force direction. The external force analysis unit 35 outputs the external force determination result to an external device such as a display device.

[0091] Here, a description will be given of the ground swelling analysis processing executed by the ground swelling analysis unit 10 and the wall displacement analysis processing (contour analysis) executed by the wall displacement analysis unit 20. Fig. 10 is a diagram for explaining the calculation processing of the road surface model in the ground swelling analysis processing executed by the external force determination system according to the first embodiment.

[0092] The swelling analysis unit 10 of the external force determination system 1A calculates a road surface model using, for example, a planar approximation method for the road surface. In this case, the swelling analysis unit 10 calculates a road surface center line C1 of the road surface portion 75. The road surface center line C1 is the center line in the width direction of the road surface portion 75. If an emergency parking lane 79 is included in the road surface portion 75, the swelling analysis unit 10 calculates the road surface center line C1 while ignoring the emergency parking lane 79. The swelling analysis unit 10 fits a figure (a broken line 76 consisting of line segments on both the left and right sides) to the cross section of the road surface portion 75. The swelling analysis unit 10 generates an approximated plane of the road surface by sweeping the broken line 76 with an average gradient in the axial direction of the road surface center line C1.

[0093] In Fig. 10, the sweep direction is indicated by direction d1. Fig. 10 also shows a case where the swelling analysis unit 10 generates an approximate plane 78A of the area 77A and an approximate plane 78B of the area 77B. The areas 77A and 77B are areas that face each other across the road surface center line C1 when the road surface portion 75 is viewed from above. Therefore, the approximate planes 78A and 78B are approximate planes that face each other across the road surface center line C1 when the road surface portion 75 is viewed from above.

[0094] By generating the approximate planes 78A and 78B as shown in FIG. 10 by the swelling analysis unit 10, the change in the local cant (the difference in height between the outer part and the inner part of the curved part of the track or road) in the road surface portion 75 remains and appears as a height difference. As a result, the road surface center line C1 overlaps with the node of the broken line 76. In addition, the approximate planes 78A and 78B intersect along the road surface center line C1, and the gradient in the axial direction of the tunnel of the approximate planes 78A and 78B becomes the same. The approximate plane calculated for the entire road surface portion 75 in the tunnel is the road surface model. The road surface portion 75 generally has a cant, and the difference in the height of the cant often differs depending on the lane. For this reason, in a two-lane tunnel, the road surface center line C1 overlaps with the node of the broken line 76. In addition, depending on the number of lanes of the road surface, the broken line 76 may have no nodes or may have two or more nodes.

[0095] The ground swelling analysis unit 10 may generate the approximate planes 78A and 78B based on a pavement construction drawing. The ground swelling analysis unit 10 may also generate the approximate planes 78A and 78B by extracting gradient change points based on a three-dimensional point cloud of the tunnel.

[0096] 11 is a diagram for explaining the ground swelling analysis process executed by the external force determination system according to the first embodiment and an example of the processing result. The ground swelling analysis unit 10 acquires a three-dimensional point cloud 61 of a tunnel (st1). The ground swelling analysis unit 10 extracts a road surface portion 60 from the three-dimensional point cloud 61 based on the reflection intensity of the three-dimensional point cloud 61 or the like (st2). The ground swelling analysis unit 10 may extract points arranged in a plane at a low position as the road surface portion 60 by a method such as Hough transformation or RANSAC (RANdom SAmple Consensus).

[0097] The ground swelling analysis unit 10 calculates a road surface model based on the road surface portion 60. The ground swelling analysis unit 10 calculates an elevation difference 63, which is the difference between the height of the approximate plane of the road surface portion 60 in the road surface model and the height of the road surface portion 60 in the three-dimensional point cloud 61 (st3). The ground swelling analysis unit 10 calculates the elevation difference 63 of the road surface portion 60 for each area in the tunnel, thereby calculating a ground swelling three-dimensional analysis result 64, which is the difference between the road surface model and the three-dimensional point cloud 61 (st4).

[0098] 11 shows the results of the 3D analysis of swelling 64 when the road surface 60 is viewed from above. In the 3D analysis of swelling 64, the displaced areas are shown by color coding or color shading according to the amount of displacement from the cross-sectional view of the comparison target.

[0099] 12 is a diagram for explaining the wall displacement analysis process executed by the external force determination system according to the first embodiment. The wall displacement analysis unit 20 of the external force determination system 1A compares the three-dimensional point cloud 51 of the current tunnel with the three-dimensional point cloud 52 of the past tunnel (st11). The three-dimensional point cloud 51 of the current tunnel is the three-dimensional point cloud obtained in the current inspection, and the three-dimensional point cloud 52 of the past tunnel is the three-dimensional point cloud obtained in the inspection before the previous one. In other words, the three-dimensional point cloud 51 of the current tunnel is the analysis three-dimensional point cloud, and the three-dimensional point cloud 52 of the past tunnel is the comparison three-dimensional point cloud.

[0100] The wall displacement analysis unit 20 extracts the difference between the three-dimensional point cloud 51 of the current tunnel and the three-dimensional point cloud 52 of the past tunnel as the displacements D1 and D2 of the wall portion (st12). In FIG. 12, the wall portion obtained from the three-dimensional point cloud 52 of the past tunnel is illustrated as the wall portion 3, and the wall portion obtained from the three-dimensional point cloud 51 of the current tunnel is illustrated as the wall portion 4. The displacements D1 and D2 of the wall portion correspond to the difference between the wall portion 3 and the wall portion 4 on the cut surface when the tunnel is cut by a plane perpendicular to the central axis of the tunnel. The displacements D1 and D2 of the wall portion are the difference in the direction of the central axis of the tunnel. The displacements D1 and D2 of the wall portion may be the difference from a point on the wall portion 4 to the closest point to the wall portion 3.

[0101] The wall displacement analysis unit 20 extracts the displacements D1 and D2 of the wall at various cross-sectional positions in the tunnel. As a result, the wall displacement analysis unit 20 generates a contour diagram F1 showing the displacements D1 and D2 at each position of the wall, a three-dimensional wall image G1 showing the displacements D1 and D2 at each position of the wall, and the like (st13). The three-dimensional wall image G1 here is the above-mentioned three-dimensional wall displacement analysis result. In the three-dimensional wall image G1, the displacement locations are shown by color coding or color shading according to the amount of displacement of the tunnel wall.

[0102] The wall displacement analysis unit 20 may generate a contour diagram F1, a wall surface three-dimensional image G1, etc. by comparing the three-dimensional point cloud 51 of the current tunnel with the design drawing of the tunnel. That is, the wall displacement analysis unit 20 may compare the design drawing of the tunnel. The design drawing of the tunnel corresponds to the cross-sectional view of the tunnel.

[0103] FIG. 13 is a diagram showing an example of a design drawing of a tunnel used when the external force determination system according to the first embodiment executes a wall displacement analysis process. The design drawing 53 is a design drawing showing a cross section perpendicular to the central axis of the tunnel. The design drawing 53 is an ideal shape of the tunnel. The wall displacement analysis unit 20 extracts the displacements D1 and D2 of the wall surface at various cross-sectional positions in the tunnel by comparing the three-dimensional point cloud 51 of the current tunnel with the design drawing 53 of the tunnel. Then, the wall displacement analysis unit 20 generates a contour diagram F1, a three-dimensional wall image G1, and the like based on the displacements D1 and D2.

[0104] The wall displacement analysis unit 20 may also generate a contour diagram F1, a wall surface three-dimensional image G1, etc. by comparing the three-dimensional point cloud 51 of the current tunnel with a model cross section of the tunnel. That is, the wall displacement analysis unit 20 may use the model cross section of the tunnel as a comparison target. The model cross section of the tunnel corresponds to the cross-sectional view of the tunnel.

[0105] FIG. 14 is a diagram showing an example of a model cross section of a tunnel used when the external force determination system according to the first embodiment executes a wall displacement analysis process. The wall displacement analysis unit 20 calculates a model cross section 54 from a three-dimensional point cloud 51 of the current tunnel. For example, the wall displacement analysis unit 20 projects the three-dimensional point cloud 51 of the tunnel onto a plane perpendicular to the central axis of the tunnel, and calculates a figure in which a line segment or a circular arc is fitted to the contour of the projection point as the model cross section 54. The wall displacement analysis unit 20 extracts displacements D1 and D2 of the wall part at various cross-sectional positions in the tunnel by comparing the three-dimensional point cloud 51 of the current tunnel with the model cross section 54. Then, the wall displacement analysis unit 20 generates a contour diagram F1, a wall three-dimensional image G1, and the like based on the displacements D1 and D2.

[0106] The external force assessment unit 30 of the external force assessment system 1A generates tunnel deformation information indicating the deformation of the tunnel by superimposing the three-dimensional ground swelling analysis result 64 calculated by the ground swelling analysis unit 10 and the three-dimensional wall displacement analysis result (three-dimensional wall image G1) calculated by the wall displacement analysis unit 20.

[0107] 15 is a diagram showing an example of tunnel deformation information generated by the external force determination system according to the first embodiment. The tunnel deformation information 57 is information in which the three-dimensional ground swelling analysis result 64 and the three-dimensional wall surface image G1 are superimposed. In other words, the tunnel deformation information 57 is data in which the analysis results of the ground swelling analysis and the analysis results of the wall surface displacement analysis are visualized in three dimensions. In the tunnel deformation information 57, the displacement locations are shown in three dimensions using colors and shades of color according to the amount of displacement of the road surface and wall surface of the tunnel.

[0108] In conventional on-site tunnel inspections, tunnel defects are detected and their location and size are recorded. Specifically, invisible lifts are detected by tapping tests, and visible defects such as cracks are detected by close visual inspection. The location and size of the detected defects are then recorded as a development diagram.

[0109] In conventional tunnel inspections, a diagnosis of the tunnel's integrity is made after an on-site inspection, and an important element in this diagnosis is the determination of whether the tunnel is being subjected to an external force that displaces it. This determination is made by comparing the results of the current on-site inspection with those of previous on-site inspections. For example, if the size of a crack is getting larger, there is a possibility that the area where the crack is located is being subjected to an external force that is displacing the tunnel.

[0110] Previously, determining the cause of external forces by comparing crack sizes was inaccurate for the following two reasons. - The width of the cracks will change depending on the season (temperature, humidity, etc.) at the time of inspection. -Manual measurements have a large margin of error.

[0111] On the other hand, the external force determination system 1A of the first embodiment performs analysis based on not only close visual inspection but also three-dimensional point clouds. Specifically, the external force determination system 1A performs a ground swelling analysis and a wall displacement analysis using a three-dimensional point cloud. This allows the user to confirm the location of the external force-induced displacement from the analysis results of the ground swelling analysis and the wall displacement analysis.

[0112] In addition, the external force determination system 1A visualizes the analysis results in three dimensions and calculates the direction of the external force, allowing the user to perform more accurate external force determination than conventional inspections and to confirm from which direction stress is being applied to the tunnel.

[0113] Furthermore, the external force determination system 1A uses at least one of the deformation development map and the topographical and geological information to perform an external force determination, so that an accurate external force determination can be performed. Also, the external force determination system 1A analyzes the external force occurrence factors, so that an accurate external force determination with a basis can be performed.

[0114] Furthermore, the external force determination performed by the external force determination system 1A can improve the efficiency of on-site inspections using mobile image measurement technology. For example, in conventional inspections, the size of the cracks to be compared must be measured accurately, but with mobile image measurement, there is a high possibility of measurement errors in crack size or failure to extract cracks due to technical specifications and the tunnel environment. In this case, manual close visual inspection is required.

[0115] On the other hand, by using the external force determination system 1A of the first embodiment, the user can accurately diagnose whether or not the tunnel is receiving an external force that displaces the tunnel simply by checking whether or not there is a crack due to an external force at the external force displacement location. Therefore, the user does not need to accurately measure the size of the crack, and even when using a traveling image measurement technology, it is sufficient to extract the crack and measure its size, thereby achieving a significant increase in the efficiency of on-site inspection.

[0116] In this way, by having the external force determination system 1A perform the external force determination, the user can carry out appropriate repairs to the tunnel, which makes it possible to reduce the cost of maintaining and managing the tunnel. In addition, by using the external force determination system 1A, it becomes possible to improve the efficiency of on-site inspections using traveling image measurement technology, which leads to cost reductions in tunnel inspections.

[0117] In addition, the external force assessment system 1A may slice the results of the 3D ground swelling analysis and the 3D wall displacement analysis into slices of approximately 1.5 m in the axial direction of the tunnel, score the deformation in regular mesh units (approximately 50 cm), and perform an external force assessment using statistical numerical values.

[0118] In this way, the external force determination system 1A of the first embodiment extracts displacement locations where the tunnel is displaced greater than a reference value based on the 3D full circumference analysis results in which the 3D wall displacement analysis results are superimposed on the 3D ground swelling analysis results. The external force determination system 1A calculates the external force direction of the external force received by the tunnel based on the correlation between the displacement locations, and performs an external force determination as to whether or not the tunnel is receiving an external force that displaces the tunnel based on the external force direction. This allows the external force determination system 1A to accurately diagnose whether or not the tunnel is receiving an external force that displaces the tunnel.

[0119] Embodiment 2 Next, a second embodiment will be described with reference to Fig. 16 to Fig. 21. In the second embodiment, the learning device learns the external force determination result corresponding to the analysis result calculated by the floor swelling analysis unit 10 and the wall displacement analysis unit 20.

[0120] FIG. 16 is a block diagram illustrating a configuration of an external force determination system according to the second embodiment. As illustrated in FIG. Of the components in FIG. 16, those that achieve the same functions as those in the external force determination system 1A of the first embodiment shown in FIG. 1 are given the same reference numerals, and duplicated explanations will be omitted.

[0121] The external force determination system 1B is a device that analyzes the displacement of a tunnel to be determined, performs an external force determination for the tunnel, and learns the external force determination result for the analysis result. The external force determination system 1B includes a ground swelling analysis unit 10, a wall displacement analysis unit 20, an external force determination unit 30, a 3D point cloud reception unit 40, a learning device 70, a learned model storage unit 45, and an inference device 80.

[0122] The swelling analysis unit 10, the wall displacement analysis unit 20, the external force judgment unit 30, the 3D point cloud reception unit 40, the learning device 70, the learned model memory unit 45, and the inference device 80 may be connected via a network or the like, or may be realized as a single computer.

[0123] Furthermore, at least one of the learning device 70, the trained model storage unit 45, and the inference device 80 may be disposed outside the external force determination system 1B. In other words, at least one of the learning device 70, the trained model storage unit 45, and the inference device 80 does not have to be a component of the external force determination system 1B.

[0124] Furthermore, learning device 70 and inference device 80 may exist on a cloud server. Furthermore, learning device 70 and inference device 80 may be realized by different computers, or learning device 70 and inference device 80 may be realized by a single computer.

[0125] The board swelling analysis unit 10 of the second embodiment, when learning the external force judgment result, transmits the three-dimensional analysis result of board swelling to the external force judgment unit 30 and the learning device 70. In addition, the board swelling analysis unit 10, when inferring the external force judgment result, transmits the three-dimensional analysis result of board swelling to the inference device 80.

[0126] When learning the external force determination result, the wall displacement analysis unit 20 of the second embodiment transmits the wall displacement three-dimensional analysis result to the external force determination unit 30 and the learning device 70. When inferring the external force determination result, the wall displacement analysis unit 20 transmits the wall displacement three-dimensional analysis result to the inference device 80.

[0127] The external force determination unit 30 calculates an external force determination result based on the three-dimensional ground swelling analysis result and the three-dimensional wall displacement analysis result. The external force determination unit 30 transmits the external force determination result to the learning device 70. The external force determination result transmitted by the external force determination unit 30 to the learning device 70 may be a determination result of the presence or absence of an external force in the tunnel, or may be tunnel deformation information 57. The external force determination result transmitted by the external force determination unit 30 to the learning device 70 may be an analysis result of the causes of the external force.

[0128] The external force determination result may be a result of a user of the external force determination system 1B determining the external force. In this case, the external force determination result is input by the user to the learning device 70. The external force determination result in the case where the user determines the external force will be described later.

[0129] The learning device 70 receives the three-dimensional ground swelling analysis result from the ground swelling analysis unit 10, and receives the three-dimensional wall displacement analysis result from the wall displacement analysis unit 20. The learning device 70 may receive the three-dimensional ground swelling analysis result and the three-dimensional wall displacement analysis result from the external force determination unit 30. The learning device 70 also receives the external force determination result from the external force determination unit 30 or a user.

[0130] The learning device 70 generates a trained model (trained model 46 described later) by learning the external force judgment results corresponding to the three-dimensional ground swelling analysis results and the three-dimensional wall displacement analysis results. In the following description, the three-dimensional ground swelling analysis results and the three-dimensional wall displacement analysis results may be collectively referred to as the three-dimensional analysis results. In the second embodiment, the three-dimensional analysis results are tunnel analysis information described later. The trained model 46 is a model for inferring the external force judgment results corresponding to the three-dimensional analysis results (tunnel analysis information). The learning device 70 generates the trained model 46 using the three-dimensional analysis results used by the external force judgment unit 30 to judge the external force and the external force judgment results judged by the external force judgment unit 30.

[0131] The trained model storage unit 45 stores the trained model 46 generated by the learning device 70. The trained model 46 stored in the trained model storage unit 45 is read by the inference device 80 when the inference device 80 infers the external force determination result.

[0132] The inference device 80 infers the external force judgment result from the three-dimensional analysis result using the trained model 46, which infers the external force judgment result corresponding to the three-dimensional analysis result. That is, the inference device 80 infers the external force judgment result by inputting the three-dimensional analysis result to the trained model 46.

[0133] The inference device 80 transmits the inferred external force determination result to an external device such as a display device. In response, the inference device 80 causes the inferred external force determination result to be displayed on the display device or the like.

[0134] 17 is a diagram showing the configuration of a learning device included in the external force determination system according to embodiment 2. The learning device 70 has a data acquisition unit 71 and a model generation unit 72.

[0135] The data acquisition unit 71 acquires learning data. Specifically, the data acquisition unit 71 acquires tunnel analysis information 47A from the ground swelling analysis unit 10 and the wall displacement analysis unit 20, and acquires external force judgment results 48X from the external force judgment unit 30 or a user. The data acquisition unit 71 acquires the tunnel analysis information 47A by accepting the ground swelling three-dimensional analysis results sent from the ground swelling analysis unit 10 and the wall displacement three-dimensional analysis results sent from the wall displacement analysis unit 20. That is, the tunnel analysis information 47A acquired by the data acquisition unit 71 includes the ground swelling three-dimensional analysis results and the wall displacement three-dimensional analysis results.

[0136] When the learning device 70 generates the trained model 46, the external force judgment result 48X calculated by the external force judgment unit 30 is input to the data acquisition unit 71. When the learning device 70 generates the trained model 46, the tunnel analysis information 47A used when the external force judgment unit 30 calculates the external force judgment result 48X is input to the data acquisition unit 71. The external force judgment result 48X input to the data acquisition unit 71 is the correct external force judgment result for the tunnel analysis information 47A. The data acquisition unit 71 sends the acquired external force judgment result 48X and tunnel analysis information 47A to the model generation unit 72.

[0137] The model generation unit 72 learns an appropriate external force determination result 48X corresponding to the tunnel analysis information 47A, based on learning data created based on a combination of the tunnel analysis information 47A and the external force determination result 48X sent from the data acquisition unit 71. In other words, the model generation unit 72 learns the external force determination result 48X that satisfies the tunnel analysis information 47A, based on learning data created based on a combination of the tunnel analysis information 47A and the external force determination result 48X. Here, the learning data is data in which the tunnel analysis information 47A and the external force determination result 48X are associated with each other.

[0138] The model generation unit 72 can use known algorithms such as supervised learning, unsupervised learning, reinforcement learning, etc. As an example, a case where a neural network is applied to the learning algorithm used by the model generation unit 72 will be described.

[0139] The model generation unit 72 learns an appropriate external force determination result 48X corresponding to the tunnel analysis information 47A by so-called supervised learning, for example, according to a neural network model. Here, supervised learning refers to a method of providing a set of data (learning data) of input and result (label) to the learning device 70, learning the features contained in the learning data, and inferring the result from the input.

[0140] A neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer or two or more layers.

[0141] Fig. 18 is a diagram for explaining a neural network used by the learning device according to the second embodiment. For example, in the case of a three-layered neural network as shown in Fig. 18, when multiple inputs are input to the input layer (X1 to X3), the values ​​are multiplied by weights W1 (w11 to w16) and input to the intermediate layer (Y1 to Y2). The results are then further multiplied by weights W2 (w21 to w26) and output from the output layer (Z1 to Z3). This output result varies depending on the values ​​of weights W1 and W2.

[0142] 17 learns external force determination result 48X corresponding to tunnel analysis information 47A by so-called supervised learning in accordance with learning data created based on a combination of tunnel analysis information 47A corresponding to a three-dimensional point group of the tunnel and external force determination result 48X acquired by data acquisition unit 71. In other words, the neural network used by learning device 70 in Fig. 17 learns external force determination result 48X corresponding to tunnel analysis information 47A by so-called supervised learning in accordance with tunnel analysis information 47A and external force determination result 48X created based on a combination of a first input and a second input (correct answer) acquired by data acquisition unit 71.

[0143] That is, the neural network learns by inputting tunnel analysis information 47A as the first input and adjusting weights W1 and W2 so that the result output from the output layer approaches the second input (correct answer).

[0144] In this way, the neural network learns by adjusting weights W1 and W2 so that the result output from the output layer when tunnel analysis information 47A is input approaches external force determination result 48X. The neural network learns the correspondence between tunnel analysis information 47A and external force determination result 48X, thereby generating a trained model 46 that can output an appropriate external force determination result 48X when tunnel analysis information 47A is input. In this way, the learning device 70 learns trained model 46 that can output external force determination result 48X, which is the correct answer, when tunnel analysis information 47A is input.

[0145] The model generation unit 72 executes the above-mentioned learning to generate and output the trained model 46. The trained model storage unit 45 stores the trained model 46 output from the model generation unit 72.

[0146] Next, a procedure of a process in which the learning device 70 learns the trained model 46 will be described with reference to Fig. 19. Fig. 19 is a flowchart showing the procedure of a learning process executed by the learning device according to the second embodiment.

[0147] The data acquiring unit 71 acquires learning data to be used for learning (step S110). Specifically, the data acquiring unit 71 acquires the tunnel analysis information 47A and the external force determination result 48X. The data acquiring unit 71 sends the tunnel analysis information 47A and the external force determination result 48X to the model generating unit 72.

[0148] The model generating unit 72 executes a learning process using the tunnel analysis information 47A and the external force determination result 48X (step S120). Specifically, the model generating unit 72 learns the external force determination result 48X corresponding to the tunnel analysis information 47A by so-called supervised learning according to learning data created based on a combination of the tunnel analysis information 47A and the external force determination result 48X acquired by the data acquiring unit 71, and generates a learned model 46.

[0149] After generating the trained model 46, the model generation unit 72 outputs the trained model 46 to the trained model storage unit 45 (step S130). The trained model storage unit 45 stores the trained model 46 generated by the model generation unit 72.

[0150] 20 is a diagram showing the configuration of an inference device provided in the external force determination system according to embodiment 2. The inference device 80 has a data acquisition unit 81 and an inference unit 82. The data acquisition unit 81 of the inference device 80 is a first data acquisition unit, and the data acquisition unit 71 of the learning device 70 is a second data acquisition unit.

[0151] The data acquiring unit 81 acquires the tunnel analysis information 47B from the ground swelling analysis unit 10 and the wall displacement analysis unit 20. The tunnel analysis information 47B is the same information as the tunnel analysis information 47A. That is, the tunnel analysis information 47B acquired by the data acquiring unit 81 includes the three-dimensional ground swelling analysis result and the three-dimensional wall displacement analysis result.

[0152] The inference unit 82 receives the tunnel analysis information 47B sent from the data acquisition unit 81. The inference unit 82 also reads out the learned model 46 from the learned model storage unit 45. The inference unit 82 uses the learned model 46 to infer an external force determination result 48Y corresponding to the tunnel analysis information 47B. That is, the inference unit 82 inputs the tunnel analysis information 47B acquired by the data acquisition unit 81 to the learned model 46, thereby being able to output an appropriate external force determination result 48Y inferred from the tunnel analysis information 47B.

[0153] The model generation unit 72 may learn an appropriate external force determination result 48X corresponding to the tunnel analysis information 47A according to learning data created by multiple external force determination systems 1B. The model generation unit 72 may also perform learning using learning data acquired from multiple external force determination systems 1B used in the same area, or may perform learning using learning data acquired from multiple external force determination systems 1B operating independently in different areas.

[0154] In addition, an external force determination system 1B that collects learning data may be added to or removed from the targets along the way. Furthermore, the learning device 70 that has learned the appropriate external force determination result 48X corresponding to the tunnel analysis information 47A for a certain external force determination system 1B may be applied to another external force determination system 1B, and the appropriate external force determination result 48X corresponding to the tunnel analysis information 47A for the other external force determination system 1B may be re-learned and updated.

[0155] Deep learning, which learns to extract features themselves, can also be used as the learning algorithm of the model generation unit 72. The model generation unit 72 may also perform machine learning according to other known methods, such as genetic programming, functional logic programming, and support vector machines.

[0156] In addition, in the second embodiment, the case has been described in which the inference device 80 outputs an appropriate external force determination result 48Y using the trained model 46 trained by the model generation unit 72 of the external force determination system 1B, but the inference device 80 may acquire the trained model 46 from another external force determination system. In this case, the inference device 80 outputs an appropriate external force determination result 48Y based on the trained model 46 acquired from the other external force determination system.

[0157] Next, a procedure of a process in which the inference device 80 infers the external force determination result 48Y using the trained model 46 will be described with reference to Fig. 21. Fig. 21 is a flowchart showing the procedure of an inference process executed by the inference device according to the second embodiment.

[0158] The data acquisition unit 81 acquires inference data used to infer the external force judgment result 48Y (step S210). Specifically, the data acquisition unit 81 acquires the tunnel analysis information 47B. The data acquisition unit 81 sends the tunnel analysis information 47B to the inference unit 82. The inference unit 82 acquires the tunnel analysis information 47B from the data acquisition unit 81, and acquires the learned model 46 from the learned model storage unit 45.

[0159] The inference unit 82 inputs the tunnel analysis information 47B to the trained model 46 (step S220) and obtains an appropriate external force determination result 48Y.

[0160] The inference unit 82 outputs data inferred using the trained model 46 and the tunnel analysis information 47B (step S230). Specifically, the inference unit 82 outputs the appropriate external force determination result 48Y obtained by the trained model 46 to a display device or the like. As a result, the inference unit 82 causes the external force determination result 48Y to be displayed on the display device or the like (step S240).

[0161] The external force determination system 1B can accurately inform the user whether or not the deformation of the tunnel is caused by an external force by displaying the external force determination result 48Y on the display device. This allows the user to consider how to deal with the tunnel by referring to the external force determination result 48Y corresponding to the tunnel analysis information 47B.

[0162] The tunnel analysis information 47A may include at least one of a deformation development map and topography and geological information. The learning device 70 uses the 3D analysis result and at least one of the deformation development map and topography and geological information as the tunnel analysis information 47A. In this case, the data acquisition unit 71 of the learning device 70 acquires the 3D ground swelling analysis result, the 3D wall displacement analysis result, at least one of the deformation development map and topography and geological information, and the external force judgment result 48X as learning data.

[0163] The model generation unit 72 generates a trained model 46 using the 3D ground swelling analysis results, the 3D wall displacement analysis results, at least one of the deformation development diagram and the topography and geological information, and the external force judgment result 48X judged by the external force judgment unit 30.

[0164] The data acquisition unit 81 of the inference device 80 acquires the 3D ground swelling analysis result, the 3D wall displacement analysis result, and at least one of the deformation development map and the topography and geological information as the tunnel analysis information 47B. Then, the inference unit 82 inputs the tunnel analysis information 47B to the trained model 46 to obtain the external force determination result 48Y.

[0165] In the external force determination system 1B, when the learning device 70 generates the trained model 46 using the deformation development diagram, the inference device 80 calculates the external force determination result 48Y using the deformation development diagram.

[0166] Furthermore, in the external force determination system 1B, when the learning device 70 generates the trained model 46 using the topography and geological information, the inference device 80 calculates the external force determination result 48Y using the topography and geological information.

[0167] The external force determination result 48X may include a result determined by a user (a user determination result). In this case, the external force determination result 48Y also includes the user determination result.

[0168] Here, examples of user judgment results will be described. Examples of user judgment results include the following result examples R1 to R7. (Result example R1) The XX section of the tunnel being evaluated is a section where there is no invert construction and the ground is swelling significantly, and the amount of spring water is negligible. (Result example R2) The tunnel being evaluated is a tunnel made of expansive ground with little water, so it expands when water is supplied, and ground swelling has occurred after it was put into service. (Result example R3) The tunnel being evaluated shows significant ring tracks compared to nearby tunnels. (Example result R4) In the tunnel being evaluated, a vicious cycle is occurring in which the digging of the trench is progressing due to the rising of the pavement slab, and the supply of water from the ring road further promotes the rising. (Example result R5) The tunnel being evaluated is experiencing a vicious cycle in which the foundation weakens due to water, which in turn increases lateral pressure and accelerates foundation swelling. (Example result R6) As a countermeasure, a wear-resistant overlay that is less likely to cause trenching will be used and a drainage ditch will be installed for the tunnel being evaluated. (Result example R7) For the tunnels being evaluated, an increase in tunnel lateral pressure can be prevented by establishing a maintenance cycle, such as frequent overlays.

[0169] Note that external force determination result 48Y inferred by inference device 80 may be corrected by the user. In this case, learning device 70 may set external force determination result 48Y corrected by the user as new external force determination result 48X. Then, learning device 70 may execute learning using new external force determination result 48X and tunnel analysis information 47A corresponding to this external force determination result 48X.

[0170] Next, the hardware configuration of the external force determination systems 1A and 1B will be described. The external force determination systems 1A and 1B are realized by a processing circuit. This processing circuit may be a processor and memory that executes a program stored in a memory, or may be dedicated hardware. The processing circuit is also called a control circuit.

[0171] 22 is a diagram showing a configuration example of a processing circuit when the processing circuit included in the external force determination system according to the first and second embodiments is realized by a processor and a memory. Since the external force determination systems 1A and 1B have similar hardware configurations, the hardware configuration of the external force determination system 1B will be described here.

[0172] The processing circuit 90 shown in FIG. 22 is a control circuit and includes a processor 91 and a memory 92. When the processing circuit 90 is configured with the processor 91 and the memory 92, each function of the processing circuit 90 is realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 92. In the processing circuit 90, the processor 91 reads out and executes the program stored in the memory 92 to realize each function. That is, the processing circuit 90 includes a memory 92 for storing an external force determination program that results in the processing of the external force determination system 1B being executed. This external force determination program can also be said to be a program for causing the external force determination system 1B to execute each function realized by the processing circuit 90. This external force determination program may be provided by a storage medium in which the program is stored, or may be provided by other means such as a communication medium.

[0173] The external force determination program executed by the external force determination system 1B has a modular configuration including a floor swelling analysis unit 10, a wall displacement analysis unit 20, an external force determination unit 30, a 3D point cloud reception unit 40, a learning device 70, and an inference device 80, which are loaded onto a main storage device and generated on the main storage device. In the case of the external force determination system 1A, the external force determination program has a modular configuration including a floor swelling analysis unit 10, a wall displacement analysis unit 20, and an external force determination unit 30, which are loaded onto a main storage device and generated on the main storage device.

[0174] Here, the processor 91 is, for example, a CPU (Central Processing Unit), a processing device, an arithmetic device, a microprocessor, a microcomputer, or a DSP (Digital Signal Processor), etc. Also, the memory 92 is, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (Electrically EPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc), etc.

[0175] Fig. 23 is a diagram showing an example of a processing circuit when the processing circuit included in the external force determination system according to the first and second embodiments is configured with dedicated hardware. The processing circuit 93 shown in Fig. 23 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a combination of these.

[0176] The processing circuits 90 and 93 may be partially implemented by dedicated hardware and partially implemented by software or firmware. In this manner, the processing circuits 90 and 93 can realize the above-described functions by dedicated hardware, software, firmware, or a combination of these.

[0177] The external force determination system 1B may be realized by one processing circuit or by multiple processing circuits. When the learning device 70 is realized by one processing circuit, the learning device 70 has a hardware configuration similar to that of the external force determination system 1B described in Figs. 22 and 23. When the inference device 80 is realized by one processing circuit, the inference device 80 has a hardware configuration similar to that of the external force determination system 1B described in Figs. 22 and 23.

[0178] As described above, according to the second embodiment, the external force determination system 1B uses the learned model 46 to infer the external force determination result 48Y from the tunnel analysis information 47B acquired by the data acquisition unit 81, so it is possible to provide the user with an appropriate external force determination result 48Y corresponding to the tunnel analysis information 47B. This allows the user to decide how to deal with the tunnel by referring to the provided external force determination result 48Y.

[0179] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or the embodiments may be combined with each other. Also, parts of the configurations may be omitted or modified without departing from the spirit of the invention.

[0180] Various aspects of the present disclosure are summarized below as appendices.

[0181] (Appendix 1) a 3D point cloud receiving unit that receives 3D point cloud data that indicates the shape of the tunnel and is to be analyzed as an analysis 3D point cloud; A swelling analysis unit that analyzes swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis unit that analyzes a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination unit that extracts displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculates an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; and Equipped with An external force determination system characterized by: (Appendix 2) The comparison target with the three-dimensional point cloud is a comparison three-dimensional point cloud which is a past three-dimensional point cloud of the tunnel, The wall displacement analysis unit calculates a difference between the comparison three-dimensional point cloud and the analysis three-dimensional point cloud as an analysis result of the wall displacement. 2. An external force determination system according to claim 1. (Appendix 3) The object to be compared with the three-dimensional point cloud is a cross-sectional view of the tunnel, The wall displacement analysis unit calculates a difference between the cross-sectional view and the analysis three-dimensional point cloud as an analysis result of the wall displacement. 2. An external force determination system according to claim 1. (Appendix 4) The cross-sectional view is a design drawing of the tunnel. 4. An external force determination system according to claim 3. (Appendix 5) The cross-sectional view is a view extracted from the analytical three-dimensional point cloud. 4. An external force determination system according to claim 3. (Appendix 6) The wall displacement analysis unit calculates a central axis of the cross section of the tunnel based on the analysis three-dimensional point cloud, and calculates an analysis result of the wall displacement while sliding the cross section along the central axis. 6. An external force determination system according to any one of claims 3 to 5, (Appendix 7) The external force determination unit analyzes a cause of the external force that displaced the tunnel based on the external force direction. 7. An external force determination system according to any one of claims 1 to 6, (Appendix 8) The external force determination unit analyzes the cause of the external force using a deformation development diagram corresponding to the analysis result of the floor swelling and the analysis result of the wall displacement. 8. The external force determination system according to claim 7. (Appendix 9) The external force determination unit analyzes the cause of the external force using at least one of information on the stratum of the ground in which the tunnel is formed, information on the fault position of the ground, information on the landslide history of the ground, information on the geology of the ground, information on the construction method of the tunnel, and information on the lining back cavity of the tunnel. 9. The external force determination system according to claim 7 or 8. (Appendix 10) An inference device for inferring an external force determination result, which is a determination result of the external force determination, The inference device comprises: A first data acquisition unit that acquires tunnel analysis information including an analysis result of the ground swelling and an analysis result of the wall displacement for the tunnel; an inference unit that infers the external force determination result from the tunnel analysis information acquired by the first data acquisition unit, using a trained model for inferring the external force determination result from the tunnel analysis information; having 10. An external force determination system according to any one of claims 1 to 9, (Appendix 11) A learning device that generates the trained model based on the tunnel analysis information and the external force determination result, The learning device includes: a second data acquisition unit that acquires the tunnel analysis information and the external force determination result as learning data; A model generation unit that generates the trained model using the training data; having 11. The external force determination system according to claim 10. (Appendix 12) The external force determination result includes an analysis result of an analysis of the cause of the external force that displaced the tunnel. 12. The external force determination system according to claim 10 or 11. (Appendix 13) a 3D point cloud receiving step in which the external force determination system receives 3D point cloud data that indicates the shape of the tunnel and is to be analyzed as an analysis 3D point cloud; A swelling analysis step in which the external force determination system analyzes swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis step in which the external force determination system analyzes a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination step in which the external force determination system extracts displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculates an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; Including, A method for determining whether an external force is present. (Appendix 14) a 3D point cloud receiving step of receiving 3D point cloud data indicating the shape of the tunnel and to be analyzed as an analysis 3D point cloud; A swelling analysis step of analyzing swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis step of analyzing a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination step of extracting displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculating an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performing an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; and An external force determination program characterized by causing a computer to execute the above steps. [Explanation of symbols]

[0182] 1A, 1B External force determination system, 3, 4 Wall section, 10 Ground swelling analysis section, 11 Road surface extraction section, 12 Road surface center line calculation section, 13 Road surface model calculation section, 14 Road surface difference calculation section, 20 Wall surface displacement analysis section, 21 Wall surface extraction section, 22 Cross-sectional view reading section, 23 Center axis calculation section, 24 Cross-sectional difference calculation section, 25 Comparison wall surface reading section, 26 3D wall surface model calculation section, 27 Time-dependent difference calculation section, 30 External force determination section, 31 3D analysis result superposition section, 32 Displacement location extraction section, 33 External force direction calculation section, 34 Supplementary information reading section, 35 External force analysis section, 40 3D point cloud reception section, 45 Learned model storage section, 46 Learned model, 47A, 47B Tunnel analysis information, 48X, 48Y External force judgment result, 51, 52, 61 3D point cloud, 53 design drawing, 54 model cross section, 57 tunnel deformation information, 60, 75 road surface, 64 3D analysis result of ground swelling, 70 learning device, 71, 81 data acquisition unit, 72 model generation unit, 76 broken line, 77A, 77B area, 78A, 78B approximate plane, 79 emergency parking area, 80 inference device, 82 inference unit, 85 drainage pilot tunnel, 90, 93 processing circuit, 91 processor, 92 memory, 95-97 contour map, 101 deformation development map, 102 3D contour map, 103 topography and geological information, 341 deformation development map reading unit, 342 topography and geological information reading unit, C1 road surface centerline, d1 direction, D1, D2 displacement, Ef1-Ef5 External force direction, F1 contour map, G1 3D wall image.

Claims

1. a three-dimensional point cloud receiving unit that receives three-dimensional point cloud data that indicates the shape of a tunnel and is to be analyzed as an analysis three-dimensional point cloud; A swelling analysis unit that analyzes swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis unit that analyzes a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination unit that extracts displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculates an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; and Equipped with An external force determination system characterized by:

2. The object to be compared with the three-dimensional point cloud is a comparison three-dimensional point cloud which is a past three-dimensional point cloud of the tunnel, The wall displacement analysis unit calculates a difference between the comparison three-dimensional point cloud and the analysis three-dimensional point cloud as an analysis result of the wall displacement.

2. The external force determination system according to claim 1 .

3. The object to be compared with the three-dimensional point cloud is a cross-sectional view of the tunnel, The wall displacement analysis unit calculates a difference between the cross-sectional view and the analysis three-dimensional point cloud as an analysis result of the wall displacement.

2. The external force determination system according to claim 1 .

4. The cross-sectional view is a design drawing of the tunnel.

4. The external force determination system according to claim 3 .

5. The cross-sectional view is a view extracted from the analytical three-dimensional point cloud.

4. The external force determination system according to claim 3 .

6. The wall displacement analysis unit calculates a central axis of the cross section of the tunnel based on the analysis three-dimensional point cloud, and calculates an analysis result of the wall displacement while sliding the cross section along the central axis.

4. The external force determination system according to claim 3 .

7. The external force determination unit analyzes a cause of the external force that displaced the tunnel based on the external force direction.

2. The external force determination system according to claim 1 .

8. The external force determination unit analyzes the cause of the external force using a deformation development diagram corresponding to the analysis result of the floor swelling and the analysis result of the wall displacement.

8. The external force determination system according to claim 7,

9. The external force determination unit analyzes the cause of the external force using at least one of information on the stratum of the ground in which the tunnel is formed, information on the fault position of the ground, information on the landslide history of the ground, information on the geology of the ground, information on the construction method of the tunnel, and information on the lining back cavity of the tunnel.

8. The external force determination system according to claim 7,

10. An inference device for inferring an external force determination result, which is a determination result of the external force determination, The inference device comprises: a first data acquisition unit that acquires tunnel analysis information including an analysis result of the swelling of the tunnel and an analysis result of the wall displacement of the tunnel; an inference unit that infers the external force determination result from the tunnel analysis information acquired by the first data acquisition unit, using a trained model for inferring the external force determination result from the tunnel analysis information; having 10. The external force determination system according to claim 1, wherein the external force determination system is a system for determining an external force caused by an external force.

11. A learning device that generates the trained model based on the tunnel analysis information and the external force determination result, The learning device includes: a second data acquisition unit that acquires the tunnel analysis information and the external force determination result as learning data; A model generation unit that generates the trained model using the training data; having The external force determination system according to claim 10 .

12. The external force determination result includes an analysis result of an analysis of the cause of the external force that displaced the tunnel. The external force determination system according to claim 10 .

13. a three-dimensional point cloud receiving step in which the external force determination system receives three-dimensional point cloud data that indicates the shape of the tunnel and is to be analyzed as an analysis three-dimensional point cloud; A swelling analysis step in which the external force determination system analyzes swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis step in which the external force determination system analyzes a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination step in which the external force determination system extracts displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculates an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performs an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; Including, A method for determining whether an external force is present.

14. a three-dimensional point cloud receiving step of receiving three-dimensional point cloud data indicating the shape of the tunnel and to be analyzed as an analysis three-dimensional point cloud; A swelling analysis step of analyzing swelling of a road surface inside a tunnel based on the analysis three-dimensional point cloud; a wall displacement analysis step of analyzing a wall displacement, which is a displacement of an inner wall surface of the tunnel, based on the analysis three-dimensional point cloud; an external force determination step of extracting displacement points where the tunnel is displaced greater than a reference value based on the analysis results of the ground swelling and the wall displacement, calculating an external force direction that is the direction of the external force that the tunnel receives based on the correlation between the displacement points, and performing an external force determination as to whether the tunnel is receiving an external force that displaces the tunnel based on the external force direction; and An external force determination program characterized by causing a computer to execute the above steps.

Images