Repair plan determination device, repair plan determination system, and repair plan determination method

Abstract

This repair plan determination device (200) is characterized by comprising: an inspection result acquisition unit (201) that acquires an inspection result for a structure; an input unit (202) that receives input of input information including the inspection result, shape information for the structure, a budget for inspection and repair of the structure, and parameters for estimating costs that would occur if the structure became unusable; a database (203) that holds information correlating crack repair methods, crack conditions that can be repaired with each repair method, time required for repair work, repair costs, and service life after repair; a repair plan determination unit (204) that, on the basis of the input information and the information held in the database, combines a simple repair at the time of inspection corresponding to the inspection result, a simple repair at the time of inspection after the above-mentioned inspection, and a large-scale repair to create a repair plan that satisfies minimizing total costs and / or leveling costs; and an output unit (205) that outputs the repair plan.

Description

[Technical Field]

[0001] This disclosure relates to a repair plan determination device, a repair plan determination system, and a repair plan determination method for repairing cracks occurring in structures. [Background technology]

[0002] Structures such as social infrastructure and plant equipment cannot be easily replaced, so it is important to maintain them through planned inspections and repairs to ensure safe operation. When formulating a repair plan, it is necessary to consider the costs of inspections and repairs while maintaining the safety of the structure. For example, Patent Document 1 discloses a system for formulating a repair plan that minimizes the cumulative maintenance costs for periodic inspections of turbines. [Prior art documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2004-258858 [Overview of the project] [Problems that the invention aims to solve]

[0004] However, the conventional technologies described above have limitations in the applicable crack repair methods, and there is a need for technologies that can create appropriate repair plans even when using a wider range of repair methods.

[0005] This disclosure is made in view of the above, and aims to provide a repair plan determination device that can create an appropriate repair plan even when various repair methods are used. [Means for solving the problem]

[0006] To solve the aforementioned problems and achieve the objective, the repair plan determination device of this disclosure includes: an inspection result acquisition unit that acquires inspection results indicating the state of cracks occurring in a structure; an input unit that accepts input information including inspection results, shape information indicating the shape of the structure, the budget for inspection and repair of the structure, and parameters for estimating the costs incurred when the structure becomes unusable; a crack repair method including simple repairs carried out simultaneously with the inspection of the structure and large-scale repairs carried out separately from the inspection; and a database that holds information relating the state of cracks that can be repaired by each repair method, the time required for the repair work, the repair costs, and the service life after the repair. The inspection results include the angle the crack makes with respect to gravity. The system is characterized by comprising: a repair plan determination unit that creates a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspecting and repairing structures, by combining simple repairs during inspections corresponding to the inspection results, simple repairs during subsequent inspections, and major repairs based on input information and information held in a database; and an output unit that outputs the repair plan. [Effects of the Invention]

[0007] This disclosure provides the benefit of obtaining a repair plan determination device that can create an appropriate repair plan even when various repair methods are used. [Brief explanation of the drawing]

[0008] [Figure 1] A diagram showing the functional configuration of the repair device according to Embodiment 1. [Figure 2] Figure 1 is a diagram illustrating the function of the repair device. [Figure 3] Figure 1 shows an example of a detailed configuration of the inspection unit. [Figure 4] Figure 1 is a diagram illustrating the function of the determination unit. [Figure 5] Diagram illustrating the relationship between repair patterns and the operation of the repaired parts. [Figure 6] Diagram illustrating the process by which the determination unit determines the material to be used. [Figure 7]Figure showing an example of the detailed configuration of the determination unit according to Embodiment 1 [Figure 8] Figure showing a bridge, which is an example of a structure to be inspected by the repair device [Figure 9] Explanatory diagram of the crack length calculated by the calculation unit [Figure 10] Explanatory diagram of the crack angle calculated by the calculation unit [Figure 11] Explanatory diagram of the first example of the specific method for the calculation unit to calculate the crack length and the crack angle [Figure 12] Explanatory diagram of the second example of the specific method for the calculation unit to calculate the crack length and the crack angle [Figure 13] Explanatory diagram of the third example of the specific method for the calculation unit to calculate the crack length and the crack angle [Figure 14] Flowchart for explaining the operation of the repair device according to Embodiment 1 [Figure 15] Flowchart for explaining the details of the determination process according to Embodiment 1 [Figure 16] Figure showing the functional configuration of the repair device according to Embodiment 2 [Figure 17] Figure showing the detailed configuration of the determination unit according to Embodiment 2 [Figure 18] Flowchart for explaining the operation of the determination unit according to Embodiment 2 [Figure 19] Figure showing the functional configuration of the learning device according to Embodiment 3 [Figure 20] Flowchart for explaining the learning process of the learning device [Figure 21] Figure showing the functional configuration of the determination unit of the repair device according to Embodiment 3 [Figure 22] Configuration diagram of the inference device related to the repair device [Figure 23] Flowchart for explaining the inference process of the inference device [Figure 24] Figure showing the functional configuration of the repair device according to Embodiment 4 [Figure 25] Figure showing the configuration of the repair content determination system according to Embodiment 5 [Figure 26] Diagram showing the configuration of the repair content determination system according to Embodiment 6. [Figure 27] Flowchart for explaining the operation of the repair content determination system according to Embodiment 6 [Figure 28] Diagram showing the configuration of the repair content determination system according to Embodiment 7. [Figure 29] Diagram showing the configuration of the repair content determination system according to Embodiment 8. [Figure 30] A diagram showing an example of the movement path of the repair device according to Embodiment 8. [Figure 31] This figure shows another example of the path taken by the repair device according to Embodiment 8 to return from the goal point to the starting point. [Figure 32] This diagram shows an example configuration of a computer system that implements a device for determining repair content. [Figure 33] This diagram shows an example of a processing circuit for realizing each function of a repair device or a repair content determination system. [Figure 34] This figure shows the functional configuration of the repair plan determination device according to Embodiment 9. [Figure 35] Flowchart illustrating the operation of the inspection result acquisition unit shown in Figure 34. [Figure 36] Diagram illustrating the angle relative to the surface. [Figure 37] Figure 34 shows an example of the input information that the input unit accepts. [Figure 38] Figure 34 shows an example of the information stored in the database. [Figure 39] Flowchart for explaining the operation of the repair plan determination unit according to Embodiment 9 [Figure 40] Flowchart illustrating the details of step S516 in Figure 39 [Figure 41] Figure 34 shows a first example of the display screen output by the output unit. [Figure 42] Figure 34 shows a second example of the display screen output by the output unit. [Figure 43] Figure 34 shows a third example of the display screen output by the output unit. [Figure 44] Figure 34 shows a fourth example of the display screen output by the output unit. [Figure 45] Figure illustrating the effects of Embodiment 9 [Figure 46] This figure shows the functional configuration of the repair plan determination device according to Embodiment 10. [Figure 47] Figure 46 shows an example of the input information that the input unit accepts. [Figure 48] Diagram illustrating the angle a crack makes with respect to gravity. [Figure 49] Figure 46 shows a first example of the information held in the database. [Figure 50] Figure 46 shows a second example of the information held in the database. [Figure 51] This figure shows the functional configuration of the repair plan determination device according to Embodiment 11. [Figure 52] Flowchart illustrating the operation of the repair plan determination unit according to Embodiment 11 [Figure 53] Figure 51 shows a first example of the display screen output by the output unit. [Figure 54] Figure 51 shows a second example of the display screen output by the output unit. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the repair content determination device, the repair device, the learning device, the inference device, the repair content determination system, the repair method, the repair plan determination device, the repair plan determination system, and the repair plan determination method according to the embodiments of this disclosure.

[0010] Conventionally, there is a technique to suppress crack propagation by applying a repair material, which is a liquid containing particles, to cracks that have formed in a structure. Cracks propagate by repeatedly opening and closing, but by applying the repair material to the crack, the particles contained in the repair material act as wedges, preventing the crack from closing, and thus reducing the rate of crack propagation. Therefore, in order to enhance the crack propagation suppression effect, it is important to allow the repair material to penetrate into the crack and remain inside the crack.

[0011] Japanese Patent Publication No. 4852163 describes a repair material for reducing the fatigue crack propagation rate of metallic materials, which has a specified viscosity range that provides excellent penetration into cracks. However, according to the above-mentioned conventional technology, there is a problem that it may be difficult to penetrate the repair material into the crack depending on the state of the crack. For example, whether or not the repair material penetrates into the crack depends on the orientation of the crack relative to the direction of gravity. In cracks where the opening faces downward, such as cracks that occur in ceiling surfaces, it may be difficult for the repair material to penetrate into the crack because the force of penetration due to the weight of the repair material does not act compared to cracks where the opening faces upward or cracks where the opening faces sideways. Embodiments 1 to 8 below describe a repair content determination device, a repair device, a learning device, an inference device, a repair content determination system, and a repair method that can improve the penetration of the repair material into the crack regardless of the state of the crack. Furthermore, embodiments 9 to 11 describe a repair plan determination device, a repair plan determination system, and a repair plan determination method that can select the repair method described in embodiments 1 to 8 as one of the "candidate repair methods to be used."

[0012] Embodiment 1. Figure 1 is a diagram showing the functional configuration of a repair device 10 according to Embodiment 1. The repair device 10 has the function of inspecting a crack C that has occurred in a structure S, determining the repair content based on the inspection results, and repairing the crack C according to the determined repair content. The repair device 10 is an example of a repair content determination device that has the function of determining the repair content of a crack C. The repair device 10 has a main body 11, a suction means 12 for fixing the main body 11 of the repair device 10 to the structure S, a driving means 13 for moving the repair device 10 along the structure S, an inspection unit 14 for inspecting the crack C to be repaired and outputting the inspection results, a determination unit 15 for determining the repair content of the crack C based on the inspection results, and a repair unit 16 for repairing the target crack C according to the repair content determined by the determination unit 15. The repair unit 16 has a pre-processing unit 17, an intermediate processing unit 18, and a post-processing unit 19.

[0013] Here, the material to be inspected is a material in which fatigue cracks occur due to repeated localized plastic deformation on the material surface, and fatigue cracks propagate through repeated blunting and re-sharpening due to plastic deformation of the crack tip. Such materials are called "materials to be inspected." Structures S include, for example, bridges, vehicles, aircraft, power generation equipment, and machine tools. Examples of materials to be inspected include steel, stainless steel, and aluminum alloys, but are not limited to metals and also include resins and ceramics. The entire structure S does not need to be made of materials to be inspected, but the cracks C to be repaired are defined as cracks C that occur in the part of structure S made of materials to be inspected. In the following explanation, the part of structure S made of materials to be inspected may be referred to as the "material to be inspected portion."

[0014] Figure 2 is a diagram illustrating the function of the repair device 10 shown in Figure 1. The repair device 10 can perform repair processing using a pretreatment material 21 and a repair material 22.

[0015] The repair material 22 is a liquid containing particles. By applying the repair material 22 to the inside of a crack C and allowing the repair material 22 to remain inside the crack C, the particles contained in the repair material 22 exert a wedge effect, thereby suppressing the propagation of the crack C. The wedge effect is also called the bridging effect. The phenomenon in which the particles contained in the repair material 22 prevent the crack C from closing is called the wedge effect. Since the crack C propagates by repeatedly opening and closing, the propagation of the crack C can be suppressed by the wedge effect. To improve the crack propagation suppression effect, it is important to allow the repair material 22 to penetrate to the tip of the crack C and to allow the penetrated repair material 22 to remain inside the crack C. The lower the viscosity of the repair material 22, the easier it is to penetrate the repair material 22 into the crack C, but the more difficult it becomes to keep the repair material 22 inside the crack C. Therefore, by applying the pretreatment material 21 into the crack C before applying the repair material 22, the penetration of the repair material 22 into the crack C can be improved. The pretreatment material 21 is a liquid with higher wettability to the structure S than the repair material 22. In other words, the contact angle θ1 between the pretreatment material 21 and the surface of the structure S is smaller than the contact angle θ2 between the repair material 22 and the surface of the structure S.

[0016] The pre-treatment unit 17 of the repair unit 16 has the function of performing a pre-treatment step of applying a pre-treatment material 21 to the inside of the crack C. The intermediate treatment unit 18 has the function of performing an intermediate treatment step of removing the excess pre-treatment material 21 applied in the pre-treatment step. The post-treatment unit 19 has the function of performing a post-treatment step of applying repair material 22 to the inside of the crack C. In Figure 2, the pre-treatment step, intermediate treatment step, and post-treatment step are all shown to be performed sequentially, so in the post-treatment step, a film of pre-treatment material 21 is formed on the inner wall surface of the crack C and the repair material 22 is filled into the crack C. However, depending on the condition of the crack C, the repair unit 16 does not necessarily have to drive all of the pre-treatment unit 17, intermediate treatment unit 18, and post-treatment unit 19. For example, the repair unit 16 may sequentially drive all of the pre-processing unit 17, the intermediate processing unit 18, and the post-processing unit 19, or it may drive only the post-processing unit 19 without driving the pre-processing unit 17 and the intermediate processing unit 18, or it may not perform any repairs at all without driving any of the pre-processing unit 17, the intermediate processing unit 18, and the post-processing unit 19.

[0017] Figure 3 shows an example of a detailed configuration of the inspection unit 14 shown in Figure 1. The inspection unit 14 includes a LiDAR (Light Detection and Ranging) scanner 141 and a camera 142. The LiDAR scanner 141 is a device that measures the distance, properties, and shape of an object by shining a laser beam onto the object and receiving the reflected light. The camera 142 is a device that acquires images of cracks C. The camera 142 is synchronized with the LiDAR scanner 141. Both the LiDAR scanner 141 and the camera 142 are equipped with gyro sensors and can acquire their own orientation. This makes it possible to correlate the surface shape of the material under inspection measured by the LiDAR scanner 141 and the camera 142 with the direction of gravity. The LiDAR scanner 141 can measure the depth inside the crack C by measuring the surface of the material under inspection. The camera 142 can output images of the surface of the material under inspection.

[0018] Figure 4 is a diagram illustrating the function of the determination unit 15 shown in Figure 1. The determination unit 15 receives an image of the crack C and direction information indicating the direction of gravity in the image as inspection results from the inspection unit 14. Based on the inspection results, the determination unit 15 determines the repair content and outputs the determined repair content. The direction information is, for example, the output of a gyro sensor. The repair content output by the determination unit 15 includes at least a repair pattern indicating whether or not to perform repair with repair material 22, and, if repair with repair material 22 is performed, whether or not to apply pre-treatment material 21 before applying the repair material 22. The repair content may also include the materials to be used for repair if repair is performed. The materials to be used for repair include at least the repair material 22 if repair is performed, and further include the pre-treatment material 21 if the pre-treatment material 21 is applied. For example, the determination unit 15 selects one of three repair patterns based on the inspection results: repair pattern (1) applying the pretreatment material 21 and then the repair material 22; repair pattern (2) applying only the repair material 22 without applying the pretreatment material 21; or repair pattern (3) no repair. Furthermore, if repair pattern (1) is selected, the determination unit 15 may determine the pretreatment material 21 and the repair material 22 to be used for the repair based on the inspection results, or if repair pattern (2) is selected, the determination unit 15 may determine the repair material 22 to be used for the repair based on the inspection results.

[0019] Figure 5 is an explanatory diagram of the relationship between the repair patterns and the operation of the repair unit 16. The determination unit 15 selects one of the following repair patterns: repair pattern (1), repair pattern (2), or repair pattern (3) based on the inspection results. Repair pattern (1) is a pattern in which the pre-treatment unit 17, intermediate treatment unit 18, and post-treatment unit 19 are driven in the order listed, and after applying the pre-treatment material 21 into the crack C, the excess pre-treatment material 21 is removed, and then the repair material 22 is applied. Repair pattern (2) is a pattern in which only the post-treatment unit 19 is driven, and the repair material 22 is applied into the crack C without applying the pre-treatment material 21. Repair pattern (3) is a repair pattern in which the repair unit 16 does not operate, and no repair is performed.

[0020] Figure 6 is an explanatory diagram of the process by which the determination unit 15 determines the materials to be used. When the determination unit 15 selects repair pattern (1), it determines the combination of pretreatment material 21 and repair material 22 to be used. For example, as shown in Figure 6, the determination unit 15 can select the pretreatment material 21 from three candidates: "a", "b", and "c". The determination unit 15 can also select the repair material 22 from three candidates: "A", "B", and "C". In Figure 6, "b" is selected as the pretreatment material 21 and "C" is selected as the repair material 22.

[0021] There are various methods for determining the repair pattern and the materials to be used for repair, but as an example, we will explain a method of determining the repair content based on the length of the crack C and the angle that the crack C makes with respect to gravity. Specifically, the angle that the crack C makes with respect to gravity can be defined as the angle that the crack C makes with respect to its depth relative to gravity. Hereafter, for simplicity, the "angle that the crack C makes with respect to gravity relative to its depth relative to gravity" will be referred to as the "angle of the crack C."

[0022] Figure 7 shows an example of a detailed configuration of the determination unit 15 according to Embodiment 1. The determination unit 15 includes a calculation unit 151, a repair pattern determination unit 152, and a material usage determination unit 153.

[0023] The calculation unit 151 calculates data that the judgment unit 15 uses for judgment from the inspection results output by the inspection unit 14. Specifically, the inspection unit 14 outputs an image of the crack C and directional information indicating the direction of gravity in the image as inspection results, and the calculation unit 151 calculates the length of the crack C and the angle of the crack C from these inspection results. The calculation unit 151 outputs the calculated length of the crack C and the angle of the crack C to the repair pattern determination unit 152 and the material used determination unit 153.

[0024] Here, the specific processing of the calculation unit 151 will be explained using a concrete example. Figure 8 shows a bridge S1, which is an example of a structure S that the repair device 10 is intended to inspect. In the bridge S1, pavement 32 is laid on top of a deck plate 31, and vehicles and other objects pass over the pavement 32. Beneath the deck plate 31, support members 30 such as U-ribs 33, transverse ribs 34, and vertical reinforcing steel members 37 support the deck plate 31.

[0025] Figure 9 is an explanatory diagram of the length of crack C calculated by the calculation unit 151. Here, a crack C that has occurred in the weld bead 35 between the deck plate 31 and the U-rib 33 of the bridge S1 is shown. Here, the crack C originates from the starting point P1 and propagates from the side surface of the weld bead 35 formed between the side surface of the U-rib 33 and the deck plate 31 to the surface of the weld bead 35 formed between the outer surface of the U-rib 33 and the deck plate 31. Here, the length L1 of the crack C is the length of the crack line on the surface of the weld bead 35. In this case, if the crack line is not a straight line, the length L1 of the crack C may be the actual length of the crack line or the length of an approximate straight line of the crack line. Although not used in Embodiment 1, the opening amount of the crack C on the surface where the crack C has occurred is defined as the opening amount W1.

[0026] Figure 10 is an explanatory diagram of the crack angle C calculated by the calculation unit 151. The crack angle C is the angle φ1 made by the depth direction D2 of the crack C with respect to the gravity direction D1. Hereafter, this angle may be referred to as the crack angle C φ1.

[0027] Figure 11 is an explanatory diagram of a first example of a specific method by which the calculation unit 151 calculates the length L1 and angle φ1 of the crack C. The length L1 of the crack C can be calculated by analyzing the image captured by the camera 142 of the inspection unit 14. In order to calculate the angle φ1 of the crack C, it is necessary to know the direction of gravity D1 and the depth direction D2 of the crack C. Here, since the LiDAR scanner 141 and camera 142 of the inspection unit 14 are each equipped with a gyro sensor and can acquire their own orientation, the information acquired by the LiDAR scanner 141 and camera 142 can be associated with the direction of gravity D1. In addition, the calculation unit 151 can estimate the depth direction D2 of the crack C from the result of depth measurement inside the crack C by the LiDAR scanner 141. Alternatively, the calculation unit 151 may calculate the vertical direction D3 at the crack line position on the surface of the weld bead 35 and use the vertical direction D3 as the depth direction D2 of the crack C.

[0028] Figure 12 shows the calculation unit 151 calculating the lengths L1-1, L1-2 and the angle φ of cracks C-1, C-2. 1-1 ,φ 1-2 This is an explanatory diagram illustrating a second example of a specific method for calculating the crack C. In the first example in Figure 11, a crack C that occurred in the weld bead 35 formed between the deck plate 31 and the U-rib 33 is illustrated. In Figure 12, a crack C that occurred in the butt weld bead 36 formed between the U-rib 33-1 and the U-rib 33-2 is illustrated. Of the cracks C that occurred in the butt weld bead 36, the crack C that occurred on the side of the U-ribs 33-1 and 33-2 is designated as crack C-1, and the crack C that occurred on the underside of the U-ribs 33-1 and 33-2 is designated as crack C-2.

[0029] Crack C-1 propagates from an initiation point P1-1 near the inner surface of U-ribs 33-1 and 33-2 toward the outer surface of U-ribs 33-1 and 33-2, and then propagates in two opposite directions on the surface of the butt weld bead 36. In this case as well, the calculation unit 151 can use the length of the crack line on the surface of the butt weld bead 36 as the length L1-1 of crack C-1. Alternatively, the calculation unit 151 can estimate the depth direction D2-1 of crack C-1 from the results of depth measurement inside crack C-1 by the LiDAR scanner 141. Or, the calculation unit 151 may calculate the vertical direction at the crack line position on the surface of the butt weld bead 36 and use the vertical direction as the depth direction D2-1 of crack C. The calculation unit 151 calculates the angle φ of crack C-1. 1-1 This can be calculated from the gravity direction D1 and the depth direction D2-1.

[0030] Similar to crack C-1, crack C-2 propagates from an initiation point P1-2 near the inner surface of U-ribs 33-1 and 33-2 toward the outer surface of U-ribs 33-1 and 33-2, and then propagates in two opposite directions on the surface of the butt weld bead 36. For crack C-2 as well, the calculation unit 151 can use the length of the crack line on the surface of the butt weld bead 36 as the length L1-2 of crack C-2. Alternatively, the calculation unit 151 can estimate the depth direction D2-2 of crack C-2 from the results of depth measurement inside crack C-2 by the LiDAR scanner 141. Or, the calculation unit 151 may calculate the vertical direction at the crack line position on the surface of the butt weld bead 36 and use the vertical direction as the depth direction D2-2 of crack C. The calculation unit 151 calculates the angle φ of crack C-2. 1-2 This can be calculated from the direction of gravity D1 and the depth direction D2-2. Crack C-2 occurs on the horizontal plane, and the depth direction D2-2 of crack C-2 is close to the direction of gravity, therefore the angle φ of crack C-2 1-2 The value will be approximately 0.

[0031] Figure 13 shows the calculation unit 151 calculating the length L1-3 of crack C-3 and the angle φ of crack C-3. 1-3This is an explanatory diagram of a third example of a specific method for calculating the length. In the third example, a crack C-3 arising from the contact area between the fillet weld bead 38 formed between the deck plate 31 and the vertical reinforcement member 37 and the deck plate 31 is illustrated. In this crack C-3, the initial crack occurs in a direction penetrating the deck plate 31 from the starting point P1-3 of the contact area between the fillet weld bead 38 and the deck plate 31, and then spreads in the in-plane direction of the deck plate 31. At this time, since force is easily applied to the part where the fillet weld bead 38 and the deck plate 31 are in contact, the crack C-3 often spreads along the edge of the fillet weld bead 38. In this case, as shown in Figure 13, the crack line of the crack C-3 is curved. In this case, the length L1-3 of the crack C-3 may be the length of the curved crack line, or, as shown in the figure, it may be the length of a straight line in the in-plane direction of the deck plate 31 and in the direction in which the crack C-3 spreads. Furthermore, the depth direction D2-3 of crack C-3 is in the thickness direction of the surface of the deck plate 31, which is a horizontal plane, and is therefore approximately in the direction of gravity D1, and the angle φ of crack C-3 1-3 This value will be close to 0.

[0032] Returning to the explanation of Figure 7, the repair pattern determination unit 152 can determine a repair pattern for the target crack C from among repair pattern (1), repair pattern (2), and repair pattern (3) based on the output of the calculation unit 151. Here, the repair pattern determination unit 152 determines the repair pattern based on the length L1 of the crack C and the angle φ1 of the crack C calculated by the calculation unit 151.

[0033] For cracks C that are short and minute in length, repair may not yet be necessary. Therefore, the determination unit 15 can determine whether or not to perform repair based on the length L1 of the crack C. Specifically, the determination unit 15 does not perform repair if the length of the crack C is less than the first threshold, and performs repair if the length of the crack C is equal to or greater than the first threshold. In addition, the ease with which the repair material 22 penetrates into the crack C and the ease with which the repair material 22 remains inside the crack C changes depending on the angle φ1 of the crack C. For example, when comparing cracks C of the same shape with an angle φ1 of 0 to 180 degrees, the larger the angle φ1 of the crack C, such as a crack C with an upward-facing opening on the upper surface of the structure S, the easier it is for the repair material 22 to penetrate into the crack C due to gravity. Also, because the tip of the crack C is in the direction of gravity, the repair material 22 tends to accumulate inside the crack C unless the crack C penetrates the structure S. Furthermore, when the angle φ1 of a crack C is small, such as a crack C that occurs on the underside of the ceiling of a structure S or a crack C that occurs on the side of a structure S, where the opening is downward or sideways, the repair material 22 has difficulty penetrating into the crack C and has difficulty remaining inside the crack C. For this reason, the determination unit 15 can decide whether or not to use the pretreatment material 21 based on the angle φ1 of the crack C. Specifically, the determination unit 15 uses the pretreatment material 21 if the angle φ1 of the crack C is less than the second threshold, and does not use the pretreatment material 21 if the angle φ1 of the crack C is equal to or greater than the second threshold.

[0034] The material determination unit 153 determines the material to be used to repair the target crack C based on the output of the calculation unit 151. The material determination unit 153 determines the material to be used according to the repair pattern determined by the repair pattern determination unit 152. Specifically, in the case of repair pattern (1), the material determination unit 153 determines the pretreatment material 21 and repair material 22 to be used; in the case of repair pattern (2), it determines the repair material 22 to be used; and in the case of repair pattern (3), since no repair is performed, the material to be used is not determined.

[0035] When determining the material to be used for repair based on the length L1 of crack C and the angle φ1 of crack C, first, based on the length L1 of crack C, the appropriate shape and size of the particles contained in the repair material 22 are determined. Also, based on the angle φ1 of crack C, the appropriate viscosity of the repair material 22 is determined. The viscosity of the repair material 22 can be adjusted by changing the content rate of the particles contained in the repair material 22. However, if the content rate of the particles is reduced to lower the viscosity, the amount of particles per unit volume of the repair material 22 decreases, so the penetration force into crack C increases, but the maximum amount of particles that can fit into the space within crack C decreases. In the selection of the repair material 22, a repair material 22 is selected such that the amount of particles within crack C is maximized, taking into account the penetration force of the repair material 22 and the amount of particles penetrated into crack C. The determination unit 15 selects a repair material 22 that contains particles of a shape and size determined according to the length L1 of crack C and has a viscosity corresponding to the angle φ1 of crack C. Subsequently, the determination unit 15 selects the pretreatment material 21 according to the selected repair material 22 and the material of the structure S.

[0036] In the case of the repair pattern (1), the material determination unit 153 determines the materials to be used such that the combination of the pretreatment material 21 and the repair material 22 satisfies "2s1×cosθ1 / ρ1>2s2×cosθ2 / ρ2". Here, let s1 be the surface tension of the pretreatment material 21, θ1 be the contact angle between the pretreatment material 21 and the surface of the structure S, ρ1 be the density of the pretreatment material 21, s2 be the surface tension of the repair material 22, θ2 be the contact angle between the repair material 22 and the surface of the structure S, and ρ2 be the density of the repair material 22.

[0037] Here, the pretreatment material 21 is preferably an oil having a density ρ1 of 0.83 g / cm 3 or more and less than 0.89 g / cm 3 and a contact angle θ1 with the surface of the structure S of 0 degrees or more and less than 10 degrees and a surface tension s1 of 20 dyn / cm or more and less than 50 dyn / cm.

[0038] Figure 14 is a flowchart illustrating the operation of the repair device 10 according to Embodiment 1. First, the repair device 10 performs an inspection process by the inspection unit 14 (step S10). Subsequently, the repair device 10 performs a determination process by the determination unit 15 based on the inspection results from the inspection unit 14 (step S20). Details of the determination process will be described later. Once the repair content is determined as a result of the determination process, the repair device 10 determines whether the determined repair content is "repair required" or not (step S30).

[0039] If the determined repair content is "repair required" (step S30: Yes), that is, if the repair pattern included in the repair content is repair pattern (1) or repair pattern (2), the repair device 10 performs the repair process using the repair unit 16 (step S40). Specifically, in the case of repair pattern (1), the repair device 10 uses the pre-treatment unit 17, intermediate treatment unit 18, and post-treatment unit 19 of the repair unit 16 to apply the pre-treatment material 21, remove any excess pre-treatment material 21, and then apply the repair material 22. At this time, if the repair content includes materials to be used for repair, the repair unit 16 performs the repair process using the pre-treatment material 21 and repair material 22 indicated in the repair content. In the case of repair pattern (2), the repair device 10 uses the post-treatment unit 19 of the repair unit 16 to apply the repair material 22. In this case, if the repair details include materials to be used for the repair, the repaired part 16 will perform the repair using the repair material 22 indicated in the repair details.

[0040] If the determined repair content is not "repair required" (step S30: No), that is, if the repair pattern included in the repair content is repair pattern (3), the process in step S40 is omitted. Next, the repair device 10 determines whether or not the repair is complete (step S50). If the repair is complete (step S50: Yes), the repair device 10 terminates the process. If the repair is not complete (step S50: No), the repair device 10 moves using the drive means 13 (step S60) and returns to the process in step S10.

[0041] Furthermore, the process of determining whether the repair is complete in step S50 can, for example, be determined to be complete when the user performs the termination operation. Alternatively, if the repair device 10 has a function to automatically move according to a specified route, the repair can be determined to be complete when it reaches the end point of the specified route.

[0042] Figure 15 is a flowchart illustrating the details of the determination process according to Embodiment 1. The process shown in Figure 15 corresponds to the determination process in step S20 of Figure 14.

[0043] The calculation unit 151 of the determination unit 15 first estimates the depth direction D2 of the crack C (step S101). Next, the determination unit 15 calculates the angle between the gravity direction D1 based on the directional information included in the inspection result and the depth direction D2 of the crack C estimated in step S101 (step S102). The calculation unit 151 also calculates the length L1 of the crack C from the captured image of the crack C included in the inspection result (step S103).

[0044] The repair pattern determination unit 152 determines whether the length L1 of the crack C calculated in step S103 is greater than or equal to a first threshold (step S104). If the length L1 of the crack C is greater than or equal to the first threshold (step S104: Yes), the repair pattern determination unit 152 determines that "repair is necessary" (step S105). If the length L1 of the crack C is less than the first threshold (step S104: No), the repair pattern determination unit 152 determines that "no repair is necessary" and selects repair pattern (3) (step S106).

[0045] Furthermore, following step S105, the repair pattern determination unit 152 determines whether the angle φ1 of the crack C is less than the second threshold (step S107). If the angle φ1 of the crack C is less than the second threshold (step S107: Yes), the repair pattern determination unit 152 determines that "pretreatment is required" and selects repair pattern (1) (step S108). Furthermore, following step S108, the material determination unit 153 selects the pretreatment material 21 and repair material 22 to be used when repairing the target crack C (step S109).

[0046] If the angle φ1 of the crack C is greater than or equal to the second threshold (step S107: No), the repair pattern determination unit 152 determines "no pretreatment" and selects repair pattern (2) (step S110). Following step S110, the material used determination unit 153 selects the repair material 22 to be used when repairing the target crack C (step S111).

[0047] In the above-described embodiment 1, the directional information is based on the self-attitude acquired by the gyro sensor, but this embodiment is not limited to this example. If a gyro sensor is not provided, a vertical indicator such as a pendulum can be used. When using a pendulum, the direction of gravity can be recorded by capturing the pendulum within the field of view of the camera 142.

[0048] The repair device 10 according to Embodiment 1 described above is an example of a repair content determination device that determines the repair content of a crack C occurring in the inspected material portion of a structure S. The repair device 10 includes an inspection unit 14, which is an inspection result acquisition unit that acquires the inspection results of a crack C occurring in the inspected material portion of a structure S, and a determination unit 15 that determines the repair content, including a repair pattern that indicates whether or not to repair the crack C with a repair material 22 which is a liquid containing particles, and whether or not to apply a pretreatment material 21 into the crack C before applying the repair material 22 if the repair is to be performed with the repair material 22. As a result, it is determined whether or not to perform repairs and, if repairs are to be performed, whether or not to apply a pretreatment material 21 before applying the repair material 22, according to the inspection results of the crack C. Therefore, regardless of the state of the crack C, it becomes possible to increase the penetration of the repair material 22 into the crack C. Furthermore, since the repair device 10 determines the repair content, a higher crack propagation suppression effect can be achieved without requiring the skill of the repair worker.

[0049] Here, the determination unit 15 can determine a repair pattern based on the length L1 of the crack C and the angle φ1 of the crack C with respect to the direction of gravity D1, as indicated by the inspection results. For cracks C with a short length L1 and that are minute, repair may not yet be necessary. Also, depending on the angle φ1 of the crack C, pretreatment material 21 may not be required. It is desirable that the repair pattern be determined taking these factors into consideration.

[0050] Furthermore, the repair details include materials used to repair the crack C. The determination unit 15 can determine the repair material 22 to be used to repair the crack C based on the inspection results when repair is to be performed using the repair material 22, and can determine the pretreatment material 21 to be used to repair the crack C based on the inspection results and the repair material 22 to be used when applying the pretreatment material 21. More specifically, the repair material 22 to be used contains particles of a size and shape corresponding to the condition of the crack C to be repaired, for example, the length L1 and opening W1 of the crack C, and it is desirable that the repair material 22 has a viscosity corresponding to the condition of the crack C to be repaired, in particular, the angle φ1 of the crack C. The pretreatment material 21 to be used is determined based on the material of the structure S to be repaired and its compatibility with the selected repair material 22.

[0051] More specifically, the determination unit 15 selects the pretreatment material 21 and the repair material 22 such that the formula "2s1 × cosθ1 / ρ1 > 2s2 × cosθ2 / ρ2" is satisfied, where s1 is the surface tension of the pretreatment material 21, θ1 is the contact angle of the pretreatment material 21 with the surface of the structure S, and ρ1 is the density of the pretreatment material 21; s2 is the surface tension of the repair material 22, θ2 is the contact angle of the repair material 22 with the surface of the structure S, and ρ2 is the density of the repair material 22. 3 More than 0.89g / cm 3 It is desirable that the contact angle θ1 with the surface of the structure S is less than 0 degrees or more and less than 10 degrees, and the surface tension s1 is 20 dyn / cm or more and less than 50 dyn / cm. This makes it possible to select a pretreatment material 21 that can more reliably improve the penetration of the repair material 22.

[0052] Embodiment 2. Figure 16 shows the functional configuration of the repair device 10A according to Embodiment 2. The configuration of the repair device 10A is the same as that of the repair device 10, except that it has a determination unit 15A instead of the determination unit 15 of the repair device 10, so a detailed explanation is omitted here.

[0053] Figure 17 shows a detailed configuration of the determination unit 15A according to Embodiment 2. The determination unit 15A includes a calculation unit 151A, a repair pattern determination unit 152A, and a material usage determination unit 153A. In addition to the function of calculating the length L1 and angle φ1 of the crack C, similar to the calculation unit 151, the calculation unit 151A also has the function of calculating the opening amount W1 of the crack C based on the inspection results.

[0054] Here, since the inspection results are the captured image and directional information of the structure S, the calculation unit 151A calculates the opening amount W1 by analyzing the captured image. The calculation unit 151A outputs the calculated crack length L1, angle φ1, and opening amount W1 to the repair pattern determination unit 152A and the material used determination unit 153A, respectively.

[0055] The repair pattern determination unit 152A determines the repair pattern for the target crack C based on the length L1, angle φ1, and opening amount W1 of the crack C output by the calculation unit 151A. For example, in the case of a closed crack C with a small opening amount W1, even if the repair material 22 is applied, penetration of the repair material 22 into the crack C may not be expected. For this reason, the repair pattern determination unit 152A can choose not to perform repairs on cracks C where the opening amount W1 is less than a third threshold. Specifically, the repair pattern determination unit 152A determines "repair is needed" when the length L1 of the crack C is greater than or equal to a first threshold and the opening amount W1 is greater than or equal to a third threshold. Furthermore, the repair pattern determination unit 152A determines "no repair" and selects repair pattern (3) if the length L1 of the crack C is less than the first threshold, or if the opening amount W1 is less than the third threshold even if the length L1 of the crack C is greater than or equal to the first threshold.

[0056] The material determination unit 153A determines the material to be used to repair the crack C based on the length L1, angle φ1, and opening W1 of the crack C output by the calculation unit 151A. Specifically, in addition to the same criteria as the material determination unit 153, the material determination unit 153A can select the shape and size of the particles contained in the repair material 22 to be used based on the opening W1.

[0057] Figure 18 is a flowchart illustrating the operation of the determination unit 15A according to Embodiment 2. Parts similar to those in the operation of the determination unit 15 according to Embodiment 1, as described using Figure 15, are denoted by the same reference numerals and their explanations may be omitted. In the omitted parts, "determination unit 15" should be read as "determination unit 15A," "calculation unit 151" as "calculation unit 151A," and "repair pattern determination unit 152" as "repair pattern determination unit 152A."

[0058] The operation from step S101 to step S103 is the same as in Figure 15, so the explanation is omitted. After step S103, the calculation unit 151A calculates the opening amount W1 of the crack C (step S201).

[0059] After step S201, the repair pattern determination unit 152A determines whether the length L1 of the crack C is greater than or equal to a first threshold (step S104). If the length L1 of the crack C is less than the first threshold (step S104: No), the repair pattern determination unit 152A determines "no repair" and selects repair pattern (3) (step S106).

[0060] If the length L1 of the crack C is greater than or equal to the first threshold (step S104: Yes), the repair pattern determination unit 152A determines whether the opening amount W1 is greater than or equal to the third threshold (step S202). If the opening amount W1 is less than the third threshold (step S202: No), the process proceeds to step S106.

[0061] If the opening amount W1 is greater than or equal to the third threshold (step S202: Yes), the repair pattern determination unit 152A determines that "repair is required" (step S105). The processing in the following steps S107, S108, and S110 is the same as in Figure 15, so the explanation is omitted.

[0062] When repair pattern (1) is selected in step S108, the material determination unit 153A selects the pretreatment material 21 and repair material 22 to be used based on the length L1 of the crack C, the angle φ1, and the opening amount W1 (step S203).

[0063] Furthermore, if repair pattern (2) is selected in step S110, the material determination unit 153A selects the repair material 22 to be used based on the length L1 of the crack C, the angle φ1, and the opening amount W1 (step S204).

[0064] As described above, the repair device 10A according to Embodiment 2 is an example of a repair content determination device that determines the repair content of a crack C occurring in the inspected material portion of a structure S. In addition to the functions of the repair device 10 according to Embodiment 1, the repair device 10A can further use the opening amount W1 of the crack C when determining the repair pattern and the material to be used. Therefore, it becomes possible to prevent repairs from being performed on cracks C where the opening portion is closed and penetration of the repair material 22 into the crack C cannot be expected. Furthermore, since the material to be used for repair is determined based on the opening amount W1, it becomes possible to further enhance the crack propagation suppression effect regardless of the skill level of the repair worker.

[0065] Embodiment 3. Embodiment 3 describes a method for determining appropriate repair content according to the state of crack C using machine learning.

[0066] Figure 19 shows the functional configuration of the learning device 50 according to Embodiment 3. The learning device 50 is a machine learning device related to the repair device 10. The learning device 50 has a learning data acquisition unit 51 and a model generation unit 52.

[0067] The learning data acquisition unit 51 acquires the inspection results and the details of any repairs performed before the inspection results were acquired as learning data. Here, the inspection results include the captured image of the structure S and directional information, which is information for identifying the direction of gravity in the captured image.

[0068] The model generation unit 52 learns the repair details based on training data that includes the inspection results and the repair details. That is, the model generation unit 52 generates a trained model that infers the repair details from the inspection results of the repair device 10. Here, the repair details include at least the repair pattern and may also include the materials used when performing the repair.

[0069] The learning algorithm used by the model generation unit 52 can be any known algorithm, such as supervised learning, unsupervised learning, or reinforcement learning. As an example, the case where reinforcement learning is applied will be described. In reinforcement learning, an agent, which is an agent acting in a certain environment, observes the parameters of the environment that indicate the current state and decides what action to take. The environment changes dynamically as a result of the agent's actions, and the agent is given a reward in accordance with the changes in the environment. The agent repeats this process and learns the action strategy that yields the most rewards through a series of actions. Representative reinforcement learning methods include Q-learning and TD-learning. For example, in the case of Q-learning, the general update formula for the action-value function Q(s,a) is expressed by the following equation (1).

[0070]

number

[0071] In the above formula (1), s t This represents the state of the environment at time t, and a t This represents the action at time t. Action a t Therefore, the state is s t+1 It changes to r. t+1 γ represents the reward obtained from the change in state, γ represents the discount rate, and α represents the learning rate. Note that γ can take values ​​in the range of 0 < γ ≤ 1 and α can take values ​​in the range of 0 < α ≤ 1. The content of the repair is behavior a t The test results indicate a state s t And so, the state at time t is s t Best course of action a t Learn about it.

[0072] The update formula, represented by equation (1), increases the action value Q of action a if the action value Q of action a with the highest Q value at time t+1 is greater than the action value Q of action a performed at time t, and decreases the action value Q if the opposite is true. In other words, it updates the action value function Q(s,a) so that the action value Q of action a at time t approaches the best action value at time t+1. As a result, the best action value in a given environment is sequentially propagated to the action values ​​in previous environments.

[0073] As described above, when a trained model is generated by reinforcement learning, the model generation unit 52 includes a reward calculation unit 53 and a function update unit 54.

[0074] The reward calculation unit 53 calculates the reward based on the repair details and inspection results. The reward calculation unit 53 calculates the reward r based on the crack propagation suppression effect of the repaired crack C. For example, if the crack propagation suppression effect improves, the reward r is increased by giving a reward of "1", and if the crack propagation suppression effect decreases, the reward r is decreased by giving a reward of "-1". The method for evaluating the crack propagation suppression effect is not particularly limited. For example, the crack propagation suppression effect may be expressed by fracture mechanics parameters or by thermoelastic temperature fluctuations. Examples of fracture mechanics parameters include the effective stress intensity factor range, J value, and energy release rate.

[0075] The function update unit 54 updates the function for determining the repair content according to the reward calculated by the reward calculation unit 53 and outputs it to the trained model storage unit 55. For example, in the case of Q-learning, the action value function Q(s) is expressed by formula (1). t ,a t ) is used as a function to calculate the repair details.

[0076] The learning process described above is repeated. The trained model memory unit 55 stores the action-value function Q(s) updated by the function update unit 54. t ,a t), in other words, it memorizes the trained model.

[0077] Next, we will explain the learning process of the learning device 50 using Figure 20. Figure 20 is a flowchart illustrating the learning process of the learning device 50.

[0078] The learning data acquisition unit 51 acquires the repair details and inspection results as learning data (step S301).

[0079] The model generation unit 52 determines whether the crack propagation suppression effect is improved based on the repair details and inspection results (step S302).

[0080] If the crack propagation suppression effect improves (Step S302: Yes), the reward calculation unit 53 increases the reward (Step S303). If the crack propagation suppression effect decreases (Step S302: No), the reward calculation unit 53 decreases the reward (Step S304).

[0081] The function update unit 54 updates the action value function Q(s) represented by formula (1) stored in the trained model memory unit 55, based on the reward calculated by the reward calculation unit 53. t ,a t Update (step S305).

[0082] The learning device 50 repeatedly executes the steps S301 to S305 described above, and generates the action value function Q(s t ,a t ) is stored as a trained model.

[0083] In the above-described learning device 50, the learned model is stored in a learned model storage unit 55 located outside the learning device 50. However, the learned model storage unit 55 may also be located inside the learning device 50.

[0084] Figure 21 shows the functional configuration of the determination unit 15B of the repair device 10B according to Embodiment 3. The determination unit 15B has an inference device 56. The configuration of the repair device 10B according to Embodiment 3 is not shown, but it has a determination unit 15B instead of the determination unit 15 of the repair device 10. This determination unit 15B can perform determination processing using machine learning. The inference device 56 uses a trained model stored in the trained model storage unit 55 to infer the repair content from the inspection results obtained by the inspection unit 14, and outputs the repair content as an inference result.

[0085] Figure 22 is a diagram showing the configuration of the inference device 56 related to the repair device 10B. The inference device 56 has an inference data acquisition unit 57 and an inference unit 58.

[0086] The inference data acquisition unit 57 acquires the test results as inference data.

[0087] The inference unit 58 uses a trained model to infer the repair details. That is, by inputting the inspection results acquired by the inference data acquisition unit 57 into this trained model, it is possible to infer repair details that are appropriate to the inspection results of the structure S.

[0088] In this embodiment, the repair device 10B used by the model generation unit 52 during training is the same as the repair device 10B targeted for inference by the inference unit 58. However, it is also possible to obtain a trained model from another repair device 10 and output the repair details based on this trained model.

[0089] Next, Figure 23 will be used to explain the process by which the inference device 56 obtains the repair details. Figure 23 is a flowchart illustrating the inference process of the inference device 56.

[0090] The inference data acquisition unit 57 acquires the inspection results as inference data (step S401). The inference unit 58 inputs the inspection results acquired by the inference data acquisition unit 57 as inference data into the trained model stored in the trained model storage unit 55 (step S402) and obtains the repair details as output. The inference unit 58 outputs the obtained repair details as an inference result (step S403).

[0091] The repair device 10B performs the repair using the outputted repair details (step S404). This allows the crack C to be repaired according to the repair details determined in accordance with the inspection results. Since these repair details include at least a repair pattern, one of the following is selected according to the condition of the crack C: a repair pattern (1) that applies pretreatment material 21 and repair material 22, a repair pattern (2) that applies repair material 22, or a repair pattern (3) that does not perform any repair. Furthermore, by using the captured image and directional information of the structure S as inspection results, it becomes possible to determine the appropriate repair details simply by inputting the captured image output by the camera 142 and the output of the gyro sensor equipped in the camera 142 into the learned model.

[0092] In this embodiment, we have described a case where reinforcement learning is applied to the learning algorithm used by the model generation unit 52. However, the learning algorithm used by the model generation unit 52 is not limited to this. In addition to reinforcement learning, supervised learning, unsupervised learning, or semi-supervised learning can also be applied to the learning algorithm.

[0093] Furthermore, the learning algorithm used in the model generation unit 52 can be deep learning, which learns to extract the features themselves, or machine learning can be performed according to other known methods, such as neural networks, genetic programming, functional reasoning programming, or support vector machines.

[0094] In this embodiment, the inference device 56 is provided within the determination unit 15B of the repair device 10B, but the invention is not limited to this example. The learning device 50 and the inference device 56 may be connected to the repair device 10B via a network, for example, and may be separate devices from the repair device 10B. Furthermore, the learning device 50 and the inference device 56 may reside on a cloud server.

[0095] Furthermore, the model generation unit 52 may learn repair content using training data acquired from multiple repair devices 10. The model generation unit 52 may acquire training data from multiple repair devices 10 used in the same area, or it may learn repair content using training data collected from multiple repair devices 10 operating independently in different areas. It is also possible to add or remove repair devices 10 that collect training data as targets during the process. Moreover, the training device 50 that has learned repair content for one repair device 10 may be applied to another repair device 10, and the repair content for that other repair device 10 may be retrained and updated.

[0096] As described above, according to Embodiment 3, it becomes possible to determine the repair content using machine learning. Repair device 10B is an example of a repair content determination device. For example, the determination unit 15B has an inference data acquisition unit 57 that acquires inspection results, and an inference unit 58 that outputs the repair content from the inspection results acquired by the inference data acquisition unit 57 using a trained model for inferring the repair content of the crack C from the inspection results. The repair content output by the inference unit 58 includes at least a repair pattern and may further include materials used to repair the crack C. This trained model is generated by a learning device 50 having, for example, a learning data acquisition unit 51 that acquires learning data including inspection results and repair content, and a model generation unit 52 that generates a trained model for inferring the repair content from the inspection results using the learning data. The model generation unit 52 can learn, for example, repair content that improves the crack propagation suppression effect. Input to the trained model is the inspection result, which may include, for example, a captured image and directional information of the structure S. Furthermore, in the above embodiment, the inspection results were the captured image and directional information of the structure S, but the inspection results input to the trained model may also be values ​​calculated from the captured image and directional information. When values ​​calculated from the captured image and directional information, such as a specific feature value like "the angle φ1 of the crack C relative to the direction of gravity," are input to the trained model, it becomes possible to reliably reflect the influence of that specific feature value on the repair content.

[0097] Embodiment 4. Figure 24 shows the functional configuration of the repair device 10C according to Embodiment 4. The repair device 10C comprises a main body 11, a suction means 12, a driving means 13, a determination unit 15, a repair unit 16, and a control means 41 that controls the suction force by the suction means 12 and the driving force by the driving means 13. The main body 11 of the repair device 10C moves along the structure S by the driving means 13 according to the control of the control means 41, and the pre-processing unit 17, intermediate processing unit 18, and post-processing unit 19 of the repair unit 16 are arranged in processing order with the direction of movement as the leading edge. Specifically, with the direction of movement as the leading edge, they are arranged in the order of pre-processing unit 17, intermediate processing unit 18, and post-processing unit 19. As a result, as the device moves, the pre-processing unit 17, intermediate processing unit 18, and post-processing unit 19 will face the crack C in that order, allowing for efficient repair work.

[0098] As described above, the repair device 10C according to Embodiment 4 includes a determination unit 15 that determines the repair content, including a repair pattern, which indicates whether or not to repair the crack C with a repair material 22 which is a liquid containing particles, and whether or not to apply a pretreatment material 21 into the crack C before applying the repair material 22, based on the inspection results of the crack C that has occurred in the material portion of the structure S to be inspected, and a repair unit 16 that performs the repair of the crack C based on the repair content determined by the determination unit 15, wherein the repair unit 16 includes a pretreatment unit 17 that performs a pretreatment step of applying a pretreatment material 21 into the crack C of the structure S, an intermediate treatment unit 18 that performs an intermediate treatment step of removing the excess pretreatment material 21 applied in the pretreatment step, and a posttreatment unit 19 that performs a posttreatment step of applying the repair material 22 to the crack C. The repair device 10C further comprises an adsorption means 12 that adheres to the structure S and fixes the main body 11 of the repair device 10C to the structure S, a driving means 13 for moving the main body 11 along the structure S, and a control means 41 for controlling the adsorption force by the adsorption means 12 and the driving force by the driving means 13. Furthermore, the pre-processing unit 17, the intermediate processing unit 18, and the post-processing unit 19 of the repair section 16 are arranged in order of processing, with the direction of movement of the repair device 10C by the driving means 13 being the starting point. This makes it possible to improve the efficiency of the repair work.

[0099] The intermediate processing unit 18 can be a suction mechanism for the pretreatment material 21, or industrial oil-absorbing paper that adsorbs the pretreatment material 21.

[0100] Embodiment 5. Figure 25 shows the configuration of the repair content determination system 1 according to Embodiment 5. The repair content determination system 1 includes an inspection device 61, a repair content determination device 64, and a repair device 10D. Hereafter, parts having the same functions as those described in Embodiments 1 to 4 will be denoted by the same reference numerals, and detailed explanations will be omitted.

[0101] The inspection device 61 includes an inspection unit 14, a calculation unit 151, a storage unit 62, and a transmission unit 63. The inspection unit 14 outputs the inspection results to the calculation unit 151. The calculation unit 151 calculates the length L1 and angle φ1 of the crack C based on the inspection results and outputs the length L1 and angle φ1 of the crack C to the storage unit 62. The storage unit 62 stores the length L1 and angle φ1 of the crack C. The transmission unit 63 transmits the length L1 and angle φ1 of the crack C stored in the storage unit 62 to the repair content determination device 64.

[0102] The repair content determination device 64 includes a receiving unit 65, a judgment unit 15D, and an output unit 66. The receiving unit 65 receives the length L1 and angle φ1 of the crack C from the inspection device 61 and outputs them to the repair pattern determination unit 152 and the material used determination unit 153 of the judgment unit 15D, respectively. The judgment unit 15D is the same as the judgment unit 15 except that it obtains the length L1 and angle φ1 of the crack C via the receiving unit 65, and outputs the determined repair content to the output unit 66. The output unit 66 outputs the determined repair content to the repair device 10D. The output unit 66 may output the repair content to the repair device 10D via communication, or it may output a display screen including the repair content, for example. In this case, an operator can perform repairs according to the determined repair content by operating the repair device 10D after viewing the display screen.

[0103] The repair device 10D includes a suction means 12, a driving means 13, a repair unit 16, and a control means 41. The repair device 10D performs repair processing according to the repair content determined by the repair content determination device 64, which is a separate device from the repair device 10D.

[0104] The inspection device 61 and the repair device 10D must be operated at the location where the structure S exists, but the repair content determination device 64 can be installed anywhere as long as it has a communication function.

[0105] As described above, according to the repair content determination system 1 of Embodiment 5, the repair content, including the repair pattern, can be determined from the inspection results by the inspection device 61 and the repair content determination device 64, which is separate from the repair device 10D. For this reason, the repair device 10D does not need to have a function to perform processing for determining the repair content, as long as it has a communication function. With this repair content determination device 64, similar to the repair device 10, it becomes possible to easily determine whether or not the application of the pretreatment material 21 is necessary and whether or not the repair with the repair material 22 is appropriate, regardless of the operator's skill level. In this example, the inspection device 61 is a separate device from the repair device 10D, but the functions of the inspection device 61 may be provided in the repair device 10D.

[0106] Embodiment 6. Figure 26 shows the configuration of the repair content determination system 1E according to Embodiment 6. The repair content determination system 1E includes an inspection device 61E, a repair content determination device 64E, and a repair device 10D.

[0107] The inspection device 61E includes an inspection unit 14, a calculation unit 151A, a storage unit 62E, and a transmission unit 63E. The inspection device 61E according to Embodiment 6 has a calculation unit 151A instead of the calculation unit 151 of the inspection device 61. The calculation unit 151A calculates the length L1 and angle φ1 of the crack C, as well as the opening amount W1. The storage unit 62E stores the length L1, angle φ1, and opening amount W1 of the crack C. The transmission unit 63E transmits the length L1, angle φ1, and opening amount W1 of the crack C to the repair content determination device 64E. The transmission unit 63E also transmits at least the opening amount W1 of the crack C to the repair effect prediction unit 67.

[0108] The repair effect prediction unit 67 predicts the repair effect. The repair effect is expressed as the crack propagation suppression effect. For example, the crack propagation suppression effect may be expressed by fracture mechanics parameters or by thermoelastic temperature fluctuations. Examples of fracture mechanics parameters include the effective stress intensity factor range, J value, and energy release rate. There are no particular limitations on the amount that indicates the repair effect. Here, since the crack opening W1 can be determined from the inspection results of the inspection unit 14, the repair effect prediction unit 67 predicts the repair effect based on the crack opening W1 before and after repair.

[0109] The repair content determination device 64E includes a receiving unit 65, a determination unit 15E, and an output unit 66. The determination unit 15E includes a repair pattern determination unit 152A and a material usage determination unit 153A.

[0110] Figure 27 is a flowchart illustrating the operation of the repair content determination system 1E according to Embodiment 6. The inspection unit 14 of the repair content determination system 1E performs an inspection process (step S10). Based on the inspection results of the inspection unit 14, the calculation unit 151A and the determination unit 15E perform a determination process (step S20). The repair device 10D determines whether or not "repair is needed" based on the result of the determination process (step S30). If "repair is needed" (step S30: Yes), the repair unit 16 of the repair device 10D performs the repair process (step S40).

[0111] When the repair device 10D performs the repair process, the inspection unit 14 of the inspection device 61E performs a post-repair inspection process (step S41). The post-repair inspection process is an inspection process performed after the repair process and is the same as the inspection process in step S10. In addition, the repair effect prediction unit 67 performs a repair effect prediction process (step S42).

[0112] If the result is "No repair needed" (Step S30: No), and after the repair effect prediction process has been performed, the repair device 10D determines whether the repair is complete or not (Step S50). If the repair is not complete (Step S50: No), the control means 41 of the repair device 10D controls the drive means 13 to move the repair device 10D (Step S60), and the process returns to Step S10. If the repair is complete (Step S50: Yes), the repair content determination system 1E terminates the process.

[0113] As described above, the repair content determination system 1E according to Embodiment 6 has, in addition to the functions of the repair content determination system 1, the ability to determine the repair content based on the opening amount W1 of the crack C, and the ability to predict the crack propagation suppression effect of the repair treatment based on the opening amount W1.

[0114] Embodiment 7. Figure 28 shows the configuration of the repair content determination system 1F according to Embodiment 7. The repair content determination system 1F includes an inspection device 61F, a learning device 50, a repair content determination device 64F, and a repair device 10D.

[0115] The inspection device 61F includes an inspection unit 14, a storage unit 62, and a transmission unit 63. In Embodiment 7, machine learning is used to infer repair details from the inspection results. Here, since the input to the trained model is the captured image and directional information, which are the inspection results, the inspection device 61F does not have calculation units 151 and 151A, and the inspection results are stored directly in the storage unit 62. If the input to the trained model is not the inspection results themselves, but values ​​calculated from the inspection results, such as the length L1 of the crack C, the angle φ1, and the opening amount W1, the inspection device 61F may have a function to calculate these values ​​using calculation units 151 and 151A. The transmission unit 63 transmits the inspection results to the repair details determination device 64F and the learning device 50.

[0116] The repair content determination device 64F has the function of inferring the repair content from the inspection results of the inspection device 61F using machine learning. The repair content determination device 64F has a receiving unit 65, a judgment unit 15F, and an output unit 66. The judgment unit 15F has an inference unit 56. The receiving unit 65 receives the inspection results from the inspection device 61F and receives the trained model from the trained model storage unit 55. The receiving unit 65 outputs the received inspection results and trained model to the judgment unit 15F. The inference unit 56 of the judgment unit 15F infers the repair content of the repair device 10D using the input inspection results and trained model. Specifically, the inference unit 56 inputs the inspection results into the trained model and obtains the repair content as output. The inference unit 56 outputs the obtained repair content to the output unit 66. The output unit 66 outputs the repair content to the repair device 10D and the learning device 50.

[0117] The learning device 50 uses the inspection results before and after repair obtained from the inspection device 61F and the repair details obtained from the repair details determination device 64F to generate a trained model for obtaining repair details from the inspection results, and stores the generated trained model in the trained model storage unit 55.

[0118] As described above, the repair content determination system 1F according to Embodiment 7 can determine the repair content using machine learning. Here, since the input to the trained model is the inspection result as is, the repair content determination system 1F does not necessarily have to have the configuration of calculation units 151 and 151A. In Embodiment 7 as well, the hardware on which each function of the repair content determination system 1F is provided can be changed as appropriate. For example, the learning device 50 may be provided in the inspection device 61F, the repair device 10D, or the repair content determination device 64F. Also, the inspection device 61F and the repair device 10D may be an integrated device.

[0119] Embodiment 8. Figure 29 shows the configuration of the repair content determination system 1G according to Embodiment 8. The repair content determination system 1G includes a repair device 10G and a repair content determination device 64. The repair device 10G is an unmanned mobile unit having inspection and repair functions.

[0120] The repair device 10G comprises an inspection device 61, a receiving unit 68, a repair unit 16, a control means 41G, a driving means 13, a suction means 12, and a route information storage unit 69. The route information storage unit 69 stores route information indicating the movement path within the structure S to be inspected and repaired. The control means 41G moves the repair device 10G along the movement path of the structure S by controlling the driving means 13 and the suction means 12 according to the route information stored in the route information storage unit 69.

[0121] The repair device 10G transmits the inspection results from the inspection device 61 to the repair content determination device 64, and the repair unit 16 performs the repair according to the repair content received from the repair content determination device 64.

[0122] Figure 30 shows an example of a movement path of the repair device 10G according to Embodiment 8. For example, as shown by the solid arrows in Figure 30, the movement path to the structure S is predetermined. In this case, the repair device 10G inspects the structure S while moving along this movement path and performs a judgment process based on the inspection results. If the judgment process finds a crack C to be repaired, the repair device 10G performs the repair process and then resumes moving along the movement path. In this case, the operation of the repair device 10G will be as shown in Figure 14 or Figure 27.

[0123] In the example shown in Figure 30, the repair device 10G moves along a predetermined path from the starting point 5-1 to the goal point 5-2, performing inspection and judgment processes, and also performing repair processes at points 6-1, 6-2, and 6-3 where cracks C to be repaired are found. Upon reaching the goal point 5-2, the repair device 10G automatically returns to the starting point 5-1. For example, as shown in Figure 30, the repair device 10G can return from the goal point 5-2 to the starting point 5-1 via the shortest path.

[0124] Alternatively, the repair device 10G may perform inspection and judgment processing while moving along a predetermined movement path, and if a crack C to be repaired is found, it may record the location information of the points 6-1, -2, and 6-3 where the crack C is occurring. In this case, no repair processing may be performed while moving from the starting point 5-1 to the goal point 5-2, and repair processing may be performed at the recorded points 6-1, 6-2, and 6-3 while returning from the goal point 5-2 to the starting point 5-1. Figure 31 is a diagram showing another example of the path taken by the repair device 10G according to Embodiment 8 to return from the goal point 5-2 to the starting point 5-1. In this embodiment, the repair device 10G is equipped with an inspection device 61 and a repair unit 16, but it is also possible to use a separate inspection device 61 from the repair device 10G to perform the inspection and repair processing separately. Even in this case, if the inspection device 61 and the repair device 10G are mounted on an unmanned mobile vehicle, inspection and repair processes can be performed along a predetermined travel route, thereby reducing working time.

[0125] Here, we will describe an example of a hardware configuration. The repair content determination devices 64, 64E, and 64F described above are implemented by a computer system, for example. The repair content determination devices 64, 64E, and 64F may be implemented by one computer system or by multiple computer systems. For example, the repair content determination devices 64, 64E, and 64F may be implemented by a cloud system. In a cloud system, the separation of the computer system hardware and devices such as servers for each function can be arbitrarily configured. For example, one computer system may have the functions of multiple devices, or multiple computer systems may have the functions of one device.

[0126] This section describes an example configuration of a computer system that implements the repair content determination devices 64, 64E, and 64F. Figure 32 shows an example configuration of a computer system that implements the repair content determination devices 64, 64E, and 64F. As shown in Figure 32, this computer system comprises a control unit 101, an input unit 102, a storage unit 103, a display unit 104, a communication unit 105, and an output unit 106, which are connected via a system bus 107.

[0127] In Figure 32, the control unit 101 is, for example, a CPU (Central Processing Unit). The control unit 101 executes a repair content determination program that describes each process to be performed by the repair content determination devices 64, 64E, and 64F of this embodiment. The input unit 102 is, for example, a keyboard, mouse, etc., and is used by the user of the computer system to input various information. The storage unit 103 includes various types of memory such as RAM (Random Access Memory) and ROM (Read Only Memory), and storage devices such as a hard disk, and stores the program to be executed by the control unit 101, necessary data obtained in the process of processing, etc. The storage unit 103 is also used as a temporary storage area for the program. The display unit 104 is, for example, an LCD (Liquid Crystal Display) and displays various screens to the user of the computer system. The communication unit 105 is a communication circuit, etc., that performs communication processing. The communication unit 105 may be composed of multiple communication circuits corresponding to multiple communication methods. The output unit 106 is an output interface that outputs data to external devices such as printers and external storage devices.

[0128] Note that Figure 32 is an example, and the configuration of the computer system is not limited to the example in Figure 32. For example, the computer system does not have to have an output unit 106. Also, if the repair content determination devices 64, 64E, and 64F are implemented by multiple computer systems, not all of these computer systems have to be the computer system shown in Figure 32. For example, some computer systems do not have to have at least one of the display unit 104, output unit 106, and input unit 102 shown in Figure 32.

[0129] Here, we will describe an example of the operation of the computer system until the repair content determination program, which describes the processing of the repair content determination devices 64, 64E, and 64F of this embodiment, becomes executable. In a computer system with the above configuration, for example, the repair content determination program is installed in the storage unit 103 from a CD-ROM or DVD-ROM set in a CD (Compact Disc)-ROM drive or DVD (Digital Versatile Disc)-ROM drive (not shown). When the repair content determination program is executed, the repair content determination program read from the storage unit 103 is stored in the area that becomes the main memory of the storage unit 103. In this state, the control unit 101 executes the processing of the repair content determination devices 64, 64E, and 64F of this embodiment according to the repair content determination program stored in the storage unit 103.

[0130] In the above description, a program describing the processing in the repair content determination devices 64, 64E, and 64F is provided using a CD-ROM or DVD-ROM as the recording medium. However, the system is not limited to this, and depending on the configuration of the computer system, the capacity of the program to be provided, a program provided via a transmission medium such as the Internet via the communication unit 105 may be used, for example.

[0131] The repair content determination program of this embodiment causes the computer to perform the following steps: acquire inspection results of cracks C occurring in the material portion of the structure S to be inspected; determine repair content including a repair pattern that indicates whether or not to repair the crack C with a repair material 22 which is a liquid containing particles, and whether or not to apply a pretreatment material 21 into the crack C before applying the repair material 22 if the repair pattern indicates that the repair will be performed with the repair material 22 and the pretreatment material 21 will be applied; apply the pretreatment material 21 into the crack C if the repair pattern indicates that the repair will be performed with the repair material 22 and the pretreatment material 21 will be applied; remove any excess of the applied pretreatment material 21 if the repair pattern indicates that the repair will be performed with the repair material 22 and the pretreatment material 21 will be applied; and apply the repair material 22 into the crack C if the repair pattern indicates that the repair will be performed with the repair material 22.

[0132] The receiving unit 65 shown in Figures 25, 26, 28, and 29 is implemented by the communication unit 105 shown in Figure 32, the determination units 15D, 15E, and 15F shown in Figures 25, 26, 28, and 29 are implemented by the control unit 101 shown in Figure 32, and the output unit 66 shown in Figures 25, 26, 28, and 29 is implemented by at least one of the communication unit 105 and the output unit 106 shown in Figure 32.

[0133] The learning device 50 and the inference device 56 are also implemented by one or more computer systems, similar to the repair content determination devices 64, 64E, and 64F. The programs for the learning device 50 and the inference device 56 to perform the operations described in this embodiment are provided by a storage medium, transmission medium, etc., and installed in the computer system, similar to the repair content determination program described above. This enables the operations of the learning device 50 and the inference device 56 described above. Alternatively, the repair content determination devices 64, 64E, and 64F and the learning device 50 and the inference device 56 may be implemented by a single computer system. In this case, the receiving units 65, 68 and the transmitting units 63, 63E may not be provided, and these functions are performed by data exchange within the computer system.

[0134] Note that the functional divisions for each device are just one example, and the functional divisions for each device are not limited to the illustrated example, as long as the repair content determination systems 1, 1E, 1F, and 1G can perform the operations described above.

[0135] Figure 33 shows an example of a processing circuit 110 for realizing each function of the repair device 10 or the repair content determination system 1. The determination units 15, 15A, and 15B of the repair devices 10, 10A, 10B, and 10C, the calculation units 151 and 151A of the inspection devices 61 and 61E, and the control means 41 and 41G of the repair devices 10C, 10D, and 10G are each realized by the processing circuit 110. These processing circuits 110 may be dedicated hardware or control circuits using a CPU.

[0136] When the above processing circuit 110 is implemented using dedicated hardware, the processing circuit 110 may be 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 thereof.

[0137] When the above processing circuit 110 is implemented using a control circuit with a CPU, the control circuit comprises a processor and memory. The processor is a CPU, also known as a processing unit, arithmetic unit, microprocessor, microcomputer, or DSP (Digital Signal Processor). Memory includes, for example, non-volatile or volatile semiconductor memory such as RAM, ROM, flash memory, EPROM (Erasable Programmable ROM), EEPROM (Registered Trademark) (Electrically EPROM), magnetic disks, flexible disks, optical disks, compact disks, minidiscs, DVDs, etc.

[0138] When the above processing circuit 110 is implemented by a control circuit, it is implemented by the processor reading and executing a program corresponding to the processing of each component stored in memory. Furthermore, memory is also used as temporary memory for each process executed by the processor.

[0139] Embodiment 9. Embodiments 1 to 8 described techniques for determining the content of repairs to cracks C in a structure S, based on the premise of a repair treatment in which a repair material 22, which is a liquid containing particles, is applied to the cracks C that have occurred in the structure S. Embodiments 9 and onward describe techniques for determining a repair plan that uses a wider range of methods to repair cracks C, not just repair treatment using the repair material 22. More specifically, while Embodiments 1 to 8 described a method for determining the content of the repairs to be carried out, Embodiments 9 and onward describe a method for determining a repair plan that includes not only the content of the repairs but also the timing of the repairs.

[0140] Figure 34 shows the functional configuration of the repair plan determination device 200 according to Embodiment 9. The repair plan determination device 200 includes an inspection result acquisition unit 201, an input unit 202, a database 203, a repair plan determination unit 204, and an output unit 205.

[0141] The inspection result acquisition unit 201 acquires inspection results indicating the state of cracks C that have occurred in the structure S. The inspection result acquisition unit 201 outputs the acquired inspection results to the input unit 202. The inspection result acquisition unit 201 may acquire inspection results from outside the repair plan determination device 200, or it may have a function to perform inspections. If the inspection result acquisition unit 201 has a function to perform inspections, for example, the inspection result acquisition unit 201 has a suction means 12 for fixing the main body 11 to the structure S, a driving means 13 for moving the main body 11 along the structure S, and an inspection unit 14 for inspecting cracks C in the structure S while moving the main body 11 along the structure S, as shown in the repair device 10 in Figure 1.

[0142] Figure 35 is a flowchart illustrating the operation of the inspection result acquisition unit 201 shown in Figure 34. Note that Figure 35 shows the case where the inspection result acquisition unit 201 has the function of performing inspections.

[0143] The inspection result acquisition unit 201 sets the inspection location within the structure S (step S501). The inspection location may be set, for example, by the user using an input means, or by reading data that has been predetermined for the inspection location. The inspection result acquisition unit 201 measures the crack C at the set inspection location (step S502) and acquires measurement information indicating the measurement result. The measurement information acquired by the inspection result acquisition unit 201 varies depending on the inspection means that the inspection result acquisition unit 201 has. For example, if the inspection result acquisition unit 201 has the functions of the inspection unit 14 shown in Figure 3, the measurement information may include, for example, information indicating the depth inside the crack C acquired using the LiDAR scanner 141, and images of the surface of the structure S taken using the camera 142.

[0144] The inspection result acquisition unit 201 calculates the location of the crack C in the structure S, the length of the crack C, and the surface angle (the angle of the crack C relative to the surface of the structure S) from the measurement information acquired in step S502 (step S503). Note that the location of the crack C, the length of the crack C, and the surface angle are examples of information indicating the state of the crack C. The inspection result acquisition unit 201 outputs the calculated information indicating the location, length, and surface angle of the crack C as an inspection result indicating the state of the crack C (step S504).

[0145] Here, we will explain the "angle relative to the surface." Figure 36 is an explanatory diagram of the angle relative to the surface. The angle relative to the surface is the angle that the crack C makes with respect to the surface of the structure S in which the crack C occurs, and is different from the "angle of the crack C" mentioned above, which is "the angle between the depth direction D2 of the crack C and the direction of gravity D1." Here, the crack C may have a simple shape as shown in Figure 2, or it may be bent as shown in Figure 36. In the case of a bent shape, the "angle relative to the surface" is the angle Θ made between the line connecting the opening and tip of the crack C and the surface of the structure S, as shown in Figure 36. For example, if the structure S is a bridge, when objects are driven on or off the part in which the crack C occurs, a tensile load is generated around the crack C, as shown by the arrow in Figure 36, and the crack C may propagate. The propagation speed of the crack C at this time, if the size of the crack C is the same, will vary depending on the angle Θ of the crack C with respect to the surface of the structure S, and will be faster the closer the angle Θ is to 90 degrees. Therefore, the angle relative to the surface can be used as information indicating the state of the crack C.

[0146] In this example, the inspection result acquisition unit 201 is assumed to have the function of performing inspections. However, if the inspection result acquisition unit 201 does not have the function of performing inspections, it may acquire the inspection results themselves from an external source and output the acquired inspection results, or it may acquire measurement information from an external source and calculate the inspection results from the acquired measurement information.

[0147] Returning to the explanation of Figure 34, the input unit 202 receives input information and outputs the received input information to the repair plan determination unit 204. The input information is the information that the repair plan determination unit 204 uses to formulate a repair plan.

[0148] Figure 37 shows an example of input information 70 received by the input unit 202 shown in Figure 34. The input information 70 includes shape information 71 indicating the shape of the structure S, inspection results 72, inspection and repair budget 73, and parameters 74 for estimating the costs incurred if the structure becomes unusable. The shape information 71 of the structure S includes information indicating the length, width, cross-sectional shape, support length, material, load, etc. of the structure S to be inspected. The shape information 71 of the structure S may be, for example, CAD (Computer Assisted Drafting) data. The inspection results 72 are information output by the inspection result acquisition unit 201 and indicate the state of cracks C that have occurred in the target structure S. The inspection and repair budget 73 is the cost available for inspection and repair, and is, for example, information shown in terms of annual amounts. Parameter 74 for estimating the costs incurred when a structure becomes unusable can be any information that allows for the estimation of the costs incurred when a structure becomes unusable, for example, the length of time that structure S is unusable and the cost per unit time, or the costs incurred when structure S becomes unusable itself. Here, "costs" can include the costs of providing alternative means required due to the unusability of structure S, and losses resulting from the unusability of structure S, such as the estimated amount of revenue that would have been expected from the operation of structure S if that revenue is not received. In other words, costs include at least one of costs and losses.

[0149] Returning to the explanation of Figure 34, the database 203 holds information that the repair plan determination unit 204 refers to when formulating a repair plan, and can output the held information to the repair plan determination unit 204. Specifically, the database 203 includes information that associates multiple candidate repair methods included in the repair plan with the state of cracks C that can be repaired using each repair method. The database 203 can also hold information indicating the repair time and cost required when repairing using each repair method, and the service life of the structure S when repairing using each repair method.

[0150] Figure 38 shows an example of the information held in the database 203 shown in Figure 34. This database 203 includes "crack length," "angle to surface," "repair method," "repair time," "cost," and "service life after repair." "Crack length" is the length of the crack C, which may be the length of the crack line as described above, or, if the crack line is not a straight line, the length of the approximate straight line of the crack line. "Angle to surface" is the angle that the crack C makes with respect to the surface of the structure S, as explained using Figure 36. Note that "crack length" and "angle to surface" are examples of information indicating the state of the crack C. "Repair method" is information indicating the type of repair method applicable to the state of the crack C indicated by "crack length" and "angle to surface." The repair method can be represented as numerical information as shown in Figure 38, in which case each number is pre-associated with a repair method such as simple repair or large-scale repair. Simple repairs are minor repairs carried out during inspections and refer to repairs that can be done within the scope of the equipment and devices installed at the time of inspection. Specifically, when inspecting cracks C on the surface of a bridge structure S, simple repairs include repairs using repair materials 22 performed on-site and replacement of parts that can be done on-site. Major repairs, on the other hand, are repairs carried out separately from inspections and refer to repairs that cannot be handled within the scope of the equipment and devices used at the time of inspection. For example, this includes repairs carried out using auxiliary devices such as scaffolding. Specifically, in the case of a bridge structure S, major repairs include adding new steel materials or reinforcing materials to repair rusted or corroded steel structures, and replacing bearings. "Repair time" is information indicating the time required to carry out repairs using each repair method. "Cost" is information indicating the cost of repairs using each repair method. "Service life after repair" is information indicating the service life of the structure S in years after repairs have been carried out using each repair method. Generally speaking, for structures in the same condition, a large-scale repair will extend their service life and allow them to withstand long-term use compared to a simple repair.

[0151] Note that the data structure of database 203 shown in Figure 38 is just one example, and the information held in database 203 can be any information that represents similar content, or information that can generate similar content.

[0152] Returning to the explanation of Figure 34, the repair plan determination unit 204 creates a repair plan based on the input information 70 received by the input unit 202 and the information held in the database 203. This plan combines the simple repairs performed during inspections corresponding to the inspection results 72 included in the input information 70, the simple repairs performed during subsequent inspections, and the major repairs. At this time, the repair plan determination unit 204 determines the repair methods included in the repair plan, the timing of each repair, etc., so as to satisfy at least one of the following: minimizing the total cost or leveling out the costs. The repair plan determination unit 204 outputs the determined repair plan to the output unit 205. It is desirable for the repair plan determination unit 204 to determine the repair plan so that the costs are leveled out for each budgeting period, for example, each year, within the period covered by the repair plan.

[0153] Figure 39 is a flowchart illustrating the operation of the repair plan determination unit 204 according to Embodiment 9. The repair plan determination unit 204 determines whether or not repair of the crack C is necessary based on the input information 70 and the database 203 (step S511). The determination of whether or not repair of the crack C is necessary can be made based on the shape information 71 and inspection results 72 included in the input information 70. Specifically, based on the shape and material information of the target structure S, the state of the crack C that would lead to failure of the structure S if not repaired is predetermined. For example, the "state of the crack C" here refers to the length, position, angle, etc. Then, the repair plan determination unit 204 determines that repair is necessary if the state of the crack C indicated by the inspection results matches the predetermined state of the crack C, and determines that repair is unnecessary otherwise. The repair plan determination unit 204 may simply pre-determine the area requiring repair based on the length of the crack C and determine whether or not repair is necessary, or it may determine whether or not repair is necessary by combining multiple conditions. In this case, the area requiring repair may be changed for each location where the crack C occurs.

[0154] If crack C does not require repair (step S511: No), the repair plan determination unit 204 estimates the amount of crack C propagation (step S512). The repair plan determination unit 204 can generate parameters indicating the propagation of crack C, such as the crack propagation rate and the stress intensity factor range, as estimation results. Based on the estimation results, the repair plan determination unit 204 determines the timing of the next inspection, proposes the determined inspection timing (step S513), and terminates the process. Specifically, the repair plan determination unit 204 predicts when the structure S will fail based on the predicted crack C propagation rate, and determines the timing of the next inspection so that it is before the predicted time when the structure S will fail.

[0155] If repair of crack C is necessary (step S511: Yes), the repair plan determination unit 204 determines whether or not simple repair is possible (step S514). Specifically, the repair plan determination unit 204 checks the information held in the database 203 to see if there is a simple repair method that can be applied to crack C in the condition indicated by the inspection result 72 included in the input information 70. The repair plan determination unit 204 then determines that simple repair is possible if a simple repair method applicable to crack C indicated by the inspection result 72 is included in the database 203, and determines that simple repair is not possible if a simple repair method applicable to crack C indicated by the inspection result 72 is not included in the database 203.

[0156] If simple repairs are not possible (Step S514: No), the repair plan determination unit 204 proposes major repairs (Step S515) and terminates the process. If simple repairs are possible (Step S514: Yes), the repair plan determination unit 204 proposes a repair plan that combines simple repairs and major repairs, taking into account the life extension period provided by simple repairs (Step S516), and terminates the process. Specifically, based on the input information 70 and the information held in the database 203, the repair plan determination unit 204 creates a repair plan that combines simple repairs at the time of inspection corresponding to the inspection results 72 included in the input information 70, simple repairs at subsequent inspections (i.e., at the next inspection and beyond), and major repairs, in order to satisfy at least one of the following: minimizing the total cost and leveling out the costs of inspections and repairs.

[0157] Here, we will explain the details of step S516. Figure 40 is a flowchart illustrating the details of step S516 in Figure 39. The repair plan determination unit 204 first extracts usable simple repair methods from the information held in the database 203 (step S521). Here, usable simple repair methods refer to simple repair methods that can be applied to cracks C in the condition indicated by the inspection results 72 included in the input information 70. The symbols representing each of the extracted simple repair methods are i1, i2, ... The repair plan determination unit 204, in the case of "replacement of parts", counts the number of cracks C occurring in each part and can select parts with a number of cracks C equal to or greater than a predetermined threshold for replacement. If the number of extracted simple repair methods is n, the repair plan determination unit 204 extracts the longest service life among the service lives after repair of the extracted simple repair methods i1 to in, and sets the extracted service life as the maximum service life Ymax (step S522).

[0158] The repair plan determination unit 204 extracts the year with the most budget from the inspection date to the maximum service life Ymax as the maximum budget year Yrich, and sets the time after the maximum budget year Yrich as the time for major repairs (step S523). The repair plan determination unit 204 proposes the simplest and least expensive repair method among the simple repair methods with a service life of Yrich or more (step S524), and ends the process.

[0159] Note that the information stored in the database 203 can include, as simple repair methods, a method of applying the repair material 22 to the crack C and a method of replacing parts. As a specific example, consider the case where the database 203 stores information indicating a method of applying the repair material 22 to the crack C and a method of replacing parts as simple repair methods. Let Y1 be the service life after repair by applying the repair material 22 to the crack C, and Y2 be the service life after repair by replacing parts. Generally, even if the repair material 22 is applied, the service life will be shorter if the product with the crack C is continued to be used, so Y1 < Y2.

[0160] In this case, the maximum service life Ymax = Y2. The repair plan determination unit 204 extracts the year with the most budget from the inspection date to Y2 years later as the maximum budget year Yrich, and sets the maximum budget year Yrich as the time for major repairs. Here, if Y1 < Yrich, the repair plan determination unit 204 selects the repair method of replacing parts as the simple repair method at the time of inspection so that it can withstand until Y2 years later, and plans major repairs after Yrich years, thereby equalizing the costs. Also, if Yrich < Y1 < Y2, the repair plan determination unit 204 selects the method of applying the repair material 22, which is the least expensive method among the repair method of replacing parts and the repair method of applying the repair material 22, as the simple repair method at the time of inspection, and plans major repairs after Yrich years to equalize the costs.

[0161] Note that in the method shown in Figure 40, for simplicity, the case where simple repairs are carried out multiple times is omitted. However, the repair plan determination unit 204 may determine the repair plan based on the service life when simple repairs are carried out multiple times.

[0162] Furthermore, the repair plan determination unit 204 can treat the case of "not performing simple repairs during inspection" as a simple repair method by using the "parameters for estimating the costs incurred when the structure S becomes unusable" included in the input information 70. Specifically, the repair plan determination unit 204 estimates the costs incurred when the structure S becomes unusable based on the "parameters for estimating the costs incurred when the structure S becomes unusable" included in the input information 70. The repair plan determination unit 204 can then use the estimated cost as the "cost" of the simple repair method of "not performing simple repairs during inspection". In this case, the "repair time" for the simple repair method of "not performing simple repairs during inspection" can be set to 0, and the "service life after repair" can be the same as before the repair. In addition, the simple repair method of "not performing simple repairs during inspection" may be applicable regardless of the state of the crack C, or constraints may be set according to the state of the crack C.

[0163] Returning to the explanation of Figure 34, the output unit 205 outputs the repair plan determined by the repair plan determination unit 204 to the user. There are no particular restrictions on the means by which the output unit 205 outputs the repair plan, but as a general output method, an example using a display screen will be described. The output unit 205 generates a display screen showing the contents of the repair plan determined by the repair plan determination unit 204, and outputs the generated display screen using a display device.

[0164] If the repair plan determination unit 204 generates a repair plan that proposes the next inspection date in step S513 of Figure 39, the output unit 205 can output a display screen, for example, as shown in Figure 41. Figure 41 is a diagram showing a first example of a display screen output by the output unit 205 shown in Figure 34. If it is determined that repair of crack C is not currently necessary, the output unit 205 can generate a display screen that includes a message indicating that repair is not currently necessary and the next inspection date determined in step S513 of Figure 39. The display screen generated at this time may also include the estimated result of crack C propagation in step S512 of Figure 39.

[0165] If the repair plan determination unit 204 generates a repair plan proposing a large-scale repair in step S515 of Figure 39, the output unit 205 can output a display screen, for example, as shown in Figure 42. Figure 42 is a diagram showing a second example of the display screen output by the output unit 205 shown in Figure 34. If it is determined that repair of crack C is currently necessary and that simple repair is not possible, the output unit 205 can generate a display screen that includes the fact that the repair to be carried out now is a large-scale repair and the timing of the large-scale repair. Here, the timing of the large-scale repair is shown as a future repair plan, but the display screen may also include repair plans after the large-scale repair.

[0166] If the repair plan determination unit 204 generates a repair plan that proposes a combination of simple repair and major repair in step S516 of Figure 39, the output unit 205 can output a display screen, for example, as shown in Figure 43. Figure 43 is a diagram showing a third example of the display screen output by the output unit 205 shown in Figure 34. If it is determined that repair of crack C is currently necessary and that simple repair can be carried out, the output unit 205 can generate a display screen that includes the fact that the repair currently being carried out is a simple repair and the timing of the next major repair as part of the future repair plan.

[0167] In Figure 43, an example of a display screen is shown that includes only the timing of the next major repair as part of the future repair plan. However, the repair plan determination unit 204 may generate a repair plan that includes multiple major repairs, multiple inspections, and multiple minor repairs, and the output unit 205 may output a display screen that includes multiple repairs, inspections, etc. Figure 44 is a diagram showing a fourth example of the display screen output by the output unit 205 shown in Figure 34. In the example shown in Figure 44, the future repair plan is shown, which includes the timing of multiple major repairs and the timing of multiple inspections. Here, "inspection and minor repair" means that minor repairs will be carried out at the same time as the inspection, and "inspection" alone means that minor repairs will not be carried out at the same time as the inspection.

[0168] Figure 45 is a diagram illustrating the effects of Embodiment 9. The upper part of Figure 45 shows a repair plan without cost leveling as a comparative example, and the lower part of Figure 45 shows an example of a repair plan determined by the repair plan determination device 200 according to Embodiment 9. In the comparative example, the cost for FY2024 is high due to the overlapping of large-scale repairs. In contrast, the repair plan determination device 200 determines a repair plan in order to level out costs according to the budget for each fiscal year. Specifically, by performing simple repairs at the same time as inspection #2, the service life of structure S is extended, making it possible to postpone the implementation of large-scale repair #2, and the costs are leveled out by shifting some of the costs of the large-scale repairs that were concentrated in FY2024 to FY2026.

[0169] As described above, according to Embodiment 9, a repair plan determination device 200 can be provided. This repair plan determination device 200 includes an inspection result acquisition unit 201 that acquires inspection results indicating the state of cracks C occurring in a structure S, an input unit 202 that accepts input information 70 including inspection results 72, shape information 71 indicating the shape of the structure, a budget 73 for inspection and repair of the structure S, and parameters 74 for estimating the costs incurred when the structure becomes unusable, a crack repair method including simple repairs carried out simultaneously with the inspection of the structure S and large-scale repairs carried out separately from the inspection, and cracks C that can be repaired by each repair method. The device includes a database 203 that stores information relating the condition of the structure, the time required for repair work, the repair cost, and the service life after repair; a repair plan determination unit 204 that, based on input information 70 and the information stored in the database 203, creates a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure S; and an output unit 205 that outputs the repair plan. The repair plan determination device 200 determines the repair plan by combining simple repairs corresponding to the inspection results, simple repairs at subsequent inspections, and major repairs, making it possible to create a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure S. Furthermore, by using input information 70 that includes parameters 74 for estimating the costs incurred when the structure becomes unusable, it becomes possible to treat cases where repairs are not performed at the time of inspection as a repair method. Here, the costs of inspection and repair include the costs associated with the "no repair" repair method, that is, the costs incurred when structure S becomes unusable due to the lack of repair, that is, the costs of providing alternative means because structure S is unusable, and the estimated loss if the expected revenue is lost due to structure S being unusable. Furthermore, total costs refer to the total amount of costs associated with inspection and repair, and as mentioned above, may also include the costs associated with the "no repair" repair method.

[0170] Furthermore, the repair plan determination unit 204 can create a repair plan that includes multiple minor repairs before major repairs are carried out, based on the input information 70 and the information held in the database 203. By carrying out multiple minor repairs, the service life of the structure S can be further extended, which increases the flexibility in adjusting the timing of major repairs and makes it easier to level out costs over an even longer period.

[0171] Furthermore, the repair plan determination unit 204 can estimate the costs incurred during the period when the structure S is unusable, based on parameters 74 for estimating the costs incurred when the structure becomes unusable. The estimated costs are then used as the costs if simple repairs are not carried out, and the case where simple repairs are not carried out is used as a candidate for the repair method to create a repair plan.

[0172] Furthermore, it is desirable that database 203 has a function to periodically update the information it holds.

[0173] Furthermore, the repair methods stored in the database 203 may include, as simple repair methods, a method of applying repair material 22 or a method of replacing parts. The inspection result acquisition unit 201 acquires inspection results including the number of cracks C that have occurred in the parts constituting the structure S, and the repair plan determination unit 204 can create a repair plan to replace parts as a simple repair if the number of cracks C per part is greater than or equal to a threshold.

[0174] Furthermore, according to Embodiment 9, a repair plan determination system can be provided. The functions of the repair plan determination device 200 can also be realized as a repair plan determination system. The repair plan determination system can be realized using one or more computer systems. The repair plan determination system receives input information 70 which includes inspection results 72 indicating the state of cracks C occurring in the structure S, shape information 71 indicating the shape of the structure S, a budget 73 for inspection and repair of the structure S, and parameters 74 for estimating the costs incurred when the structure becomes unusable. Based on the input information 70, the system can output a repair plan that satisfies at least one of the following: minimizing the total cost and leveling the costs of inspection and repair of the structure S.

[0175] Furthermore, according to Embodiment 9, a method for determining a repair plan can be provided. The method for determining a repair plan includes the steps of: obtaining inspection results 72 indicating the state of cracks C in a structure S; receiving input information 70 including the inspection results 72, shape information 71 indicating the shape of the structure S, a budget 73 for inspection and repair of the structure S, and parameters 74 for estimating the costs incurred if the structure becomes unusable; and determining the location, length, and The process includes the steps of creating a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of structure S, by combining simple repairs performed at the time of inspection when inspection results 72 are obtained, simple repairs performed at subsequent inspections, and major repairs, based on angle conditions, repair time and costs incurred when repairs are carried out using each repair method, a database 203 that holds information indicating the service life of the structure when repairs are carried out using each repair method, and input information 70, and outputting the repair plan.

[0176] Embodiment 10. Figure 46 shows the functional configuration of the repair plan determination device 200A according to Embodiment 10. The repair plan determination device 200A includes an inspection result acquisition unit 201A, an input unit 202, a database 203A, a repair plan determination unit 204A, and an output unit 205. The following mainly describes the parts that differ from Embodiment 9.

[0177] The inspection result acquisition unit 201A acquires inspection results in the same manner as the inspection result acquisition unit 201 of Embodiment 9, following the flow shown in Figure 35. At this time, while the inspection result acquisition unit 201 calculates the position, length, and surface angle of the crack C from the measurement information, the inspection result acquisition unit 201A calculates, in addition to the position, length, and surface angle of the crack C, the angle φ1 that the crack C makes with respect to the gravity direction D1 and the opening amount of the crack C.

[0178] Figure 47 shows an example of input information 70A received by the input unit 202 shown in Figure 46. The input information 70A includes shape information 71 of the structure S, inspection results 72A, inspection and repair budget 73, and parameters 74 for estimating the costs incurred if the structure S becomes unusable. The information included in the inspection results 72A includes, in addition to the information included in the inspection results 72, the angle φ1 made by the crack C with respect to the gravity direction D1 and the opening amount of the crack C.

[0179] Figure 48 is an explanatory diagram of the angle φ1 of the crack C with respect to the direction of gravity D1. The "angle φ1 of the crack C with respect to the direction of gravity D1" corresponds to the "angle φ1 of the crack C" and the "angle φ1 of the depth direction D2 of the crack C with respect to the direction of gravity D1" mentioned above. Here, as shown in Figure 48, when the crack C is bent, the depth direction D2 of the crack C can be the direction along the fracture surface at the entrance of the crack C. This is because the ease with which the liquid repair material 22 can remain inside the crack C changes depending on the angle of the fracture surface near the entrance with respect to the direction of gravity D1, and the repair material 22 suitable for use changes accordingly. In embodiments 1 to 9 as well, when the crack C is bent, the "angle φ1 of the crack C" and the "angle φ1 of the depth direction D2 of the crack C with respect to the direction of gravity D1" can be the angle between the depth direction D2 of the crack C, which is the direction along the fracture surface at the entrance of the crack C, and the direction of gravity D1.

[0180] Figure 49 shows a first example of the information held in the database 203A shown in Figure 46. This database 203A includes "crack length", "angle relative to the surface", "angle of the crack with respect to gravity", "amount of crack opening", "repair method", "repair time", "cost", and "service life after repair". Database 203A further includes the angle φ1 of the crack C with respect to gravity D1 and the amount of crack opening as information indicating the state of the crack C. Furthermore, by using "angle of the crack with respect to gravity" and "amount of crack opening", the "repair method" included in database 203A can include methods such as applying pretreatment material 21 and repair material 22, as described in Embodiments 1 to 8, and applying repair material 22 without applying pretreatment material 21. If the "repair method" in database 203A is a method of applying pretreatment material 21 and repair material 22, or a method of applying repair material 22 without applying pretreatment material 21, then each can be treated as a different repair method for each material used for repair. In this case, for example, the symbol for "repair method" will include information that identifies the material used for repair, in addition to the repair method.

[0181] The repair plan determination unit 204A performs the same processing as in Figures 39 and 40, but when determining whether simple repair is possible in step S514, and when extracting a simple repair method that can be used in step S521, it uses "angle of the crack with respect to gravity" and "amount of crack opening" in addition to "crack length" and "angle relative to the surface" contained in the inspection result 72A and database 203A, respectively. This makes it possible to select the method of applying the repair material 22 as a simple repair method according to the state of the crack C. Furthermore, by assigning a symbol for the "repair method" in database 203A to each material used for repair, the repair plan determination unit 204A can perform simple repair by applying the repair material 22 to the crack C using a material that matches the state of the crack C, specifically the length of the crack C, the angle of the crack C, and the amount of crack opening C.

[0182] Figure 50 shows a second example of the information held in database 203A shown in Figure 46. In addition to the information shown in the first example in Figure 49, database 203A further includes "material of the structure" and "applicability determined based on constraints." Some repair methods may not be applicable depending on the material of the structure S in the area where the crack C occurs, the combination of the pretreatment material 21 and repair material 22, and the state of the crack C. For example, if the angle of the crack C with respect to the gravity direction D1 is small, it may not be possible to apply the low-viscosity repair material 22, and depending on the material of the structure S, the repair material 22 may not adhere to the surface of the structure S and may not be able to perform its intended function. Therefore, in the second example shown in Figure 50, information on "material of the structure" and information on the state of the crack C in each record and "applicability determined based on constraints" determined based on "material of the structure" are further included.

[0183] In the example shown in Figure 50, the database 203A is responsible for storing information on "applicability determined based on constraints." However, instead of the database 203A storing the information on applicability, the repair plan determination unit 204A may perform the process of determining applicability based on constraints.

[0184] As described above, according to Embodiment 10, a repair plan determination device 200A can be provided. The repair plan determination device 200A includes: an inspection result acquisition unit 201 that acquires inspection results 72A including the length of a crack C in a structure S, the angle of the crack C with respect to the direction of gravity D1, and the opening amount of the crack C; an input unit 202 that accepts input information 70A including the inspection results 72A, shape information 71 indicating the shape of the structure S, and the budget 73 for the inspection and repair of the structure S; a repair method including simple repairs carried out simultaneously with the inspection of the structure S and large-scale repairs carried out separately from the inspection; a database 203A that holds information relating the state of the crack C that can be repaired by each repair method, the time required for the repair work, the repair cost, and the service life after the repair; and the length of the crack C and the direction of gravity The system includes a repair plan determination unit 204A that creates a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure S, by combining simple repairs performed during inspections when inspection results 72A are obtained, simple repairs performed during subsequent inspections, and major repairs, based on input information 70A including the angle of the crack C and the opening amount of the crack C, and information held in the database 203A, and an output unit 205 that outputs the repair plan, wherein the database 203A includes the opening amount of the crack C and the angle φ1 of the crack C with respect to the gravity direction D1 as the state of the crack C, and the simple repair method of the above repair method may include a method of applying a repair material 22 to the crack C. This makes it possible to plan the method of applying a repair material 22 to the crack C as a simple repair during inspection, making it possible to easily repair the crack C and extend the service life of the structure S.

[0185] Furthermore, similar to the repair plan determination unit 204, the repair plan determination unit 204A can also create a repair plan that includes multiple minor repairs before major repairs are carried out, based on the input information 70A and the information held in the database 203A. By carrying out multiple minor repairs, the service life of the structure S can be further extended, which increases the flexibility in adjusting the timing of major repairs and makes it easier to level out costs over a longer period.

[0186] Furthermore, the input unit 202 can accept input information 70A that further includes parameters 74 for estimating the costs incurred when the structure becomes unusable, similar to Embodiment 9. In this case, the repair plan determination unit 204A estimates the costs incurred during the period when the structure S is unusable based on the above parameters, uses the estimated costs as the costs when simple repairs are not carried out, and can create a repair plan with the case where simple repairs are not carried out as a candidate repair method. This makes it possible to treat cases where repairs are not carried out at the time of inspection as a repair method.

[0187] Furthermore, similar to the database 203 in Embodiment 9, it is desirable that the database 203A has a function to periodically update the information it holds.

[0188] Furthermore, as shown in Figure 50, the database 203A may also hold information on the materials of the structure. In this case, the repair plan determination unit 204A can determine whether it is possible to carry out repairs using each of the multiple repair methods, based on the constraints on the materials of the structure.

[0189] The inspection result acquisition unit 201A can acquire inspection results including the number of cracks C in the components constituting the structure S. The repair plan determination unit 204A can create a repair plan that involves replacing the component as a simple repair if the number of cracks C per component is above a threshold. If multiple cracks C occur in a single component, it may be preferable to replace the component rather than performing repairs such as applying the repair material 22. Therefore, by determining whether or not to consider replacing the component based on the number of cracks C per component, it becomes possible to create a more appropriate repair plan.

[0190] Furthermore, according to Embodiment 10, a repair plan determination system can be provided. The functions of the repair plan determination device 200A can also be realized as a repair plan determination system. The repair plan determination system can be realized using one or more computer systems. The repair plan determination system receives input information 70A, which includes inspection results 72A including the length of the crack C in the structure S, the angle φ1 of the crack C with respect to the gravity direction D1, and the opening amount of the crack C, shape information 71 indicating the shape of the structure S, and a budget 73 for the inspection and repair of the structure S. Based on the input information 70A, the system can output a repair plan that satisfies at least one of the following: minimizing the total cost and leveling the costs of inspection and repair of the structure S.

[0191] Furthermore, Embodiment 10 provides a method for determining a repair plan. The repair plan determination method includes the steps of: obtaining inspection results 72A including the length of a crack C in a structure S, the angle of the crack C with respect to the direction of gravity D1, and the opening amount of the crack C; receiving input information 70A including the inspection results 72A, shape information 71 indicating the shape of the structure S, and the budget 73 for the inspection and repair of the structure S; a repair method including simple repairs to be carried out simultaneously with the inspection of the structure S and large-scale repairs to be carried out separately from the inspection; and associating the state of the crack C that can be repaired by each repair method, the time required for the repair work, the repair cost, and the service life after the repair. The process includes the steps of creating a repair plan that satisfies at least one of minimizing total costs and leveling costs by combining simple repairs performed at the time of inspection when the inspection results are obtained, simple repairs performed at subsequent inspections, and major repairs, based on the information held in the database 203A that holds the information and the input information 70A, wherein the database 203A includes the opening amount of the crack C and the angle φ1 made by the crack C with respect to the gravity direction D1 as the state of the crack C, and may include a method of applying a repair material 22 to the crack C as a simple repair.

[0192] Embodiment 11. Figure 51 shows the functional configuration of the repair plan determination device 200B according to Embodiment 11. The repair plan determination device 200B includes an inspection result acquisition unit 201, an input unit 202, a database 203, a repair plan determination unit 204B, and an output unit 205.

[0193] The repair plan determination unit 204B has the function of determining a repair plan, taking into account the extended lifespan of the structure S due to changes in its operating conditions. Operating conditions are conditions that affect the load on the structure S, and specifically include restrictions on bridge traffic volume and setting an upper limit on the rotational speed of the generator. It is conceivable that the service life of the structure S can be extended by changing the operating conditions to reduce the load on the structure S.

[0194] In this description, the repair plan determination device 200B is described as being the same as the repair plan determination device 200 according to Embodiment 9, except for the function of determining the repair plan while considering the extended lifespan due to changes in operating conditions. However, the repair plan determination device 200A according to Embodiment 10 may be modified to include the function of determining the repair plan while considering the extended lifespan due to changes in operating conditions.

[0195] Figure 52 is a flowchart illustrating the operation of the repair plan determination unit 204 according to Embodiment 11. Steps S511 to S514 are the same as in Figure 39, so their explanation is omitted. If simple repair is not possible (Step S514: No), the repair plan determination unit 204B determines whether or not it is possible to change the operating conditions (Step S531). For example, by pre-determining the range in which the operating conditions can be changed, the repair plan determination unit 204B can compare the current operating conditions with the pre-determined range of changeable conditions and determine whether or not it is possible to change the current operating conditions within the pre-determined range to reduce the load on the structure S, thereby determining whether or not it is possible to change the operating conditions.

[0196] If it is not possible to change the operating conditions (Step S531: No), the repair plan determination unit 204B proposes a major repair (Step S515) and terminates the process. If it is possible to change the operating conditions (Step S531: Yes), the repair plan determination unit 204B proposes the timing of the major repair, taking into account the life extension period due to the change in operating conditions (Step S532), and terminates the process. The life extension period due to the change in operating conditions can be a value calculated according to the content of the change in operating conditions.

[0197] If simple repairs are possible (Step S514: Yes), the repair plan determination unit 204B determines whether or not it is possible to change the operating conditions (Step S533). The determination of whether or not it is possible to change the operating conditions can be made in the same way as in Step S531. If it is not possible to change the operating conditions (Step S533: No), the repair plan determination unit 204B proposes a repair plan that combines simple repairs and major repairs, taking into account the life extension period by simple repairs (Step S516), and terminates the process. If it is possible to change the operating conditions (Step S533: Yes), the repair plan determination unit 204B proposes a repair plan that combines simple repairs and major repairs, taking into account the life extension period by simple repairs and changes to operating conditions (Step S534), and terminates the process.

[0198] By changing the operating conditions, the load on structure S can be reduced, thereby extending the service life of structure S. This, in turn, allows for a delay in the final deadline for carrying out repair work. Extending the deadline increases the number of potential repair timeframes, making it possible to spread out the timing of repair work and thus facilitate the staggering and leveling of repair costs.

[0199] In adjusting the timing of large-scale repairs, Figure 45 shows an example of leveling costs by postponing the work beyond a predetermined period. However, it is also possible to level costs by accelerating the work rather than postponing it. Here, the predetermined period may be a regular period, such as every 10 years, or it may be a period calculated using other methods.

[0200] Furthermore, the repair plan determination units 204, 204A, and 204B may determine a repair plan that increases the number of inspections since the most recent inspection, or may determine a repair plan that decreases the number of inspections since the most recent inspection. Furthermore, the repair plan determination units 204, 204A, and 204B may determine a repair plan that increases the scope of inspections since the most recent inspection, or may determine a repair plan that decreases the scope of inspections since the most recent inspection. If the crack C propagation rate is considered to be slow, the number of inspections or the scope of inspection may be reduced. Furthermore, if the crack C propagation rate is considered to be fast, it is conceivable to increase the number of inspections or the scope of inspection in order to respond quickly to changes in the condition of the structure S. Furthermore, the repair plan determination units 204, 204A, and 204B may determine a repair plan that adds condition monitoring at the location where the crack C is occurring, based on the inspection results.

[0201] Figure 53 shows a first example of the display screen output by the output unit 205 shown in Figure 51. If it is determined that simple repairs are not possible and that the operating conditions can be changed, the output unit 205 can generate a display screen that includes information on how to change the operating conditions and the timing of the major repair determined in step S532 of Figure 52. Figure 53 shows an example of a display screen that includes information indicating that the repair currently being carried out is a major repair, the value of the maximum rotational speed before and after the change as operating conditions, and information indicating the timing of the major repair as a future repair plan.

[0202] Figure 54 shows a second example of the display screen output by the output unit 205 shown in Figure 51. When it is determined that simple repairs are possible and that the operating conditions can be changed, the output unit 205 can generate a display screen that includes information on how to change the operating conditions and the repair plan determined in step S534 of Figure 52. Figure 54 shows an example of a display screen that includes information indicating that the repair currently being carried out is a simple repair, the operating conditions including the value of the maximum rotational speed before and after the change, and information indicating the timing of major repairs as part of the future repair plan.

[0203] As described above, the 11th embodiment provides a repair plan determination device 200B. In the repair plan determination device 200B, the repair plan determination unit 204B can determine a repair plan that takes into account extending the service life of the structure S by changing the operating conditions of the structure S to reduce the load on the structure S. Operating conditions are conditions that affect the load on the structure S, and specifically include limiting the traffic volume on the bridge and setting an upper limit on the rotational speed of the generator. It is conceivable that the service life of the structure S can be extended by changing the operating conditions to reduce the load on the structure S. In the example shown in Figure 52, when repair of the crack C is necessary, the operating conditions are changed regardless of whether or not a simple repair is performed if it is possible to change the operating conditions. However, if a simple repair is performed, the operating conditions may not be changed. Alternatively, the repair plan determination unit 204B may decide whether or not to change the operating conditions based on the service life after the simple repair is performed.

[0204] Furthermore, the repair plan determination unit 204B can create a repair plan that changes the number or scope of inspections performed after the inspection corresponding to the inspection result 72, a repair plan that adds condition monitoring at the location where crack C was detected during the inspection, or a repair plan that accelerates the timing of major repairs. These functions may also be provided by the repair plan determination units 204 and 204A.

[0205] Here, an example of the hardware configuration in Embodiments 9 to 11 will be described. The functions of the repair plan determination devices 200, 200A, and 200B described above are realized by a computer system, for example. The repair plan determination devices 200, 200A, and 200B may be realized by one computer system or by multiple computer systems. For example, the repair plan determination devices 200, 200A, and 200B may be realized by a cloud system. In a cloud system, the separation of the computer system hardware and devices such as servers for each function can be arbitrarily configured. For example, one computer system may have the functions of multiple devices, or multiple computer systems may have the functions of one device.

[0206] Here, the computer system that implements the repair plan determination devices 200, 200A, and 200B may be the computer system with the configuration described in Figure 32 above. As described above, this computer system comprises a control unit 101, an input unit 102, a storage unit 103, a display unit 104, a communication unit 105, and an output unit 106, which are connected via a system bus 107. The control unit 101 executes a repair plan determination program that describes each process performed by the repair plan determination devices 200, 200A, and 200B of Embodiments 9 to 11. The functions of each part of the computer system are as described above with reference to Figure 32. Furthermore, the operation of the computer system until the repair plan determination program describing the processes of the repair plan determination devices 200, 200A, and 200B becomes executable is the same as the example of the operation of the computer system until the repair content determination program becomes executable. At this time, the repair plan determination program may be provided in a state recorded on a recording medium, or it may be provided via the communication unit 105 through a transmission medium such as the Internet.

[0207] A repair plan determination program for realizing the functions of the repair plan determination device 200 according to Embodiment 9 includes the steps of: receiving input information 70 from a computer, which includes inspection results 72 indicating the state of cracks C in a structure S, shape information 71 indicating the shape of the structure S, a budget 73 for inspection and repair of the structure S, and parameters 74 for estimating the costs incurred if the structure becomes unusable; and outputting a repair plan based on the input information 70, which combines simple repairs to be carried out at the time of inspection corresponding to the inspection result 72, simple repairs to be carried out at inspections after the inspection corresponding to the inspection result 72, and large-scale repairs to be carried out separately from the inspection, to satisfy at least one of the following: minimizing the total cost and leveling the costs of inspection and repair of the structure S.

[0208] Furthermore, the repair plan determination program for realizing the functions of the repair plan determination device 200A according to Embodiment 10 includes the steps of: receiving input information 70A from a computer, which includes inspection results 72A including the length of a crack C in the structure S, the angle φ1 of the crack C with respect to the direction of gravity D1, and the opening amount of the crack C; shape information 71 indicating the shape of the structure S; and a budget 73 for the inspection and repair of the structure S; and outputting a repair plan that combines simple repairs to be performed at the time of the inspection in which the inspection results 72A were obtained, simple repairs to be performed at subsequent inspections corresponding to the inspection results 72A, and large-scale repairs to be performed separately from the inspection, based on the input information 70A, to satisfy at least one of the following: minimizing the total cost and leveling the costs of inspection and repair of the structure S.

[0209] Note that the functional divisions in each device are just one example, and the functional divisions in each device are not limited to the illustrated example, as long as the repair plan determination devices 200, 200A, and 200B can perform the operations described above.

[0210] Furthermore, the functions of the repair plan determination devices 200, 200A, and 200B may be realized using the processing circuit 110 shown in Figure 33.

[0211] The configurations shown in the above embodiments are examples only, and it is possible to combine them with other known technologies, combine different embodiments, and omit or modify parts of the configuration without departing from the gist of the invention.

[0212] For example, in the above embodiment, the inspection results were assumed to be captured images and directional information, but the system is not limited to this example. For example, the inspection results may indicate the condition of the structure S, in particular the condition of any cracks C that have occurred in the inspected material portion of the structure S.

[0213] Furthermore, the division of functions shown in the above embodiment is merely an example. As long as the above functions can be realized, each process may be executed in any device. Inspection and repair processes must be performed at the location where the structure S exists, but calculation processes such as judgment processes may be performed in any device, and there are no particular restrictions on where the device is installed.

[0214] Furthermore, in the above embodiment, the repair device 10 or the like performs the repair process, but the repair worker may perform the repair manually according to the repair content determined by the repair content determination device 64 or the like. Alternatively, the repair worker may perform the repair manually according to the repair plan determined by the repair plan determination devices 200, 200A, and 200B. [Explanation of Symbols]

[0215] 1,1E,1F,1G Repair content determination system, 5-1 Start point, 5-2 Goal point, 6-1,6-2,6-3 Point, 10,10A,10B,10C,10D,10G Repair device, 11 Main body, 12 Suction means, 13 Driving means, 14 Inspection unit, 15,15A,15B,15D,15E,15F Judgment unit, 16 Repair unit, 17 Pre-treatment unit, 18 Intermediate treatment unit, 19 Post-treatment unit, 21 Pre-treatment material, 22 Repair material, 30 Support member, 31 Deck plate, 32 Paving, 33,33-1,33-2 U-rib, 34 Transverse rib, 35 Weld bead, 36 Butt weld bead, 37 Vertical reinforcement member, 38 Fillet weld bead, 41,41G Control means, 50 Learning device, 51 Learning data acquisition unit, 52 Model generation unit, 53 Reward calculation unit, 54 Function update unit, 55 Learned model storage unit, 56 Inference device, 57 Inference data acquisition unit, 58 Inference unit, 61, 61E, 61F Inspection device, 62, 62E Storage unit, 63, 63E Transmission unit, 64, 64E, 64F Repair content determination device, 65, 68 Receiving unit, 66, 106 Output unit, 67 Repair effect prediction unit, 69 Route information storage unit, 70, 70A Input information, 71 Shape information, 72, 72A Inspection results, 73 Inspection and repair budget, 74 Parameters for estimating costs incurred when a structure becomes unusable, 101 Control unit, 102 Input unit, 103 Storage unit, 104 Display unit, 105 Communication unit, 107 System bus, 110 Processing circuit, 141 LiDAR scanner, 142 Camera, 151,151A Calculation unit, 152,152A Repair pattern determination unit, 153,153A Material used determination unit, 200,200A,200B Repair plan determination device, 201,201A Inspection result acquisition unit, 202 Input unit, 203,203A Database, 204,204A,204B Repair plan determination unit, 205 Output unit, C,C-1,C-2,C-3 Crack, D1 Gravity direction, D2,D2-1,D2-2,D2-3 Depth direction, D3 Vertical direction, L1,L1-1,L1-2,L1-3 Length, P1,P1-1,P1-2,P1-3 Starting point, S Structure, S1 Bridge, W1 Opening amount, φ1,φ 1-1 ,φ 1-2 ,φ 1-3 angle.

Claims

1. An inspection result acquisition unit that acquires inspection results showing the state of cracks that have occurred in a structure, An input unit that accepts input information including the inspection results, shape information indicating the shape of the structure, the budget for inspection and repair of the structure, and parameters for estimating the costs incurred if the structure becomes unusable. A crack repair method including simple repairs carried out simultaneously with the inspection of the aforementioned structure and large-scale repairs carried out separately from the inspection; a database that holds information relating the state of the crack that can be repaired by each repair method, the time required for the repair work, the repair cost, and the service life after the repair; A repair plan determination unit creates a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure, by combining the input information, including the angle of the crack with respect to gravity which is the inspection result, and the information held in the database, with the simple repairs performed during the inspection corresponding to the inspection result, the simple repairs performed during subsequent inspections, and the major repairs. An output unit that outputs the aforementioned repair plan, A repair plan determination device characterized by comprising the following:

2. An inspection result acquisition unit that acquires inspection results including the length of a crack in a structure, the angle the crack makes with respect to gravity, and the opening amount of the crack, An input unit that receives input information including the inspection results, shape information indicating the shape of the structure, and the budget for the inspection and repair of the structure. A repair method including simple repairs carried out simultaneously with the inspection of the aforementioned structure and large-scale repairs carried out separately from the inspection; a database that holds information relating the state of cracks that can be repaired by each repair method, the time required for the repair work, the repair cost, and the service life after the repair; A repair plan determination unit creates a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure, by combining the simple repair performed at the time of inspection when the inspection results were obtained, the simple repair performed at subsequent inspections, and the major repair, based on the input information including the length of the crack, the angle the crack makes with respect to gravity, and the amount of crack opening, and the information held in the database. An output unit that outputs the aforementioned repair plan, Equipped with, The repair planning device is characterized in that the database includes the opening amount of the crack and the angle the crack makes with respect to gravity as the state of the crack, and the repair method includes a method of applying a repair material to the crack as the simple repair method.

3. The repair plan determination device according to claim 1 or 2, characterized in that the repair plan determination unit creates a repair plan for carrying out multiple simple repairs before carrying out the large-scale repair, based on the input information and the information held in the database.

4. The repair plan determination device according to claim 1, characterized in that the repair plan determination unit estimates the costs incurred during the period when the structure cannot be used based on the parameters, sets the estimated costs as the costs when the simple repair is not carried out, and creates the repair plan with the case where the simple repair is not carried out as a candidate for the repair method.

5. The input unit receives the input information, which further includes parameters for estimating the costs incurred if the structure becomes unusable. The repair plan determination device according to claim 2, characterized in that the repair plan determination unit estimates the costs incurred during the period when the structure cannot be used based on the parameters, sets the estimated costs as the costs when the simple repair is not carried out, and creates the repair plan with the case where the simple repair is not carried out as a candidate for the repair method.

6. The repair plan determination device according to claim 1 or 2, characterized in that the database has a function to periodically update the information held in the database.

7. The aforementioned database further holds the materials of the structure, The repair plan determination device according to claim 2 or 5, characterized in that the repair plan determination unit determines whether or not it is possible to carry out repairs using each of the multiple repair methods based on constraints on the materials of the structure.

8. The repair plan determination device according to claim 1 or 2, characterized in that the repair plan determination unit determines the repair plan taking into consideration the extension of the service life of the structure by changing the operating conditions of the structure in a manner that reduces the load on the structure.

9. The repair plan determination device according to claim 1 or 2, characterized in that the repair plan determination unit creates a repair plan that changes the number or scope of inspections to be performed after the inspection corresponding to the inspection result, a repair plan that adds condition monitoring at the location where a crack was detected during the inspection, or a repair plan that brings forward the timing of the large-scale repair.

10. The inspection result acquisition unit acquires the inspection results, including the number of cracks that have occurred in the components constituting the structure. The repair plan determination device according to claim 1 or 2, characterized in that the repair plan determination unit creates a repair plan that includes replacing the part as a simple repair if the number of cracks per part is equal to or greater than a threshold value.

11. The system accepts input information including inspection results showing the state of cracks in a structure, shape information showing the shape of the structure, the budget for inspection and repair of the structure, and parameters for estimating the costs incurred if the structure becomes unusable. A repair plan determination system characterized by outputting a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspecting and repairing the structure, by combining simple repairs performed at the time of inspection corresponding to the inspection results, simple repairs performed at subsequent inspections, and large-scale repairs performed separately from the inspections, based on the input information including the angle of the crack with respect to gravity, which is the inspection result.

12. The system accepts input information including inspection results, which include the length of the crack in the structure, the angle the crack makes with respect to gravity, and the opening amount of the crack; shape information indicating the shape of the structure; and the budget for the inspection and repair of the structure. A repair plan determination system characterized by outputting a repair plan that satisfies at least one of the following: minimizing total costs and leveling out the costs of inspection and repair of the structure, by combining the aforementioned input information with the aforementioned simple repairs performed at the time of the inspection in which the inspection results were obtained, the aforementioned simple repairs performed at subsequent inspections, and the aforementioned major repairs performed separately from the aforementioned inspection.

13. The steps include obtaining inspection results that show the state of cracks in the structure, A step of receiving input information including the inspection results, shape information indicating the shape of the structure, the budget for inspection and repair of the structure, and parameters for estimating the costs incurred if the structure becomes unusable. A crack repair method including simple repairs carried out simultaneously with the inspection of the structure and major repairs carried out separately from the inspection; a step of creating a repair plan that satisfies at least one of minimizing the total cost and leveling the costs, by combining the simple repairs carried out at the time of the inspection when the inspection results were obtained, the simple repairs carried out at subsequent inspections, and the major repairs, based on information held in a database that holds information relating the state of the crack that can be repaired by each repair method, the time required for the repair work, the repair cost, and the service life after the repair, and input information including the angle of the crack with respect to gravity, which is the inspection result; The steps include outputting the aforementioned repair plan, A method for determining a repair plan, characterized by including the following.

14. A step of obtaining inspection results including the length of the crack in the structure, the angle the crack makes with respect to gravity, and the opening amount of the crack, A step of receiving input information including the inspection results, shape information indicating the shape of the structure, and the budget for inspection and repair of the structure, A repair method including simple repairs carried out simultaneously with the inspection of the structure and major repairs carried out separately from the inspection; a step of creating a repair plan that satisfies at least one of the following: minimizing total costs and leveling costs, by combining the simple repairs carried out at the time of the inspection when the inspection results were obtained, the simple repairs carried out at subsequent inspections, and the major repairs, based on information held in a database that holds information relating the state of cracks that can be repaired by each repair method, the time required for the repair work, the repair costs, and the service life after the repair, and the input information; The steps include outputting the aforementioned repair plan, Includes, The repair plan determination method is characterized in that the database includes the opening amount of the crack and the angle the crack makes with respect to gravity as the state of the crack, and the repair method includes a method of applying a repair material to the crack as the simple repair method.

Images