Diagnostic case presentation device, method, and program for a structure

Abstract

The present invention provides a structure diagnosis case presentation device, method and program that can assist a diagnoser in making a more accurate diagnosis when diagnosing a damage of a target structure as a diagnosis target. When information (damage information) related to a target structure as a diagnosis target is acquired by a first information acquisition section (20), a similar damage extraction section (22-1) extracts a similar damage similar to a damage of the target structure from a database (12) based on the acquired damage information. A specific diagnosis case extraction section (24-1) extracts diagnosis results of structures having the similar damage and different diagnosis results of two or more points in time as specific diagnosis cases from the database (12). Information related to the extracted specific diagnosis cases is displayed on a display section (14).

Description

Technical Field

[0001] This invention relates to a diagnostic case prompting device, method, and procedure for structures, and more particularly to a technique for prompting information related to specific diagnostic cases that are prone to misdiagnosis when diagnosing structures. Background Technology

[0002] In the past, when diagnosing structures, the diagnostician would visually observe the damaged areas of the structure at close range, and conduct hammering sounds and other examinations as needed, and diagnose the damage to the structure based on the damage situation (determination of the degree of damage, estimation of the cause of damage, determination of the integrity of the structure, determination of whether repair is needed, selection of repair methods, etc.).

[0003] In response, an information processing device was proposed to determine the properties of deformed parts of structures in an image (Patent Document 1).

[0004] The information processing device described in Patent Document 1 detects deformed parts such as cracks in a structure in an input image, extracts feature quantities related to a portion of the deformed part from the input image based on the detection results, and uses the extracted feature quantities to determine the properties of the deformed part.

[0005] When the deformed part is a crack, its properties include the crack width, the degree of crack hazard, and the cause of crack formation.

[0006] Furthermore, Patent Document 1 describes how the attribute of the deformable part can be used to add a "misdetection" category to the crack width category.

[0007] Previous technical documents

[0008] Patent documents

[0009] Patent Document 1: Japanese Patent Application Publication No. 2018-198053 Summary of the Invention

[0010] The technical problem to be solved by the invention

[0011] Diagnosing structures requires a high level of skill and experience, and misdiagnosis can sometimes occur due to a lack of skill or experience on the part of the diagnostician. Furthermore, the number of experienced diagnosticians is decreasing.

[0012] If a misdiagnosis occurs during the diagnosis of structural damage, optimal repair may not be possible, leading to reduced cost-effectiveness of the repair.

[0013] The information processing device described in Patent Document 1 detects cracks and other deformed parts of a structure from an input image, and uses feature quantities related to the image portion of the detected deformed part to determine the properties of the deformed part, but does not assist the diagnostician in diagnosing the structure (especially in reducing misdiagnosis).

[0014] The present invention was made in view of this situation, and its object is to provide a diagnostic case prompting device, method and procedure for structures that can assist diagnosticians in making more accurate diagnoses when diagnosing damage to the object structure being diagnosed.

[0015] means for solving technical problems

[0016] To achieve the above objectives, the invention involved in the first aspect is a diagnostic case prompting device for a structure, which includes a processor and a database. The database stores information related to the structure, including at least one of photographic images and damage information of the structure, and diagnostic results for the damage of the structure at two or more time points. The processor performs the following processing: acquiring information related to the target structure, including at least one of photographic images and damage information of the target structure; extracting similar damages to the target structure based on the information related to the target structure and the information related to the structure stored in the database; extracting diagnostic results for structures with similar damages but different diagnostic results at two or more time points from the database as specific diagnostic cases; and outputting information related to the specific diagnostic case to a display.

[0017] According to a first aspect of the present invention, if information related to an object structure being diagnosed is obtained, specific diagnostic cases are extracted from a database based on the obtained information related to the object structure, and information related to the specific diagnostic cases is displayed on a screen. Here, a specific diagnostic case is one where the diagnostic results for a structure with similar damage to the object structure differ at two or more points in time. Therefore, when diagnosing an object structure, the diagnostician can refer to the information related to the displayed specific diagnostic cases, enabling even a less experienced diagnostician to make an appropriate diagnosis.

[0018] In the diagnostic case indication device for structures according to the second aspect of the present invention, the specific diagnostic case is a misdiagnosed diagnostic case or a diagnostic case that is easily misdiagnosed. This is because the diagnostic results of the specific diagnostic case are different at more than two time points.

[0019] In the structural diagnostic case prompting device according to the third aspect of the present invention, the damage information stored in the database preferably includes at least one of the type of damage to the structure, the location of the damage, and the degree of damage.

[0020] In the structural diagnostic incident prompting device according to the fourth aspect of the present invention, it is preferable to store in the database at least one of the following: photographic images of the same part of the structure taken at multiple time points, damage information detected from the photographic images at multiple time points at multiple time points, and information indicating the time-dependent changes in damage information. The processor performs the following processing: acquiring information related to the target structure at multiple time points; detecting the time-dependent changes in damage information based on the information related to the target structure at multiple time points; and using the information indicating the time-dependent changes as a means to extract information on similar damage to the target structure from the database.

[0021] In the diagnostic incident prompting device for a structure according to the fifth aspect of the present invention, the processor preferably performs the following processing: acquiring a photographic image of the object structure and actual size calculation information related to the photographic image; detecting damage to the object structure from the photographic image, and calculating the degree of the detected damage based on the actual size calculation information.

[0022] In the diagnostic case prompting device for a structure according to the sixth aspect of the present invention, the processor preferably performs the following processing: acquiring a group of segmented photographic images of the object structure; and performing panoramic synthesis of the group of segmented photographic images.

[0023] In the diagnostic case prompting device for structures according to the seventh aspect of the present invention, the diagnostic results preferably include at least one of the following: a determination result of the degree of damage, a determination result of the differentiation of countermeasures, a determination result of the integrity, a presumption result of the cause of damage, a determination result of whether repair is required, and a selection result of the repair method.

[0024] In the diagnostic case prompting device for structures according to the eighth aspect of the present invention, preferably, the diagnostic results at two or more time points include the diagnostic result at the first time point and the diagnostic result at the second time point, which is a time point later than the first time point. The diagnostic result at the first time point is the diagnostic result at the initial inspection or the diagnostic result at the time point of periodic inspection. The diagnostic result at the second time point is the diagnostic result determined by a diagnostician different from the diagnostician at the first time point, the diagnostic result at the time point of inspection that is more detailed than the inspection at the first time point, or the diagnostic result at the time point of repair design of the structure.

[0025] In the diagnostic case prompting device for structures according to the ninth aspect of the present invention, the processor preferably uses information related to the object structure as a first feature vector, uses information related to the structure stored in the database as a second feature vector, calculates the distance between the first feature vector and the second feature vector in the feature space, and extracts similar damage to the damage to the object structure from the database based on the information related to the structure having a second feature vector with a distance of less than a threshold.

[0026] In the structure diagnostic case prompting device according to the tenth aspect of the present invention, preferably the processor extracts the diagnostic results of structures with similar damage from the database as specific diagnostic cases and structures with different diagnostic results at more than two time points, and the diagnostic results are consistent with the diagnostic purpose of the target structure.

[0027] In the diagnostic case prompting device for the structure according to the 11th aspect of the present invention, it is preferable that the processor extracts the specific diagnostic case with the highest similarity, or extracts the top few specific diagnostic cases with high similarity.

[0028] In the diagnostic case prompting device for a structure according to the 12th aspect of the present invention, the structure-related information stored in the database preferably includes at least one of: photographic images of the structure and damage information of the structure; and at least one of: structural information, environmental information, historical information and inspection information of the structure. The structure-related information acquired in the information acquisition process includes at least one of: photographic images of the object structure and damage information of the object structure; and at least one of: structural information, environmental information, historical information and inspection information of the object structure.

[0029] In the diagnostic case prompting device for a structure according to the 13th aspect of the present invention, the processor preferably performs the following processing: extracting at least one similar damage; extracting at least one specific diagnostic case; calculating the misdiagnosis rate of the specific diagnostic case based on the number of extracted similar damages and the number of extracted specific diagnostic cases; and outputting at least one specific diagnostic case and the misdiagnosis rate from the extracted specific diagnostic cases to a display.

[0030] The diagnostic case suggestion method for structures according to the 14th aspect of the present invention performs the following processing by a processor: acquiring information related to the target structure, including at least one of a photographic image of the target structure and damage information; extracting similar damages similar to the damage to the target structure based on the information related to the target structure and the information related to the structure stored in the database; extracting diagnostic results from the database for structures with similar damages and different diagnostic results at two or more time points stored in the database as specific diagnostic cases; and outputting information related to the specific diagnostic case to a display.

[0031] The diagnostic case prompting program for structures according to the 15th aspect of the present invention performs the following processing via a computer: acquiring information related to the target structure, including at least one of photographic images and damage information of the target structure; extracting similar damages to the target structure based on the information related to the target structure and the structure-related information stored in the database; extracting diagnostic results from the database for structures with similar damage and different diagnostic results at two or more time points stored in the database as specific diagnostic cases; and outputting information related to the specific diagnostic case to a display.

[0032] Invention Effects

[0033] According to the present invention, when a diagnostician diagnoses damage to an object structure that is the subject of diagnosis, information related to a specific diagnostic case is provided, so that even a less skilled diagnostician can make a more appropriate diagnosis. Attached Figure Description

[0034] Figure 1 This is a block diagram illustrating an embodiment of the hardware structure of a diagnostic event notification device for a structure according to one aspect of the present invention.

[0035] Figure 2 This is a block diagram illustrating a first embodiment of a diagnostic incident indication device for a structure according to one aspect of the present invention.

[0036] Figure 3 This is a block diagram illustrating a second embodiment of a diagnostic incident indication device for a structure according to one aspect of the present invention.

[0037] Figure 4 This is a diagram illustrating an example of a method for extracting similar damage based on a similar damage extraction unit.

[0038] Figure 5 It is a chart that shows the types of diagnostic purposes and the diagnostic results at two time points for each diagnostic purpose.

[0039] Figure 6 This is a flowchart illustrating an embodiment of a diagnostic case suggestion method for a structure according to one aspect of the present invention. Detailed Implementation

[0040] Hereinafter, a preferred embodiment of the diagnostic incident prompting device, method and procedure for a structure according to one aspect of the present invention will be described with reference to the accompanying drawings.

[0041] [Hardware structure of the diagnostic case study for the structure]

[0042] Figure 1This is a block diagram illustrating an embodiment of the hardware structure of a diagnostic event notification device for a structure according to one aspect of the present invention.

[0043] like Figure 1 As shown, the diagnostic case prompting device 1 for the structure can be composed of a personal computer, workstation, etc., and includes a processor 10, a memory 11, a database 12, a display unit (monitor) 14, an input / output interface 16, and an operation unit 18.

[0044] The processor 10 comprises a CPU (Central Processing Unit) and the like, and includes all parts of the diagnostic case prompting device 1 that control the structure, and, for example, as... Figure 2 The first information acquisition unit 20, the similar injury extraction unit 22-1, and the specific diagnostic case extraction unit 24-1 shown in the figure are functioning.

[0045] Here, structures include buildings, such as bridges, tunnels, dams and other civil engineering structures, as well as buildings, houses, walls, columns, beams and other structures.

[0046] When the processor 10 acquires information related to the object structure being diagnosed by the first information acquisition unit 20, it extracts specific diagnostic cases from the database 12 storing information related to the structure (past information) through a damage extraction unit 22-1 and a specific diagnostic case extraction unit 24-1, and outputs information related to the extracted specific diagnostic cases to the display unit 14. Furthermore, regarding... Figure 2 Details of the first information acquisition unit 20, the similar injury extraction unit 22-1, and the specific diagnostic case extraction unit 24-1 shown will be described later.

[0047] The memory 11 includes flash memory, ROM (Read-only Memory), and RAM (Random Access Memory), etc. The flash memory and ROM are non-volatile memories that store the operating system, various programs including the diagnostic prompt program for the structure according to one aspect of the present invention, etc. RAM functions as a working area for processing by the processor 10. Furthermore, the diagnostic prompt program for the structure is temporarily stored in the flash memory, etc. Additionally, the processor 10 may have a portion of the memory 11 (RAM) built into it. Alternatively, the diagnostic prompt program for the structure may be recorded on an external recording medium (not shown) and distributed, and installed by the processor 10 from its recording medium. Or, the diagnostic prompt program for the structure may be stored in a state accessible from the outside on a server connected to a network, and downloaded by the processor 10 to the flash memory or ROM upon request for installation and execution.

[0048] The processor 10 uses RAM as its working area based on the diagnostic case prompting program for the structure, and simultaneously controls and processes each part of the diagnostic case prompting device 1 for the structure.

[0049] Database 12 is the part that stores and manages information related to the structure by associating it with diagnostic results of damage to the structure at two or more time points. Furthermore, details regarding the information related to the structure managed by Database 12, and the diagnostic results of damage to the structure at two or more time points, will be described later.

[0050] Display unit 14 displays information related to a specific diagnostic case extracted by processor 10, based on information related to the object structure being diagnosed. When diagnosing an object structure, the diagnostician can refer to the information displayed on the screen related to the specific diagnostic case to perform the diagnosis. Furthermore, the display can be used as part of the user interface when receiving instructions from the diagnostician.

[0051] The input / output interface 16 includes a connection unit for connecting to external devices and a communication unit for connecting to a network. As the connection unit for connecting to external devices, USB (Universal Serial Bus) and HDMI (High-Definition Multimedia Interface) (HDMI is a registered trademark) can be used. The processor 10 can obtain desired information related to the object structure via the input / output interface 16. Furthermore, it can replace the display unit 14 by using an external display device connected to the input / output interface 16.

[0052] The operation unit 18 includes a pointing device such as a mouse and a keyboard, and functions as a user interface for receiving various specifications based on the diagnostician.

[0053] [First Embodiment of a Diagnostic Case Display Device for Structures]

[0054] Figure 2 This is a block diagram illustrating a first embodiment of a diagnostic incident indication device for a structure according to one aspect of the present invention.

[0055] Figure 2 The diagnostic case prompting device for the structure shown in the first embodiment consists of... Figure 1 The hardware structure shown comprises a processor 10, a database 12, and a display unit 14 for the diagnostic case prompting device 1. The processor 10 functions as a first information acquisition unit 20, a similar damage extraction unit 22-1, and a specific diagnostic case extraction unit 24-1.

[0056] The first information acquisition unit 20, which functions as an input unit, performs information acquisition processing. This information acquisition processing acquires information related to the object structure, including at least one of a photographic image of the object structure being diagnosed and damage information, based on instructions from the diagnostician. In this example, the first information acquisition unit 20 acquires damage information of the object structure.

[0057] Damage information of the object structure acquired by the first information acquisition unit 20 is output to the similar damage extraction unit 22-1.

[0058] Database 12 is the part that stores and manages a large amount of information related to structures diagnosed in the past and associates it with the diagnostic results of damage to structures at more than two time points.

[0059] Information related to the structure includes at least one of photographic images of the structure and damage information of the structure. Damage information includes at least one of the type of damage, location of damage, and extent of damage. Furthermore, it may include images representing damage detected from the photographic images of the structure (damage images).

[0060] <Examples of diagnostic results at more than two time points>

[0061] Diagnostic results at two or more time points include the diagnostic result at time point 1 and the diagnostic result at time point 2, which is later than time point 1.

[0062] The diagnostic result at point 1 can be considered as the initial diagnostic result of the test, or the diagnostic result at a periodic test point of visual examination.

[0063] The diagnostic results at point 2 can be considered as diagnostic results determined by a different diagnostician than at point 1 (e.g., consulting bodies such as diagnostic result confirmation meetings), diagnostic results at inspection points that are more detailed than visual inspection (in addition to visual inspection, destructive inspection, non-destructive inspection, etc.), or diagnostic results at the time of structural repair design.

[0064] When diagnostic results at two or more time points are consistent or inconsistent, the diagnostic results at later time points are more reliable than those at earlier time points.

[0065] <Example of diagnostic results>

[0066] The diagnostic results include at least one of the following: the determination of the degree of damage, the determination of the countermeasures, the determination of the integrity, the presumption of the cause of the damage, the determination of whether repair is needed, and the selection of the repair method.

[0067] • Determination of the degree of injury

[0068] The results of the damage level determination a / b / c / d / e (Reference: Guidelines for Periodic Inspection of Bridges: Ministry of Land, Infrastructure, Transport and Tourism of Japan)

[0069] • Result of the determination of the countermeasure distinction

[0070] Countermeasure differentiation: Judgment results A / B / C / E, etc. (Reference: Guidelines for periodic bridge inspections: Ministry of Land, Infrastructure, Transport and Tourism of Japan)

[0071] A: No repair is needed.

[0072] B: Repairs need to be made depending on the situation.

[0073] C1: From a preventative maintenance perspective, repairs need to be carried out quickly.

[0074] C2: From the perspective of bridge structural safety, repairs need to be carried out quickly.

[0075] E1: From the perspective of bridge structural safety, emergency measures are required.

[0076] E2: In addition, emergency measures are required.

[0077] M: This needs to be addressed through maintenance work.

[0078] S1: A detailed investigation is needed.

[0079] S2: Follow-up investigation is required.

[0080] • Determination of soundness

[0081] Soundness: I / II / III / IV (Reference: Guidelines for Periodic Inspection of Bridges: Ministry of Land, Infrastructure, Transport and Tourism of Japan)

[0082] Examples of causes of injury

[0083] [Conditions of concrete components]

[0084] Deterioration: fatigue (repetitive load), salt damage, neutralization, alkali-aggregate reaction, freezing damage, chemical corrosion

[0085] Factors during construction: heat of hydration and drying shrinkage during construction.

[0086] Structural factors: excessive external forces, inappropriate design

[0087] [Regarding steel components]

[0088] Deterioration: Fatigue (repetitive load), salt damage

[0089] Structural factors: excessive external forces, inappropriate design

[0090] • Determination of whether repair is needed

[0091] Need / Do not need repair

[0092] • Results of the selection of repair methods

[0093] <Example of repair method>

[0094] [Examples of repair methods for concrete components]

[0095] Crack repair processes (crack injection process, crack filling process), cross-section repair processes (painting method, spraying method, filling method), surface treatment processes (surface coating process, surface impregnation process), replacement processes, anti-peeling processes, electro-corrosion protection processes, desalination processes, re-alkalization processes, and waterproofing processes.

[0096] [Examples of repair methods for steel components]

[0097] Plate reinforcement process, component replacement process, paint renovation process, waterproofing / waterproofing process, drilling crack prevention process, welding repair process, bolt replacement, types of repair materials

[0098] Furthermore, the repair performance varies not only depending on the type of repair method but also on the type (manufacturer, model) of the repair materials used. Therefore, the selection of a repair method is a concept that includes both the type of repair method and the selection of repair materials.

[0099] Then, the similar damage extraction unit 22-1 extracts information similar to the information related to the object structure from the information related to the structure stored in the database 12 (a large amount of information related to the structure diagnosed in the past).

[0100] Similar determinations can be made based on damage information such as the type of damage, the location of the damage, and the degree of damage (length, width, area, density, depth, etc.) (average value, maximum value, etc.).

[0101] Furthermore, similar determinations can be made not only based on damage information but also based on the changes in the location and extent of damage over time. In this case, the database 12 needs to store at least one of the following: photographic images of the same part of the structure taken at multiple time points, damage information detected from the photographic images at multiple time points at multiple time points, and information indicating the changes in damage information over time. The first information acquisition unit 20 needs to acquire information related to the object structure at multiple time points.

[0102] Based on the similar damage extraction unit 22-1, the similar damage extraction processing detects the temporal changes in damage information according to information related to the target structure at multiple time points. This temporal change information can be used as one of the information points for extracting similar damage to the target structure from the database 12. Therefore, the temporal changes in damage information can also extract similar specific diagnostic cases. Furthermore, the "multiple time points" for acquiring photographic images of the same part of the structure stored in the database 12 and the damage information detected from the photographic images, and the "multiple time points" for acquiring information related to the target structure, can all be the same, some can be the same, or all can be different.

[0103] Furthermore, the damage extraction unit 22-1 can also consider information other than damage information, such as at least one of the following: structural information of the structure, environmental information, historical information, and inspection information, to make a similar determination. Details regarding the structural information, environmental information, historical information, and inspection information of the structure will be described later.

[0104] The specific diagnostic case extraction unit 24-1 extracts specific diagnostic results (specific diagnostic cases) from the diagnostic results of structures with similar damage extracted by the similar damage extraction unit 22-1 (i.e., diagnostic results that are associated with information about similar damage) extracted from the database 12. The diagnostic results extracted as specific diagnostic cases are diagnostic results of structures with different diagnostic results at two or more time points.

[0105] That is, a specific diagnostic case is a past diagnostic result with damage similar to that of the target structure, and is a diagnostic result with different results at more than two time points (misdiagnosis result, or error-prone diagnostic result).

[0106] The processor 10 outputs the information related to the specific diagnostic case extracted by the specific diagnostic case extraction unit 24-1 to the display unit 14.

[0107] Display unit 14 displays information related to a specific diagnostic case on specific diagnostic case prompt unit 14A. Information related to a specific diagnostic case includes information about the specific diagnostic case itself, or information about cases that are separate from or together with the specific diagnostic case and are prone to misdiagnosis.

[0108] Furthermore, it is preferable to display photographic images, damage information, etc., corresponding to a specific diagnostic case on the display unit 14. In addition, the display unit 14 can display photographic images, damage images, damage diagrams, etc. of the object structure.

[0109] When diagnosing a structure, the diagnostician can refer to information related to specific diagnostic cases indicated in the specific diagnostic case prompt section 14A to make a diagnosis, thereby enabling even a non-skilled diagnostician to make an appropriate diagnosis.

[0110] [Second Embodiment of the Diagnostic Case Indication Device for Structures]

[0111] Figure 3 This is a block diagram illustrating a second embodiment of a diagnostic incident indication device for a structure according to one aspect of the present invention.

[0112] Figure 3 The diagnostic case prompting device for the structure shown in the second embodiment consists of... Figure 1 The hardware structure shown comprises a processor 10, a database 12, and a display unit 14 for the diagnostic case prompting device 1. The processor 10 functions as an image acquisition unit 32, a damage detection unit 34, an actual size information acquisition unit 35, a panoramic synthesis unit 36, a second information acquisition unit 38, a similar damage extraction unit 22-2, and a specific diagnostic case extraction unit 24-2.

[0113] Image acquisition unit 32, damage detection unit 34, actual size information acquisition unit 35, and panoramic synthesis unit 36 ​​are equivalent to Figure 2 The first information acquisition unit 20 shown generates damage information based on photographic images of the object structure contained in information 30 related to the object structure.

[0114] That is, the image acquisition unit 32 acquires photographic images of the object structure to be diagnosed according to the instructions from the diagnostician, and outputs the acquired photographic images to the damage detection unit 34.

[0115] The damage detection unit 34 performs damage detection processing on the photographic image of the object structure input from the image acquisition unit 32 to detect damage to the object structure in the photographic image. The damage detection unit 34 can, for example, apply a learned model such as a CNN (Convolutional Neural Network) that has undergone machine learning for damage detection, but is not limited to this, and can also detect damage using a detection algorithm.

[0116] Furthermore, among the other inputs to the damage detection unit 34, actual size calculation information (actual size information) related to the actual size of the object structure is added from the actual size information acquisition unit 35. The actual size information is the actual size of the feature parts of the object structure in the photographic image (e.g., the length, width, etc. of the steel component), or the resolution (mm / pixel) of the photographed object.

[0117] The damage detection unit 34 can detect damage to the target structure and, based on actual dimensional information, detect the size of the damage (crack length and crack width in the case of a crack) or the degree of damage. This allows for the extraction of specific diagnostic cases with similar degrees (sizes) of damage.

[0118] Furthermore, the damage detection unit 34 can detect damage to concrete components such as cracks, water leakage / free lime, peeling / exposed rebar, bubbling, surface bubbles, pitting (honeycomb), cold joints, lap joints, sanding, and grout leakage. For steel components, it can detect damage such as cracking, corrosion, and deterioration of anti-corrosion properties. Moreover, the damage detection results can be appropriately corrected by the diagnostician.

[0119] Furthermore, the damage information detected by the damage detection unit 34 may include at least one of the following: the type of damage to the structure, the location of the damage, and the degree of damage (length, width, area, density, depth, average value, maximum value, etc.).

[0120] For example, when the image acquisition unit 32 acquires a group of segmented photographic images obtained by segmenting and photographing the object structure, the panoramic synthesis unit 36 ​​performs a synthesis process that performs panoramic synthesis on the group of segmented photographic images and also performs panoramic synthesis on the damage information (damage image).

[0121] If the desired resolution (e.g., the resolution required to detect a 0.1 mm crack) cannot be obtained from a single photographic image of the object structure, the object structure is segmented and photographed (including photographs of overlapping portions between adjacent images), and a group of segmented photographic images is obtained. Then, by performing panoramic synthesis on the group of segmented photographic images, and also performing panoramic synthesis on the damage information, it is possible to connect the cracks in each photographic image, for example, when photographing a single crack in multiple images. Furthermore, if the desired resolution is obtained from a single photographic image, the panoramic synthesis based on the panoramic synthesis unit 36 ​​can be omitted.

[0122] The damage information of the generated object structure is then output to a damage extraction unit 22-2.

[0123] The second information acquisition unit 38 acquires information other than photographic images from the information 30 related to the object structure (other information) as the second information.

[0124] <Other Information>

[0125] Other information includes at least one of the following: structural information, environmental information, historical information, and inspection information of the structure.

[0126] • Structural information: Structural type (bridge types: beam bridge, rigid frame bridge, truss bridge, arch bridge, cable-stayed bridge, suspension bridge), component types (bridge types: floor slabs, piers, abutments, beams, etc.), materials (steel, reinforced concrete, PC (prestressed concrete), etc.)

[0127] • Environmental information: Traffic volume (daily, monthly, yearly, cumulative, etc.), distance from the sea, climate (average temperature, average humidity, rainfall, snowfall, etc.)

[0128] Historical information: Conditions at the time of construction (temperature, etc.), number of years since completion (completion date, date of commissioning, number of years since then), repair history, disaster history (earthquakes / typhoons / floods, etc.).

[0129] • Inspection information: Monitoring information (deflection of the structure / amplitude of vibration / period of vibration, etc.), core pull-out test information, non-destructive inspection information (ultrasonic, radar, infrared, hammer impact sound, etc.)

[0130] Furthermore, other information may include the diagnostic objectives of the object's structure. These objectives include determining the extent of damage, identifying appropriate countermeasures, assessing its integrity, estimating the cause of damage, determining whether repair is necessary, and selecting appropriate repair methods.

[0131] The second information acquisition unit 38 acquires other information (second information) from the information 30 related to the object structure, outputs the second information to the similar damage extraction unit 22-2, and outputs information indicating the diagnostic purpose to the specific diagnostic case extraction unit 24-2. Furthermore, the information indicating the diagnostic purpose is not limited to being output from the second information acquisition unit 38 to the specific diagnostic case extraction unit 24-2; a diagnostician can also input the information indicating the diagnostic purpose into the specific diagnostic case extraction unit 24-2 using the operation unit 18.

[0132] The similar damage extraction unit 22-2 extracts information similar to the information related to the object structure from a large amount of past information related to the structure stored in the database 12, including damage information of the object structure input from the panoramic synthesis unit 36 ​​and second information (other information) input from the second information acquisition unit 38.

[0133] Figure 4 This is a diagram illustrating an example of a method for extracting similar damage based on a similar damage extraction unit.

[0134] exist Figure 4In the feature space based on feature vector A and feature vector B, a large amount of damage information related to the structure and the damage information of the object being diagnosed are described in the database 12.

[0135] In addition, Figure 4 In this context, damage information related to the structure stored in database 12 is represented by an × symbol, while damage information of the object being diagnosed is represented by a ● symbol. Furthermore, feature vector A represents the maximum crack width (mm), and feature vector B represents the number of years the structure has been in service. The feature space based on feature vectors can be set as a multi-dimensional space composed of three or more feature vectors, but... Figure 4 For simplicity, the diagram is illustrated using a two-dimensional space consisting of two feature vectors.

[0136] Similar damage extraction section 22-2 in Figure 4 In the feature space shown, the distance between the feature vector of the damage information of the current diagnostic object (the first feature vector), marked with ●, and the feature vector of the damage information (the second feature vector), marked with ×, is calculated. This distance is then extracted as below a threshold (within...). Figure 4 Damage information marked with an × (within the circle indicated by the dashed line) is considered similar damage. This threshold can be optimized using statistical methods.

[0137] Furthermore, the distance can be either the distance without weighting the multiple parameters of the first and second eigenvectors (Euclidean distance) or the distance with weighting (Mahaviran distance). The assignment of weights to which parameters can be determined using statistical methods such as principal component analysis.

[0138] In addition to the above-mentioned criteria, additional search conditions can be specified as points or ranges in the feature space. For example, when specifying bridges with a completion date after January 1, 1990, or those with a beam bridge as their basic structure, damage similar to that of the structure can be extracted within the specified range.

[0139] Furthermore, in addition to the above, it is also possible to set damage information, structural information, environmental information, historical information, and inspection information contained in other information as axes of the feature space and extract similar damage.

[0140] Furthermore, similar damage extraction methods can also employ approaches different from those based on distance in the feature space. For example, they can be extracted using AI (Artificial Intelligence) that determines similarity from images, AI that determines similarity by combining images, damage information, and other information.

[0141] Specific Diagnostic Case Extraction Section 24-2 and Figure 2 Similarly, the specific diagnostic case extraction unit 24-1 extracted the diagnostic results of structures with different diagnostic results at more than two time points among the diagnostic results of structures with similar damage from the database 12 as specific diagnostic cases. However, the specific diagnostic case extraction unit 24-2 further extracted specific diagnostic cases based on the condition that the diagnostic purpose of the target structure is consistent with the diagnostic purpose.

[0142] Figure 5 It is a chart showing the types of diagnostic purposes and the diagnostic results at two time points for each purpose. Additionally, in Figure 5 The text shows a case where the diagnostic results differed at two time points (time point 1 and time point 2).

[0143] The specific diagnostic case extraction unit 24-2 extracts specific diagnostic cases where the susceptibility determination results differ at two different points in time, provided that the diagnostic purpose information input from the second information acquisition unit 38 is, for example, a susceptibility determination. Furthermore, there can be two or more diagnostic purposes. In this case, it is preferable to extract specific diagnostic cases where the diagnostic results for each of the two or more diagnostic purposes differ at two different points in time; however, it is also possible to extract specific diagnostic cases where one or more of the diagnostic purposes have different diagnostic results at two different points in time.

[0144] Furthermore, when multiple specific diagnostic cases are detected, the specific diagnostic case extraction unit 24-2 can extract the specific diagnostic case with the highest similarity, or it can extract the top few (e.g., the top 3) specific diagnostic cases with high similarity.

[0145] The display unit 14 displays information related to a specific diagnostic case extracted by the specific diagnostic case extraction unit 24-2 on the specific diagnostic case prompt unit 14A. Furthermore, when the specific diagnostic case extraction unit 24-2 extracts the first few specific diagnostic cases with high similarity, multiple specific diagnostic cases can be displayed in descending order of similarity, or multiple specific diagnostic cases can be scrolled and displayed in descending order of similarity based on the diagnostician's scrolling operation.

[0146] Furthermore, the display unit 14 can display information 30 related to the object structure (photographed images of the object structure and other information), as well as damage information, etc.

[0147] When diagnosing a structure, the diagnostician can refer to information related to specific diagnostic cases indicated in the specific diagnostic case prompt section 14A to make a diagnosis, thereby enabling even a non-skilled diagnostician to make an appropriate diagnosis.

[0148] Furthermore, the processor 10 can perform a misdiagnosis rate calculation process, which calculates the misdiagnosis rate of specific diagnostic cases, based on the number of similar injuries extracted by the similar injury extraction units 22-1 and 22-2 (similar injury extraction processing) and the number of specific diagnostic cases extracted by the specific diagnostic case extraction units 24-1 and 24-2 (specific diagnostic case extraction processing). Additionally, the processor 10 extracts at least one similar injury in the similar injury extraction units 22-1 and 22-2 (similar injury extraction processing). Furthermore, the processor 10 extracts at least one specific diagnostic case in the specific diagnostic case extraction units 24-1 and 24-2 (specific diagnostic case extraction processing).

[0149] The misdiagnosis rate can be calculated as the ratio of the total number of similar injuries to the number of specific diagnostic cases in which the diagnostic results differ at two different time points within the same similar injury.

[0150] The processor 10 can display specific diagnostic cases and misdiagnosis rates on the display unit 14. The processor 10 can display at least one specific diagnostic case and misdiagnosis rate on the display unit 14. By viewing the displayed specific diagnostic cases and misdiagnosis rates, the diagnostician can determine whether the diagnosis of damage to the object structure is prone to misdiagnosis. If the misdiagnosis rate is high, the diagnostician can refer to the specific diagnostic cases to make a more careful diagnosis.

[0151] [Structural Diagnostic Case Studies and Methods]

[0152] Figure 6 This is a flowchart illustrating an embodiment of a diagnostic incident notification method for a structure according to one aspect of the present invention. Additionally, Figure 6 The processing of each step shown is done by Figure 1 The diagnostic case of the structure shown is prompted by the processor 10 of device 1.

[0153] exist Figure 6 In step S10, the processor 10 acquires photographic images of the object structure to be diagnosed based on instructions from the diagnostician.

[0154] The processor 10 detects damage to the object structure in the photographic image based on the photographic image of the object structure, and obtains damage information representing the damage (step S20, damage detection processing, information acquisition processing).

[0155] The processor 10 extracts similar damages to the damage of the object structure from the database 12 based on information related to the object structure including damage information and information related to the structure stored in the database 12 (step S30, similar damage extraction processing).

[0156] Next, the processor 10 extracts specific diagnostic results (specific diagnostic results with different diagnostic results at two or more time points) from the diagnostic results of structures with similar damage extracted in step S30 from the database 12 (step S40, specific diagnostic case extraction processing). Specific diagnostic results are diagnostic results that are misdiagnosed due to diagnostic results with different diagnostic results at two or more time points, or diagnostic results that are easily misdiagnosed.

[0157] The processor 10 outputs the information related to the specific diagnostic case extracted in step S40 to the display unit 14 and displays it on the specific diagnostic case prompt unit 14A (step S50, output processing). The information related to the specific diagnostic case preferably includes, in addition to diagnostic results with different results at two or more time points, photographic images and damage information corresponding to the specific diagnostic case.

[0158] Therefore, when diagnosing a structural object, the diagnostician can refer to information related to a specific diagnostic case as indicated in the specific diagnostic case prompt section 14A to make a diagnosis, so that even a non-skilled diagnostician can make an appropriate diagnosis.

[0159] [other]

[0160] In this embodiment, specific diagnostic cases with different diagnostic results at two or more time points are extracted from the diagnostic results of structures with similar damage to the target structure. However, it is not limited to this; the diagnostic results of structures with similar damage to the target structure can also be extracted from cases with different diagnostic results at two or more time points as specific diagnostic cases.

[0161] Furthermore, in this embodiment, for example, the hardware structure of the processing unit (CPU) that performs various processes and the database 12 is as follows: various processors. These processors include: general-purpose processors that execute software (programs) and function as various processing units, such as CPUs (Central Processing Units); processors such as FPGAs (Field Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, such as Programmable Logic Devices (PLDs); and processors such as ASICs (Application Specific Integrated Circuits) that have circuits specifically designed for performing specific processes, such as dedicated circuits.

[0162] A processing unit can be composed of one of these various processors, or it can be composed of two or more processors of the same or different types (e.g., multiple FPGAs or a combination of CPU and FPGA). Furthermore, a single processor can also constitute multiple processing units. As examples of a single processor constituting multiple processing units, firstly, in the case of computers such as client and server computers, a single processor is composed of a combination of one or more CPUs and software, and this processor functions as multiple processing units. Secondly, in the case of systems on a chip (SoC), a processor that implements the overall system functionality including multiple processing units is used through a single IC (Integrated Circuit) chip. Thus, various processing units are constructed as hardware structures using one or more of the aforementioned processors.

[0163] Furthermore, more specifically, the hardware structure of these various processors is a circuit composed of combined semiconductor elements and other circuitry.

[0164] Furthermore, the present invention includes a diagnostic case prompting program for a structure that enables the computer to function as a diagnostic case prompting device for the structure involved in the present invention by being installed in a computer, and a non-volatile storage medium recording the diagnostic case prompting program for the structure.

[0165] Furthermore, the present invention is not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present invention.

[0166] Symbol Explanation

[0167] 1-Diagnostic case prompting device, 10-Processor, 11-Memory, 12-Database, 14-Display unit, 14A-Specific diagnostic case prompting unit, 16-Input / output interface, 18-Operation unit, 20-First information acquisition unit, 22-1, 22-2-Similar damage extraction units, 24-1, 24-2-Specific diagnostic case extraction units, 32-Image acquisition unit, 34-Damage detection unit, 35-Actual size information acquisition unit, 36-Panoramic synthesis unit, 38-Second information acquisition unit, S10~S50-Steps.

Claims

1. A diagnostic event notification device for a structure, comprising a processor and a database, wherein the database stores information related to the structure, including at least one of photographic images of the structure and damage information of the structure, and diagnostic results for damage to the structure at two or more time points. The processor performs the following processing: Acquire information related to the object structure, including at least one of photographic images of the object structure as the subject of diagnosis and damage information; Based on information related to the object structure and information related to the structure stored in the database, similar damages that are similar to the damage to the object structure are extracted; As a specific diagnostic case, the diagnostic results of structures with similar damage and different diagnostic results at more than two time points are extracted from the database; Information related to the specific diagnostic case will be output to the display.

2. The diagnostic event notification device for a structure according to claim 1, wherein, The specific diagnostic cases mentioned are those that were misdiagnosed or those that are easily misdiagnosed.

3. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The damage information stored in the database includes at least one of the following: the type of damage to the structure, the location of the damage, and the extent of the damage.

4. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The database stores at least one of the following: photographic images of the same part of the structure taken at multiple time points; damage information detected from the photographic images at multiple time points at the multiple time points; and information indicating the time-varying nature of the damage information. The processor performs the following processing: Obtain information related to the object structure at multiple points in time; Based on the information related to the object structure at the multiple time points, the time-dependent changes in the damage information are detected, and the information representing the time-dependent changes is used as one of the information for extracting similar damages that are similar to the damage to the object structure from the database.

5. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor performs the following processing: Obtain the photographic image of the object structure and information for calculating the actual dimensions associated with the photographic image; Damage to the object structure is detected from the photographic image, and the extent of the detected damage is calculated based on the actual dimensions.

6. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor performs the following processing: Acquire a group of segmented photographic images of the object structure; The segmented photographic image group is then used to create a panoramic composite.

7. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The diagnostic results include at least one of the following: the determination of the degree of damage, the determination of the differentiation of countermeasures, the determination of the integrity, the presumption of the cause of damage, the determination of whether repair is needed, and the selection of the repair method.

8. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The diagnostic results at two or more time points include the diagnostic result at the first time point and the diagnostic result at the second time point, which is a time point later than the first time point. The diagnostic result at the first time point is a test of the initial diagnostic result or the diagnostic result at a periodic test time point. The diagnostic result at the second time point is the diagnostic result determined by a different diagnostician than the diagnostician at the first time point, the diagnostic result at the time point of a more detailed examination than the examination at the first time point, or the diagnostic result at the time point of the repair design of the structure.

9. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor uses information related to the object structure as a first feature vector and information related to the structure stored in the database as a second feature vector. It calculates the distance between the first feature vector and the second feature vector in the feature space. Based on the information related to the structure that has a second feature vector with a distance below a threshold, it extracts similar damages to the damage to the object structure from the database.

10. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor extracts the diagnostic results from the database for the structure with similar damage and different diagnostic results at more than two time points, as a specific diagnostic case, and the diagnostic results are consistent with the diagnostic purpose of the object structure.

11. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor extracts the specific diagnostic case with the highest similarity, or extracts the top few specific diagnostic cases with high similarity.

12. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The information related to the structure stored in the database includes at least one of: photographic images of the structure and damage information of the structure; and at least one of: structural information, environmental information, historical information, and inspection information of the structure. The information acquired related to the object structure includes at least one of: photographic images of the object structure and damage information of the object structure; and at least one of: structural information, environmental information, historical information, and inspection information of the object structure.

13. The diagnostic event notification device for a structure according to claim 1 or 2, wherein, The processor performs the following processing: Extract at least one of the aforementioned similar damages; Extract at least one of the specific diagnostic cases; The misdiagnosis rate of the specific diagnostic case is calculated based on the number of similar injuries extracted and the number of specific diagnostic cases extracted. At least one specific diagnostic case from the extracted specific diagnostic cases and the misdiagnosis rate are output to the display.

14. A method for indicating diagnostic cases of a structure, wherein the processor performs the following processing: Acquire information related to the object structure, including at least one of photographic images of the object structure as the subject of diagnosis and damage information; Based on information related to the object structure and information related to the structure stored in the database, similar damages that are similar to the damage to the object structure are extracted; As a specific diagnostic case, the diagnostic results of structures with similar damage and different diagnostic results at more than two time points stored in the database are extracted from the database; Information related to the specific diagnostic case will be output to the display.

15. A computer-readable non-transitory recording medium, comprising a recording program that performs the following processing via a computer: Acquire information related to the object structure, including at least one of photographic images of the object structure as the subject of diagnosis and damage information; Based on information related to the object structure and information related to the structure stored in the database, similar damages that are similar to the damage to the object structure are extracted; As a specific diagnostic case, the diagnostic results of structures with similar damage and different diagnostic results at more than two time points stored in the database are extracted from the database; Information related to the specific diagnostic case will be output to the display.

Images