Evaluation device used for residual proof stress evaluation in structure, evaluation method, generating method and learned model

Abstract

To provide a technique for evaluating residual proof stress in a structure such as a pier.SOLUTION: A machine learning section 12 performs machine learning that uses teacher data using a deterioration degree of a pile and an external force condition to the pile as explanation variables and a damage state of the pile as an objective variable to generate a learned model. A recording section 13 records the learned model generated by the machine learning section 12. An input section 14 inputs the deterioration degree of the pile that becomes an evaluation target and the external force condition to the pile to the learned model recorded in the recording section 13 as input items. A determination section 15 determines use propriety of the pile when external force in accordance with the external force condition is applied, on the basis of the damage state of the pile obtained in accordance with the input to the learned model by the input section 14. An output section 16 outputs damage state data corresponding to the damage state of the pile obtained in accordance with the input to the learned model by the input section 14 and use propriety data corresponding to use propriety of each pile constituting a pier.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a technique for evaluating the remaining strength of a structure.

Background Art

[0002] Among various port structures, particularly piers are placed in a harsh environment against chloride damage and must be properly maintained. However, there is very little achievement regarding the evaluation of the remaining strength of deteriorated piers.

[0003] In response to such problems, at present, it is impossible to evaluate the remaining strength without conducting an inspection survey (detailed inspection diagnosis) and performing a structural analysis based on the results. The timing of the detailed inspection diagnosis is usually at least once at an appropriate time during the service period for a regular inspection diagnosis facility, and also at the timing of extending the service period (see Non-Patent Document 1).

[0004] Even if a detailed inspection diagnosis is performed, in order to evaluate the remaining strength of a pier, it is necessary to perform a structural analysis of the entire pier system, but the remaining strength is often not evaluated. In this case, since the strength currently possessed by the pier cannot be grasped, when repairs or reinforcements are carried out, a quantitative effect cannot be confirmed, and it is not reasonable to return to the original possessed strength on the premise of restoring the original shape.

[0005] Regardless of the timing of the regular diagnosis, it is possible to grasp the remaining strength by performing a detailed inspection diagnosis. However, the cost is high and the inspection period is long, so at present, it is not actively carried out especially for privately-owned piers. In addition, since the period from inspection to evaluation of the remaining strength becomes long, the possibility of a large external force (for example, seismic force, etc.) attacking during that period also increases. Furthermore, if the remaining strength is not evaluated even after a detailed inspection diagnosis is performed, as described above, it is premised on restoring the original possessed strength on the premise of restoring the original shape, so a quantitative and effective repair and reinforcement are not carried out, and as a result, the cost may increase, which is not reasonable.

[0006] From the above, there is a need for a technique that can perform remaining strength evaluation more simply, quickly, and inexpensively. Therefore, Non-Patent Document 2 proposes a method for relatively easily performing remaining strength evaluation of a pier using a general-purpose structural analysis tool. However, this proposes a remaining strength evaluation method for beam deterioration and does not target piles or floor slabs.

Prior Art Documents

Non-Patent Documents

[0007]

Non-Patent Document 1

Non-Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0008] By the way, in a pier, vehicles such as trucks pass or wait on the upper surfaces of beams and floor slabs, generating a loading weight due to this. The loaded items include not only vehicles but also goods loaded and unloaded from vehicles and transported items such as containers unloaded from ships by cranes. When the floor slab is deteriorated, when the beam, which is a supporting member for the floor, is deteriorated, and when the foundation pile that supports the beam as a supporting member is deteriorated, there is a possibility that the loading weight assumed at the time of design cannot be maintained. In that case, damage such as holes or deformation may occur in the floor slab, and disasters such as vehicles and loaded items falling or being damaged may occur.

[0009] In a pier composed of deteriorated floor slabs, it is considered possible to evaluate the remaining strength of a single floor slab based on the deterioration degree determination result, etc. However, it is not easy to grasp which floor slab will be damaged to what extent by external forces in the entire pier including piles and beams. The following four factors are mainly involved. (1) Since there are a large number of beams and floor slabs constituting the pier, it takes a great deal of time and cost to grasp all of them. (2) The floor slab is supported by beams and piles, and the beam is supported by (or connected to) the pile. Depending on the deterioration status of the beam and pile, even if the floor slab is sound or has deterioration that is not severe enough to cause damage to the floor slab, it may not be able to resist external forces such as the superimposed load. In particular, it is necessary to judge the usability of the floor slab in consideration of the deterioration and evaluation of the remaining strength of the beam and pile. (3) The external force affecting the floor slab is mainly the superimposed load, but there are also many external forces other than the superimposed load that affect the beams and piles supporting the floor slab. (4) Since the pile is joined to the beam and the floor slab via the beam, it is not easy to evaluate the remaining strength of the pile considering these members (whether these members are sound or deteriorated).

[0010] The present invention has been made in view of the above-described background, and an object thereof is to provide a technique for evaluating the remaining strength in structures such as piers and bridges.

Means for Solving the Problem

[0011] The evaluation device according to the present invention is an evaluation device used for evaluating the remaining load-bearing capacity of a structure. It uses, as explanatory variables, the degree of deterioration in each pile of the structure and the external force conditions for each of the piles, and uses, as the target variable, the damage state of each of the piles when an external force corresponding to the external force conditions is applied to each of the piles. It includes a recording unit that records a learned model generated by machine learning using teacher data, an input unit that inputs, as input items, the degree of deterioration of the pile to be evaluated among each of the piles and the external force conditions for the pile into the learned model, and an output unit that outputs damage state data corresponding to the damage state of the pile obtained in response to the input to the learned model by the input unit.

[0012] The explanatory variables in the learned model further include the deterioration position of each of the piles and the degree of deterioration at the deterioration position. The input unit may further input, as the input items, the deterioration position of the pile to be evaluated and the degree of deterioration at the position into the learned model.

[0013] The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each of the piles and the external force conditions for the support members. The target variable in the learned model includes the damage state of the plurality of support members supported by each of the piles when an external force corresponding to the external force conditions is applied to each of the piles and the plurality of support members supported by the pile. The input unit may further input, as the input items, the degree of deterioration of the plurality of support members supported by the pile and the external force conditions for the support members into the learned model.

[0014] The explanatory variables in the learned model further include a plurality of support members supported by each of the piles, the degree of deterioration of the floor slab supported by the plurality of support members, and external force conditions for the support members and the floor slab. The objective variable in the learned model includes the damage states of the plurality of support members supported by each of the piles and the floor slab supported by the plurality of support members when an external force corresponding to the external force conditions is applied to each of the piles, the support members supported by the piles, and the floor slab supported by the support members. The input unit may further input, as the input items, the degree of deterioration of the plurality of support members supported by the piles and the floor slab supported by the plurality of support members and the external force conditions for the support members and the floor slab into the learned model.

[0015] A determination unit may be provided to determine the usability of the pile when an external force corresponding to the external force conditions is applied, based on the damage state of the pile and the arrangement information of the pile obtained according to the input to the learned model by the input unit.

[0016] A determination unit may be provided to determine the usability of the pile and the support members when an external force corresponding to the external force conditions is applied, based on the damage states of the pile and the plurality of support members supported by the pile and the arrangement information of the pile and the plurality of support members supported by the pile obtained according to the input to the learned model by the input unit.

[0017] A determination unit may be provided to determine the usability of the pile, the support members, and the floor slab when an external force corresponding to the external force conditions is applied, based on the damage states of the pile, the plurality of support members supported by the pile, and the floor slab supported by the plurality of support members, and the arrangement information of the pile, the plurality of support members supported by the pile, and the floor slab supported by the plurality of support members output by the output unit.

[0018] Further, the evaluation device according to the present invention is an evaluation device used for evaluating the remaining load-bearing capacity of a structure, which uses, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position in each pile of the structure and the external force conditions for each of the piles, and uses, as the objective variable, the usability of each pile when an external force corresponding to the external force conditions is applied to each of the piles. The evaluation device includes a recording unit that records a learned model generated by machine learning using teacher data, an input unit that inputs, as input items, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of the pile to be evaluated among each of the piles and the external force conditions for the pile into the learned model, and an output unit that outputs usability data corresponding to the usability of the pile obtained according to the input by the input unit.

[0019] The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each of the piles and the external force conditions for the support members. The input unit may further input, as the input items, the degree of deterioration of the plurality of support members supported by the pile and the external force conditions for the support members into the learned model.

[0020] The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each of the piles and a floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab. The input unit may further input, as the input items, the degree of deterioration of the plurality of support members supported by the pile and the floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab into the learned model.

[0021] The degree of deterioration may include at least any one of whether the deterioration is pitting corrosion, grooving corrosion, or both, the range of pitting corrosion or grooving corrosion, and the amount of grooving corrosion when the degree of deterioration is grooving corrosion.

[0022] The explanatory variables further include the attributes of each of the piles. The input unit may further input the attributes of the pile into the learned model as the input items.

[0023] The external force condition may be at least any one of seismic force, shore approach force, traction force, dead load, or superimposed load on the pile.

[0024] The damage state data may be data representing at least any one of the degree of damage, the area of damage, or the area ratio of damage.

[0025] The output unit maps the damage states of each of the piles, the plurality of support members supported by each of the piles, and the plurality of floor slabs supported by the plurality of support members to a structural diagram showing a structure composed of the plurality of support members and the plurality of floor slabs supported by the plurality of support members as the damage state data, and maps and outputs the serviceability of each of the piles to the structural diagram.

[0026] A determination unit is provided for determining the repair priorities of the piles, the floor slabs, and the support members to be repaired based on the damage states of each of the piles, the plurality of support members supported by the piles, and the floor slabs supported by the plurality of support members, and the serviceability of each of the piles, and the output unit may output the arrangement positions and the repair priorities of the piles, the floor slabs, and the support members to be repaired that have been determined.

[0027] A prediction unit is provided for predicting the degree of deterioration of each of the piles at an arbitrary future time from the degree of deterioration of each of the piles at the current time using a probability model for performing future prediction, and the explanatory variable may include the predicted degree of deterioration.

[0028] Further, the present invention may be an evaluation method implemented using the above evaluation device.

[0029] Further, the present invention may be a generation method for generating a learned model by machine learning using, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of a pile of a structure and the external force conditions for the pile, and using, as an objective variable, the damage state of the pile when an external force corresponding to the external force conditions is applied to the pile.

[0030] The explanatory variables in the learned model may further include the degree of deterioration of a plurality of support members supported by the pile and the external force conditions for the support members, and the objective variable in the learned model may include the damage states of the plurality of support members supported by the pile when an external force corresponding to the external force conditions is applied to the pile and the support members.

[0031] The explanatory variables in the learned model may further include the degree of deterioration of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab, and the objective variable in the learned model may include the damage states of the plurality of support members supported by the pile and the floor slab supported by the plurality of support members when an external force corresponding to the external force conditions is applied to the pile, the support members, and the floor slab.

[0032] Further, the present invention may be a learned model generated by the above generation method.

Advantages of the Invention

[0033] According to the present invention, the remaining strength of a structure can be evaluated.

Brief Description of the Drawings

[0034]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Mode for Carrying Out the Invention

[0035] (Example 1) (Configuration) FIG. 1 is a diagram showing the hardware configuration of an evaluation apparatus 10 according to Example 1 which is an example of an embodiment of the present invention. The evaluation apparatus 10 is an evaluation apparatus used for evaluating the remaining strength of a structure (here, a pier), and physically, it is configured as a computer apparatus including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, and a bus connecting these. Each of these devices operates by power supplied from a power source (not shown). In this embodiment, the pier as an example of the structure is composed of a plurality of floor slabs, a plurality of beams which are support members supporting each floor slab, and a plurality of piles supporting each beam.

[0036] Each function in the evaluation apparatus 10 is realized by causing the processor 1001 to read a predetermined software (program) onto hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculations, controls communication by the communication device 1004, acquires data transmitted from other devices, and controls at least one of reading and writing of data in the memory 1002 and the storage 1003.

[0037] The processor 1001 controls the entire computer by operating, for example, an operating system. The processor 1001 may be composed of a central processing unit (CPU: Central Processing Unit) including an interface with peripheral devices, a control device, an arithmetic device, registers, and the like.

[0038] The processor 1001 reads a program (program code), a software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program for causing a computer to execute at least a part of the operations described later is used.

[0039] The memory 1002 is a computer-readable recording medium and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may be referred to as a register, a cache, a main memory (main recording device), etc. The memory 1002 can store a program (program code), a software module, etc. executable for implementing the method according to the present embodiment.

[0040] The storage 1003 is a computer-readable recording medium and is, for example, a hard disk drive, a flash memory, or the like.

[0041] The communication device 1004 is hardware (a transmission / reception device) for performing communication between computers. The device that is the output destination where data is output by this communication device 1004 may be a portable terminal such as a smartphone or a tablet that is pre-registered in the evaluation device 10.

[0042] The input device 1005 is an input device (for example, a keyboard, a mouse, a microphone, a switch, a button, etc.) that receives an external input. The output device 1006 is an output device (for example, a display, a speaker, an LED lamp, etc.) that performs an output to the outside.

[0043] FIG. 2 is a diagram showing the functional configuration of the evaluation device 10. The evaluation device 10 realizes functions such as an acquisition unit 11, a machine learning unit 12, a recording unit 13, an input unit 14, a determination unit 15, and an output unit 16.

[0044] The acquisition unit 11 acquires teacher data for the machine learning unit 12 to perform supervised learning. The explanatory variables included in this teacher data are the degree of deterioration in each pile constituting the pier with various sizes and shapes, and the external force conditions for each of these piles. The degree of pile deterioration includes at least any one of whether the deterioration is pitting corrosion, section loss, or both, the range of pitting corrosion or section loss, and the amount of section loss when the degree of deterioration is section loss. The external force condition is information representing the stress generated on each pile to be evaluated, and when the external force condition is determined, the value of the external force is also determined based on the external force condition. The external force conditions assumed in this embodiment are information representing at least any one of the shore approach force, traction force, seismic force (level 1), seismic force (level 2), dead load, or superimposed load. Note that the seismic force (level 1) and the seismic force (level 2) are external forces classified according to the magnitude of the earthquake, but these may be combined as a single seismic force as an external force condition.

[0045] Also, when there are multiple types of external force conditions for each pile, the external force conditions are set as illustrated in FIG. 3. In FIG. 3, each external force condition is represented by No. 1, No. 2, No. 3, No. 4, and No. 5. No. 1 is the shore approach force generated by the approach of a ship to the pier, No. 2 is the traction force by the ship moored to the pier, No. 3 is the seismic force (level 1), No. 4 is the seismic force (level 2), and No. 5 is the superimposed load by a vehicle or the superimposed load by the goods loaded and unloaded from the vehicle. By combining these external force conditions No. 1, No. 2, …, No. 5, the external force conditions are set as combined external force No. 1, combined external force No. 2, …, combined external force No. 10.

[0046] Also, the objective variable included in this teacher data is the damage state of each pile when an external force corresponding to the above external force condition is applied to each pile. The damage state of each pile is at least any one of the degree of damage of each pile, the area of damage of each pile, or the area ratio of damage of each pile.

[0047] For each pile, various values are prepared in advance as analysis conditions for the degree of deterioration and external force conditions. The damage state of each pile can be obtained by performing a structural analysis according to these analysis conditions.

[0048] As described above, a set of training data consists of the degree of deterioration of a certain pile among each pile and the external force conditions (explanatory variables) for that pile, and the damage state (objective variable) of that pile when an external force corresponding to the external force conditions is applied to that pile. The entire training data is composed of these multiple sets of explanatory variables and objective variables.

[0049] The explanatory variables may include the deterioration position in each pile and the degree of deterioration at that deterioration position. In this case, as the deterioration position of each pile, at least one of the pile head, the pile tip, or the distance from the bottom of the water where the pile is installed may be included. Note that the degree of deterioration at the deterioration position also includes information indicating the deterioration position.

[0050] Figure 4 is a diagram illustrating the numbering of each pile. In Figure 4, a rule for numbering the pile numbers for each pile s is determined in advance. Also, the attributes of the piles described later may be associated with each pile number. In addition, in order to clarify which pile among each pile is the evaluation target pile when evaluating the damage degree of the pile, by using the pile number, it is possible to obtain the arrangement information indicating the position where the pile to be evaluated is arranged in the structure (here, the trestle) to be evaluated. As a result, even if a plurality of piles have the same degree of damage, since the influence exerted by the damaged pile on the surrounding members varies depending on the arrangement position in the trestle, different judgment results may be obtained when determining whether it can be put into use, which will be described later. For example, when the external force conditions are the shore approach force or the traction force, even if the stress is the same, the degree of influence on the surrounding members is different between the piles located on the sea side and the piles located on the backland side. Similarly, even when the external force condition is the seismic force, the damage expansion range varies depending on the arrangement position (for example, the central part and the end part of the trestle) of the pile to be evaluated.

[0051] Here, FIG. 5 is a diagram illustrating the corrosion environment of the pile, and FIG. 6 is a diagram illustrating the corrosion rate of the pile. As illustrated in FIG. 5, the corrosion environment of the pile is divided into, for example, six sections according to the position in the pile, and the corrosion rate is different in each section. From this, it can be said that which position of the pile is deteriorated has a great causal relationship with the damage state of the pile.

[0052] The explanatory variables may further include the attributes of each pile, such as attributes such as dimensions, Young's modulus, wall thickness, etc. When including values such as dimensions as explanatory variables of the pile in the explanatory variables, in addition to the method of using the real values, it is also possible to use the maximum value ratio. Also, a method using so-called two-class classification, three-class classification, etc. may be used.

[0053] Returning to FIG. 2, the machine learning unit 12 performs machine learning using, as explanatory variables, the degree of deterioration of the pile and the external force conditions on the pile acquired by the acquisition unit 11, and the damage state of the pile acquired by the acquisition unit 11 as the target variable, thereby generating a learned model (hereinafter referred to as a damage state learned model).

[0054] The recording unit 13 records the damage state learned model generated by the machine learning unit 12.

[0055] The input unit 14 inputs, as input items, the degree of deterioration of the pile to be evaluated and the external force conditions on the pile into the damage state learned model recorded in the recording unit 13.

[0056] The determination unit 15 is a separate function provided in the recording unit 13, and determines the usability of the pile when an external force corresponding to the external force condition is applied based on the damage state of the pile, which is the target variable obtained according to the input to the damage state learned model recorded in the recording unit 13 by the input unit 14, and the arrangement information of the pile. More specifically, the determination unit 15 obtains in advance, by calculation, the correspondence relationship between the damage state of the pile, the arrangement information of the pile, and the usability when an external force corresponding to the external force condition is applied to the pile, and obtains the usability result corresponding to the damage state of the pile obtained according to the input to the damage state learned model recorded in the recording unit 13. Further, the determination unit 15 may use a learned model obtained by machine learning the relationship between the damage state of the pile and the usability when an external force corresponding to the external force condition is applied to the pile. In this case, the machine learning unit 12 performs supervised learning using teacher data including, as explanatory variables, the damage degree of each pile constituting the trestle with various sizes and shapes and the external force conditions for each pile, and, as the target variable, the damage state of the pile when an external force corresponding to the external force condition is applied to the pile. The determination unit 15 records the obtained learned model (referred to as a usability learned model), and inputs the damage state of the pile output as the target variable by the damage state learned model recorded in the determination unit 15 to the usability learned model to obtain the usability of the pile.

[0057] The output unit 16 outputs damage state data corresponding to the damage state of the pile obtained according to the input to the damage state learned model by the input unit 14, and usability data corresponding to the usability of each pile constituting the trestle based on the damage state data.

[0058] (Operation) Next, the operation of machine learning by the evaluation device 10 will be described. In FIG. 7, the acquisition unit 11 acquires teacher data for the machine learning unit 12 to perform supervised learning (step S1). This teacher data includes, as explanatory variables, the deterioration degree of each pile constituting the trestle with various sizes and shapes and the external force conditions for each pile, and, as the target variable, the damage state of the pile when an external force corresponding to the external force condition is applied to the pile.

[0059] Next, the machine learning unit 12 generates a learned damage state model by performing machine learning using the teacher data consisting of the explanatory variables and the objective variables acquired by the acquisition unit 11 (step S2).

[0060] The recording unit 13 records the learned damage state model generated by the machine learning unit 12 (step S3).

[0061] Next, the operation when the remaining strength evaluation is performed by the evaluation device 10 will be described. In FIG. 8, the input unit 14 inputs, as input items, the degree of deterioration of the pile to be evaluated and the external force conditions applied to the pile, into the learned damage state model recorded in the recording unit 13 (step S11). Further, as input items to the learned damage state model, information on any one of the deterioration position in the pile to be evaluated, the degree of deterioration at the deterioration position, and the attributes of each pile may be included. Similarly, in the following Examples 2 and 3, it may also be included as input items.

[0062] The determination unit 15 acquires the damage state of the pile and the arrangement information of the pile in response to the input to the learned damage state model recorded in the recording unit 13 by the input unit 14 (step S12). Then, the determination unit 15 determines the usability of the pile when an external force corresponding to the external force condition is applied based on the acquired damage state and arrangement information (step S13).

[0063] The output unit 16 outputs damage state data corresponding to the damage state of the pile obtained in response to the input to the learned damage state model recorded in the recording unit 13 by the input unit 14, and usability data corresponding to the usability of each pile obtained in response to the input to the learned usability model recorded in the determination unit 15 (step S14).

[0064] More specifically, as shown in FIG. 9, the output unit 16 maps and outputs, for the structure diagram of a trestle composed of a plurality of piles, a plurality of beams which are support members supported by the piles, and a floor slab supported by the plurality of beams, by, for example, differentiating the damage states of the respective piles s with colors, different gradations, symbols, etc. Further, as shown in FIG. 10, the output unit 16 can map and output the serviceability data of the respective piles s by, for example, differentiating with colors, different gradations, symbols, etc. In FIGS. 9 and 10, each rectangular figure which is substantially square and arranged in a grid pattern means each floor slab f, each rectangular figure which is rectangular and located around each floor slab f means the beam b that supports the floor slab f, and a plurality of small rectangular figures which are substantially square and sandwiched between the respective beams b mean the respective piles s that support the beam b. Note that the shapes of the piles, beams, and floor slabs are shown using simple shapes for the purpose of explanation, but they may have different shapes in an actual plan view. The output unit 16 may superpose and output simultaneously the mapping example shown in FIG. 9 and the mapping example shown in FIG. 10. Also, in FIG. 9, the damage state is expressed in two categories of large and small, but the classification of the damage state is not limited to this example. For example, it may be classified by damage up to the yield load, damage up to the ultimate load, etc.

[0065] According to the first embodiment described above, it is possible to evaluate the remaining bearing capacity of piles under various external force conditions without performing structural analysis based on the degree of deterioration of the piles. The number of piles in a trestle is very large, and a great deal of time and cost are required when performing structural analysis. However, since structural analysis is not required as described above, it is possible to immediately grasp the remaining bearing capacity. Further, even when attempting to evaluate the remaining bearing capacities of the piles of a plurality of trestles, according to the first embodiment described above, the labor and time can be significantly reduced. Therefore, for example, after evaluating all the remaining bearing capacities of the piles of a plurality of trestles, it is also possible to utilize it as a primary screening function, such as performing a more detailed structural analysis only on those with significant damage to grasp the specific damaged locations.

[0066] (Second Embodiment) In Example 2 described below, in addition to those described in Example 1, the degree of deterioration of a beam, which is a support member supported by piles, and the external force conditions on the beam are used as explanatory variables for machine learning. In addition to those described in Example 1, the damage state of the beam is used as the target variable for machine learning. In this example, a beam is used as the support member for supporting the floor slab, but the support member is not limited to this, and any member having the role of supporting the floor slab may be used. The hardware configuration and functional configuration of the evaluation apparatus 10 in Example 2 are the same as those in FIGS. 1 and 2 described in Example 1, and the operations of the respective configurations are different.

[0067] FIG. 11 is a plan view illustrating the degree of deterioration of the beam. In FIG. 11, each rectangular figure having a substantially square shape arranged in a grid pattern means each floor slab f, and each rectangular figure having a rectangular shape located around each floor slab f means a beam b that supports the floor slab f. A plurality of small rectangular figures having a substantially square shape sandwiched between the respective beams b mean each pile s that supports the beam b. Note that the shapes of the piles, beams, and floor slabs are shown using simple shapes for the sake of explanation, but they may have different shapes in an actual plan view. In this Example 2, the degree of deterioration of the beam is expressed in four stages of a, b, c, and d according to the degree of deterioration, but the number of divisions may be three divisions or five divisions, and the number of divisions is not particularly limited.

[0068] Furthermore, the explanatory variables may include the dimensions of each beam (e.g., the thickness in the z direction and / or the lengths in the x and y directions). Here, FIG. 12 is a diagram illustrating the numbering of each beam, and FIG. 13 is a diagram illustrating the dimensions of each beam. In FIG. 12, the rule for numbering the beam numbers for each beam is determined in advance, and the dimensions of each beam (e.g., the thickness in the z direction and / or the lengths in the x and y directions) are set in association with the numbered beam numbers. When including the dimensions of the beam as explanatory variables, in addition to the method of using the real values of the dimensions as in the piles in Example 1, methods using the maximum value ratio, so-called two-class classification, three-class classification, etc. may also be used. Also, in order to clarify which beam among the plurality of beams is the beam to be evaluated when evaluating the damage degree of the beam, by using the beam number, it is possible to obtain together the arrangement information indicating the position where the beam to be evaluated is arranged in the trestle to be evaluated. As a result, even if a plurality of beams have the same degree of damage, the influence of the damaged beam on the surrounding members may differ depending on the arrangement position in the trestle, and thus different judgment results may be obtained when determining whether it can be put into use, which will be described later.

[0069] For the degree of deterioration of each pile, the degree of deterioration of each beam, and the external force conditions, various values are prepared in advance as analysis conditions. The damage state of each beam is at least any one of the degree of damage of each beam, the area of damage of each beam, or the area ratio of damage of each beam. The damage states of each pile and each beam as target variables are obtained by performing a structural analysis according to these analysis conditions.

[0070] Returning to FIG. 2, the machine learning unit 12 performs machine learning using the teacher data with the degree of deterioration of the piles, the degree of deterioration of the beams, and the external force conditions for the piles and beams acquired by the acquisition unit 11 as explanatory variables, and the damage states of the piles and the beams acquired by the acquisition unit 11 as target variables, thereby generating a learned damage state model.

[0071] The recording unit 13 records the learned damage state model generated by the machine learning unit 12.

[0072] The input unit 14 inputs, as input items, the degree of deterioration of the pile to be evaluated, the degree of deterioration of the beam supported by the pile, and the external force conditions for the pile, into the damage state learned model recorded in the recording unit 13.

[0073] The determination unit 15 determines the usability of the pile and the beam when an external force according to the external force condition is applied, based on the damage state of the pile and the damage state of the beam obtained in response to the input to the learned damage state model recorded in the recording unit 14 by the input unit 14, and the arrangement information of the pile and the beam. More specifically, the determination unit 15 obtains in advance, by calculation, the correspondence relationship between the damage state of the pile and the damage state of the beam, and the usability when an external force according to the external force condition is applied to the pile and the beam, and obtains the result of the usability corresponding to the damage state of the pile and the damage state of the beam obtained in response to the input to the learned damage state model recorded in the recording unit 13. Further, the determination unit 15 may use a learned model obtained by machine learning the relationship between the damage state of the pile and the beam and the usability when an external force according to the external force condition is applied to the pile and the beam. In this case, the machine learning unit 12 uses teacher data consisting of the damage state of the pile and the damage state of the beam as explanatory variables prepared in advance, the arrangement information of the pile and the beam, and the usability when an external force according to the external force condition is applied to the pile and the beam as the objective variable, and generates a learned model (referred to as a learned usability model) obtained as a result of performing supervised learning. The determination unit 15 records the learned usability model, and inputs the damage state of the pile and the damage state of the beam and the arrangement information of the pile and the beam to the learned usability model to obtain the usability of the pile and the beam. The relationship between the damage state of the pile and the damage state of the beam and the usability of the pile and the beam is as follows. First, based on the damage state of the pile and the arrangement information of the pile, the usability of the pile when an external force according to the external force condition is applied is determined. Next, based on the damage state of the beam and the arrangement information of the beam, the usability of the beam when an external force according to the external force condition is applied is determined. Then, the usability of the set of the pile and the beam supported by the pile is determined based on the usability of each of the pile and the beam. That is, among the set of the pile and the beam supported by the pile, if all of the pile and the beam are usable, the set is usable. On the other hand, among the set of the pile and the beam supported by the pile, if at least one of the pile or the beam is unusable, the set is unusable.

[0074] The output unit 16 outputs damage state data corresponding to the damage state of the pile obtained according to the input to the damage state learning completed model recorded in the recording unit 13 by the input unit 14, and availability data corresponding to the availability of each pile constituting the pier.

[0075] (Operation) Next, the operation of the machine learning by the evaluation device 10 will be described. In FIG. 7 mentioned above, the acquisition unit 11 acquires teacher data for the supervised learning by the machine learning unit 12 (step S1). This teacher data includes, as explanatory variables, the degree of deterioration of each pile constituting piers of various sizes and shapes, the degree of deterioration of a plurality of beams supported by each pile, and external force conditions for the pile and the plurality of beams supported by the pile, and as objective variables, the damage state of the pile when an external force corresponding to the above external force conditions is applied to each pile and the plurality of beams supported by the pile, and the damage state of the plurality of beams supported by the pile.

[0076] Next, the machine learning unit 12 generates a damage state learning completed model by performing machine learning using the teacher data composed of the explanatory variables and the objective variables acquired by the acquisition unit 11 (step S2).

[0077] The recording unit 13 records the damage state learning completed model generated by the machine learning unit 12 (step S3).

[0078] Next, the operation when performing the remaining strength evaluation by the evaluation device 10 will be described. In FIG. 8, the input unit 14 inputs, as input items, the degree of deterioration of the pile to be evaluated, the degree of deterioration of the plurality of beams supported by the pile, and the external force conditions for the pile and the plurality of beams supported by the pile, into the damage state learning completed model recorded in the recording unit 13 (step S11).

[0079] The determination unit 15 acquires the damage state of the pile, the damage states of the plurality of beams supported by the pile, and the arrangement information of the pile and the plurality of beams supported by the pile in response to the input to the learned damage state model by the input unit 14 (step S12). Then, the determination unit 15 determines the usability of the pile when an external force corresponding to the external force condition is applied based on the acquired damage state of the pile, the damage states of the plurality of beams supported by the pile, and the arrangement information of the pile and the plurality of beams supported by the pile (step S13).

[0080] The output unit 16 outputs damage state data corresponding to the damage state of the pile obtained in response to the input to the learned damage state model by the input unit 14, damage state data of the plurality of beams supported by the pile, and usability data corresponding to the usability of each pile and beam (step S14).

[0081] More specifically, as shown in FIG. 14, the output unit 16 maps and outputs, for example, by colors, different gradations, or symbols, the damage state of each pile and the damage state of each beam with respect to the structure diagram of the trestle composed of a plurality of piles and a plurality of beams supported by the piles. Further, as shown in FIG. 10 described above, the output unit 16 can map and output, for example, by colors, different gradations, or symbols, the usability data of each pile obtained in response to the input to the learned usability model recorded in the determination unit 15. In FIG. 14, each rectangular figure having a substantially square shape arranged in a grid pattern means each floor slab f, each rectangular figure having a rectangular shape located around each floor slab f means the beam b that supports that floor slab f, and the plurality of small rectangular figures having a substantially square shape sandwiched between each beam b mean each pile s that supports the beam b. Note that the shapes of the piles, beams, and floor slabs are shown using simple shapes for the sake of explanation, but they may have different shapes in an actual plan view. The output unit 16 may output the mapping example shown in FIG. 14 and the mapping example shown in FIG. 10 superimposed and simultaneously. Also, in FIG. 14, the damage state is expressed in two categories of large and small, but the classification of the damage state is not limited to this example. For example, it may be classified by damage up to the yield load, damage up to the ultimate load, etc.

[0082] According to the second embodiment described above, it is possible to evaluate the remaining bearing capacity of piles and beams under various external force conditions without performing structural analysis based on the deterioration degree of piles and the deterioration degree of beams. The number of piles in a trestle is very large, and a great deal of time and cost are required for structural analysis. However, since structural analysis is not required as described above, it is possible to immediately grasp the remaining bearing capacity. Furthermore, even when attempting to evaluate the remaining bearing capacity of piles and beams of multiple trestles, according to the second embodiment, the labor and time can be significantly reduced. Therefore, for example, after evaluating the remaining bearing capacity of all multiple trestles, it is also possible to utilize it as a primary screening function, such as performing more detailed structural analysis only on those with significant damage to identify specific damaged locations.

[0083] (Embodiment 3) (Configuration) In the third embodiment to be described next, as explanatory variables for machine learning, in addition to those described in the second embodiment, the deterioration degree of the floor slab supported by the beam, which is a support member supported by the pile, and the external force conditions for the pile, beam, and floor slab are used. As the objective variable for machine learning, in addition to those described in the second embodiment, the damage state of the floor slab is used. The hardware configuration and functional configuration of the evaluation device 10 in the third embodiment are the same as those in FIGS. 1 and 2 described in the first and second embodiments, and the operations of each configuration are different.

[0084] In Example 3, the acquisition unit 11 (FIG. 2) acquires teacher data for the machine learning unit 12 (FIG. 2) to perform supervised learning. The explanatory variables included in this teacher data are the degree of deterioration of each pile constituting the pier with various sizes and shapes, the degree of deterioration of each of the plurality of beams that are support members supported by each pile, the degree of deterioration of each floor slab supported by the plurality of beams, and the external force conditions for each pile, the plurality of beams supporting each pile, and the floor slab supported by the plurality of beams. Further, the objective variables included in this teacher data are the damage state of the pile when an external force corresponding to the above external force conditions is applied to each pile, each beam, and each floor slab, the damage state of the plurality of beams supported by each pile, and the damage state of each floor slab supported by the plurality of beams. The degree of deterioration of each pile, the degree of deterioration of each beam, the degree of deterioration of each floor slab, and the external force conditions for each pile, each beam, and each floor slab are prepared in advance with various values as analysis conditions. The damage states of each pile, each beam, and each floor slab are obtained by performing a structural analysis according to these analysis conditions. The damage state of each floor slab is at least one of the degree of damage of each floor slab, the area of damage of each floor slab, or the area ratio of damage of each floor slab.

[0085] The explanatory variables may include the dimensions of each floor slab or the number of beams supporting each floor slab. Here, FIG. 15 is a diagram illustrating the numbering of each floor slab, and FIG. 16 is a diagram illustrating the dimensions of each floor slab. In FIG. 15, a rule for numbering the floor slab numbers for each floor slab is determined in advance, and the dimensions of each floor slab (for example, the thickness in the z direction and / or the lengths in the x and y directions) are set in association with the numbered floor slab numbers. Note that when including the dimensions of the floor slab as explanatory variables, in addition to the method of using the real values of the dimensions, similar to the piles and beams in Examples 1 and 2, methods using the maximum value ratio or methods using so-called two-class classification, three-class classification, etc. may also be used. Also, in order to clarify which floor slab among a plurality of floor slabs is the floor slab to be evaluated when evaluating the damage degree of the floor slab, by using the floor slab number, it is possible to obtain the arrangement information indicating the position where the floor slab to be evaluated is arranged on the trestle. As a result, even if a plurality of floor slabs have the same degree of damage, the influence of the damaged floor slab on the surrounding members may be different depending on the arrangement position on the trestle, and thus different judgment results may be obtained when determining whether it can be put into use, which will be described later.

[0086] FIG. 17 is a plan view illustrating the deterioration degrees of the floor slab and the beam. In FIG. 17, each of the substantially square-shaped rectangles arranged in a grid pattern means each floor slab f, each of the plurality of rectangular rectangles located around each floor slab f means the beam b supporting that floor slab f, and each of the plurality of small substantially square-shaped rectangles sandwiched between each beam b means each pile s supporting the beam b. In the third embodiment, the deterioration degrees of the floor slab and the beam are expressed in four levels of a, b, c, and d according to the degree of deterioration, but the number of levels may be three levels or five levels, and the number of levels is not particularly limited.

[0087] The machine learning unit 12 (FIG. 2) performs machine learning using, as explanatory variables, the deterioration degree of the pile, the deterioration degree of the beam, the deterioration degree of the floor slab, and the external force conditions for the pile, the beam, and the floor slab acquired by the acquisition unit 11, and, as objective variables, the damage states of the pile, the beam, and the floor slab acquired by the acquisition unit 11, to generate a learned damage state model.

[0088] The recording unit 13 (Fig. 2) records the learned damage state model generated by the machine learning unit 12.

[0089] The input unit 14 (Fig. 2) inputs, as input items, the degree of deterioration of the pile to be evaluated, the degrees of deterioration of a plurality of beams supported by the pile, the degree of deterioration of the floor slab supported by the beams, and the external force conditions for the pile, the beams, and the floor slab, into the learned damage state model recorded in the recording unit 13. Note that the dimensions of each of the floor slab and the plurality of beams supporting the floor slab (for example, the thickness in the z direction and / or the lengths in the x and y directions) may be included as input items.

[0090] The determination unit 15 (Fig. 2) determines the usability of the pile, beam, and slab when an external force corresponding to the external force condition is applied, based on the damage state of the pile obtained in response to the input to the damage state learning model recorded in the recording unit 13 by the input unit 14, the damage states of the plurality of beams supported by the pile, and the damage state of the slab supported by the plurality of beams, as well as the arrangement information of the pile, the plurality of beams supported by the pile, and the slab supported by the plurality of beams. More specifically, the determination unit 15 calculates in advance the correspondence between the damage state of the pile, the damage states of the plurality of beams supported by the pile, and the damage state of the slab supported by the beams, and the usability when an external force corresponding to the external force condition is applied to the pile, and obtains the usability result corresponding to the damage state of the pile, the damage state of the beam, and the damage state of the slab obtained in response to the input to the damage state learning model recorded in the recording unit 13. Further, the determination unit 15 may use a learned model obtained by machine learning the relationship between the damage state of the pile, the damage states of the plurality of beams supported by the pile, the damage state of the slab supported by the beams, the arrangement information of the pile, the plurality of beams supported by the pile, and the slab supported by the plurality of beams, and the usability when an external force corresponding to the external force condition is applied to the pile, beam, and slab. In this case, the machine learning unit 12 generates a learned model (referred to as a usability learned model) obtained from the result of supervised learning using teacher data consisting of the damage state of the pile, the damage states of the plurality of beams supported by the pile, the damage state of the slab supported by the beams, the arrangement information of the pile, the plurality of beams supported by the pile, and the slab supported by the plurality of beams as explanatory variables in advance, and the external force condition, and the usability when an external force corresponding to the external force condition is applied to the pile, beam, and slab as the target variable, records it in the determination unit 15, and inputs the damage state of the pile, the damage state of the beam, and the damage state of the slab and the arrangement information of the pile, beam, and slab to the usability learned model to obtain the usability of the pile, beam, and slab. The relationship between the damage state of the pile, the damage state of the beam, and the damage state of the slab, and the usability of the pile, beam, and slab is as follows. First, based on the damage state of the pile and the arrangement information of the pile, the usability of the pile when an external force corresponding to the external force condition is applied is determined.Next, based on the damage state of the beam and the arrangement information of the beam, it is determined whether the beam can be used when an external force corresponding to the external force condition is applied. Next, based on the damage state of the floor slab and the arrangement information of the floor slab, it is determined whether the floor slab can be used when an external force corresponding to the external force condition is applied. And the usability of the set of the pile, the beam supported by the pile, and the floor slab supported by the beam is determined based on the usability of each of the pile, the beam, and the floor slab. That is, among the set of the pile, the beam supported by the pile, and the floor slab supported by the beam, if all of the pile, the beam, and the floor slab are usable, the set is usable. On the other hand, among the set of the pile, the beam supported by the pile, and the floor slab supported by the beam, if at least any one of the pile, the beam, or the floor slab is unusable, the set is unusable.

[0091] The output unit 16 outputs damage state data corresponding to the damage states of the pile, the beam, and the floor slab obtained according to the input to the damage state learned model recorded in the recording unit 13 by the input unit 14.

[0092] (Operation) Next, the operation of machine learning by the evaluation device 10 will be described. In FIG. 7 mentioned above, the acquisition unit 11 acquires teacher data for the machine learning unit 12 to perform supervised learning (step S1). This teacher data includes, as explanatory variables, the degree of deterioration of each pile constituting the trestle of various sizes and shapes, the degree of deterioration of each beam, the degree of deterioration of each floor slab, and the external force conditions for each pile, each beam, and each floor slab, etc., and as target variables, the damage state of each pile when an external force corresponding to the external force condition is applied to the pile, the damage states of a plurality of beams supported by the pile, and the damage state of the floor slab supported by the beam.

[0093] Next, the machine learning unit 12 generates a damage state learned model by performing machine learning using the teacher data composed of the explanatory variables and the target variables acquired by the acquisition unit 11 (step S2).

[0094] The recording unit 13 records the damage state learned model generated by the machine learning unit 12 (step S3).

[0095] Next, the operation when the evaluation device 10 performs the remaining strength evaluation will be described. In FIG. 8 mentioned above, the input unit 14 inputs, as input items, the degree of deterioration of the pile to be evaluated, the degree of deterioration of a plurality of beams supported by the pile, the degree of deterioration of the floor slab supported by the beam, and the external force conditions for the pile, the beam, and the floor slab, into the learned damage state model recorded in the recording unit 13 (step S11).

[0096] The determination unit 15 acquires the damage state of the pile, the damage state of the beam, and the damage state of the floor slab, and the arrangement information of the pile, the beam, and the floor slab in response to the input by the input unit 14 to the learned damage state model recorded in the recording unit 13 (step S12). Then, the determination unit 15 determines the usability of the pile when an external force corresponding to the external force conditions is applied based on the acquired damage state of the pile, the damage state of the beam, and the damage state of the floor slab, and the arrangement information of the pile, the beam, and the floor slab (step S13).

[0097] The output unit 16 outputs damage state data corresponding to the damage state of the pile, the damage state of the beam, and the damage state of the floor slab obtained in response to the input by the input unit 14 to the learned damage state model recorded in the recording unit 13, and usability data corresponding to the usability of each pile, beam, and floor slab constituting the trestle (step S14).

[0098] More specifically, as shown in FIG. 18, the output unit 16 can map and output, for a structural diagram showing the structure of a trestle composed of a plurality of floor slabs, a plurality of beams, and a plurality of piles, the damage states of the respective floor slabs, the damage states of the respective beams, and the damage states of the respective piles, for example, by differentiating them with colors, different gradations, symbols, or the like. Further, as shown in FIG. 10 described above, the output unit 16 can map and output, for the above structural diagram, the serviceability of each pile, for example, by differentiating it with colors, different gradations, symbols, or the like. In FIG. 18, each rectangular figure having a substantially square shape arranged in a grid pattern means each floor slab f, and each rectangular figure having a rectangular shape located around each floor slab f means the beam b supporting that floor slab f. A plurality of small rectangular figures having a substantially square shape sandwiched between each beam b mean each pile s supporting the beam b. Note that the output unit 16 may output by overlapping the mapping example shown in FIG. 18 and the mapping example shown in FIG. 10 at the same time. Also, in FIG. 18, the damage state is expressed in two categories of large and small, but the classification of the damage state is not limited to this example. For example, it may be classified by damage up to the yield load, damage up to the ultimate load, or the like.

[0099] According to the third embodiment described above, it is possible to evaluate the remaining strengths of the piles, beams, and floor slabs of a structure such as a trestle under various external force conditions without performing a structural analysis based on the deterioration degree of the piles, and the deterioration degrees of the beams and floor slabs. The number of piles in a trestle is very large, and a great deal of time and cost are required when performing a structural analysis. However, since the structural analysis is not required as described above, it is possible to immediately grasp the remaining strength. Further, even when attempting to evaluate the remaining strengths of the piles, beams, and floor slabs of a plurality of trestles, according to the third embodiment, the labor and time can be significantly reduced. Therefore, for example, after evaluating the remaining strengths of all of a plurality of trestles, it is also possible to utilize it as a primary screening function, such as performing a more detailed structural analysis only on those with significant damage to identify specific damaged locations.

[0100] (Modification example) The present invention is not limited to the above-described embodiments (Examples 1 to 3). The above-described embodiments may be modified as follows. Also, two or more of the following modification examples may be combined and implemented.

[0101] (Modification Example 1) In the above embodiment, a pier was used as an object for remaining strength evaluation. However, the present invention is applicable to structures other than piers as long as they are structures having piles, support members supported by the piles, and floor slabs supported by the support members.

[0102] (Modification Example 2) The steps S11 to S14 in FIG. 6 in the above-described Example 1 may be realized by a single learned model. In this case, the learned model uses, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of the pile of the structure, and the external force conditions applied to the pile, and is generated by machine learning using teacher data having, as the objective variable, the usability of the pile when an external force corresponding to the external force conditions is applied to the pile. That is, the evaluation device according to the present invention is an evaluation device used for evaluating the remaining load-bearing capacity of a structure, and uses, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of each pile of the structure, the arrangement information of each pile, and the external force conditions applied to each pile, and is generated by machine learning using teacher data having, as the objective variable, the usability of each pile when an external force corresponding to the external force conditions is applied to each pile. The evaluation device may include a recording unit that records a learned model, an input unit that inputs, as input items, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of the pile to be evaluated among each pile, the arrangement information of the pile, and the external force conditions applied to the pile into the learned model, and an output unit that outputs usability data corresponding to the usability of the pile obtained according to the input by the input unit. Note that the explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each pile and the arrangement information of the beam, and the input unit may input, as input items, the degree of deterioration of a plurality of support members supported by the pile and the arrangement information of the beam into the learned model. Further, the explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each pile and a floor slab supported by the plurality of support members, and the arrangement information of the beam and the floor slab, and the input unit may input, as input items, the degree of deterioration of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members, and the arrangement information of the beam and the floor slab into the learned model. In the present embodiment, it is not necessary to separately provide the determination unit 15 in the recording unit 13.

[0103] (Modification Example 3) In the present invention, the determination unit 15 for determining the availability described in Examples 1, 2, and 3 is not essential, and it may only output the damage state. Further, in the present invention, the configuration for performing machine learning and the configuration for performing the remaining strength evaluation do not have to be provided in one device, and different devices may be provided respectively.

[0104] (Modification Example 4) When repairing piles, it is important which pile to repair in what order. Therefore, a determination unit may be provided between the recording unit 13 and the output unit 16 shown in FIG. 2, and based on the damage state and arrangement information of each pile, and the availability determination of each pile, the arrangement position of the pile to be repaired and the priority of repair may be determined. When there is no determination unit 15, the determination unit determines the priority of repair based on the damage state of each pile. Specifically, a group of piles that are not available is extracted, and among the pile group, since the piles at the end of the pier are affected by a greater external force when the ship berths, they are repaired in order from the ones closer to the end of the pier. Next, an example is conceivable where piles that are available but have a large damage state are repaired in order. That is, the evaluation device according to the present invention includes a determination unit that determines the arrangement position of the pile to be repaired and the priority of repair based on the damage state and arrangement information of each pile, and the availability of each pile, and the output unit may output the determined position of the pile to be repaired and the priority of repair.

[0105] (Modification Example 5) Regarding each pile, it is also conceivable to predict the degree of deterioration at an arbitrary future time point from the current degree of deterioration. As an algorithm for predicting the degree of deterioration at an arbitrary future time point from the current degree of deterioration, those generally used as probability models for future prediction (for example, Markov chain models, etc.) can be utilized. That is, the evaluation device according to the present invention includes a prediction unit that predicts the degree of deterioration at an arbitrary future time point from the current degree of deterioration using a probability model for future prediction, and the explanatory variable may include the predicted degree of deterioration.

[0106] (Modification Example 6) The present invention may also be implemented as an evaluation method implemented using the above-described evaluation apparatus.

[0107] (Modification Example 7) Further, the present invention may be implemented as a program generated by a generation method that generates a damage state learned model by machine learning using, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position in a pile of a structure, and the external force condition for the pile, and using, as the objective variable, the damage state of the pile when an external force corresponding to the external force condition is applied to the pile. The program for operating the above-described evaluation apparatus may be provided in a state recorded on a computer-readable recording medium such as a CD-ROM (Compact Disc Read only memory), or may be downloaded via a communication network such as the Internet.

Explanation of Reference Numerals

[0108] 10: Evaluation apparatus, 11: Acquisition unit, 12: Machine learning unit, 13: Recording unit, 14: Input unit, 15: Determination unit, 16: Output unit, 1001: Processor, 1002: Memory, 1003: Storage, 1004: Communication device, 1005: Input device, 1006: Output device, f... Floor slab, b... Beam, s... Pile.

Claims

1. An evaluation device used for evaluating the remaining bearing capacity in a structure, wherein the degree of deterioration in each pile of the structure and the external force conditions for each pile are used as explanatory variables, a recording unit that records a learned model generated by machine learning using teacher data with the damage state of each pile when an external force corresponding to the external force conditions is applied to each pile as the target variable, an input unit that inputs, as input items, the degree of deterioration of the pile to be evaluated among each of the piles and the external force conditions for the pile into the learned model, and an output unit that outputs damage state data corresponding to the damage state of the pile obtained in response to the input to the learned model by the input unit An evaluation device comprising:

2. The explanatory variables in the learned model further include the deterioration position of each pile and the degree of deterioration at the deterioration position, The input unit further inputs, as the input items, the deterioration position of the pile to be evaluated and the degree of deterioration at the position into the learned model. The evaluation device according to claim 1.

3. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each pile and the external force conditions for the support members, The target variable in the learned model includes the damage state of a plurality of support members supported by each pile when an external force corresponding to the external force conditions is applied to each pile and the plurality of support members supported by the pile, The input unit further inputs, as the input items, the degree of deterioration of a plurality of support members supported by the pile and the external force conditions for the support members into the learned model. The evaluation device according to claim 1 or 2.

4. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each pile and a floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab, The target variable in the learned model includes the damage state of a plurality of support members supported by each pile and the floor slab supported by the plurality of support members when an external force corresponding to the external force conditions is applied to each pile, the plurality of support members supported by the pile, and the floor slab supported by the plurality of support members. The input unit further inputs, as the input items, the degree of deterioration of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members, and external force conditions for the support members and the floor slab, into the learned model, according to the evaluation device described in claim 1 or 2.

5. A determination unit is provided that determines the usability of the pile when an external force corresponding to the external force condition is applied, based on the damage state of the pile and the arrangement information of the pile obtained according to the input to the learned model by the input unit. The evaluation device described in claim 1 or 2.

6. A determination unit is provided that determines the usability of the pile and the support members when an external force corresponding to the external force condition is applied, based on the damage state of the pile and a plurality of support members supported by the pile, and the arrangement information of the pile and the plurality of support members supported by the pile, obtained according to the input to the learned model by the input unit. The evaluation device described in claim 3.

7. A determination unit is provided that determines the usability of the pile, the support members, and the floor slab when an external force corresponding to the external force condition is applied, based on the damage state of the pile, a plurality of support members supported by the pile, and a floor slab supported by the plurality of support members, output by the output unit, and the arrangement information of the pile, the plurality of support members supported by the pile, and the floor slab supported by the plurality of support members. The evaluation device described in claim 4.

8. An evaluation device used for evaluating the remaining load-bearing capacity of a structure, wherein the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of each pile in the structure, and the external force conditions for each pile are used as explanatory variables, a recording unit that records a learned model generated by machine learning using teacher data with the usability of each pile when an external force corresponding to the external force condition is applied to each pile as the target variable, an input unit that inputs, as input items, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of the pile to be evaluated among each pile, and the external force conditions for the pile, into the learned model, and an output unit that outputs usability data corresponding to the usability of the pile obtained according to the input by the input unit. The evaluation device comprising the above components.

9. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each pile, and the external force conditions for the support members. The input unit further inputs, as the input items, the degree of deterioration of a plurality of support members supported by the pile and the external force conditions for the support members to the learned model, according to the evaluation apparatus of claim 8.

10. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by each of the piles and a floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab. The input unit further inputs, as the input items, the degree of deterioration of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members, and the external force conditions for the support members and the floor slab to the learned model, according to the evaluation apparatus of claim 8.

11. The degree of deterioration includes at least any one of whether the deterioration is pitting corrosion, loss of thickness, or both, the range of pitting corrosion or loss of thickness, and the amount of thickness loss when the degree of deterioration is loss of thickness. The evaluation apparatus according to claim 1 or 8.

12. The explanatory variables further include the attributes of each of the piles. The input unit further inputs the attributes of the pile as the input items to the learned model, according to the evaluation apparatus of claim 1 or 8.

13. The external force conditions are at least any one of seismic force, shore approach force, traction force, dead load, or superimposed load on the pile. The evaluation apparatus according to claim 1 or 8.

14. The damage state data is data representing at least any one of the degree of damage, the area of damage, or the percentage of the area of damage. The evaluation apparatus according to claim 1.

15. The output unit As the damage state data, for a structural diagram showing a structure composed of a plurality of support members supported by each of the piles and a plurality of floor slabs supported by the plurality of support members, maps the damage states of each of the piles, the support members, and the floor slabs. Maps and outputs the serviceability of each of the piles with respect to the structural diagram. The evaluation apparatus according to claim 7.

16. A determination unit is provided for determining the priority of repair of the piles, the floor slabs, and the support members to be repaired, based on the damage states of each of the piles, the plurality of support members supported by the piles, and the floor slabs supported by the plurality of support members, and the serviceability of each of the piles. The output unit outputs the arrangement positions and the repair priorities of the piles, the floor slabs, and the support members to be repaired, which are determined. The evaluation apparatus according to claim 7.

17. A prediction unit that predicts the degree of deterioration of each of the piles at an arbitrary future point in time from the degree of deterioration of each of the piles at the current time using a probability model for future prediction is provided. The explanatory variable includes the predicted degree of deterioration. The evaluation device according to claim 1 or 8.

18. An evaluation method implemented using the evaluation device according to claim 1 or 8.

19. A generation method for generating a learned model by machine learning using, as explanatory variables, the degree of deterioration, the deterioration position, or the degree of deterioration at the deterioration position of a pile of a structure and the external force condition for the pile, and using, as the objective variable, the damage state of the pile when an external force corresponding to the external force condition is applied to the pile.

20. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by the pile and the external force condition for the support members. The objective variable in the learned model includes the damage state of a plurality of support members supported by the pile when an external force corresponding to the external force condition is applied to the pile and the support members. The generation method according to claim 19.

21. The explanatory variables in the learned model further include the degree of deterioration of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members, and the external force condition for the support members and the floor slab. The objective variable in the learned model includes the damage state of a plurality of support members supported by the pile and a floor slab supported by the plurality of support members when an external force corresponding to the external force condition is applied to the pile, the support members, and the floor slab. The generation method according to claim 19.

22. A learned model generated by the generation method according to any one of claims 19 to 21.

Images