Prediction device

Abstract

A prediction device (10) according to the present disclosure comprising: a dividing unit (11) that divides a surface of interest of a structure into a plurality of cells in a grid; a setting unit (12) that sets, in a cell corresponding to a degraded portion where degradation has become apparent on the surface of interest, a degree of degradation corresponding to the state of degradation of the degraded portion; and an estimation unit (13) that estimates the degree of degradation of each of the plurality of cells on the basis of the degree of degradation set for the cell, said estimation using a predictive model that predicts the progression of degradation on the basis of degradation in the structure varying continuously with respect to the position of the surface of interest.

Description

Prediction Device

[0001] The present disclosure relates to a prediction device.

[0002] The state in which corrosion progresses due to exposure of reinforcing bars to the outside air caused by cracks or spalling of concrete in reinforced concrete structures (RC structures) is generally considered to be the lifespan (service limit) of the RC structure (see Non-Patent Documents 1-3). Therefore, once the reinforcing bars are exposed (hereinafter referred to as "exposed reinforcing bars"), the RC structure is considered to have reached its service limit, and immediate repairs or replacements are carried out.

[0003] In addition to the aging of infrastructure structures, it is predicted that the number of personnel responsible for maintaining infrastructure structures will decrease in the future. This will require further efficiency in infrastructure maintenance and management, and it is predicted that infrastructure structures will need to be operated to their full capacity.

[0004] As mentioned above, conventionally, RC structures after reinforcement exposure have been considered to be at the limit of their service life, and their behavior has not been fully understood (see Non-Patent Document 4). Therefore, no method has been established to predict the deterioration of structures after reinforcement exposure.

[0005] RC structures with cracks or exposed reinforcement are repaired by repairing cross sections, etc. However, it is not clear to what extent cracks or exposed reinforcement should be repaired when cracks or exposed reinforcement occur in only a portion of an RC structure. Furthermore, when cracks or exposed reinforcement occur due to corrosion of reinforcing steel in concrete caused by salt damage or carbonation, corrosion may be progressing over a large area inside the concrete, and the cracks or exposed reinforcement may only be apparent in a small area.

[0006] Therefore, it is important to understand the extent of corrosion of rebar in areas of undeteriorated concrete near cracked or exposed reinforcement, where concrete deterioration is not apparent, but there are no fully established methods for doing so. Therefore, the general method is to determine the extent of corrosion by visually checking the extent of corrosion along the line of the rebar from the exposed reinforcement during the process of chipping the concrete at the repair site, and then determine the extent of repair.

[0007] There are electrochemical methods for measuring the corrosion state of unexposed rebars. Typically, the potential measurement method conforming to ASTM (American Society for Testing and Materials) C876 (see Non-Patent Documents 5 and 6) is applied. This method involves exposing the unexposed rebars and measuring the potential difference between the exposed rebars and a reference electrode installed on the concrete surface to obtain a potential map of the surface under investigation. The corrosion area is then estimated from the obtained potential map. However, this method requires exposing the unexposed rebars to connect the electrodes, and it is not a definitive diagnosis. Therefore, visual inspection by chipping out the rebars tends to be preferred over potential measurement methods. Furthermore, electrochemical measurement is difficult when cavities exist within the concrete due to jump forces or corrosion expansion of the rebars.

[0008] To predict the future structural strength of a structure, it is necessary to estimate the strength by finite element analysis under conditions that reflect the future deterioration state (see Non-Patent Document 7).

[0009] Kakizaki, Masayoshi, "Life Prediction of Reinforced Concrete Buildings," Safety Engineering, Vol. 31, No. 6, pp. 421-431 (1991). Araki, Kosuke et al., "Spalling of Cover Concrete Due to Corrosion and Expansion of Steel Bars and Its Prediction," Transactions of the Japan Society of Civil Engineers, No. 802, pp. 209-222 (2005). Iyoda, Takeshi et al., "Development of a System for Predicting the Progress of Deterioration of Concrete Structures by Cause," Production Research, Vol. 51, No. 11, pp. 777-780 (1999). Tsuchiya, Naoko et al., "Study on the Manifestation Process of Cracking, Lifting, and Separation Caused by Corrosion of Steel Bars on the Surface of RC Walls with Mortar Finishes," Journal of Structural Engineering and Construction Engineering, Architectural Institute of Japan, Vol. 87, No. 799, pp. 854-865 (2022). Toyoaki Miyagawa, "Measurement of Electric Potential in Concrete Structures," Boshoku Gijutsu, Vol. 36, No. 7, pp. 465-467 (1987). Y. Kawasaki et al., "Phenomenological Process of Rebar Corrosion in Reinforced Concrete Evaluated by Acoustic Emission and Electrochemical Noise," Construction and Building Materials, Vol. 352, Article 128829 (2022). Narihiko Saito et al., "Effect of Rebar Corrosion Distribution on the Flexural Load-Carrying Properties of RC Beams," Journal of the Japan Society of Civil Engineers, Proceedings of the Society of Civil Engineers, Vol. 64, No. 4, pp. 601-611 (2008).

[0010] As mentioned above, it is not clear how the exposed reinforcement expands in reinforced concrete structures after the reinforcement is exposed. In the exposed reinforcement, corrosion of the rebar near the boundary between the exposed and unexposed reinforcement progresses concrete spalling. Furthermore, the larger the extent of corrosion of the rebar in the unexposed reinforcement, the more significant the expansion of the exposed reinforcement.

[0011] It is desirable to repair not only exposed reinforcement but also unexposed reinforcement, but because the extent of rebar corrosion near the exposed reinforcement is unknown until the reinforcement is removed, it is difficult to estimate and determine the extent of repair in advance. Therefore, even if repairs are carried out, if the unexposed reinforcement is not repaired sufficiently, there is a risk that further repairs will be required in a short period of time.

[0012] Therefore, there is a need for a technology to predict deterioration in areas of structures where deterioration is not apparent, based on apparent deterioration such as cracks or exposed reinforcement.

[0013] The purpose of the present disclosure, made in consideration of the above-mentioned problems, is to provide a prediction device that can predict deterioration in areas of a structure where deterioration is not apparent from deterioration that has already become apparent.

[0014] In order to solve the above problem, the prediction device disclosed herein is a prediction device that predicts the progression of deterioration of a structure, and includes a division unit that divides the target surface of the structure into a plurality of grid-like cells, a setting unit that sets a deterioration level in a cell corresponding to a deteriorated portion on the target surface where deterioration is apparent, according to the deterioration state of the deteriorated portion, and an estimation unit that estimates the deterioration level of each of the plurality of cells based on the deterioration level set in the cell, using a prediction model that predicts the progression of deterioration based on the fact that deterioration in the structure changes continuously with respect to the position on the target surface.

[0015] According to the prediction device of the present disclosure, it is possible to predict deterioration in areas of a structure where deterioration is not apparent from deterioration that has already become apparent.

[0016] 1. A diagram showing an example of the configuration of a prediction device according to an embodiment of the present disclosure. 1. A diagram showing an example of the configuration of a manhole, which is a reinforced concrete structure. 2. A diagram showing an example of the configuration of the ceiling part of the manhole shown in FIG. 2A. 3. A diagram showing an example of deterioration information. 4. A flowchart showing an example of the operation of the prediction device shown in FIG. 1. 5. A diagram showing an example of division of a target surface by the division unit shown in FIG. 1. 6. A diagram for explaining the remaining diameter of a reinforcing bar. 7. A diagram for explaining the cover of a reinforcing bar. 8. A diagram showing an example of setting of a deterioration level by the setting unit shown in FIG. 1. 9. A diagram for explaining calculation of an average value by the estimation unit shown in FIG. 1. 10. A diagram showing an example of an estimation result of a deterioration level using a cellular automaton model by the estimation unit shown in FIG. 1. 11. A diagram showing another example of an estimation result of a deterioration level using a cellular automaton model by the estimation unit shown in FIG. 1. 12. A diagram showing yet another example of an estimation result of a deterioration level using a cellular automaton model by the estimation unit shown in FIG. 1. 13. A diagram showing yet another example of an estimation result of a deterioration level using a cellular automaton model by the estimation unit shown in FIG. 1. 14. A flowchart showing another example of the operation of the prediction device shown in FIG. 1. 15. A diagram for explaining the deterioration level predicted in FIG. 10. 16. A diagram showing another example of division of a target surface by the division unit shown in FIG. 1. 17. A diagram showing another example of setting of a deterioration level by the setting unit shown in FIG. 1. Fig. 2 is a diagram showing an example of a result of estimation of a deterioration level using a nonlinear regression model by the estimation unit shown in Fig. 1. Fig. 3 is a diagram showing another example of a result of estimation of a deterioration level using a nonlinear regression model by the estimation unit shown in Fig. 1. Fig. 4 is a diagram showing an example of the configuration of a computer that functions as the prediction device shown in Fig. 1.

[0017] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0018] 1 is a diagram illustrating an example configuration of a prediction device 10 according to an embodiment of the present disclosure. The prediction device 10 according to the present disclosure predicts the progress of deterioration of a structure. In this embodiment, the structure is described as a reinforced concrete structure (RC structure) including a plurality of reinforcing bars extending in a predetermined direction, but the structure is not limited to this.

[0019] In the following description, the structure is a manhole 1 buried underground as shown in Fig. 2A, and the progress of deterioration in a ceiling portion (slab) 1A of the manhole 1 is predicted. Fig. 2B is a diagram showing the state of looking up at the ceiling portion 1A from inside the manhole 1. As shown in Fig. 2B, in the ceiling portion 1A, for example, a plurality of reinforcing bars 2 extending in a predetermined direction (x direction) are arranged side by side in the y direction.

[0020] As shown in FIG. 1, a prediction device 10 according to this embodiment includes a division unit 11, a setting unit 12, an estimation unit 13, and an output unit 14.

[0021] The dividing unit 11 receives input of target surface information. The target surface information is information relating to a target surface of a structure that is a target for predicting deterioration. The target surface information is, for example, information such as the shape and dimensions of the target surface. The dividing unit 11 divides the target surface of the structure indicated in the target surface information into a plurality of cells in a lattice pattern. The dividing unit 11 outputs the result of dividing the target surface into a plurality of cells to the setting unit 12.

[0022] Deterioration information is input to the setting unit 12. The deterioration information is information related to deterioration on a target surface. The deterioration information may be, for example, information indicating the deterioration state of each cell on the target surface of a structure. The deterioration information may also be, for example, a photographed image of the target surface of the structure, as shown in FIG. 3. FIG. 3 shows an example of the deterioration information being a photographed image of the ceiling portion 1A of a manhole 1, in which deterioration such as cracks or exposed reinforcement has become apparent. Deterioration of a structure includes exposed reinforcement of several centimeters to several tens of centimeters, leakage of rust fluid, exposed reinforcement in small areas where aggregate has fallen out, and surface-wide concrete lifting or cracking.

[0023] Based on the input deterioration information, the setting unit 12 sets a deterioration degree corresponding to the deterioration state of a deteriorated portion in a cell corresponding to a deteriorated portion in which deterioration is apparent on the target surface. For example, if the deterioration information is information indicating the deterioration state of each cell, the setting unit 12 sets a deterioration degree corresponding to the deterioration state of each cell indicated in the deterioration information in the corresponding cell of the target surface. Also, for example, if the deterioration information is a photographed image of a structure in which deterioration is apparent, as shown in FIG. 3, the setting unit 12 sets a deterioration degree corresponding to the deterioration state in a cell corresponding to the deterioration that is apparent in the photographed image.

[0024] The estimation unit 13 uses a prediction model that predicts the progress of deterioration in the structure to estimate the degree of deterioration of each of the multiple cells based on the degree of deterioration set for the cell by the setting unit 12. Here, the prediction model is a model that predicts the progress of deterioration based on the fact that the deterioration in the structure changes continuously with the position on the target surface.

[0025] An example of such a prediction model is a cellular automaton model. A cellular automaton is a method of predicting future states by setting rules for interactions between neighboring cells and changing the state over time for a large number of cells arranged in a grid pattern in space. A cellular automaton model is a model that applies this method. In this embodiment, the cellular automaton model estimates the deterioration level of a cell (estimation target cell) whose deterioration level is to be estimated using the deterioration levels of cells surrounding the cell. Another example of a prediction model is a nonlinear regression model. A nonlinear regression model is a model that estimates the deterioration level of a cell (estimation target cell) by regression analysis using the deterioration levels of cells in the same row or column as the estimation target cell whose deterioration level is to be estimated. Details of degradation level estimation using each model will be described later.

[0026] The estimation unit 13 outputs the estimation result of the deterioration level of the target surface of the structure to the output unit 14 .

[0027] The output unit 14 outputs the estimation result of the deterioration degree of the target surface of the structure output from the estimation unit 13. The output unit 14 outputs the estimation result of the deterioration degree by, for example, displaying it on a display device.

[0028] Next, the estimation of the deterioration level by the estimation unit 13 will be described. As described above, the estimation unit 13 estimates the deterioration level of the target surface using a prediction model that predicts the progress of deterioration based on the fact that the deterioration of the structure changes continuously with respect to the position on the target surface. Such prediction models include a cellular automaton model or a nonlinear regression model. First, the estimation of the deterioration level using a cellular automaton model will be described.

[0029] As described above, the cellular automaton model is a model that estimates the deterioration level of an estimation target cell using the deterioration levels of cells surrounding the estimation target cell. Therefore, in this embodiment, the deterioration level of each of the multiple cells obtained by dividing the target surface is expressed numerically. Because the concrete cover (the depth from the concrete surface to the rebar 2) and the properties of the concrete continuously change within a structure, it is thought that deterioration continuously changes with the position on the target surface. Therefore, the deterioration states of adjacent cells are potentially similar. Therefore, in this embodiment, the deterioration level of a cell (estimation target cell) corresponding to a portion where deterioration is not apparent is estimated from the deterioration levels of the cells surrounding the estimation target cell using a cellular automaton model.

[0030] 4 is a flowchart showing an example of the operation of the prediction device 10 according to this embodiment, and is a diagram for explaining a prediction method by the prediction device 10 according to this embodiment. In FIG. 4, the operation of the prediction device 10 when a cellular automaton model is used as a prediction model will be explained.

[0031] To estimate the degree of deterioration according to the concept of cellular automata, the aggregation targets and the number of repetitions N for the deterioration threshold α, the deterioration rate β, and the average value μ are set in advance. The deterioration threshold α is a threshold for determining whether deterioration is progressing in a cell based on the cell's deterioration level. For example, if the expected final state of deterioration is 1 and the intermediate state of deterioration, such as cracking or peeling of concrete, is 0.9 to 0.7, the deterioration threshold α is set to a value between 0.7 and 0.2. The deterioration rate β is a value that is uniformly added to cells determined to be undergoing deterioration and determines the degree of progression of deterioration. The deterioration rate β can be any value, but when predicting detailed deterioration, a value of approximately 0.1 is set. The deterioration threshold α and the deterioration rate β are appropriately set according to the condition of the structure. The aggregation targets for the average value μ are cells used to calculate the average value μ as the deterioration level of blank cells, as described below. The number of repetitions N is the number of times the process described with reference to FIG. 4 is repeated. At the start of the process shown in FIG.

[0032] The various constants mentioned above are set by preparing inspection results or photographic images of the structure that can confirm the progression of deterioration of the structure, reflecting the deterioration in multiple cells in a grid, and setting them so that the progression of actual deterioration matches the estimation results of the prediction model. In this way, constants can be set to match the actual situation of the structure.

[0033] The dividing unit 11 divides the target surface of the structure into a plurality of cells in a lattice pattern (step S11). In the following, it is assumed that the dividing unit 11 divides the rectangular target surface into 16 cells (four cells in the x direction and four cells in the y direction orthogonal to the x direction) as shown in Fig. 5 .

[0034] Based on the deterioration information, the setting unit 12 sets a deterioration degree corresponding to the deterioration state of the deteriorated portion in a cell corresponding to a deteriorated portion where deterioration is apparent on the target surface (step S12). If the structure is a reinforced concrete structure, the deterioration degree is an index indicating the cause or result of corrosion of the reinforcing bar 2. Examples of such an index include the remaining diameter of the reinforcing bar 2, the exposed length, the exposed area, and the cover of the reinforcing bar 2. As shown in FIG. 6A, the remaining diameter of the reinforcing bar 2 is the diameter of the reinforcing bar 2 reduced by corrosion. As shown in FIG. 6B, the cover of the reinforcing bar 2 is the depth from the concrete surface to the reinforcing bar 2. The exposed area can be calculated by multiplying the diameter of the reinforcing bar 2 by the exposed length.

[0035] In reinforced concrete structures, a corrosion-resistant environment is maintained by burying reinforcing bars in alkaline concrete, but carbon dioxide neutralizes the alkali from the surface of the concrete. Therefore, if the cover of the reinforcing bars 2 is thin, the reinforcing bars 2 are more susceptible to corrosion.

[0036] As mentioned above, if the cover of the reinforcing bar 2 is thin, the reinforcing bar 2 is prone to corrosion. When the remaining diameter of the reinforcing bar 2 decreases due to corrosion, the corrosion products generate expansion pressure. This expansion pressure causes cracks in the concrete, causing spalling. If the cracks in the concrete are hairline cracks of about 0.1 mm, they are often difficult to detect, but after the reinforcing bar is exposed, the corroded reinforcing bar 2 becomes exposed, making it easy to visually confirm.

[0037] Fig. 7 is a diagram showing an example of setting the deterioration level by the setting unit 12. As shown in Fig. 7, the setting unit 12 sets a deterioration level in a cell corresponding to a deteriorated portion and leaves other cells blank. Fig. 7 shows an example in which the deterioration level of a cell corresponding to a deteriorated portion is set to 1.

[0038] 4 again, the estimation unit 13 estimates the degradation level of blank cells among the plurality of cells obtained by dividing the target surface. In this embodiment, the estimation unit 13 calculates the average value μ of the degradation levels of the cells surrounding the cell whose degradation level is to be estimated (the estimation target cell) as the degradation level of the estimation target cell (step S13).

[0039] 8 is a diagram for explaining cells used when calculating the average value μ as the degradation degree of blank cells, in which cell a is assumed to be the cell to be estimated.

[0040] The estimation unit 13 calculates, for example, the average value μ of the degradation levels set in cells a1 to a4 above, below, left, and right of the estimation target cell a as the degradation level of the estimation target cell a. The estimation unit 13 also calculates, for example, the average value μ of the degradation levels set in cells a1 to a8 above, below, left, right, upper right, upper left, lower left, and lower right of the estimation target cell a as the degradation level of the estimation target cell a. If all of the cells surrounding the estimation target cell a are blank, the estimation unit 13 cannot calculate the average value μ and leaves the estimation target cell a as a blank cell.

[0041] Referring again to FIG. 4, the estimation unit 13 determines whether the average value μ calculated for the blank cells (estimation target cells) is equal to or less than the deterioration progress threshold value α (μ≦α) (step S14).

[0042] If it is determined that the average value μ calculated for the blank cell is equal to or less than the deterioration progression threshold value α (step S14: Yes), the estimation unit 13 assumes that no deterioration has occurred in the part corresponding to the blank cell and inputs 0 as the deterioration degree of the blank cell (step S15).

[0043] If it is determined that the average value μ calculated for the blank cell is greater than the deterioration progression threshold value α (step S14: No), the estimation unit 13 assumes that deterioration has occurred in the part corresponding to the blank cell and inputs the average value μ as the deterioration degree of the blank cell (step S16).

[0044] After the processing of step S15 or step S16, the estimation unit 13 adds the deterioration progress rate β to the values ​​of the cells excluding blank cells and cells in which 0 is entered as the deterioration degree (step S17). In this way, the progress of deterioration can be simulated.

[0045] Next, the estimation unit 13 determines whether the variable n is less than the number of repetitions N (n<N) (step S18).

[0046] If it is determined that the variable n is less than the number of repetitions N (step S18: Yes), the estimation unit 13 adds 1 to the variable n (step S19) and returns to the processing of step S13.

[0047] If it is determined that the variable n has reached the number of repetitions N (step S18: No), the estimation unit 13 outputs the estimated results of the deterioration level of each of the multiple cells into which the target surface is divided to the output unit 14 and terminates the processing.

[0048] 9A to 9D are diagrams illustrating an example of a degradation level estimation result using a cellular automaton model. In FIGS. 9A to 9D, the degradation progress threshold α is set to 0.5, and the degradation progress rate β is set to 0.1. Also, in FIGS. 9A to 9D, the average degradation level of the four cells above, below, left, and right of the cell being estimated is calculated as the average value μ. FIG. 9A is a diagram illustrating an example of a degradation level estimation result (i.e., the initial value of the degradation level) when the degradation level estimation is repeated 0 times. FIG. 9B is a diagram illustrating an example of a degradation level estimation result when the degradation level estimation is repeated 1 time. FIG. 9C is a diagram illustrating an example of a degradation level estimation result when the degradation level estimation is repeated 3 times. FIG. 9D is a diagram illustrating an example of a degradation level estimation result when the degradation level estimation is repeated 5 times. In Figures 9A to 9D, for example, if the deterioration level for exposed reinforcement is set to 1 or higher and the deterioration level for cracked / loose concrete is set to 0.8 or higher, the deterioration level at the position corresponding to each cell on the target surface can be estimated from the deterioration level value of each cell.

[0049] 9A to 9D, the more the number of repetitions, the more deteriorated parts with a deterioration level of 0.5 or higher will be, and the greater the deterioration level in the deteriorated parts will be. Therefore, by setting constants such as the deterioration progression threshold value α, the deterioration progression rate β, and the number of repetitions N to appropriate values ​​that match the actual conditions of the structure whose deterioration level is to be estimated, it is possible to estimate the deterioration level of the target surface of the structure.

[0050] Next, estimation of the deterioration level using a nonlinear regression model will be described.

[0051] The regression model is expressed by the following equation (1). In equation (1), z is the deterioration level, y is the position, and A, B, and C are constants. The constants A, B, and C are derived by nonlinear regression: z = A (y + B) ２ +C formula (1)

[0052] As in the case of using a cellular automaton model, the dividing unit 11 divides the target surface into a plurality of cells in a lattice pattern.

[0053] Based on the deterioration information, the setting unit 12 sets a deterioration degree z corresponding to the deterioration state of the deteriorated portion in a cell corresponding to the deteriorated portion of the target surface where deterioration is apparent. For example, if the cover of the reinforcing bar 2 can be measured, the actual measured value may be used as the deterioration degree z. Furthermore, if the actual measured value of the cover of the reinforcing bar 2 is not available, for example, the deteriorated length or deteriorated area of ​​the reinforcing bar 2 may be used as the deterioration degree z.

[0054] The estimation unit 13 uses a nonlinear regression model to estimate the degradation level of each cell based on the degradation level set by the setting unit 12 .

[0055] Fig. 10 is a flowchart showing another example of the operation of the prediction device 10 according to this embodiment, and is a diagram for explaining the prediction method by the prediction device 10 according to this embodiment. Fig. 10 explains the operation of the prediction device 10 when a nonlinear regression model is used as the prediction model. Below, as shown in Fig. 11, an example will be explained in which the cover of the reinforcing bars 2 in the unexposed reinforcement bars is estimated as the deterioration degree z from the cover of the reinforcing bars 2 in the exposed reinforcement bars.

[0056] The dividing unit 11 divides the target surface of the structure into a plurality of cells in a lattice pattern (step S21). In the following, it is assumed that the dividing unit 11 divides the rectangular target surface into 25 cells (5 cells in the x direction and 5 cells in the y direction orthogonal to the x direction) as shown in Fig. 12 .

[0057] Based on the deterioration information, the setting unit 12 sets a deterioration level corresponding to the deterioration state of the deteriorated portion in the cell corresponding to the deteriorated portion where deterioration is apparent on the target surface (step S22).

[0058] Fig. 13 is a diagram showing an example of setting the deterioration level to cells by the setting unit 12. As shown in Fig. 13, the setting unit 12 sets the deterioration level (cover of reinforcing bars 2 (depth from the concrete surface of the exposed reinforcement part to the reinforcing bars 2)) to cells corresponding to deteriorated parts, and leaves other cells blank.

[0059] Referring again to FIG. 10, the estimation unit 13 selects one cell to be estimated from the blank cells (step S23).

[0060] The estimation unit 13 determines whether the degradation level of the estimation target cell can be estimated using a nonlinear regression model (step S24). Specifically, the estimation unit 13 determines whether the row or column including the estimation target cell includes four or more cells with degradation levels set. If the row or column including the estimation target cell includes four or more cells with degradation levels set, the estimation unit 13 determines that the degradation level of the estimation target cell can be estimated. If the row or column including the estimation target cell does not include four or more cells with degradation levels set, the estimation unit 13 determines that the degradation level of the estimation target cell cannot be estimated.

[0061] When it is determined that the degradation level of the estimation target cell cannot be estimated (step S24: No), the estimation unit 13 returns to the process of step S22. In this way, when the degradation level of the estimation target cell cannot be estimated, the degradation level can be additionally input, thereby making it possible to estimate the degradation level of the estimation target cell.

[0062] If it is determined that the degradation level of the cell to be estimated can be estimated (step S24: Yes), the estimation unit 13 estimates the degradation level of the cell to be estimated using a nonlinear regression model based on the degradation levels of the cells included in the row or column containing the cell to be estimated (step S25).

[0063] The estimation of the deterioration level by the estimation unit 13 will be described using an example shown in FIG.

[0064] For example, suppose the estimation unit 13 selects the cell in row 2, column 1 as the estimation target cell. In this case, since the first column contains four cells with degradation levels set, the estimation unit 13 estimates the degradation level of the estimation target cell using a nonlinear regression model based on the degradation levels of these cells. As shown in FIG. 14 , the estimation unit 13 sets the estimated degradation level as the degradation level of the estimation target cell (the cell in row 2, column 1).

[0065] 13, for example, the cell in row 2, column 4 is selected as the estimation target cell. In this case, neither row 2 nor column 4 includes four or more cells with a degradation level set, so the estimation unit 13 determines that it cannot estimate the degradation level of the estimation target cell.

[0066] Note that both the column and row containing the estimation target cell may contain four or more cells with a degradation level set. That is, regression analysis may be possible in both the x-axis direction and the y-axis direction. In this case, the estimation unit 13 may use, for example, the larger of the degradation levels estimated by regression analysis in the x-axis direction and the y-axis direction as the degradation level of the estimation target cell.

[0067] Furthermore, the estimation unit 13 may use the degradation level estimated for the estimation target cell to estimate the degradation level of another estimation target cell, thereby making it possible to sequentially estimate the degradation levels of blank cells.

[0068] For example, in the example shown in Fig. 14, the estimation unit 13 selects the cell in row 2, column 4 as the cell to be estimated. In this case, after the degradation level of the cell in row 2, column 1 is estimated, four or more cells with degradation levels set are included in the second row. Therefore, the estimation unit 13 can estimate the cell in row 2, column 4, as shown in Fig. 15, based on the degradation levels of the cells included in the second row.

[0069] By estimating the cover of the rebar 2 as the deterioration level of each cell, for example, if the cover of the rebar 2 is 30 mm or more and is sound, cells with a deterioration level of less than 30 mm are likely to deteriorate and are in a latent deterioration area, making it possible to take measures such as repairing them before the deterioration becomes apparent.In addition, since the shallower the cover, the higher the possibility of deterioration, it is possible to compare the deterioration levels of each cell and determine the priority of repairs.

[0070] As described above, the prediction device 10 according to this embodiment includes a dividing unit 11, a setting unit 12, and an estimating unit 13. The dividing unit 11 divides the target surface of the structure into a plurality of cells in a grid pattern. The setting unit 12 sets a deterioration level in a cell corresponding to a deteriorated portion on the target surface where deterioration has become apparent, according to the deterioration state of the deteriorated portion. The estimating unit 13 estimates the deterioration level of each of the plurality of cells based on the deterioration level set for the cell, using a prediction model that predicts the progress of deterioration based on the fact that the deterioration of the structure changes continuously with respect to the position on the target surface.

[0071] By setting a deterioration level in a cell corresponding to an apparent deteriorated part according to the deterioration state of the deteriorated part, and using a prediction model to estimate the deterioration level of each of multiple cells based on the deterioration level set in the cell, it is possible to predict deterioration in areas of a structure where deterioration is not apparent from the apparent deterioration.

[0072] The prediction device 10 described above can be realized by a computer 20 shown in FIG. 16 . A program for causing the computer 20 to function as the prediction device 10 may be provided. The program may be stored in a storage medium or provided via a network. FIG. 16 is a block diagram showing a schematic configuration of a computer 20 functioning as the prediction device 10. The computer 20 may be a general-purpose computer, a dedicated computer, a workstation, a PC (Personal Computer), an electronic notepad, or the like. The program instructions may be program code, code segments, or the like for performing necessary tasks.

[0073] 16, a computer 20 includes a processor 21, a ROM (Read Only Memory) 22, a RAM (Random Access Memory) 23, a storage 24, an input unit 25, a display unit 26, and a communication interface (I / F) 27. Each component is communicably connected to one another via a bus 29. The processor 21 is specifically a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), a SoC (System on a Chip), or the like, and may be configured with multiple processors of the same or different types.

[0074] The processor 21 is a control unit that controls each component and performs various arithmetic processing. That is, the processor 21 reads a program from the ROM 22 or the storage 24 and executes the program using the RAM 23 as a work area. The processor 21 controls each component and performs various arithmetic processing in accordance with the program stored in the ROM 22 or the storage 24. In this embodiment, the ROM 22 or the storage 24 stores a program for causing the computer 20 to operate as the prediction device 10 according to the present disclosure. The program is read and executed by the processor 21 to realize each component of the prediction device 10, such as the division unit 11, the setting unit 12, the estimation unit 13, and the output unit 14.

[0075] The program may be provided in a form stored on a non-transitory storage medium such as a CD-ROM (Compact Disk Read Only Memory), a DVD-ROM (Digital Versatile Disk Read Only Memory), a USB (Universal Serial Bus) memory, etc. The program may also be provided in a form downloaded from an external device via a network.

[0076] The ROM 22 stores various programs and various data. The RAM 23 temporarily stores programs or data as a working area. The storage 24 is configured with an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs including the operating system and various data.

[0077] The input unit 25 includes a pointing device such as a mouse and a keyboard, and is used to input various information. The input unit 25 receives input of, for example, deterioration information and target surface information.

[0078] The display unit 26 is, for example, a liquid crystal display, and displays various types of information. The display unit 26 may employ a touch panel system and function as the input unit 25. The display unit 26 displays, for example, the result of estimation by the estimation unit 13 of the deterioration degree of the target surface of the structure.

[0079] The communication interface 27 is an interface for communicating with other devices, for example, an interface for a LAN.

[0080] The following additional notes are provided regarding the above-described embodiments.

[0081] [Supplementary Item 1] A prediction device for predicting the progress of deterioration of a structure, comprising a control unit, wherein the control unit divides a target surface of the structure into a plurality of lattice-like cells, sets a degree of deterioration in a cell corresponding to a deteriorated portion on the target surface where deterioration is apparent, according to the deterioration state of the deteriorated portion, and estimates the degree of deterioration of each of the plurality of cells based on the degree of deterioration set in the cell, using a prediction model that predicts the progress of deterioration based on the fact that deterioration in the structure changes continuously with respect to the position on the target surface.

[0082] [Supplementary Item 2] In the prediction device according to Supplementary Item 1, the prediction model is a cellular automaton model that estimates the deterioration level of an estimation target cell using the deterioration levels of cells surrounding the estimation target cell.

[0083] [Supplementary Item 3] In the prediction device described in Supplementary Item 1, the prediction model is a nonlinear regression model that estimates the deterioration level of the estimation target cell by regression analysis using the deterioration levels of cells included in the same row or column as the estimation target cell, whose deterioration level is to be estimated.

[0084] [Supplementary Item 4] In the prediction device according to any one of Supplementary Items 1 to 3, the structure is a reinforced concrete structure, and the deterioration level is a remaining diameter of rebar, an exposed rebar length, an exposed rebar area, or a cover of rebar.

[0085] Although the above-described embodiments have been described as typical examples, it will be apparent to those skilled in the art that many modifications and substitutions can be made within the spirit and scope of the present disclosure. Therefore, the present invention should not be interpreted as being limited by the above-described embodiments, and various modifications and alterations are possible without departing from the scope of the claims. For example, multiple building blocks shown in the block diagrams of the embodiments can be combined into one, or one building block can be divided.

[0086] REFERENCE SIGNS LIST 1 Manhole 1A Ceiling 2 Reinforcing bar 10 Prediction device 11 Division unit 12 Setting unit 13 Estimation unit 14 Output unit 20 Computer 21 Processor 22 ROM 23 RAM 24 Storage 25 Input unit 26 Display unit 27 Communication I / F 29 Path

Claims

1. A prediction device for predicting the progression of deterioration of a structure, comprising: a division unit for dividing a target surface of the structure into a plurality of lattice-like cells; a setting unit for setting a deterioration level in a cell corresponding to a deteriorated portion on the target surface where deterioration is evident, according to the deterioration state of the deteriorated portion; and an estimation unit for estimating a deterioration level of each of the plurality of cells based on the deterioration level set in the cell, using a prediction model for predicting the progression of deterioration based on the fact that deterioration of the structure changes continuously with respect to the position on the target surface.

2. A prediction device as described in claim 1, wherein the prediction model is a cellular automaton model that estimates the deterioration level of a cell to be estimated using the deterioration levels of cells surrounding the cell to be estimated.

3. A prediction device as described in claim 1, wherein the prediction model is a nonlinear regression model that estimates the deterioration level of a cell to be estimated by regression analysis using the deterioration levels of cells included in the same row or column as the cell to be estimated, the deterioration level of which is to be estimated.

4. A prediction device according to claim 1, wherein the structure is a reinforced concrete structure, and the degree of deterioration is the remaining diameter of rebar, exposed rebar length, exposed rebar area, or rebar cover.