JP2007140608A - Structure repair construction plan support system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a structure repair construction plan support system providing necessity of repair work as evaluation information wherein the necessity is objectively and quantitatively evaluated when drafting a repair work plan to a civil engineering structure, and allowing objective and quantitative evaluation even to aging deterioration of the structure to support the drafting of the structure repair work business plan with the objective and high-accuracy evaluation. <P>SOLUTION: This structure repair construction plan support system has an information input device, an information storage device, an information calculation device, and an information output device, and calculates the necessity of the repair work in the structure on the basis of a distinction boundary line or a distinction boundary plane (hereinafter referred to as the distinction boundary plane including the distinction boundary line) for separating the necessity of the repair work obtained by use of results data of past repair construction/non-construction and factor data related to a factor of the deterioration in each structure. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention prevents the occurrence of defects or accidents in a structure on the basis of a repair determination boundary surface obtained by analyzing information on construction / non-construction results of repair work for a plurality of structures. The present invention relates to a structure repair work plan support system that evaluates the degree of necessity of repair work and evaluates the effects of deterioration and repair work that occur in the structure.

Civil engineering structures such as bridges and tunnels are regularly inspected for maintenance, and if damage is found, the extent is usually determined and necessary repair measures are taken. However, the determination of the degree of damage is largely based on the subjectivity based on the experience of the inspection engineer, and it cannot be denied that the criteria for determining the repair policy were ambiguous.
For this reason, there are many discrepancies between the evaluation results and the actual damage situation, and there are still problems of accuracy and objectivity, such as the evaluation itself completely changing if the evaluator changes.
In recent years when effective use of civil engineering structures is required, maintenance of existing social capital is an urgent task, but in order to implement this more efficiently, it has higher accuracy and objectivity. It is considered indispensable to establish a method for evaluating the damaged state.
In addition to civil engineering structures, such evaluation methods are used when reinforcing work and countermeasures such as drainage grooves are applied to steep slopes from the viewpoint of preventing natural disasters such as earth and sand disasters. The present inventors have already conducted various studies from the viewpoint of preventing natural disasters.

  For example, regarding research to obtain highly accurate information by computer processing data related to the occurrence or non-occurrence of actual disasters to support the planning of disaster prevention business plans, the present inventors have already used it to predict the occurrence of landslides. As shown in Non-Patent Document 1, a method of setting a breakage occurrence limit line, an evacuation reference line, and a warning reference line, which is a generated boundary between generated rain and non-occurrence rain, is disclosed.

Non-Patent Document 1 uses a radial basis function network (RBFN) excellent in non-linear discrimination for the purpose of setting a high-precision occurrence limit line, etc., without performing a linear approximation of complex natural phenomena, A method for setting a critical rainfall curve for landslides is proposed. In the technology disclosed in Non-Patent Document 1, a non-linear collapse occurrence limit rainfall line is set by using RBFN and determining the optimum weight of the intermediate layer and the output layer using the learning function.
As a result, for example, in Non-Patent Document 1, a discrimination boundary surface having an effective rainfall on the horizontal axis and an hourly rainfall on the vertical axis is drawn as a set of curves.
This curve shows a so-called contour line, which indicates a non-linear landslide occurrence limit line. The discrimination boundary surface plots the occurrence and non-occurrence effective rainfall and hourly rainfall, and sets the teacher value to -1 in the case of a disaster as the height direction, and the teacher value in the case of a non-occurrence. This is calculated by superposing the radial basis functions with +1. Accordingly, these contour lines are higher near the origin, and gradually lower from the lower left corner where the origin exists to the diagonal direction.
It is possible to judge highly accurate disaster prevention projects by quantitatively and objectively drawing such disaster occurrence limit lines, evacuation reference lines, and warning reference lines (hereinafter collectively referred to as CL). In addition, since a huge amount of data can be processed in a short time by computer processing, it is possible to prevent the CL from becoming obsolete and provide highly accurate information.

Patent Document 1 discloses a system provided with a means for automatically selecting and displaying a disaster countermeasure to be executed when a disaster occurs, and indicating the progress status as a “disaster countermeasure support system”. Yes.
The disaster countermeasure support system disclosed in this Patent Document 1 basically reads and copes with a list of countermeasures stored in association with events that occur in advance and corresponding countermeasures in an if-then format. is there. It was designed to enable accurate judgments in situations where there is no mental, temporal, or human capacity at the time of a disaster. In addition, by displaying the standard work time, the work time required during actual work, and the remaining time that can be taken, it is possible to grasp the progress of the measure in real time, and at the same time, measures with high importance and low measures It can also be used to select.

Further, Patent Document 2 discloses an invention in which the technology disclosed in Non-Patent Document 1 is applied to a warning and evacuation system. In the invention disclosed in this patent document 2, a short-term rainfall index, for example, the maximum time within 3 hours from the time of occurrence is taken into account, taking into account the topographic factors, geological / soil factors, environmental factors and earthquake factors that affect disasters. Rainfall (hereinafter, a typical rainfall within a certain period of time may be abbreviated as “hourly rainfall”), and an effective rainfall with a half-life at that time of 72 hours, for example, as a long-term rainfall index, CL is calculated.
By using CL thus obtained, it is possible to provide a highly reliable warning and evacuation support system.

On the other hand, there are inventions disclosed in, for example, Patent Documents 3 and 4 regarding a system for evaluating the cost related to the maintenance of a structure and the degree of deterioration thereof.
In Patent Document 3, “Concrete structure maintenance management device” accurately calculates the costs related to the maintenance of facilities, taking into account factors such as the natural environment, concrete materials, and construction methods that are affected by the deterioration phenomenon of concrete structures An invention that can be made is disclosed. In the present invention, the first deterioration state prediction means for predicting the future deterioration state, the second deterioration state prediction means for predicting the deterioration state after repair, and the magnitude of the potential damage in the facility or the like as a risk. A potential risk calculation means for quantitatively calculating is provided. With these components, it is possible to calculate a deterioration state and a potential risk, respectively.
Further, in Patent Document 4, as a “structure maintenance management system, maintenance management method, and its content file storage device”, it is possible to introduce private funds while ensuring safety for small and medium-sized distributed structures, An invention relating to a structure management system using only taxes or subsidies is disclosed.
In the maintenance management system of this structure, it is possible to quantitatively grasp the characteristics of the structure such as the remaining life and the proof stress, and to provide the structure data file in which the data is stored and the state of the bridge and other structures, for example, For maintenance management or maintenance management by constructing a system capable of quantitatively diagnosing the remaining life, proof stress or degree of fatigue damage, and predicting deterioration / damage against them, and appropriately selecting countermeasure methods and expenses for dealing with them It is possible to accurately assess the cost of
Kazumasa Kuramoto et al. 5: Research on the setting of the non-linear collapse occurrence limit rainfall line using the RBF network, No. 672 / VI-50, pp. 117-132, 2001.3 JP 2002-230235 A JP 2003-184098 A Japanese Patent Laid-Open No. 2001-200355 JP 2001-306670 A

However, in the inventions disclosed in Non-Patent Document 1 and Patent Document 2, the focus is on setting a disaster occurrence limit line, an evacuation reference line, and a warning reference line, and a specific area or a certain condition In the regional groups compiled for each, the objective was to objectively evaluate the extent to which the short-term rainfall index and the long-term rainfall index reached the risk of disaster occurrence. Extremely speaking, the data of short-term and long-term rainfall index accumulated at the same point is input, and how much rain will cause a disaster based on the rain data accumulated at that point. Judgment was made.
Even though this is an objective and quantitative evaluation, it is possible to carry out individual specific evaluations for each region or group, but it is not a specific region but a general and universal common to all regions. There was a problem that it was difficult to evaluate. In other words, as data, comprehensive potential hazards obtained by using various regional data together, grasping various factors included in them, selecting them as variables and combining them There was a problem that it was difficult to evaluate the degree.

In addition, in the invention disclosed in Patent Document 1, a specific implementation of countermeasures using a list-structured data structure with predetermined or known conditions and countermeasures although they are basically complicated. The procedure is shown. Certainly, although the countermeasure list can be corrected and updated, the judgment is basically made based on the input data, and there is a problem that the computer only performs a process of combining the event and the countermeasure. there were.
The invention disclosed in Patent Document 1 shows a protective measure after an event has occurred, and does not teach a precautionary measure. Even if it is used for planning support for repair work, it is difficult to quantitatively grasp the effect of repair work from the potential risk due to aging of the structure and the risk after repair work, for example. There is also a problem of being.

  Furthermore, the invention disclosed in Non-Patent Document 1 and Patent Documents 1 and 2 relates to the prevention of natural disasters, and the object is natural shaped objects such as cliffs and slopes, and artificial structures such as bridges and tunnels. The concept of deterioration over time is difficult to be reflected, so evaluation of deterioration is inadequate, and it is difficult to apply it to artificial structures as it is, considering the risk of cliffs and slopes, and evaluation of countermeasures as well. There was a problem.

Moreover, in the invention disclosed in Patent Document 3, the idea of surely predicting the deterioration state of the structure is disclosed. However, the deterioration state is predicted by inputting the natural environment such as the weather conditions in the area where the structure exists, the concrete material of the structure, and the construction method into a general prediction formula that already exists. It does not use raw data obtained as a result of inspecting a structure to be evaluated, and does not leave a range of qualitative prediction based on a general formula. That is, there is a problem that it is difficult to evaluate each individual structure, and it is very difficult to perform a quantitative evaluation in consideration of unique circumstances of the structure.
Also, in the invention disclosed in Patent Document 4, it is possible to quantitatively diagnose the remaining life, proof stress, degree of fatigue damage, etc. of the structure as deterioration / damage prediction by providing the structure database. However, the content of the evaluation to be input to the structure database is based on expert assistance, and according to paragraph 0022, in addition to qualitative judgment such as visual inspection, objective diagnosis or By evaluating the performance, characteristics such as the remaining life and strength of the structure are quantitatively grasped and databased in this structure data file. However, the specific contents of this quantitative grasping method are unknown. Yes, the problem of using the conventional evaluation method remains. That is, the present invention implements the contents that have been implemented so far using a computer and a database connected thereto, and the computation contents and data contents are considered to be conventional.

  The present invention has been made in response to such a conventional situation, and when preparing a repair work plan for a civil engineering structure, the necessity of repair work is objectively determined based on data of a large number of items inspected. In addition, it is presented as evaluation information that has been quantitatively evaluated. In addition, objective and quantitative evaluation is possible for deterioration of structures over time, and repair work is performed on structures that have undergone repair work. By quantitatively judging how much the necessity of repair work has been reduced before and after being repaired, and comparing it with the repair work need of other structures that have not been repaired at the same level, A structure that can support the planning of a structural repair work business plan with an objective and high-accuracy evaluation that can perform a unified evaluation on the necessity of new repair work regardless of whether or not repair work is required Repair work An object of the present invention is to provide the field support system.

In order to achieve the above object, a structure repair construction plan support system according to claim 1 includes an information input device, an information storage device, an information calculation device, and an information output device. Discriminant boundary line or discriminant boundary surface (hereinafter referred to as discriminant boundary including discriminant boundary line) that separates the necessity of repair work obtained from factor data related to deterioration factors and past repair construction / non-construction results data Is a structure repair construction plan support system that calculates the degree of necessity of repair work in a certain structure on the basis of
The information input device is means capable of inputting deterioration factor data in the structure and boundary data constituting the discrimination boundary surface to the information storage device,
The information calculation device reads the factor data in the structure and the boundary data from the information input device or the information storage device, and a space of two or more dimensions (hereinafter referred to as a multidimensional space) in which the boundary data is configured. .) An analysis condition setting unit for inputting the read factor data as coordinates above,
A repair work necessity calculation unit that calculates the distance from the determination boundary surface to the coordinates of the factor data in the structure as the necessity of the repair work,
The information output device is a means capable of outputting at least one piece of information among the factor data, the boundary data, and the necessity of the repair work in the structure.
In the present invention, the “necessity of repair work” is used, but this also includes the concept of “unnecessity of repair work” and is not excluded at all. The same applies to the inventions described in the following claims.

Further, in the structure repair construction plan support system described in claim 2, in the invention described in claim 1, the factor data in the structure includes time data indicating a point in time when the factor data is acquired. And
The information calculation device reads the factor data in the structure from the information input device or the information storage device, and a first distance from the determination boundary surface to the coordinates of the factor data at a certain point of the structure, Calculating a second distance from the determination boundary surface to the coordinates of the factor data at a time different from the certain time in the structure;
A degradation degree evaluation unit that calculates a difference between the first distance and the second distance as a degradation degree between different times from the certain time point and the certain time point is provided.

The structure repair construction plan support system described in claim 3 is the invention described in claim 1 or claim 2, wherein the information input device includes deterioration factor data in the structure and the discrimination boundary surface. Is a means capable of inputting into the information storage device the boundary data that constitutes the presence / absence of repair work applied to the structure and the time of repair work,
The information calculation device reads the factor data in the structure from the information input device or the information storage device using the repair presence / absence data in the structure as a key, and repairs the structure from the discrimination boundary surface Calculating a third distance to the coordinates of the factor data at the time after the execution and a fourth distance from the discrimination boundary surface to the coordinates of the factor data at the time before the repair work on the structure;
A repair effect calculating unit that calculates a difference between the third distance and the fourth distance as a repair effect is provided.

The structure repair execution plan support system described in claim 4 is the invention described in claim 3, wherein the repair work effect calculation unit relates to data relating to the repair work effect and a method type of the repair work. Storing the data together with the factor data of the structure in the information storage device;
The information calculation device includes a repair method selection unit that reads data relating to a method type of the repair work stored in the information storage device using the type of the factor data as a key.

  The structure repair construction plan support system described in claim 5 is the invention described in claim 4, wherein the repair method selection unit uses the data related to the effect of the repair as a key to the type of repair method. An order is attached to such data.

  The structure repair construction plan support system described in claim 6 is the invention described in any one of claims 1 to 5, wherein the discrimination boundary surface is set by analysis using a support vector machine. It is what is done.

  The structure repair construction plan support system described in claim 7 is the invention described in any one of claims 1 to 5, wherein the discriminating boundary surface is obtained by analysis using a radial basis function network. Is set.

The structure repair execution plan support system described in claim 8 is the invention described in any one of claims 1 to 7, wherein the information storage device stores the position data of the structure and the structure in advance. Stores map data around objects,
The information calculation device visually displays at least one piece of information on the position data of the structure and the degree of necessity of repair work, the degree of deterioration, the effect of repair work, or the priority of repair work on the map data. It has a function of causing the output device to output the information shown in an identifiable form.

The present invention objectively and quantitatively evaluates the degree of necessity for determining whether or not repair work is necessary to prevent, for example, expansion of damage or accidents, when drafting a civil engineering structure repair work business plan. It is possible to provide material.
In addition, since the necessity of repair work related to common deterioration factors is calculated quantitatively for each different structure, it is possible to objectively determine the priority of repair work based on the evaluation. is there.

Furthermore, according to the invention described in claim 2 in particular, the first distance, the second distance, and the difference between them are calculated based on factor data at two different time points separated by time in the same structure. It is possible to quantitatively evaluate the deterioration with time.
By accumulating data by structure and material of the structure, and by environment such as the region and season, it is also possible to quantitatively and objectively evaluate the influence of each element on deterioration over time.
Furthermore, by combining this quantitative evaluation of deterioration over time with the evaluation of the necessity of repair work and the effect of repair work, which will be described later, it is possible to eliminate the time-dependent elements even from the factor data at different times. Become.

In particular, according to the invention described in claim 3, the effect of the repair work is quantitatively calculated by calculating the third distance, the fourth distance and the difference thereof based on the factor data before and after the repair work. Can be evaluated.
Furthermore, in particular, according to the invention described in claim 4, since the data related to the type of repair work method is read using the factor data type as a key, the repair work method can be efficiently selected for each factor data. . Further, in claim 5, since the data relating to the type of repair work is further ordered with the data relating to the effect of the repair work as a key, it is determined which repair work method is appropriate as the repair work for the factor data. Material can be provided.
In particular, according to the invention described in claim 8, it can be used more visually as a map for repair work.

Before describing the best mode and embodiments of the present invention, in order to facilitate understanding of the invention, embodiments and examples described in the claims and specification of the present application, the present specification and patents are described. The definition of the word used in a claim is shown.
First, “structure” as used herein refers to steel bridges, prestressed concrete (hereinafter abbreviated as “PC”) bridges, civil engineering structures such as tunnels, dams, dikes, buildings, and towers. It also includes building structures such as
In addition, “repair work” or “repair work” refers to all work methods that are carried out as repair works, mainly for the purpose of recovering damages, accidents, collapses, etc. that have occurred preventively.

In addition, the “deterioration factor” as used in the present application is a concept that includes factors that can cause deterioration of the structure over time, and also includes factors that may indicate the damage status of the structure and cause an accident such as a collapse. .
Specifically, although it varies slightly depending on the structure, abnormal noise, water leakage, water leakage, settlement, loosening or loss of fixing bolts, drainage clogging or damage, cracks (width, length, direction, distribution, pattern, etc.) , Amount of free lime, rust, corrosion, damage, pavement abnormalities, road surface irregularities, peeling, rebar exposure, discoloration, scouring, squeezing of concrete.

  As a “discrimination boundary line” used in the present invention, for example, in a two-dimensional plane, CL disclosed in the previous Non-Patent Document 1 and Patent Document 2 is representative. As shown in these documents, using RBFN or the like, teacher values (-1, +1 respectively) are used for occurrence and non-occurrence events for a rainfall index at a certain point, and first, the discriminant boundary surface is analyzed, and then desired The intersection line between the horizontal plane and the discrimination boundary surface is extracted as CL. In addition to the discrimination boundary surface analyzed using the previous RBFN, as a representative example of the discrimination boundary surface, there is a separation hyperplane analyzed using a support vector machine as described in the embodiment of the present application. . Of course, the discriminant boundary line and the discriminant boundary surface are not limited to these analyses, but are conceptualized in a plane or multi-dimensional space in which at least two factors are selected from the factors of deterioration of the structure, which is called repair work. From the viewpoint, it includes all the lines or planes for separating the repair work side and the repair work unnecessary side. However, the analysis of these discriminant boundary lines or discriminant boundary surfaces does not have the essence of the invention of the present application, but is used based on the existence of these lines and surfaces.

Hereinafter, a structure repair construction plan support system according to an embodiment of the present invention will be described with reference to FIGS.
FIG. 1 is a configuration diagram of a structure repair construction plan support system according to the present embodiment. Moreover, FIG. 2 is a flowchart which shows the arithmetic processing method using this structure repair construction plan support system.
In FIG. 1, the structure repair construction plan support system includes an input unit 1, a calculation unit 2, an output unit 11, and a plurality of databases 13, 16, 18, 21, 23, 27.
The input unit 1 is used to input data 12a stored in these databases in advance, or to directly input data 12a and analysis conditions 12b when the arithmetic unit 2 is operated. Specifically, for example, it is composed of multiple types of devices such as a keyboard, mouse, pen tablet, or a receiving device that receives data via a communication line from an analysis device such as a computer or a measuring device, etc. Devices are possible.

The calculation unit 2 includes a standardization analysis unit 3, an analysis condition setting unit 4, a repair work necessity calculation unit 5, a repair work effect calculation unit 7, a repair work priority calculation unit 8, a repair method selection unit 9, and a deterioration evaluation unit 10. It is comprised from.
The calculation unit 2 uses the data 12a related to the discrimination boundary line and discrimination boundary surface read from the database or input from the input unit 1, the data 12a related to the performance of repair work on the structure, and the analysis condition 12b to repair the operation. It consists of sections that analyze the necessity of construction and the effect of repair work, the priority of repair work and the selection of repair methods, and the analysis of deterioration over time that occurs in structures. These sections can input and output operation results as data. Specifically, the computing unit 2 may be a computer such as a workstation or a personal computer.
As the database, the past inspection result data 14 for the structure and the present time, that is, the inspection database 13 for storing the current state inspection data 15 in a state where analysis is not performed immediately after the inspection, and the repair history data 17 for the structure are stored. Is stored in the repair history database 16, the boundary database 18 for storing the determination boundary line data 19 and the determination boundary surface data 20 for analyzing the necessity of repair work, the analysis condition data 24 for various analysis, the parameter data 25, the analysis database 23 for storing the repair function necessity function data 26, the repair method database 21 for storing the repair method data 22 to be applied to the structure, and the repair work obtained as a result of the analysis using the calculation unit 2 Necessity data 28, degradation data 29, repair effect data 30 and There is evaluation information database 27 for storing Fix construction priority data 31.
Specifically, the database as hardware may be one in which data is stored in a computer storage device such as a magnetic disk or optical disk, and the output unit 11 may be a display device using CRT, liquid crystal, plasma, organic EL, or the like. Alternatively, a display device such as a printer device, and a transmission device such as a transmitter for performing transmission to an external device are conceivable.

The structure repair construction plan support system according to the present embodiment mainly including the above-described components can perform the processing generally by the following processing procedure.
As shown in step S1 of FIG. 2, in the data input process by the input unit 1, first, a process of inputting data is performed. As the input data, for example, discriminant boundary line data stored in the boundary database 18 is used. 19 or discrimination boundary surface data 20. In addition, past inspection record data 14 as quantitative data (hereinafter referred to as factor data) relating to the cause of deterioration of the structure stored in the inspection database 13, or in principle, obtained immediately before the analysis time point. There is a current status inspection data 15 that has been obtained. Such inspection data may be actual measurement data, or may be standardized data by performing a standardization process. Quantitative factor data means, for example, if water leakage is considered as a factor, the numerical value when the amount of water leakage per unit time is measured as cubic meters per hour, or for example, the looseness of bolts is judged In such a case, the levels 1, 2, 3, etc. are quantitative when expressed in three levels. In other words, in addition to what can be expressed numerically as a physical quantity, when it is a non-physical quantity or can only be expressed qualitatively, even when the state is expressed at some level, the numerical value at that level should be quantitative It is.
In addition to these input data, there are repair method data 22 stored in the repair method database 21, analysis condition data 24 and parameter data 25 stored in the analysis database 23, and the like.
In this embodiment, data input processing is first performed as step S1, but data may be input as appropriate in accordance with the analysis process.

  Tables 1, 2, and 3 are listed as actual examples of inspection result data 14 that can be calculated by the present invention. Table 1 shows tunnel inspection data, which is composed of seven factors of deterioration from A maximum crack width to G water leakage. Table 2 shows PC bridge inspection data, which is composed of three factors that cause deterioration, including the type of damage, the degree of damage, and the number of damaged parts. Table 3 shows steel bridge inspection data, which consists of nine factors of deterioration such as loose bolts and abnormal sounds. These tables do not include the inspection time except for Table 3, but the inspection time is omitted, and each inspection time is included in the inspection result data 14 as data. In addition, Table 3 also shows only the year as the inspection time, but in actuality, it may include the month or month / day. The same applies to the current status inspection data 15.

  In the input unit 1, each data is stored in each database as described above. However, these data may be transmitted directly to the calculation unit 2 without being stored in the database.

In the standardization analysis unit 3 of the calculation unit 2, the inspection result data 14, the current inspection data 15, the discrimination boundary data 19, or the discrimination boundary surface data 20 is not standardized, and the repair work necessity level, the repair effect or These data are standardized when they are obtained as standardized evaluations such as the degree of deterioration. The inspection result data 14 and the current state inspection data 15 include factor data, and when it is not standardized, if it is desirable to standardize these, standardization processing is performed using the standardization analysis unit 3. Similarly, with respect to the discrimination boundary line data 19 and the discrimination boundary plane data 20, a standardization process is performed on the portion related to the factor data.
Conditions used for standardization analysis such as a reference value at that time are stored as analysis condition data 24 in the analysis database 23. The standard value is stored as the analysis condition data 24 while the reference value is set to the maximum value of the factor data in the standard structure, for example, and the standardization analysis unit 3 reads the analysis condition data 24 from the analysis database 23 and the inspection database 13 The standardization process is performed using the inspection result data 14 and the current state inspection data 15 read out from, or the discrimination boundary line data 19 or the discrimination boundary surface data 20 read out from the boundary database 18. The reference value is not limited to the maximum value of the factor data, and a desired reference value may be stored in advance in the analysis database 23 as the analysis condition data 24.
Since the processing in the standardization analysis unit 3 is also selective, it is not shown as a part of the process in FIG.

  However, in the present embodiment, the standardization analysis unit 3 can analyze the discriminant boundary line data 19 and the discriminant boundary surface data 20 stored in the boundary database 18. These data do not necessarily need to be analyzed inside the arithmetic unit 2 and may be input to the boundary database 18 in step S1 as described above, but the past inspection record data 14 and the repair history database may be input. It is also possible to analyze the discriminant boundary line data 19 and the discriminant boundary surface data 20 by performing so-called initial learning based on the repair history data 17 stored in FIG. In FIG. 2, after selecting any inspection result data 14 and repair history data 17 in the analysis condition setting in step S <b> 2, the analysis can be performed as step S <b> 3. The acquisition of the discriminant boundary line data 19 and the discriminant boundary surface data 20 can be obtained by using RBFN disclosed in Non-Patent Document 1 or the like, or by performing analysis using a support vector machine. Since this is a known technique, a detailed description thereof will be omitted.

Next, the analysis condition setting unit 4 of the calculation unit 2 sets an object to be analyzed, parameters, etc., as shown in step S2 in FIG. Specifically, a combination of any factor data of any structure is extracted from the inspection database 13 from the inspection database 13 and the current inspection data 15, and any boundary data corresponding thereto, that is, any discriminant boundary line data is extracted. 19 or whether the discrimination boundary surface data 20 is to be extracted is set.
Here, the analysis condition setting unit 4 prompts the user to input the conditions for the analysis via the input unit 1, and accesses the inspection database 13 and the boundary database 18 using the input conditions as keys. The inspection result data 14, the current inspection data 15 and the discrimination boundary data 19 or the discrimination boundary surface data 20 are read out. Since the parameter data 25 indicating the data contents or data structure stored in the inspection database 13 and the boundary database 18 displayed for prompting input is stored in the analysis database 23, the analysis condition setting unit 4 first The analysis database 23 may be accessed to read the parameter data 25 and display the parameter data 25 using the output unit 11.
In response to this display, the user of the present structure repair construction plan support system can select the inspection result data 14, the current state inspection data 15, the discrimination boundary line data 19, or the discrimination boundary surface data 20.

In response to the selection, the analysis condition setting unit 4 forms discrimination boundary data 19 or discrimination boundary surface data 20 formed corresponding to the combination of factor data included in the inspection result data 14 and the current inspection data 15. The factor data in the structure to be evaluated included in the inspection result data 14 and the current state inspection data 15 are input on the multidimensional space.
In the description of the analysis condition setting unit 4, the discriminant boundary line data 19 and the discriminant boundary surface data 20 have been described as being read from the boundary database 18. However, as described above, the analysis boundary data 19 and the discriminant boundary surface data 20 are analyzed from the inspection record data 14 and the repair history data 17. In this case, the factor data may be input after the analysis in step S3.

As shown in step S4 in FIG. 2, the repair work necessity level calculation unit 5 determines the discriminant boundary line data 19 or the discriminant boundary surface data 20 set by the analysis condition setting unit 4 and the factor data in the structure to be evaluated. Is used to calculate the distance from the discrimination boundary surface represented by the discrimination boundary line data 19 or the discrimination boundary surface data 20 to the coordinates (point Bj) of the factor data of the region to be evaluated.
The calculated distance is stored in the evaluation information database 27 by the repair work necessity calculation unit 5 as repair work necessity data 28 or directly output to the output unit 11.

Here, referring to FIG. 3, the discrimination boundary line data 19 or the discrimination boundary plane data 20 and the discrimination boundary plane based on the discrimination boundary line data 19 or the discrimination boundary plane data 20 as well as the inspection result data 14 and the current status inspection are described. The data 15 will be specifically described.
FIG. 3 is a conceptual diagram showing a discrimination boundary surface analyzed using a support vector machine on a two-dimensional plane. In FIG. 3, the horizontal axis represents abnormal noise that is one of the deterioration factors of the steel bridge, and the vertical axis represents water leakage that is also one of the deterioration factors of the steel bridge. Since this figure is a conceptual diagram, the axis scale is not given in detail, but the need for repair increases as the distance from the origin increases. In the figure, g1 represented by a thick solid line represents a separation plane (discrimination boundary plane).
What constitutes the separation plane g1 is the discrimination boundary plane data 20 stored in the boundary database 18.
In addition, black circles indicate data that requires repair for certain structures, and white circles indicate data that do not require repair for certain structures. The points are plotted on this two-dimensional plane corresponding to the quantitative data of the factors. In the drawing, the degree of necessity for repair increases as the distance from the separation surface g1 increases.
These black circle and white circle data are the inspection result data 14 or the current state inspection data 15. The plotted position is based on the quantity value of the factor data.
In the present embodiment, the horizontal axis represents the magnitude of abnormal sound, which is one of the causes of deterioration, and the vertical axis represents the amount of water leakage. Needless to say, the repair side is unnecessary, but it goes without saying that the reverse may exist depending on the deterioration factor. Further, not only the deterioration factor but also the repair required side or the repair unnecessary side depending on the distance from the origin is widely based on the characteristics of the deterioration factor data of the structure, and is not based on the characteristics of the present invention. Furthermore, regardless of the nature of the factor data, it may be determined as appropriate whether to take the repair required side or the repair unnecessary side closer to the origin on the vertical axis and the horizontal axis, particularly in the present embodiment. Not what you want. The same applies to the following description of the embodiment.

The repair work necessity level calculation unit 5 calculates the distance (g1 (x, y)) from the separation surface g1 shown in FIG. 3 to the data point of the structure to be evaluated, and repairs the distance. Necessary. Therefore, as shown in FIG. 3, the data point near the origin from the discriminant boundary surface has a positive degree of repair work and is not required for repair work. On the other hand, the data point far from the origin has a negative repair work degree. It turns out that it becomes the repair essential side.
In addition, since it is expressed as a distance, the degree of necessity for repair work in the structure to be evaluated is quantitatively expressed, and can be objectively determined in comparison with other structures.
Each piece of data shown in Fig. 3 is plotted at various positions on a two-dimensional plane because the deterioration factor data varies from structure to structure. However, by collecting these data, repairing deterioration factors, etc., or damage or accidents The accuracy of the evaluation of the relationship between the cause of occurrence and the actual repair situation, the occurrence / non-occurrence of damage and accidents is improved, and a more general and general evaluation can be performed.

  Analyzing a separation plane created from various deterioration factors using a support vector machine based on past inspection record data 14 and repair history data 17 for a steel bridge existing in a certain area, as current inspection data 15 Table 4 shows a calculation example of the degree of necessity of repair work obtained using data obtained by carrying out the inspection in 2004 shown in Table 3. The management number P-1 or the like in the table indicates the inspection location of the structure, and the last f (xi) column indicates the analyzed degree of necessity for repair work. In this column, a positive value indicates that the need for repair work is low, and a negative value indicates that the need for repair work is high. In addition, the greater the absolute value of the number, the greater the necessity of necessity.

  FIG. 4 shows the five levels based on the necessity of repair work set here and the judgment of a professional engineer based on the data (number of data: 503) obtained at the time of inspection conducted in a certain tunnel as inspection result data 14 It shows the correlation of evaluation. An example of the five-step evaluation used for engineer judgment is as shown in Table 5.

The inspection data of the tunnel contains the inspection results of seven items related to damage such as crack width / length and pattern and the presence or absence of free lime for each span. (Based on the new face evaluation method proposed by Japan Highway Public Corporation). In addition to this total score, a five-step evaluation is given to the necessity of countermeasures as a judgment of the inspection engineer (Table 5).
Here, the description content of the inspection sheet of the new face evaluation score method is used as an input factor, and a five-level evaluation based on the judgment of an engineer is used as a teacher value (3A: Urgent countermeasure required 2A: Immediate countermeasure required 1; other countermeasures For the evaluation with low necessity, the analysis by the support vector machine (SVM) was performed under the conditions of C = 100 and R = 0.5. C is a parameter that determines the degree of misclassification, and the larger the value, the less misclassification. R means the radius of the Gaussian function.
As a result, a high correlation could be obtained between the evaluation of each inspection data by f (x) and the five-step evaluation by the engineer's judgment (FIG. 4). This result greatly exceeds the correlation between the total score of the new face evaluation method and the engineer's judgment evaluation (FIG. 5), indicating that the present method can separate the necessity of countermeasures with high accuracy.

Next, FIG. 6 shows the repair policy based on the engineer's judgment read from the repair history data 17 based on the deterioration factor based on the data (number of data: 157) obtained at the time of the inspection performed on the steel bridge as the inspection result data 14. Is a teacher value (-1 for repair, 1 for no repair for the time being), and the result of analysis by SVM is shown. Steel bridge inspection data includes seven items of inspection results related to damage such as loose bolts, abnormal noise, and the presence or absence of water leakage at each damaged part. For each damaged part, the policy of treatment is determined in view of the inspection results, but the relationship between the determination criteria and the inspection results is not clearly shown, and there are many parts based on the judgment of individual engineers.
As a result, as is clear from FIG. 6, a high correlation could be obtained between the evaluation of each inspection data by f (x) (when there is one deterioration factor) and the repair performance.
Further, FIG. 7 shows the deterioration factor based on the data (number of data: 189) obtained at the time of the inspection carried out on the PC bridge as the inspection result data 14, and the treatment policy determined by the engineer as the teacher value ("emergency" “Measures needed” and “repair needed” were -1; “Responding with maintenance work” and “Implementing detailed investigation” were conducted 1) SVM analysis. As a result, a high correlation could be obtained between the evaluation of each inspection data by f (x) and the treatment policy by the engineer's judgment.

The inspection data on the PC bridge shows the damage type, the degree of damage, and the number of damaged parts for each damaged part. For each damaged part, the policy of treatment is determined in view of the inspection results, but the relationship between this criterion and the inspection results is not clearly stated, and this is also left to the judgment of individual engineers. ing.
In the present embodiment, the description content of the inspection result for each damaged portion is used as the input deterioration factor. The engineer also determines that emergency measures and repairs are necessary in areas where the negative value of f (x) is large, and conversely, in areas where the positive value is large, the engineer also handles maintenance work or conducts detailed investigations. Judgment is made.

  As described above, in the structure repair construction plan support system according to the present embodiment, analysis of the necessity level of repair work in the repair work degree calculation unit 5 is effective and is stored in the inspection database 13. Based on the inspection record data 14 and the repair history data 17 stored in the repair history database 16, it was possible to obtain a high correlation even in an analysis performed as initial learning using, for example, SVM. In other words, an objective universal universal is obtained by obtaining a discriminant boundary line or discriminant boundary surface in a coordinate system that quantitatively indicates deterioration factors by some method, and analyzing the distance from the discriminant from the inspection result data 14 or the current inspection data 15. It is understood that an analysis on the degree of necessity for repair work is possible.

Moreover, the applicability with respect to the test data of the discrimination | determination boundary surface constructed | assembled by learning data was verified in order to confirm the versatility of the evaluation by the structure repair construction plan support system which concerns on this Embodiment.
FIGS. 8A and 8B show the evaluation results using learning / test data for the tunnel. The learning data is 267 data from the eastern part of Yamaguchi Prefecture (Ibeda, Iwakuni, Uda, Okari, Amagato), and 236 test data from western Yamaguchi Prefecture (Sawae, Hofu) based on the discriminant boundary f1 constructed by this. evaluated. The results are as shown in the figure. The learning data and test data are well separated from the necessity for repair, and the versatility of the discriminant boundary surface was recognized. Reference numerals such as 3A, 2A, A, and B shown in the figure are based on the five-step evaluation shown in Table 5.
Here, the learning data means the data used for the initial learning performed to construct the discrimination boundary surface f1, and the test data is the same data format as the learning data but does not overlap the learning data. Data used for test analysis to confirm the versatility of the boundary surface f1. Both are created based on the inspection record data 14 stored in the inspection database 13 and the repair history data 17 stored in the repair history database 16. The same applies to FIGS. 9 and 10 below.
FIGS. 9A and 9B show the evaluation results using the learning / test data for the PC bridge. The learning data were 120 data of Nishioki Bridge, Asahi Bridge, Shiraishi Noki Bridge, and 69 data of Shimoya Bridge and Sunagawa Bridge were evaluated as test data based on the discriminant boundary f1 constructed by this. Both learning data and test data also separated the necessity of repair well, and the versatility of the discrimination boundary surface was recognized.
FIGS. 10A and 10B show the evaluation results based on learning / test data for steel bridges. Inspection data for steel bridges were available for a long period from 1985 to 2004. Of these, inspection data from 1985 to 1999 was used as learning data, and the inspection data for 2004 was based on the discriminant boundary f1 constructed by this. Tested. In this regard, the necessity of repair was well separated in both learning data and test data, and the versatility of the discriminant boundary surface was recognized.
From the above, it can be said that the evaluation method using the structure repair construction plan support system according to the present embodiment has versatility, and it is possible to evaluate other data using the analysis result of the learning data. .

FIG. 11 is a flowchart showing an example of an algorithm for calculating the degree of necessity of repair work by obtaining the distance between the data on the discrimination boundary surface expressed as step S4 in FIG. 2 and the data point (Bj) in a certain structure. is there.
In FIG. 11, step S4-1 sets 1 to make i of the point Ai (xi, yi) conceptualized on the discrimination boundary surface as the first point, and sets k to indicate the distance between the discrimination boundary surface and the point Bj. The initial value is infinite.
In step S4-2, the distance between the points Ai and Bj is calculated. In step S4-3, the calculated distance ki is compared with the value of k so far. In step S4-4, if ki is smaller than k. The distance ki calculated as k is used, and if it is larger, k is set as it is.
In step S4-5, it is checked whether i is the last data in the discriminant boundary line data 19 or the discriminant boundary surface data 20. If not, i is incremented by one, and step S4- is repeated. If the calculation from 2 is performed and the last value is obtained, the value of k is obtained as the distance f (xj, yj) between the discrimination boundary surface and the data point Bj in step S4-6.
In other words, the algorithm calculates the distance from all data points constituting the discrimination boundary surface to the data point of the structure to be evaluated, and calculates the distance by updating the minimum value.

Although the algorithm shown in FIG. 11 uses the two-dimensional discrimination boundary surface g1, the same calculation can be performed on a three-dimensional or higher plane, and the algorithm is not limited to two dimensions. Further, the algorithm is not limited to this algorithm, and it goes without saying that any algorithm can be used as long as it can calculate the distance from a multidimensional space or curve to a certain point. The same applies to the embodiments described below. The function of ki indicating the distance shown in step S4-2 in FIG. 11 is a function that is stored in advance as the repair work necessity function data 26 from the input unit 1 into the analysis database 23, and the repair work need calculation is performed. The part 5 is read from the analysis database 23 at the time of analysis.
In addition to being stored in the evaluation information database 27 as repair work necessity data 28, the distance calculated by the repair work need calculating part 5 may be directly output via the output unit 11. Further, the output unit 11 displays or transmits signal of deterioration factors included in the inspection result data 14 of a certain structure, discrimination boundary surface data 19 and discrimination boundary line data 20 relating to the discrimination boundary surface used for the analysis. And so on.
The system configuration necessary for calculating the degree of repair work has been described above.

Artificial building structures and civil engineering structures will deteriorate over time after construction, and the possibility of accidents such as cracks and collapses will increase with time.
Therefore, it is desired to quantitatively grasp how fast the deterioration with time of these structures proceeds.
In the structure repair construction plan support system according to the present embodiment, a deterioration degree evaluation unit is provided so as to be applied to such needs.

Hereinafter, a method for evaluating the deterioration level in the deterioration level evaluation unit will be described with reference to FIG. 12 in addition to FIGS.
In FIG. 1, the deterioration level evaluation unit 10 uses the repair work necessity level of the structure calculated by the repair work level calculation unit 5. For example, the inspection result data 14 acquired by the inspection performed at the time K and the inspection result data 14 acquired by the inspection performed at the subsequent time L are used.
Using these inspection result data 14 and 14, the distance from the discrimination boundary surface regarding the appropriately selected deterioration factor is calculated, and this is used as the necessity of repair work at each time.
FIG. 12 is a schematic diagram illustrating this state.
The original data is data related to factor 1 and factor 2 at time K, and the new data is data related to factors 1 and 2 at time L. It can be seen that time has passed since the original data, and that the new data has moved to the side that requires repair work. This is the progress of deterioration, and the deterioration degree evaluation unit 10 calculates the difference between the respective repair work necessity g1 (x ′, y ′) and g1 (x, y) shown in FIG. It is calculated as the degree of deterioration during the period.
This degree of deterioration can basically be obtained by calculating all structures that have been inspected with a time difference. The degree of deterioration is also affected by the structure, construction method, material, and environment of the structure. However, periodic inspections of multiple components and members within the same structure, and structures within the same area By constructing a database from the results of periodic inspections on objects and periodic inspections carried out for each type of structure, it becomes possible to carry out highly accurate evaluations.

Further, it is preferable that the deterioration degree evaluation unit 10 can calculate the deterioration degree that progresses per unit time by dividing the previous difference by the elapsed time as the deterioration rate.
By using this deterioration rate, it is possible to calculate the degree of deterioration from the most recent inspection time by multiplying the time elapsed from the most recent inspection time by this deterioration rate even if it is not immediately after the inspection.
By using such a degree of deterioration obtained in advance, when there is no current inspection data 15 at the time of analysis of the degree of necessity of repair work, the past inspection result data 14 is used to carry out the analysis. It is also possible to request the degree of repair work.

For example, FIG. 2 shows the analysis of the degree of deterioration as step S5. This is an analysis of the necessity of repair work in step S4 executed in the repair work degree calculation unit 5 described above. Rather than using the current status inspection data 15 obtained, if it is necessary to analyze the necessity of repair work for the structure using the inspection performance data 14 obtained in the past, the inspection is performed from the current point of analysis. It means that the period until the acquisition time of the record data 14 is multiplied by a known deterioration rate obtained in advance and the degree of deterioration in that period is analyzed to correct the necessity for repair work. .
Of course, not only the correction of the necessity for repair work as described above, but also the analysis in the above explanation of obtaining the difference based on the inspection result data 14 at two times and the analysis for obtaining the deterioration rate are also executed in this step S5. Is possible.
The deterioration degree calculated by the deterioration degree evaluation unit 10 is stored in the evaluation information database 27 as deterioration degree data 29. Even when the deterioration rate is calculated, the deterioration degree data 29 may be stored in the evaluation information database 27. Alternatively, the calculated deterioration degree and deterioration rate may be directly output from the output unit 11.

Next, steps S6-1 and 6-2 provided after step S5 in FIG. 2 will be described. Steps S6-1 and 6-2 are based on the degree of deterioration obtained through the analysis, and evaluate the progress of deterioration to determine whether the next inspection should be accelerated or conversely possible to extend. is there. Therefore, when executing Steps S6-1 and S6-2, a certain degree of deterioration analysis is performed and accumulated in the evaluation information database 27 as deterioration degree data 29, which is stored in the deterioration degree evaluation unit 10. Needs to be read and executed.
Steps S6-1 and 6-2 will be described with reference to FIGS.
FIG. 13 is a conceptual diagram showing the progress of deterioration. The white circles in the figure indicate deterioration factors with respect to a plurality of inspection result data 14 or current inspection data 15 acquired at intervals of 2 on the vertical and horizontal axes. This is plotted for the dimension, and the solid line indicates the discrimination boundary surface. Although (a) has progressed considerably in the initial stage, it has returned to a healthy state again due to the effect of repair work performed midway. In such a place, it is considered possible to extend the timing of the next inspection in consideration of the past deterioration results.
On the other hand, although (b) is in the safe area at present, the deterioration has progressed since the start of inspection, and it is shown that the current situation is still in the process. It can be judged that it is desirable to perform a temporary inspection without waiting for the next periodic inspection because the distance from the determination boundary surface, that is, the necessity for repair work is high.
However, since the quantitative evaluation of the distance to the discriminating boundary surface is considered to be different for each structure, the relationship between the value of the degree of necessity for repair work and the judgment is determined based on a predetermined reference value. It is desirable to specify that the timing should be extended or that a temporary inspection be performed.
For this reason, in Steps S6-1 and 6-2, the discrimination boundary obtained in S3 for the past inspection result data 14 (Xn (n = 1 to i)) of the inspection target location of the structure in each inspection year. A change in the safety degree: f (Xn) is verified by performing evaluation on the discriminating boundary surface g1 obtained from the surface I or the discriminating boundary line data 19 or the discriminating boundary surface data 20 stored in the boundary database 18 in advance.
Table 6 shows a part of the degradation status evaluation results obtained by analyzing inspection data from 1985 to 2004 of a steel bridge as an example using a support vector machine.

  As step S6-1 shown in FIG. 2, the deterioration degree evaluation unit 10 reads the analyzed deterioration degree data or the deterioration degree data 29 stored in the evaluation information database 27, and performs inspection earlier than the periodic inspection. Determine if implementation is necessary. Here, the change over time in the distance f (Xn) value from the discrimination boundary surface g1 of the support vector machine is analyzed, and the f (Xn) value is less than 0 earlier than the scheduled period for the next periodic inspection due to the progress of the deterioration. Extract data that may become (dangerous data on the discrimination boundary). FIG. 14 shows an example from the steel bridge inspection data. In the inspection location (P-398) shown in this example, although no significant deterioration has been observed until 1995, the deterioration has progressed significantly between 1995 and 1999. Although the inspection for the steel bridge in this example is carried out at intervals of approximately once every five years, the deterioration of P-398 may progress earlier than the next periodic inspection. It can be determined that an early re-inspection is desirable. It is desirable to determine the degree of early implementation for each structure or for each inspection object in relation to the progress of deterioration.

Next, in step S6-2, the analyzed deterioration degree data or the deterioration degree data 29 stored in the evaluation information database 27 is read to determine whether the periodic inspection interval can be extended.
Again, the f (Xn) value is analyzed over time, and the f (Xn) value is 0 or more (safe side data on the discriminating boundary surface) even at the next scheduled periodic inspection due to the tendency of deterioration. Extract the most likely locations. For such points, the interval between periodic inspections can be extended, and the cost of the inspection business can be reduced. FIG. 15 shows an example obtained from the steel bridge inspection data. At the inspection point (P-400) shown in this example, although the deterioration has progressed gradually by 1995, due to the effect of the repair work carried out in 1998, the inspection in 1999 and 2004 started from 1985. Are also found to be in a safe state. It is considered possible to extend the previous periodic inspection interval of 5 years for such points. The extension width is preferably determined in advance according to the progress of deterioration of individual data.
As for the shortening or extension of the inspection cycle as described above, the determination result is output from the deterioration degree evaluation unit 10 to the output unit 11.
The analysis of the deterioration level and the deterioration rate executed in the deterioration level evaluation unit 10 has been described above.

Next, analysis of the repair effect executed in the repair effect calculation unit 7 shown in FIG. 1 will be described with reference to FIG. 16 in addition to FIGS.
The analysis of the repair effect in the repair effect calculation unit 7 is shown as step S7 in FIG. This analysis of the effect of the repair work is intended to objectively and quantitatively evaluate the effect of the repair work when the repair work is a structure that has already been constructed.
In order to analyze the effect of the repair work, in addition to the case where the inspection result data 14 in the previous embodiment includes two different time points, the current inspection data 15 is obtained immediately after the repair work is performed. The effect may be analyzed with the past inspection result data 14.
In any case, first, using the inspection result data 14 before the repair work, the distance g1 (x _p , y _p ) from the separation plane (discrimination boundary plane) g1 is obtained for each data as shown in FIG. . Next, the inspection result data 14 or the current state inspection data 15 after the repair work is collected, and the distance g1 (x _f , y _f ) from the separation surface g1 is obtained. By calculating the difference between g1 (x _f , y _f ) and g1 (x _p , y _p ), it is possible to analyze the change in safety from before to after repair of each data, that is, the effect of the repair work it can.
The selection of the inspection result data 14 and the current state inspection data 15 when analyzing the effect of such repair work may be performed in advance through the input unit 1 when setting the analysis conditions in step S2 of FIG. The work effect calculation unit 7 may read the data. When reading from the repair effect calculating unit 7, it is preferable to read while searching for data and time data related to the target structure included in the inspection result data 14 and the current inspection data 15 as keys.

However, it is the degree of deterioration described above that must be noted when performing such an analysis. The inspection result data 14 before the repair work is data acquired at the time of the check, and is obtained at a time different from the time when the inspection result data 14 or the current state check data 15 after the repair work is collected. Therefore, it has deteriorated with time, and repair work has been carried out and improved with respect to those deteriorated with time. Accordingly, the inspection result data 14 before the repair work needs to be corrected on the assumption that the deterioration over time has progressed until the repair work is performed.
For this correction, as shown in FIG. 2, the deterioration degree evaluation unit 10 performs the deterioration degree analysis in step S5, and stores the obtained deterioration degree or deterioration rate in the evaluation information database 27 as deterioration degree data 29. Is read out by the repair effect calculating unit 7 and added to the inspection result data 14 before the repair work is performed. Of course, when the deterioration rate is used, the deterioration degree is calculated by multiplying the deterioration rate by the period from the time when the inspection data 14 before the repair work is performed until the time when the repair work is performed.
In addition, when the inspection result data 14 after the repair work is acquired after a considerable period from the repair work, the inspection result data 14 may be corrected to add a deterioration degree. desirable. This correction method is the same as the correction of the inspection result data 14 before the previous repair work. However, it goes without saying that the correction including the degree of deterioration may not be performed if it is acquired immediately after the repair work is performed in the current status inspection data 15.

Next, the result of analyzing the effect of repair work using actual inspection result data will be described with reference to Table 7 and FIG. Table 7 shows the inspection result data at two time points as a list. The first point of time is the inspection in 1999, and the “result of inspection before repair” in the table is the inspection result data before repair work. The second time point is the time of inspection in 2004, and the “result of inspection after repair” in the table is the inspection result data after repair work. However, as can be understood by referring to the table, the repair work was carried out in 2002, and there is a two-year gap from the inspection after the repair.
In the present embodiment, correction based on the degree of deterioration is not performed with respect to the lapse of two years.

As described above, the analysis of the effect of the repair work is performed by obtaining the distance from the discrimination boundary surface, that is, the repair work necessity level before and after the repair work, and calculating the difference. Table 7 is analyzed as f1 (X _p ) and f1 (X _f ), respectively. Then, the difference is shown as Table _{7 f1 (X f) -f1 (} X p), it is the repair Engineering effect.
In this way, the basic repair effect is analyzed.

However, as mentioned above, since three years have passed from the time of the inspection result before repair (1999) to the repair work, at the time of repair, the three-year deterioration from the inspection result before repair should be considered, Since two years have passed from the time of repair work to the time of the inspection results after repair, deterioration over time for two years from the time of repair work should be considered during the inspection after repair. In other words, for accurate analysis of the effect of repair work, the inspection results data from the pre-repair inspection after 3 years from the pre-repair inspection, the repair work performed immediately after that, and the post-repair inspection performed immediately thereafter It is necessary to obtain the distance from the discriminant boundary surface based on the respective data using the inspection result data by and to obtain the difference.
With regard to this deterioration over time, if there are inspection results data at multiple points in time before and after repair work, it is possible to determine the deterioration degree and unit time change of deterioration degree before and after repair work, that is, the deterioration rate. Correction can be performed by adding the product of the deterioration rate and the elapsed time to the inspection result data before and after.
The repair effect calculated while being corrected in the repair effect calculation unit 7 as necessary is stored in the evaluation information database 27 as the repair effect data 30 by the repair effect calculation unit 7. Or you may output to the output part 11 directly.

Here, explanation is added about the difference in the deterioration degree and deterioration rate before and after repair work. FIG. 17 shows a transition of factor data due to aging after repair as a conceptual diagram. (A) is a case where the repair work effect is small, and (b) shows a case where the repair work effect is large.
In FIG. 17 (a), the data immediately after the repair is asymptotic to the discriminant boundary surface after 3 years and 5 years, but in (b) 5 years until reaching the position after 3 years of (a), Similarly, it takes 10 years to reach the position after 5 years, and this clearly indicates that the repair effect in (b) is greater.
As is clear from this figure, even for the same member of the same structure, there may be a difference with respect to subsequent aging depending on the repair work. Therefore, by accumulating data relating to the type and degree of repair work and creating a database, there is a possibility that the deterioration rate for the repair work performed can be obtained. Of course, since there are factors of the target structure, it is considered that the deterioration rate should be arranged for each type of structure.
If it is considered that there is a possibility that the deterioration rate may be different before and after repair work even for the same structure in this way, it is important to analyze the deterioration rate before and after repair work. The effect itself is also fed back.
In other words, the distance between the discriminant boundary surface obtained from the inspection results data after the repair work and the point of the factor data is considered to be an effect of aging deterioration unless it is the inspection result data immediately after the repair work. The type and degree of repair work affect the deterioration rate of aging itself.
By accumulating data relating to the repair work that affects the deterioration rate, it is possible to select that the repair work is suitable for a certain type of structure. This is the step S10 in FIG. It is a process shown by. As step S10 will be described later, step S8 will be described next.

In step S8, the necessity of repair work is determined based on the repair work necessity analyzed in step S4. The process of step S8 is also executed by the repair work necessity degree calculation unit 5.
In step S4, the degree of repair work is analyzed in consideration of the inspection time and the time of the analysis time while analyzing the degree of deterioration by the deterioration degree evaluation unit 10 as necessary, and the repair work degree calculation unit 5 performs the repair. Construction necessity data 28 is stored in the evaluation information database 27. Therefore, in step S 8, the repair work necessity calculation unit 5 reads the repair work necessity data 28 from the evaluation information database 27, and further, the repair work necessity data 28 is stored in advance as a part of the analysis condition data 24. A reference value for determining necessity is read from the analysis database 23, and this is compared with the previous repair work necessity data 28 to determine the need for repair work.
If the necessity of repair work is currently denied in the determination in step S8, the user of this system considers the subsequent response policy in response to the determination.

On the other hand, if the need for repair work is affirmed in the determination in step S8, the process further proceeds to step S9. In step S9, the repair work priority calculation unit 8 rearranges the data according to the numerical value of the repair work necessity level. Of course, data rearrangement may be executed in consideration of factors such as necessary expenses and importance of structures in addition to the numerical value of the degree of necessity for repair work.
The repair work priority obtained in step S9 is stored in the evaluation information database 27 by the repair work priority calculation unit 8 as repair work priority data 31.

Furthermore, after the priority of repair work is determined, the repair work actually performed on the structure to be repaired is selected in step S10.
As described above, when the subsequent aging deterioration differs depending on the repair work, it is needless to say that the one having a small aging deterioration is appropriate as the repair work.
Therefore, it is considered possible to determine the correspondence between the repair method and the structure with a certain degree of accuracy by acquiring data on the repair effect as described above.
The repair method data 22 is a summary of this correspondence as data. In this method, data accumulated in advance is stored in the repair method database 21.
The repair method data 22 is a data set appropriately selected from the type of structure, the site of the structure, the cause of deterioration, the effect of repair, the deterioration rate, the required cost, etc., and corresponds to the repair method. Also, the data is configured to be searchable. The repair method selection unit 9 lists the repair methods according to the cause of the deterioration using the factor data as a key, or lists the repair methods in descending order of the deterioration rate using the target structure or target part of the repair work as a key. This is displayed as a list on the part 11. Alternatively, repair methods having a high repair effect may be listed using the repair effect as a key and displayed as a list on the output unit 11. Further, as a display method, one of the most appropriate construction methods among the repair work candidates may be displayed on the output unit 11, or up to about the best three may be displayed.

Further, the repair method selection unit 9 displays on the output unit 11 whether the search is to be performed with the type of the structure, the site of the structure, the deterioration rate, the repair method, or the required cost as a key. It is preferable that the user can input a selection from the input unit 1 so that the search can be appropriately performed. That is, even if the structure to be repaired or its portion does not actually exist, the user can search the repair method data 22 stored in the repair method database 21 using the repair method selection unit 9 at any time. It is something to keep. As described above, by making the search possible at any time, it is possible to grasp the relationship between the structure or part included in the repair method data 22 and the deterioration rate, the repair method, and the necessary expenses as needed.
When the selection of the repair method is completed as described above, the actual repair work can be carried out with reference to this as shown in FIG. After that, periodic inspections will be conducted. However, the implementation of the repair work and the regular inspection are not included in the content of the invention of the present application.

Next, an embodiment of a structure repair construction plan support system capable of creating and displaying a structure repair plan map will be described with reference to FIG.
So far, the structure repair execution plan support system that calculates and evaluates the necessity of repair work, the effect of repair work, and the degree of deterioration has been described. However, the structure repair work plan support system according to the present embodiment is calculated repair It is a structure repair construction plan support system that can be displayed as information on a map that includes structures to be evaluated for the degree of construction necessity, the effect of repair work, and the degree of deterioration.
As shown in FIG. 18, the obtained repair work necessity level, the repair work effect, and the deterioration level are displayed together with the determination of the structure number, the necessity of repair, and the like. This determination is that the greater the degree of necessity for repair work is, the smaller the need for repair work is, and the greater the value for negative work is, the greater the need for repair work is. However, what value should be used for repair work should be determined for each structure because factors such as the type of structure and age after construction should be taken into consideration.
In the figure, information on structures existing at a point in the form of a bridge or tunnel is displayed in the form of a table.
For such display, for example, map data is stored in advance in the analysis database 23 shown in FIG. 1 via the input unit 1, and calculation / evaluation information of structures in the map data is linked to the output unit 11. This is realized by displaying via the.
Specifically, deterioration factor data and inspection result data 14 or current inspection data 15 are input for each structure from the input unit 1 at the time of analysis or stored in the inspection database 13 via the input unit 1 in advance. In this case, the position data including the position data that can identify the area where the structure exists is stored.
On the other hand, the position data of the structure is also included in the map data. For example, when the repair work necessity calculation unit 5 outputs information on a desired structure via the output unit 11, the repair work necessity calculation unit 5 first calculates the repair work necessity data calculated by itself. 28 or the repair work necessity data 28 stored in the evaluation information database 27 is read, and the map data is collated from the analysis database 23 using the position data related to the structure included in the repair work need data 28 as a key. , The structure that matches the position data included in the repair work necessity data 28 and, if necessary, the surrounding area are read out, and the repair work necessity data 28 is indicated by a sign or symbol in the area indicated by the position data, It is displayed on the output unit 11 with a number or the like. Further, the repair work effect calculation unit 7 or the deterioration level evaluation unit 10 also has the same function as that for visually displaying the repair work effect data 30 and the deterioration level data 29. Therefore, as described above, it is desirable to store the position data of the structure as it is with respect to the calculated necessity for repair work, the effect of repair work, and the degree of deterioration. In this embodiment, the necessity of repair work, the effect of repair work, and the degree of deterioration are displayed together with the determination of the structure number, necessity of repair, etc. The construction priority order data and the desired repair construction type data may be appropriately changed according to the intended use.
In addition, the repair history data 17 stored in the repair history database 16 includes position data, and is displayed on the structure repair plan map, so that the repaired construction status can also be grasped. can do.

  Structures in all organizations and companies related to construction structures, civil engineering structures, such as local governments, administrative organizations that manage highways, tunnels, dams, high-rise buildings, inspection organizations, design companies, construction companies, consulting companies, etc. It has a wide range of applications, from construction of construction to planning of repair plans and management after construction of repair works. It is also expected to be used as a teaching material for preventing accidents and disasters in structures and for evacuation training in educational institutions. Furthermore, companies that operate construction and civil engineering projects can use it as a tool for uncovering the needs of repair work projects, proposing business proposals, or sharing tools for collaboration with public institutions. It can also be applied to applications such as technology research and development and design projects.

It is a block diagram of the structure repair construction plan support system which concerns on this Embodiment. It is a flowchart which shows the arithmetic processing method using this structure repair construction plan support system. It is the conceptual diagram which showed the discrimination | determination boundary surface analyzed using the support vector machine on the two-dimensional plane. It is the graph which showed the correlation of five-step evaluation by professional engineer judgment and the necessity of repair work based on inspection performance data. It is the graph which showed the correlation of the score total by a new face evaluation score method, and five-step evaluation by engineer judgment. It is the graph which showed the result (correlation) of the analysis by SVM which implemented the repair policy by engineer judgment as a teacher value based on inspection performance data. It is the graph which showed the result (correlation) of the analysis by SVM which implemented the treatment policy by engineer judgment as a teacher value based on inspection performance data. (A) is a graph which shows the evaluation result in the learning data for tunnels, (b) is a graph which shows the evaluation result in the test data for tunnels. (A) is a graph which shows the evaluation result in the learning data for PC bridge, (b) is a graph which shows the evaluation result in the test data for PC bridge. (A) is a graph which shows the evaluation result in the learning data for steel bridge, (b) is a graph which shows the evaluation result in the test data for steel bridge. It is a flowchart which shows an example of the algorithm which calculates | requires the distance of the data on a discrimination | determination boundary surface, and the data point (Bj) in a certain structure, and calculates repair construction necessity. It is a schematic diagram for demonstrating the analysis of a deterioration degree. (A), (b) is a conceptual diagram which shows the progress of deterioration. It is the graph which traced the progress of the aged deterioration obtained based on the steel bridge inspection data. It is the graph which traced the progress of the aged deterioration obtained based on the steel bridge inspection data. It is a schematic diagram for demonstrating the analysis of a repair work effect. (A), (b) is a conceptual diagram which shows transition of the factor data by the secular deterioration after repair. It is a conceptual diagram which shows an example of a structure repair plan map.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Input part 2 ... Calculation part 3 ... Standardization analysis part 4 ... Analysis condition setting part 5 ... Repair work necessity calculation part 7 ... Repair work effect calculation part 8 ... Repair work priority calculation part 9 ... Repair method selection part 10 ... Degradation degree evaluation part 11 ... Output part 12a ... Data 12b ... Analysis condition 13 ... Inspection database 14 ... Inspection result data 15 ... Current inspection data 16 ... Repair history database 17 ... Repair history data 18 ... Boundary database 19 ... Discrimination boundary line data 20 ... discriminating boundary surface data 21 ... repair method database 22 ... repair method data 23 ... analysis database 24 ... analysis condition data 25 ... parameter data 26 ... repair work necessity function data 27 ... evaluation information database 28 ... repair work need data 29 ... Degradation degree data 30 ... Repair effect data 31 ... Repair work priority Position data

Claims (8)

It has an information input device, an information storage device, an information calculation device, and an information output device, and was obtained using factor data relating to the cause of deterioration in each structure and past repair construction / unconstructed performance data. Structure repair work that calculates the necessity of repair work in a certain structure based on the discriminant boundary line or discriminant boundary surface (hereinafter referred to as discriminant boundary surface including the discriminant boundary line) that separates the necessity of repair work A planning support system,
The information input device is means capable of inputting deterioration factor data in the structure and boundary data constituting the discrimination boundary surface to the information storage device,
The information calculation device reads the factor data in the structure and the boundary data from the information input device or the information storage device, and a space of two or more dimensions (hereinafter referred to as a multidimensional space) in which the boundary data is configured. .) An analysis condition setting unit for inputting the read factor data as coordinates above,
A repair work necessity calculation unit that calculates the distance from the determination boundary surface to the coordinates of the factor data in the structure as the necessity of the repair work,
The structure repair construction plan support system, wherein the information output device is a means capable of outputting at least one piece of information among factor data, boundary data, and necessity of repair work in the structure. The factor data in the structure includes time data representing the time when the factor data was acquired,
The information calculation device reads the factor data in the structure from the information input device or the information storage device, and a first distance from the determination boundary surface to the coordinates of the factor data at a certain point of the structure, Calculating a second distance from the determination boundary surface to the coordinates of the factor data at a time different from the certain time in the structure;
The structure repair according to claim 1, further comprising a deterioration degree evaluation unit that calculates a difference between the first time point and the second distance as a deterioration degree between the certain time point and the certain time point. Construction plan support system. The information input device includes the deterioration factor data in the structure, boundary data constituting the determination boundary surface, presence / absence of repair work performed on the structure, and time of repair work. Means capable of input to the storage device,
The information calculation device reads the factor data in the structure from the information input device or the information storage device using the repair presence / absence data in the structure as a key, and repairs the structure from the discrimination boundary surface Calculating a third distance to the coordinates of the factor data at the time after the execution and a fourth distance from the discrimination boundary surface to the coordinates of the factor data at the time before the repair work on the structure;
The structure repair construction plan support system according to claim 1, further comprising a repair work effect calculation unit that calculates a difference between the third distance and the fourth distance as a repair work effect. The repair work effect calculation unit stores the data related to the repair work effect and the data related to the type of repair work together with the structure factor data in the information storage device,
The said information arithmetic device is provided with the repair method selection part which reads the data which concern on the method type of the said repair work stored in the said information storage device by using the type of the said factor data as a key. Structure repair construction plan support system.   The structure repair construction plan support system according to claim 4, wherein the repair method selection unit ranks data related to a method type of the repair work with data related to the repair effect as a key.   The structure repair construction plan support system according to any one of claims 1 to 5, wherein the discrimination boundary surface is set by analysis using a support vector machine.   The structure repair construction plan support system according to any one of claims 1 to 5, wherein the discrimination boundary surface is set by analysis using a radial basis function network. The information storage device stores in advance position data of the structure and map data around the structure,
The information calculation device visually displays at least one piece of information on the position data of the structure and the degree of necessity of repair work, the degree of deterioration, the effect of repair work, or the priority of repair work on the map data. The structure repair construction plan support system according to any one of claims 1 to 7, which has a function of causing the output device to output the information as an identifiable information.