JP2007249955A - Soundness evaluation system based on grading data sheet usable for inspection - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a soundness evaluation system which can carry out objective and highly precise quantitative evaluation based on data relating to many inspected items by excluding prejudice and subjectivity of an engineer and inspector when evaluating the necessity of repairing civil structure and calamity danger area or danger of disaster occurrence. <P>SOLUTION: The soundness evaluation system comprises an input section 1, a calculating section 2, storages 12, 14, 16, 18, 20, and 23, and an output section 10, and makes a grading data sheet to calculate the necessity of measures against objects for inspection based on a boundary of discrimination for separating execution or non execution of repair and occurrence or non occurrence of disaster obtained by using factorial data 17 relating to factors for soundness degradation of the objects for inspection and repair work data 15 or disaster history data 28 of the objects for inspection. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention is based on a discriminating boundary surface that separates the construction and non-construction of repairs or the occurrence and non-occurrence of disasters obtained from the analysis of data on soundness deterioration in inspection objects such as civil engineering structures and disaster risk points, for example. A system that evaluates the health of the inspection object by creating a score data sheet that is set using the calculated necessity of repair and countermeasures for the inspection object and using it for inspection work About.

Civil engineering structures such as bridges, tunnels, steel towers, water supply and sewerage systems, and disaster hazards are inspected on a daily basis for maintenance and management, and if damage is found, the extent is determined and necessary repairs are made. Measures are usually 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 and disaster hazards is required, maintenance of existing social capital is an urgent task. However, in order to implement this more efficiently, Establishing an objective assessment method for damage status is considered indispensable.
In addition to civil engineering structures, such evaluation methods include measures such as reinforcement work and drainage trenches on steep slopes from the viewpoint of preventing natural disasters such as earth and sand disasters and depression disasters. This is necessary for evaluating the degree of risk, and 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.

  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 objects such as bridges, tunnels, and steel towers. There was a problem that evaluation about deterioration was insufficient because the concept of deterioration with time in a structure was difficult to be reflected.

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.

In addition, various data sheets widely used in inspection work for bridges, tunnels, steel towers, civil engineering structures such as water and sewers, and disaster hazards are often unclear on the basis for setting them. Some were unable to demonstrate sufficient accuracy. In recent years, when the effective use of civil engineering structures is required, maintenance of existing social capital is an urgent task. However, in order to implement this more efficiently, more accurate and objectivity is required. This technology was devised as one of the risk assessment methods.
In addition, civil engineering structures such as bridges, tunnels, steel towers, water supply and sewerage, and disaster hazards are inspected on a daily basis for maintenance, and if damage is found, the extent is judged. The necessary repair measures are usually taken. In many cases, a check sheet (inspection data sheet) that can be easily used on site is used for this inspection work. These sheets are devised so that the safety of the current situation can be evaluated by assigning a grade according to the damage situation of the object. However, there are hardly any clear reasons for determining the score of a sheet, and the final judgment is often left to the judgment of an advanced engineer.
In this regard, based on the past inspection data and repair performance data, a mathematical expression such as a support vector machine (hereinafter sometimes abbreviated as SVM) or a radial basis function network (hereinafter sometimes abbreviated as RBFN). We have invented a system that sets the necessity of repair by using the pattern classification method and resets the score of the inspection data sheet based on the analysis result. The new data sheet obtained by this system has high accuracy in determining whether structural repairs are necessary, and it can also ensure objectivity based on past performance, thus improving the efficiency of maintenance and repair work for civil engineering structures. A big effect can be expected in the realization of high accuracy.

  The present invention has been made in response to such a conventional situation, and prejudice by an engineer or an inspector when evaluating the necessity of repairing a civil engineering structure or a disaster risk location or the risk of occurrence of a disaster. Soundness that enables objective and highly accurate quantitative assessment of the necessity of repair work and the risk of disaster hazards based on the data of a large number of items that have been inspected, while eliminating subject matter and subjectivity The purpose is to provide an evaluation system.

In order to achieve the above object, a soundness evaluation system based on a score type data sheet that can be used for inspection work according to claim 1 has an input unit, a calculation unit, a storage unit, and an output unit. , Discriminating boundary that separates the construction and non-construction of repairs or the occurrence and non-occurrence of disasters obtained by using the factor data related to the cause of soundness deterioration in the inspection target and the repair result data or disaster history data for the inspection target This is a soundness evaluation system that creates a score type data sheet for calculating the degree of necessity of countermeasures for an inspection object based on a line or a discrimination boundary surface (hereinafter referred to as a discrimination boundary surface including a discrimination boundary line). The input unit is a means capable of inputting the cause deterioration factor data of the inspection object and the boundary data constituting the discrimination boundary surface into the storage unit, and the calculation unit receives the boundary data. Read from the storage unit and input from the input unit on the factor data of health deterioration in the inspection object read from the storage unit on the two-dimensional space (hereinafter referred to as multidimensional space) in which this boundary data is configured An analysis condition setting unit that inputs factor data of the inspection object as coordinates, and a representative value calculation unit that calculates the distance from the discrimination boundary surface to the coordinates of the factor data of the inspection object as a repair necessity level or a disaster risk level; An evaluation point calculation unit for calculating an evaluation point calculated from the coordinates of the factor data in the inspection object, the distance to the discrimination boundary surface, and the importance of the factor data in the inspection object, and the output unit includes the inspection object It is a means that can output at least one of the factor data and its importance, boundary data, repair necessity or disaster risk, or evaluation points. Which is a health evaluation system based on the available scores formula data sheet inspection operations and features.
In addition, the inspection object in the present application including the description of claim 1 is a civil engineering structure constructed by performing civil engineering work such as a highway, a bridge, a tunnel, a dam, a high-rise building, a steel tower, and water and sewerage. , And a concept including a disaster risk point where a landslide (landslide), a ground depression, a debris flow and the like may occur. In addition, in this application, repair result data is data related to the results of construction for maintenance / repair performed on the inspection object, and disaster history data is a landslide (landslide) that occurred in the inspection object. , Data on the history of natural disasters such as ground depression and debris flow. Furthermore, the repair necessity level of the present application means the necessity of construction for the previous maintenance / repair, and the disaster risk level means the risk level related to the occurrence of the previous natural disaster. Further, in terms of the opposite meanings of these words, the degree of repair unnecessary, the disaster safety degree, etc. may be used, and the concept of these opposite words is included.

  Further, the invention according to claim 2 is a soundness evaluation system based on a score type data sheet that can be used for the inspection work according to claim 1. The analysis condition setting unit inputs factor data as coordinates on the multidimensional space for each of the plurality of categories, and the representative value calculation unit For each category, the distance from the discriminant boundary surface to the coordinates of the factor data on the inspection object is calculated as the degree of necessity for repair or disaster risk, and the representative value for each category of degree of need for repair or disaster risk is calculated and evaluated. The point calculation unit calculates the evaluation points to be written on the data sheet from the importance of each category of each factor data and the necessary value of repair or the risk of disaster, and the output unit Factor data of importance for each of the plurality of categories in the object, the boundary data, repair necessity or disaster risk, or among the evaluation points, those which are capable of outputting means at least one of information.

  According to a third aspect of the present invention, in the soundness evaluation system based on the scoring data sheet that can be used for the inspection work according to the first aspect, the calculation unit provides the factor data of the soundness deterioration in the inspection object as the factor. It has a category classification unit that classifies in multiple categories separated by qualitative or quantitative ranges included in the data, and the analysis condition setting unit has factor data in a multidimensional space for each of the categories classified by the category classification unit The representative value calculation unit calculates the distance from the discriminant boundary surface to the coordinates of the factor data on the inspection object as the degree of necessity for repair or the risk of disaster for each category, and the output unit displays the inspection object. Output at least one of factor data and its importance, boundary data, repair necessity or disaster risk, or evaluation points for each category of goods. Those which are means possible.

  Furthermore, the invention described in claim 4 is a soundness evaluation system based on the score type data sheet that can be used for the inspection work according to claim 1, wherein the cause deterioration data of the inspection object is a plurality of cause data. The calculation unit includes an importance calculation unit that calculates importance for a plurality of factor data, and calculates evaluation points from the degree of necessity for repair or the risk of disaster and importance.

  Finally, in the health evaluation system based on the score type data sheet that can be used for the inspection work according to any one of claims 1 to 4, the invention according to claims 5 and 6 includes It is set by analysis using a support vector machine or RBFN.

  The present invention obtains a discrimination boundary surface that separates construction / non-construction of repair and occurrence / non-occurrence of disaster using repair performance data and disaster history data of inspection objects such as civil engineering structures and disaster risk points. Based on this, it is possible to calculate the necessity of countermeasures on the inspection object as an evaluation point, and to perform an objective and quantitative evaluation with high accuracy.

  In particular, the invention according to claim 2 classifies the factor data into a plurality of categories, and calculates the necessity of repair or the degree of disaster risk for each category, thereby enabling a more accurate soundness evaluation. Is.

  Further, in the invention described in claim 3, when the factor data input by providing the category classification unit is not classified into categories, the classification can be performed to enable the classification. Similarly, a highly accurate soundness evaluation can be performed.

  In the invention described in claim 4, when there are a plurality of cause deterioration factors data on the inspection object, it is important which one of the cause data has a great influence on the repair necessity and the disaster risk. The degree calculation unit can calculate the importance of the factor data. By executing this for all of the factor data, it is possible to perform sensitivity analysis on the factor data, and it is possible to extract more appropriate factor data and evaluate the repair necessity and disaster risk, Highly accurate soundness evaluation can be performed.

  In the inventions according to claims 5 and 6, it is possible to perform evaluation with higher versatility by setting the discrimination boundary surface by analysis using an SVM or RBF network.

Hereinafter, a soundness evaluation system based on a score type data sheet that can be used for inspection work according to an embodiment of the present invention will be described with reference to FIGS.
FIG. 1 is a configuration diagram of a soundness evaluation system based on a score type data sheet that can be used for inspection work according to the present embodiment. Moreover, FIG. 2 is a flowchart which shows the soundness evaluation method using the soundness evaluation system based on the score type | formula data sheet which can be utilized for this check work.
In FIG. 1, the soundness evaluation system includes an input unit 1, a calculation unit 2, an output unit 10, and a plurality of databases 12, 14, 16, 18, 20, and 23.
The input unit 1 is used to input the data 11a stored in these databases in advance, or to directly input the data 11a and the analysis conditions 11b during the operation of the calculation unit 2. 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 an analysis condition setting unit 3, an important factor extraction unit 4, a discrimination boundary surface analysis unit 5, a category classification unit 6, a representative value calculation unit 7 for each category, an importance calculation unit 8, and an evaluation score calculation unit 9. It is composed.
The calculation unit 2 is categorized into input factors using the data 11a related to the discriminating boundary surface read from the database or input from the input unit 1, the data 11a related to the performance of repair work on the structure, and the analysis condition 11b. And a section for calculating a representative value of each factor category, extracting an important factor, calculating an importance level of each factor, and calculating a new evaluation score. 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.
The database includes an inspection database 12 that stores past inspection record data 13 for civil engineering structures and disaster risk points, repair record data 15 for the necessity of repair work, and past disaster histories such as slopes, ground, and rivers. Among the factors of the repair record / disaster history database 14 and the inspection record data 13 in which the data 28 is stored, the important factor database 17 in which the important factor data 17 that is a factor closely related to the repair record and the disaster history is stored. 16, boundary database 18 for storing discriminant boundary surface data 19 for analyzing the necessity of repair and countermeasure work, analysis database 20 for storing analysis condition data 21 and parameter data 22 for various analyses, Category data 24 of each factor obtained as a result of analysis using the calculation unit 2, for each category Representative value data 25, important data 26 for each factor, there is evaluation information database 23 for storing the new evaluation point data 27.
Examples of inspection results data 13 stored in the inspection database 12 via the input unit 1 are shown in the tunnel inspection data shown in Table 1, the debris flow dangerous mountain stream inspection data shown in Table 2, and Tables 3 and 4. There are road slope inspection data and sewerage equipment inspection data shown in Table 5. Each data table has a column of teacher values. These are the repair work results (repair results data), past disaster histories (disaster history data), or depression histories (existence history data). It is shown.
Further, in the inspection result data 13, there are cases where the actual place name is included as a place name as shown in Table 1, when the place name is entered as a number as shown in Table 2, or in addition to this, it is inputted as a symbol. Sometimes it is.

  Specifically, the hardware database may be data stored in a computer storage device such as a magnetic disk or optical disk, and the output unit 10 may be a display device such as a printer device, a CRT, a liquid crystal, or a plasma. Alternatively, a display device such as an organic EL, and a transmitter such as a transmitter for transmitting to an external device can be considered.

The soundness evaluation system based on the score type data sheet that can be used for the inspection work according to the present embodiment mainly including the components as described above 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, a structure stored in the inspection database 12 is changed. There is past inspection result data 13 as quantitative data (hereinafter referred to as factor data) relating to the cause of the condition. Further, there is discriminant boundary surface data 19 stored in the boundary database 18. Such data may be actually measured data, but may be standardized data by performing standardization processing. 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, those that can be expressed numerically as physical quantities are quantitative with such numerical values.
Furthermore, when it is a non-physical quantity or cannot be expressed quantitatively, the state is expressed qualitatively, for example, east, west, south, north when expressing the direction, spring, summer, which represents the season, Since each category, such as autumn, winter, morning, noon, and evening, which represents time zones, cannot be expressed quantitatively, these should be classified as qualitative and qualitative categories in factor data. It is.
In addition to these input factors, analysis condition data 21 and parameter data 22 stored in the analysis database 20, important factor data 17 stored in the important factor database 16, and repairs stored in the repair record / disaster history database 14 The record data 15 and the disaster history data 28 are also input as input data.
In the present embodiment, data input processing is first performed as step S1, but data may be input as appropriate in accordance with the analysis process.

An example of tunnel inspection data is given as an example of inspection result data 13 that can be calculated by the present invention. One of the tunnel soundness evaluation methods that has been used in the past is a JH inspection method. In the JH inspection method, the inspection results of seven items related to damage such as crack width / length and pattern, presence or absence of free lime are written for each span, and the degree of damage is the sum of the grades given according to them. It is shown. Table 6 shows on-site inspection data for tunnels using the JH inspection method, and is composed of seven factors of deterioration from A maximum crack width to G water leakage. Each factor data is quantitatively indicated in the table.
Tables 7 and 8 show road slope inspection data, which is composed of 26 factor data from slope topography (G1) to deformation 2 (adjacent slope). Table 9 shows sewage inspection data, which is composed of twelve factor data from pipe material to elapsed years.

  On the other hand, in addition to the total score, a five-step evaluation from 3A to blank is given for the necessity of countermeasures as a judgment of the inspection engineer (Table 10). In this implementation, this evaluation will be used as repair performance data, and 2A and 3A that require immediate and urgent measures will be entered as -1, and A and B that do not require immediate measures will be entered as 1. did. Also, in Table 11, three levels of items relating to the damage history are given for the road slope, apart from the factor data as shown in Table 8. In this embodiment, this item is used as a damage history, and “Yes” (refer to damage record table / details unknown) is input as −1, and “1” is not input. Further, in Table 12, five levels of items regarding the depression history are given separately from the factor data as shown in Table 9 regarding sewerage. In this implementation, this item will be used as the collapse history, −1 for the cause caused by non-artificial pipes, etc. It is assumed that the depression is entered and other blanks are entered as 1.

  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.

The analysis condition setting unit 3 of the calculation unit 2 sets an object to be analyzed, parameters, and the like as shown in step S2 in FIG. Specifically, which combination of factor data of which structure among the inspection result data 13 is extracted from the inspection database 12 and which discrimination boundary surface data 19 corresponding to the combination is extracted is set. .
Here, the analysis condition setting unit 3 prompts the user to input the conditions for the analysis via the input unit 1, and accesses the inspection database 12 and the boundary database 18 using the input conditions as a key. The inspection result data 13 and the discrimination boundary surface data 19 to be read are read out. Analysis condition data 21 indicating the data contents or data structure stored in the inspection database 12 and the boundary database 18 displayed for prompting input, and parameter data 22 indicating under what conditions analysis is performed. Since it is stored in the analysis database 20, the analysis condition setting unit 3 first accesses the analysis database 20 to read the parameter data 22, and displays the parameter data 22 using the output unit 10. Good.
In response to this display, the user of the soundness evaluation system, when all of the inspection result data 13, the important factor data 17, and the discrimination boundary surface data 19 have been input, the inspection result data 13, the important factor data 17, and the discrimination boundary surface. If data 19 extraction, inspection result data 13 and important factor data 17 have been input, analysis of the determination boundary surface, and if only inspection result data 13 has been input, the determination boundary after extraction of important factors The choice of surface analysis can be made.

Here, as an example of a method for determining the parameter data 22 that indicates under which conditions the analysis is performed, a parameter study method using SVM as a pattern classification method will be described.
In SVM, there are two parameters, C and r, respectively, and under these conditions, it is determined under what conditions the discrimination boundary surface is formed. Briefly explaining these parameters, first, C is a parameter indicating how much an abnormal value of the SVM result is allowed. As C is larger, an abnormal value is not recognized and data is to be strictly divided. R is a parameter that determines the influence of data. The larger the value of r, the greater the variation in data, but the more abnormal values are likely to increase.
First, in determining the parameters of the SVM, the parameters when the hit rate is maximum are used. Here, the hit rate is a ratio indicating how accurately the repair record can be captured by the SVM, and here, the hit rate is defined by equation (1).

The number of hit data in the formula (1) means the number of data in which the risk / safety judgment result by each method coincides with the repair result data 15.
Next, when determining the parameters of the SVM, those having a large variation in distance from the discrimination boundary surface created by the SVM to the coordinates of the factor data of the area to be evaluated are adopted. This is because, when the representative value calculation unit 7 for each category later calculates the representative value for each category of each factor, the larger the data variation, the larger the variation of the representative value for each category of the factor. This is because it is convenient to finally set an evaluation score. Specifically, the standard deviation is used as an index indicating data variation.
Here, as an example, a parameter study when tunnel inspection data is used as an input factor of SVM is introduced. Here, the parameter study was performed with 30 cases of C = 10, 20,..., 300 and 10 cases of r = 0.1, 0.2,.
The results are shown in Table 13. As a result, C = 300 and r = 0.9 were set as SVM parameters as parameters having the highest hit ratio and the largest standard deviation.

  Table 13 shows the results of parameter studies on tunnel inspection data. Tables 14 and 15 show the results of parameter studies on road slope inspection data and sewerage equipment inspection data. In order to provide generalization capability, C = 50 and r = 7 were used in road slope inspection data, and C = 100 and R = 1 were used in sewerage facility inspection data.

Each factor data included in the inspection results data 13 stored in the inspection database 12 includes factors that are closely related to the repair results of the structure (important factors) and factors that are not related to the repair results (not important) Factor).
In the present invention, structural integrity evaluation is performed by excluding insignificant factors from each factor data included in the inspection result data 13 stored in the inspection database 12 and creating a data sheet using only important factors. It was decided to improve the accuracy of the system.

In this embodiment, as shown in step S3 in FIG. 2, the important factor extraction unit 4 can extract important factors. These data do not necessarily need to be analyzed in the arithmetic unit 2, and in this case, the important factor data 17 stored in the important factor database 16 is read out. The important factor data 17 may be stored in the important factor database 16 via the input unit 1 in advance as described above.
As an example, an important factor extraction method according to the procedure of the flowchart of FIG. 3 will be introduced. In this method, out of the inspection result data 13 stored in the inspection database 12, one factor is excluded from each factor used in the factor database in the structure to be evaluated, and a method such as SVM is used. When analysis is performed and the hit rate (see formula (1)) is lower than the results when all inspection data are used, the factor is an important factor, and the hit rate is not reduced. The important factors are extracted as the factors that are not important.

Table 16 shows the result of extracting important factors of the tunnel inspection performance data when analyzed by this method using SVM as an example. Factors marked with an asterisk in the leftmost column of the table are important factors, and factors with the leftmost column left blank are unimportant factors. The analysis result by SVM using only the important factors extracted by this method has a high correlation with the five-step evaluation by the engineer judgment (Fig. 4), and only the unimportant factors extracted by this method are used. It greatly exceeds the correlation (FIG. 5) between the analysis result by SVM and the engineer judgment, and it can be seen that the important factors are correctly extracted by this method.
The important factor extraction method can be extracted by using other methods such as rough sets in addition to SVM. In the present invention, these factors may be used to extract important factors. Since these methods are already known techniques, a detailed description thereof will be omitted.
The result of extracting the important factor is stored as the important factor data 17 in the important factor database 16 by the important factor extracting unit 4.

  Table 16 shows the extraction results of important factors related to tunnel inspection data. Tables 17 and 18 show the calculation results of important factors related to road slope inspection data and sewerage equipment inspection data when the same method is used. Show.

  In the present embodiment, the discriminating boundary surface data 19 stored in the boundary database 18 can be analyzed by the discriminating boundary surface analysis unit 5 as described above. 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 important factor data 17 and the repair performance database 14 It is also possible to analyze the discriminant boundary surface data 19 by performing so-called initial learning based on the stored repair record data 15 and disaster history data 28. In FIG. 2, after selecting any one of the important factor data 17 and the repair result data 15 in the analysis condition setting in step S2, the analysis can be performed as step S4. The acquisition of the discriminating boundary surface data 19 can be obtained by using an RBF network or performing an analysis using an SVM. However, since these methods are already known techniques, a detailed description thereof will be omitted. The discriminant boundary surface data 19 obtained as a result of the analysis by the discriminant boundary surface analyzing unit 5 is stored in the boundary database 18 by the discriminating boundary surface analyzing unit 5.

As shown in step S <b> 5 in FIG. 2, the category classification unit 6 accesses the important factor database 16, retrieves relevant important factor data 17, and performs category classification of each factor data included in the important factor data 17.
For example, in the case of crack width, which is one of the factors of tunnel inspection data, no crack width is set as category 1 due to data distribution, etc., and thereafter, it is classified into 5 categories with a crack width of 0.5 mm.
As for the category classification method, in addition to the method introduced here, a method of taking the median of the data distribution and equally dividing the data distribution can be used. In the present invention, these methods may be used for category classification.
The result of the category classification is stored in the evaluation information database 23 by the category classification unit 6 as the category data 24 of each factor.

The representative value calculation unit 7 for each category calculates a representative value for each category of each factor as evaluation point basic data, as shown in step S6 in FIG. The category data 24 of each factor stored in the evaluation information database 23 is accessed, the distance from the discrimination boundary surface to the coordinate of the factor data of the region to be evaluated is first calculated, and then the representative value for each category is calculated. calculate. As an example, FIG. 6 shows a relationship between representative values for each category (in this example, the average value is a representative value) when the crack width of the tunnel inspection data is divided into categories of 0.5 mm.
The calculated representative value of the distance is stored in the evaluation information database 23 by the representative value calculation unit 7 for each category as representative value data 25 for each category of each factor. The representative value of the calculated distance corresponds to the repair necessity level or the disaster risk level. With the discrimination boundary as a reference, the degree of repair necessity and the risk of disaster increase or decrease in a direction away from the discrimination boundary. In other words, the distance is positive and negative, takes a positive and large value, and the distance away from the discrimination boundary is lower when it is away from the discrimination boundary surface, and the risk of disaster is lower. Disaster risk is high.
Tables 19 to 25 show the average f (x) for each category of each factor in the tunnel inspection as an example of the representative value for each category.
In this example, the arithmetic average is used as the representative value, but other values such as an arithmetic average, a geometric average, and a median may be used. Further, when there is no category classification or there is a category classification, the distance from the discrimination boundary surface to the coordinates of the factor data of the area to be evaluated may be calculated without using the representative value. In that case, the distance corresponds to the necessity for repair or the risk of disaster. That is, the representative value calculation unit in the present application does not always calculate a representative value, but may first calculate the distance from the determination boundary surface to the coordinates of the factor data in the inspection object. Moreover, when there are a plurality of categories, after calculating the distance from the determination boundary surface to the coordinates of the factor data in the inspection object for each of the plurality of categories, the average value as described above is calculated, This is the representative value.

  Tables 19 to 25 show the average f (x) of each factor for the tunnel inspection data for each category. However, for each factor regarding the road slope inspection data and the sewerage facility inspection data when the same method is used. The average f (x) for each category is shown in Table 26 and Table 27, respectively.

As shown in step S7 in FIG. 2, the importance calculation unit 8 determines how much each factor data included in the inspection result data 13 stored in the inspection database 12 is an expressway, a bridge, a tunnel, a dam, and a high-rise building. The importance is calculated as an indicator of whether it is closely related to the repair history of structures such as steel towers, water supply and sewerage, and disaster history such as slopes, ground, and rivers.
As an example, an importance calculation method using SVM is introduced. In this method, one factor is excluded from the factors used in the factor database for the inspection object to be evaluated, the analysis is performed by SVM, and the result and target when all inspection data are used as teacher values. Make a moderate comparison. Here, it is assumed that the hit rate decreases as the more important factor is excluded, and the importance is calculated by the equation (2). Here, the importance is defined as a difference, but of course, the ratio obtained by the ratio of P and Pn, P / Pn, or another calculation method may be used as the importance.

Table 28 shows the result of calculating the importance of the tunnel inspection performance data as an example.
Note that the importance of each factor can be extracted by using other methods such as rough sets in addition to the method introduced here. In the present invention, these factors are used to extract important factors. It shall be good. Since these methods are already known techniques, a detailed description thereof will be omitted.
The result of calculating the importance is stored as importance data 26 in the evaluation information database 23 by the importance calculation unit 8.

  In Table 28, importance calculation results related to tunnel inspection data are shown. Table 29 and Table 30 show importance calculation results related to road slope inspection data and sewage equipment inspection data, respectively, when a similar method is used. Shown in

As shown in step S8 in FIG. 2, the evaluation score calculation unit accesses the evaluation information database 23 and reads the representative value 25 and importance data 26 for each category of each factor. Then, a new evaluation score is calculated from the representative value 25 and importance level data 26 for each factor category.
Table 31 to Table 37 show the evaluation score calculation results for each factor of the tunnel inspection performance data as an example. Here, the new evaluation score was calculated by multiplying the product of the representative value (average value) for each category of each factor by the importance data. Of course, in addition to the product, the new evaluation point may be calculated by another calculation method, for example, a method of taking the square root of the sum or product, or may be multiplied by a coefficient as appropriate.
The result of calculating the new evaluation score is stored in the evaluation information database 23 by the evaluation score calculation unit 9 as new evaluation score data 27.

  Tables 31 to 37 show the evaluation score calculation results for each factor related to tunnel inspection data, but the evaluation results for road slope inspection data and sewerage facility inspection data when using the same method are shown respectively. Tables 38 and 39 show the results.

The computing unit 2 accesses the evaluation information database 23, reads out the category data 24, representative value data 25, importance level data 26, and new evaluation point data 27 of each factor, and creates a data sheet.
Table 40 shows the new tunnel inspection data sheet. In Table 40, only the category data 24 and the new evaluation point data 27 for each factor are read to create a data sheet. In particular, it is not always necessary to read out the category data 24, the representative value data 25, the importance level data 26, and the new evaluation point data 27 of each factor, and any one of these may be selected.

FIG. 7 shows the correlation between the total score in the conventional JH inspection method and the five-step evaluation by the engineer. As shown in FIG. 7, it is difficult to say that there is a correlation between the total evaluation score in the JH inspection method and the engineer determination result.
Next, FIG. 8 shows the relationship between the total of the evaluation points of the inspection data based on the new data sheet (Table 40) created by the present invention and the five-step evaluation based on the judgment of the engineer. As shown in FIG. 8, a high correlation could be obtained between the sum of the evaluation points of the inspection data by the new data sheet created by the system of the present invention and the five-step evaluation by the engineer's judgment. In addition, this result greatly exceeds the result of the conventional JH inspection method, and shows that the data sheet created by the structural soundness evaluation system can separate the necessity for repair with high accuracy.
In addition, as a result of applying the new data sheet to the data of region A different from the learning data (FIG. 9), a clear correlation was obtained between the evaluation point total and the engineer judgment. In other regions B and C, a correlation was obtained between the total score and the engineer's judgment (FIGS. 10 and 11). Therefore, it was confirmed that the data sheet created by the soundness evaluation system has versatility. The areas A to C are identification codes regarding the tunnel from which data is acquired.
In the above-described embodiment, the new data sheet has been described using the tunnel inspection data. However, as shown in Table 41 and Table 42, a new data sheet created using the road slope inspection data, As shown in Fig. 4, there is a new data sheet created using sewerage equipment inspection data.
In the new data sheet using the road slope inspection data of Table 41 and Table 42, the evaluation points are obtained by the same method as the tunnel inspection data using the evaluation categories shown in Table 3 and Table 4.
Moreover, in the new data sheet using the inspection data of the sewer facilities of Table 43, the new evaluation score was calculated by the same method as the tunnel inspection data for each factor such as a deformation crack described in the leftmost column.

FIG. 13 shows the relationship between the total score in the conventional road slope inspection data and the disaster history. As shown in FIG. 13, it is difficult to say that there is a correlation between the total score in the conventional road slope inspection method and the disaster history.
Next, FIG. 14 shows the relationship between the total score of inspection data according to the new data sheets (Table 41 and Table 42) created by the present invention and the disaster history. As shown in FIG. 14, it was possible to obtain a high correlation between the total score of the inspection data based on the new data sheet created by the system of the present invention and the disaster history. In addition, this result greatly exceeds the result of the conventional road slope inspection method, and shows that the data sheet created by the structural soundness evaluation system can separate the presence or absence of a disaster with high accuracy.
In addition, as a result of applying the new data sheet to data in region D different from the learning data (FIG. 15), a clear correlation was obtained between the total score and the disaster history. Therefore, it was confirmed that the data sheet created by the soundness evaluation system has versatility. The region D is an identification code regarding the road slope from which data is acquired.
In the same way as the new data sheet using the tunnel inspection data, the representative value and importance data for each category are updated by other calculation methods such as taking the square root of the sum or product in addition to taking the product. An evaluation score may be calculated. The same applies to the case of using other data, and is not particularly limited.

FIG. 16 shows the relationship between the total score and the depression history in the inspection data of conventional sewerage facilities. As shown in FIG. 16, it is difficult to say that there is a correlation between the total score in the conventional sewerage facility inspection method and the depression history.
Next, FIG. 17 shows the relationship between the total score of inspection data according to the new data sheet (Table 43) created by the present invention and the depression history. As shown in FIG. 17, it was possible to obtain a high correlation between the total score of the inspection data based on the new data sheet created by the system of the present invention and the depression history. In addition, this result greatly surpasses the result of the conventional inspection method for sewerage facilities, and shows that the data sheet created by the structural soundness evaluation system can separate the presence or absence of a disaster with high accuracy.
In addition, as a result of applying the new data sheet to the data of region E different from the learning data (FIG. 18), a clear correlation was obtained between the total score and the depression history. In other areas F, a correlation was obtained between the total score and the depression history (FIG. 19). Therefore, it was confirmed that the data sheet created by the soundness evaluation system has versatility. Areas E and F are identification codes relating to sewerage facilities from which data has been acquired.
In the same way as the new data sheet using the tunnel inspection data, the representative value and importance data for each category are updated by other calculation methods such as taking the square root of the sum or product in addition to taking the product. An evaluation score may be calculated. The same applies to the case of using other data, and is not particularly limited.

  As a method for further improving the accuracy of the created data sheet according to the present invention, it is possible to limit the observation items. Here, as an example, consider tunnel inspection data. In tunnel inspection, seven factors shown in Table 16 are extracted as important factors. Looking at the importance calculation results in Table 28, two factors are important compared to other important factors: free lime and water leakage. It can be seen that the degree is low. Therefore, the data sheet was created again excluding these two factors (Table 44).

FIG. 12 shows the relationship between the total evaluation score of the newly created data sheet of Table 44 and the repair results. As a result, compared with the result when using the seven factors shown in FIG. 8, it was possible to obtain a result that accurately captured the characteristics of the repair result data.
Thus, in the present invention, it is possible to improve the accuracy of soundness evaluation by the data sheet by limiting the observation items of the data sheet.
As mentioned above, although the soundness evaluation system using SVM was shown in this Embodiment, even if it replaces with SVM and uses a RBF network, the same soundness evaluation system can be implemented.

  Management organizations that manage highways, tunnels, dams, high-rise buildings, steel towers, etc., including local governments, inspection organizations, design companies, construction companies, consulting companies, etc. In companies, it has a wide range of applications, from construction of structures to planning of repairs of structures and hazardous areas, and management after construction of repair works. It is also expected to be used as educational material for accidents in structures and accidents and disasters at disaster risk points 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 soundness evaluation system based on the score type | formula data sheet which can be utilized for the check work which concerns on this Embodiment. It is a flowchart which shows the soundness evaluation method using the soundness evaluation system based on the score type | formula data sheet which can be utilized for this check work. It is a flowchart which shows an example of the extraction method of an important factor. It is a graph which shows the analysis result by SVM of an important factor based on tunnel inspection performance data. It is a graph which shows the analysis result by SVM of the factor which is not important based on the tunnel inspection performance data. It is the graph which showed the relationship of the average f (x) for every category when the crack width of tunnel inspection data was classified into every 0.5 mm. It is a graph which shows the correlation with the 5-point evaluation by engineer judgment with the score total in the conventional JH inspection method. It is a graph which shows the relationship between the sum total of the evaluation score of the inspection data by a new data sheet, and five-step evaluation by engineer judgment. It is a graph which shows the relationship between evaluation of the inspection data by a new data sheet, and engineer judgment in the area A. It is a graph which shows the relationship between evaluation of the inspection data by a new data sheet, and engineer judgment in the area B. It is a graph which shows the relationship between evaluation of the inspection data by a new data sheet, and engineer judgment in the area C. The relationship between the total evaluation score of the total inspection data of the data sheet shown in Table 44 and the repair results is shown. It is a graph which shows the relationship between the score total in the conventional road slope inspection data, and a disaster history. It is a graph which shows the relationship between the score total of road slope inspection data by a new data sheet, and disaster history. It is a graph which shows the relationship between the evaluation of road slope inspection data by a new data sheet, and disaster history in the area D. It is a graph which shows the relationship between the score total in the conventional sewer equipment inspection data, and a depression history. It is a graph which shows the relationship between the score total of the sewer equipment inspection data by a new data sheet, and depression history. It is a graph which shows the relationship between the evaluation of the sewer equipment inspection data by the new data sheet, and the depression history in the area E. It is a graph which shows the relationship between evaluation of the sewer equipment inspection data by a new data sheet, and depression history in the area F.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Input part 2 ... Operation part 3 ... Analysis condition setting part 4 ... Important factor extraction part 5 ... Discrimination boundary surface analysis part 6 ... Category classification part 7 ... Representative value calculation part 8 ... Importance degree calculation part 9 ... Evaluation point calculation part DESCRIPTION OF SYMBOLS 10 ... Output part 11a ... Data 11b ... Analysis conditions 12 ... Inspection database 13 ... Inspection results data 14 ... Repair results / disaster history database 15 ... Repair results data 16 ... Important factor database 17 ... Important factor data 18 ... Boundary database 19 ... Discrimination Boundary surface data 20 ... analysis database 21 ... analysis condition data 22 ... parameter data 23 ... evaluation information database 24 ... category data of each factor 25 ... representative value data for each category 26 ... importance data 27 ... new evaluation point data 28 ... disaster Historical data

Claims (6)

It has an input unit, a calculation unit, a storage unit, and an output unit, and was obtained by using factor data relating to the cause of soundness deterioration in the inspection object and repair result data or disaster history data for the inspection object. Necessary to take countermeasures for a certain inspection object based on the discriminant boundary line or discriminant boundary surface (hereinafter referred to as discriminant boundary surface including the discriminant boundary line) that separates repair construction from non-construction or occurrence and non-occurrence of disasters A soundness evaluation system for creating a score type data sheet for calculating a degree,
The input unit is a means capable of inputting into the storage unit factor data of soundness deterioration in the inspection object and boundary data constituting the determination boundary surface,
The arithmetic unit reads the boundary data from the storage unit, and the inspection object read from the storage unit on a two-dimensional space (hereinafter referred to as a multidimensional space) in which the boundary data is configured. Analysis condition setting unit that inputs factor data of soundness deterioration in the above or the factor data in the inspection object input from the input unit as coordinates,
A representative value calculation unit for calculating a distance from the determination boundary surface to the coordinates of the factor data in the inspection object as a repair necessity level or a disaster risk level;
An evaluation point calculation unit for calculating an evaluation point calculated from the coordinates of the factor data in the inspection object and the distance to the determination boundary surface and the importance of the factor data in the inspection object;
The output unit is a means capable of outputting at least one information of factor data and importance of the inspection object, the boundary data, the repair necessity or disaster risk, or the evaluation point. A soundness evaluation system based on a score type data sheet that can be used for inspection work. The cause deterioration data of the inspection object is classified into a plurality of categories separated by a qualitative or quantitative range included in the cause data,
The analysis condition setting unit inputs the factor data as coordinates on the multidimensional space for each of the plurality of categories,
The representative value calculation unit calculates a distance from the determination boundary surface to the coordinates of the factor data in the inspection object as a repair necessity level or a disaster risk level for each of the plurality of categories, and the repair necessity level or the disaster risk level Calculate the representative value for each category of
The evaluation score calculation unit calculates the evaluation score described in the data sheet from the importance for each category of each factor data and the representative value of the repair necessity or disaster risk,
The output unit can output at least one piece of information among factor data for each category of the inspection object and its importance, the boundary data, the repair necessity or disaster risk, or the evaluation score. The soundness evaluation system based on a score type data sheet that can be used for inspection work according to claim 1, wherein the system is a means. The calculation unit includes a category classification unit that classifies the factor data of deterioration of health in the inspection object into a plurality of categories divided by a qualitative or quantitative range provided in the factor data,
The analysis condition setting unit inputs the factor data as coordinates on the multidimensional space for each of a plurality of categories classified by the category classification unit, and the representative value calculation unit is configured to perform the determination for each of the plurality of categories. Calculate the distance from the boundary surface to the coordinates of the factor data in the inspection object as the repair necessity or disaster risk,
The output unit can output at least one piece of information among factor data for each category of the inspection object and its importance, the boundary data, the repair necessity or disaster risk, or the evaluation score. The soundness evaluation system based on a score type data sheet that can be used for inspection work according to claim 1, wherein the system is a means. Factor data of soundness deterioration in the inspection object is a plurality of factor data,
The calculation unit includes an importance calculation unit that calculates the importance for the plurality of factor data,
The health evaluation system based on a score type data sheet usable for inspection work according to claim 1, wherein an evaluation score is calculated from the degree of necessity for repair or disaster risk and the importance level.   The score type data sheet usable for inspection work according to any one of claims 1 to 4, wherein the discriminant boundary surface is set by analysis using a support vector machine. Health evaluation system based on. 5. The scoring formula data usable for the inspection work according to claim 1, wherein the discriminant boundary surface is set by analysis using a radial basis function network. A health evaluation system based on sheets.