Information processing device, information processing method, and program

Abstract

This information processing device comprises: an extraction unit which extracts, from each of pieces of displacement data of a first sensor and a second sensor, first extraction displacement data and second extraction displacement data on the basis of extraction conditions; a calculation unit which uses, at each movement in a first measurement time and a second measurement time, first array data composed of the first extraction displacement data and second array data composed of the second extraction displacement data and calculates a displacement ratio for each element corresponding to the first array data and the second array data; an estimation unit which uses the displacement ratio array data composed of the displacement ratios and estimates a probability distribution; and a diagnosis unit which diagnoses the soundness of a structure state according to a statistical analysis process using the estimated probability distribution.

Description

Information processing device, information processing method, and computer-readable recording medium

[0001] The present disclosure relates to an information processing device and an information processing method for diagnosing the soundness of a structure, and further to a computer-readable recording medium on which a program for realizing these is recorded.

[0002] The useful life of structures such as bridges is generally said to be around 50 years. Many of these structures were constructed en masse during the period of high economic growth (1960s), and many have exceeded their useful life. As a result, the soundness of many of these structures needs to be evaluated. However, the number of workers who can assess the soundness of structures is decreasing year by year. Therefore, there is a demand for a method to assess the soundness of structures without relying on human labor.

[0003] As a method for diagnosing the soundness of a structure, a method has been disclosed in which the deflection of the structure due to live load is measured, and if the measured deflection (displacement) exceeds an allowable value, the structure is diagnosed as being in an abnormal state.

[0004] As a related technique, Patent Document 1 discloses a structural deterioration diagnosis system that detects structural deterioration at an early stage. According to the structural deterioration diagnosis system of Patent Document 1, first, time-series data of live load displacement is generated for each of a plurality of sensors installed in the structure, and the maximum displacement amount for each same time range is calculated from the generated time-series data of live load displacement. Next, the structural deterioration diagnosis system finds a correlation value of the maximum displacement amount calculated for each sensor, and diagnoses the deterioration of the structure based on the correlation value.

[0005] Japanese Patent Application Laid-Open No. 2022-102230

[0006] However, in the technology of Patent Document 1 and the like, the amount of deflection (displacement data) is used to diagnose the soundness of the structure, so the diagnosis result depends on the weight (live load) of the moving body that moves the structure. Therefore, if the weight of the moving body is light, it may not be possible to obtain accurate diagnosis results.

[0007] An example of an object of the present disclosure is to obtain accurate diagnostic results of the health of a structure without depending on the weight of a moving body.

[0008] In order to achieve the above object, an information processing device according to one aspect of the present disclosure is characterized by having: an extraction unit that acquires displacement data measured using a first sensor and a second sensor installed on a structure each time a moving body moves on the structure, and extracts first extracted displacement data and second extracted displacement data to be used for diagnosing the health of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; a calculation unit that calculates, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data, using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; an estimation unit that estimates a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement; and a diagnosis unit that diagnoses the health of the structure using the estimated probability distribution.

[0009] Furthermore, in order to achieve the above object, an information processing method according to one aspect of the present disclosure is characterized in that the information processing device acquires displacement data measured using a first sensor and a second sensor installed on the structure each time a moving body moves on the structure, and extracts first extracted displacement data and second extracted displacement data to be used for diagnosing the health of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor based on preset extraction conditions, respectively; calculates, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; estimates a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement; and diagnoses the health of the structure using the estimated probability distribution.

[0010] Furthermore, in order to achieve the above object, a computer-readable recording medium having a program recorded thereon according to one aspect of the present disclosure is characterized in that it causes a computer to: acquire displacement data measured using a first sensor and a second sensor installed on the structure each time a moving body moves on the structure, and extract first extracted displacement data and second extracted displacement data to be used for diagnosing the health of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor based on preset extraction conditions; calculate, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; estimate a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement; and diagnose the health of the structure using the estimated probability distribution.

[0011] As described above, according to the present disclosure, it is possible to obtain highly accurate diagnosis results of the soundness of a structure without relying on the weight of a moving body.

[0012] FIG. 1 is a diagram illustrating an example of an information processing device. FIG. 2 is a diagram illustrating an example of a system having an information processing device. FIG. 3 is a diagram illustrating an example of a structure. FIG. 4 is a diagram illustrating an example of displacement data. FIG. 5 is a diagram illustrating an example of extracted displacement data in the form of a graph. FIG. 6 is a diagram illustrating an example of extracted displacement data. FIG. 7 is a diagram illustrating an example of extracted displacement data in the form of a graph. FIG. 8 is a diagram illustrating an example of a probability distribution. FIG. 9 is a diagram illustrating an example of the operation of the information processing device. FIG. 10 is a diagram illustrating an example of a computer that realizes the information processing device in the embodiment and the modified example.

[0013] Hereinafter, an embodiment will be described with reference to the drawings. In the drawings described below, elements having the same or corresponding functions are denoted by the same reference numerals, and repeated description thereof may be omitted.

[0014] [Device Configuration] The configuration of an information processing device (soundness diagnosis device) that diagnoses the soundness of a structure in an embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram for explaining an example of an information processing device.

[0015] The structure may be, for example, a hardened substance (concrete, mortar, etc.) solidified using at least sand, water, and cement, or metal, or a structure constructed using these. The structure may also be a whole building or a part thereof. The structure may also be a whole machine or a part thereof.

[0016] 1 has a function for diagnosing the soundness of a structure. The information processing device 10 also has an extraction unit 11, a calculation unit 12, an estimation unit 13, and a diagnosis unit 14.

[0017] The extraction unit 11 acquires displacement data measured using a first sensor and a second sensor installed on the structure each time the moving body moves on the structure, and extracts first extracted displacement data and second extracted displacement data to be used for diagnosing the health of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions.

[0018] For each movement, the calculation unit 12 uses first array data composed of first extracted displacement data and second array data composed of extracted second extracted displacement data corresponding to the second sensor to calculate a displacement ratio for each corresponding element of the first array data and the second array data.

[0019] The estimation unit 13 estimates a probability distribution using displacement ratio sequence data configured by the displacement ratio calculated for each movement.

[0020] The diagnosing unit 14 diagnoses the soundness of the state of the structure using the estimated probability distribution. Specifically, the diagnosing unit 14 may diagnose whether there is a difference in the state of the structure between two measurement times by performing a test process to determine whether there is a difference between two probability distributions obtained at different measurement times, or may diagnose the presence or absence of an abnormality in the structure, such as deterioration over time or damage, by estimating structural parameters of the structure through a statistical analysis process such as reproducing a probability distribution obtained at a certain measurement time through a simulation. In either case, the diagnosing unit 14 diagnoses the soundness of the state of the structure through a statistical analysis process such as a test process using the probability distribution estimated using the displacement ratio data.

[0021] In this way, in the embodiment, the displacement ratio of displacement data (deflection amount) measured at two points on the structure is used, so the health of the structure can be diagnosed without depending on the weight of the moving body. In other words, since the deflection of the structure is proportional to the weight of the moving body (live load), the weight of the moving body can be ignored by using the displacement ratio at two points. Therefore, the health of the structure can be diagnosed without depending on the weight of the moving body.

[0022] [System Configuration] The configuration of the information processing device 10 in this embodiment will be described in more detail with reference to Fig. 2. Fig. 2 is a diagram illustrating an example of a system including an information processing device.

[0023] 2 , a system including the information processing device 10 according to the embodiment includes the information processing device 10, a plurality of sensors 21 (21a to 21h), a storage device 30, and an output device 40. The information processing device 10 also includes an extraction unit 11, a calculation unit 12, an estimation unit 13, a diagnosis unit 14, a conversion unit 15, and an output information generation unit 16.

[0024] The information processing device 10 is, for example, an information processing device such as a CPU (Central Processing Unit), a programmable device such as an FPGA (Field-Programmable Gate Array), a GPU (Graphics Processing Unit), or a circuit equipped with one or more of these, a server computer, a personal computer, or a mobile terminal.

[0025] The sensors 21 (21a to 21h) are, for example, contact-type displacement meters attached to the structure 20. The sensors 21 transmit measurement data (displacement data) to the information processing device 10 via a network.

[0026] The structure 20 is, for example, a bridge deck. Fig. 3 is a diagram for explaining an example of a structure. A vehicle 22 travels back and forth on the deck (structure 20) shown in Fig. 3 a plurality of times. Note that in the example of Fig. 3, the deck is the structure 20, but the structure 20 is not limited to a deck.

[0027] Specifically, as shown in Fig. 3, a plurality of sensors 21 (21a to 21h) are attached to the structure 20, and measure the displacement of the structure 20 at the position where each sensor 21 is attached. Next, each of the sensors 21a to 21h transmits the measured displacement (displacement data) to the conversion unit 15 of the information processing device 10. Note that communication between the sensors 21 and the conversion unit 15 is performed using wired communication, wireless communication, or the like via a network.

[0028] However, the sensor 21 is not limited to the contact-type displacement meter described above, and may be, for example, an acceleration sensor, etc. When an acceleration sensor is used, acceleration data is converted into displacement data for use.

[0029] The network is a general communication network constructed using communication lines such as the Internet, a LAN (Local Area Network), a dedicated line, a telephone line, an in-house network, a mobile communication network, Bluetooth (registered trademark), and Wi-Fi (Wireless Fidelity).

[0030] The storage device 30 is a database, a server computer, a circuit with memory, etc. The storage device 30 stores, for example, various types of information. In the example of Fig. 2, the storage device 30 is provided outside the information processing device 10, but it may also be provided inside the information processing device 10.

[0031] The output device 40 acquires the output information converted into an outputtable format by the output information generation unit 16, and outputs generated images, sounds, etc. based on the output information. The output device 40 is, for example, an image display device using a liquid crystal, an organic EL (Electro Luminescence), or a CRT (Cathode Ray Tube). Furthermore, the image display device may also include an audio output device such as a speaker. The output device 40 may also be a printing device such as a printer. The output information will be described later.

[0032] The information processing device will now be described. The conversion unit 15 collects measurement data (displacement data) transmitted via a network using wired or wireless communication from each of a plurality of sensors 21 (21a to 21h) attached to a deck (structure 20). The conversion unit 15 then stores the measurement data in a storage device 30.

[0033] Specifically, a moving body (vehicle 22) is moved multiple times on the deck (structure 20), and for each movement, displacement data measured by each sensor 21 is collected. Note that the weight and speed of the vehicle 22 may be changed for each movement or for each of multiple movements.

[0034] The displacement data will be described with reference to Fig. 4 and Fig. 5. Fig. 4 is a diagram for explaining an example of the displacement data. Fig. 5 is a diagram for explaining an example of the extracted displacement data in the form of a graph.

[0035] 4 shows displacement data measured at measurement time T1 (first measurement time) and displacement data (deflection amount) measured at measurement time T2 (second measurement time). Measurement time T1 is, for example, the time when the structure 20 is constructed or a time before measurement time T2. Measurement time T2 is a time after measurement time T1, for example, one year after measurement time T1 or a time after a predetermined period of time.

[0036] The table of measurement times T1 and T2 shown in Fig. 4 shows displacement data measured by each of sensors 21a, 21b, 21c, 21d, 21e, 21f, 21g, and 21h (S1, S2, S3, S4, S5, S6, S7, and S8) for each movement (1, 2, 3, ...). The displacement data shown in Fig. 4 is information for identifying the displacement data.

[0037] The displacement data in Fig. 4 will be described. For example, in the case of "dispT1_S1_1" of the "displacement data" shown in Fig. 4, "dispT1_S1_1" is associated with the displacement data measured by the sensor 21a (S1) during the first movement "1" at the measurement time T1.

[0038] 5A shows displacement data measured by the sensor 21a (S1) associated with "dispT1_S1_1." In the example of FIG. 5, the vertical axis shows displacement [mm] (millimeters), and the horizontal axis shows time [seconds]. Furthermore, FIG. 5B shows displacement data measured by the sensor 21g (S7).

[0039] The extraction unit 11 first acquires the first and second displacement data measured at measurement time T1 or T2 from the storage device 30 according to a preset timing, and stores the first and second extracted displacement data, which are the processing results, in the storage device 30. Next, the calculation unit 12 acquires the first and second extracted displacement data from the storage device 30, and stores the processing results, the displacement ratio array data, in the storage device 30. Next, the estimation unit 13 acquires the displacement ratio array data from the storage device 30, and stores the processing results, the probability distribution information, in the storage device 30. In other words, the extraction unit 11, the calculation unit 12, and the estimation unit 13 calculate the probability distribution information from the displacement data at measurement time T1 or T2 and store it in the storage device 30. The following description will focus on the processing performed on the displacement data at measurement time T1. Similar processing is also performed on the displacement data at measurement time T2.

[0040] The extraction unit 11 first acquires, from the storage device 30, displacement data (first displacement data and second displacement data) measured using sensors 21 at two locations (first sensor and second sensor) at measurement time T1 used for diagnosing the soundness. Next, the extraction unit 11 extracts extracted displacement data (first extracted displacement data and second extracted displacement data) to be used for diagnosing the soundness for each of the acquired displacement data based on preset extraction conditions (extraction process). Next, the extraction unit 11 stores the extracted displacement data in the storage device 30. The extraction conditions are, for example, conditions for extracting data surrounding a minimum value of the displacement data.

[0041] The extraction process will be described. In the extraction process, the extraction unit 11 first detects a minimum value for each of the displacement data (first displacement data and second displacement data). Next, the extraction unit 11 extracts data within a predetermined extraction range that includes the detected minimum value from each of the displacement data (first displacement data and second displacement data), and sets the extracted displacement data (first extracted displacement data and second extracted displacement data).

[0042] The extraction range may be, for example, the time t0 (seconds) of the minimum value ±0.05 (seconds). However, the extraction range is not limited to the time t0 ±0.05 (seconds) of the minimum value. The extraction range is determined, for example, by experiments, simulations, etc.

[0043] Another extraction condition may be, for example, to extract displacement data in a range in which the absolute value of the displacement data is greater than a preset extraction threshold value.

[0044] The extraction of displacement data will be described with reference to Fig. 6 and Fig. 7. Fig. 6 is a diagram for explaining an example of extracted displacement data. Fig. 7 is a diagram for explaining an example of extracted displacement data in the form of a graph.

[0045] The broken line ranges 71a and 71b in Figures 6A and 6B represent extraction ranges. The example in Figure 7 shows displacement data extracted at measurement time T1.

[0046] The table of measurement time T1 shown in FIG. 7 shows the extracted displacement data for each of the sensors 21a and 21g (S1 and S7) for each movement (1, 2, 3, ...). For example, "dispT1_S1_11," "dispT1_S1_12," "dispT1_S1_13," "dispT1_S1_14," and "dispT1_S1_15" shown in FIG. 7 represent the extracted displacement data for the sensor 21a (S1) for movement "1." Also, "dispT1_S7_11," "dispT1_S7_12," "dispT1_S7_13," "dispT1_S7_14," and "dispT1_S7_15" shown in FIG. 7 represent the extracted displacement data for the sensor 21g (S7) for movement "1."

[0047] The calculation unit 12 first acquires extracted displacement data (first extracted displacement data and second extracted displacement data) used for diagnosing the soundness from the storage device 30. Next, for each shift in measurement time T1, the calculation unit 12 calculates a displacement ratio for each corresponding element of the first array data and the second array data using first array data configured from the extracted displacement data (first extracted displacement data) corresponding to the first sensor and second array data configured from the extracted displacement data (second extracted displacement data) corresponding to the second sensor (displacement ratio calculation process). Next, the calculation unit 12 stores in the storage device 30 displacement ratio array data configured from the displacement ratios calculated for each shift in measurement time T1.

[0048] The displacement ratio calculation process will be described below assuming that the first sensor is the sensor 21a (S1) in Figures 2 and 3 and the second sensor is the sensor 21g (S7) in Figures 2 and 3.

[0049] For example, if the first extracted displacement data "dispT1_S1_11", "dispT1_S1_12", "dispT1_S1_13", "dispT1_S1_14", and "dispT1_S1_15" corresponding to the sensor 21a (S1) of movement "1" are "4.072", "4.088", "4.100", "4.086", and "4.088", the first array data δT1_S1_1 corresponding to the sensor 21a (S1) of movement "1" is expressed as shown in Equation 1.

[0050] (Equation 1) δT1_S1_1=[4.072, 4.088, 4.100, 4.086, 4.088]

[0051] Furthermore, if the extracted displacement data "dispT1_S7_11", "dispT1_S7_12", "dispT1_S7_13", "dispT1_S7_14", and "dispT1_S7_15" corresponding to sensor 21g (S7) of movement "1" are "4.436", "4.436", "4.441", "4.441", and "4.434", the second array data δT1_S7_1 corresponding to sensor 21g (S7) of movement "1" is expressed as shown in Equation 2.

[0052] (Equation 2) δT2_S1_1=[4.436, 4.436, 4.441, 4.441, 4.434]

[0053] Next, the calculation unit 12 calculates, for each movement, a displacement ratio between corresponding elements of the first array data and the second array data, using the first array data and the second array data. For example, the calculation unit 12 calculates the displacement ratio using Equation 3.

[0054] (Math 3) r ｉ ≡ ((δ ２，ｉ / δ １，ｉ )-1) x 100 r ｉ : Displacement ratio sequence data for movement i i : Movement identifier δ １，ｉ : Array data of the first sensor δ ２，ｉ : array data of the second sensor

[0055] For example, in the case of movement "1" at measurement time T1, in the case of array data δT1_S1_1 corresponding to sensor 21a (S1) and array data δT1_S7_1 corresponding to sensor 21g (S7), the displacement ratio array data will be the result (array data) shown in Equation 4.

[0056] (Math. 4) r １ = [8.939, 8.513, 8.317, 8.688, 8.464] r １ : Displacement ratio [%] (percent) at movement "1"

[0057] The displacement ratio may be calculated using the above-mentioned Equation 3, or may be calculated using the decimal value before multiplying by 100 in Equation 3, or may be calculated by using the ratio (δ ２，ｉ / δ １，ｉ ) may also be used.

[0058] The estimation unit 13 calculates a first probability distribution (distribution of probability density with respect to displacement ratio) corresponding to the measurement time T1 using the displacement ratio sequence data calculated for each movement of the measurement time T1.

[0059] Specifically, the estimation unit 13 first acquires displacement ratio array data calculated for each movement of the measurement time T1. Next, the estimation unit 13 inputs each displacement ratio array data into a probability distribution estimation model and estimates a first probability distribution corresponding to the measurement time T1 (probability distribution estimation process). Next, the estimation unit 13 stores probability distribution information representing the estimated first probability distribution corresponding to the measurement time T1 in the storage device 30.

[0060] The probability distribution estimation process obtains a frequency distribution of the displacement ratio and estimates the probability distribution. The probability distribution estimation model estimates the probability distribution using, for example, kernel density estimation, Gaussian fitting, or the like.

[0061] The above has described the processing details of the extraction unit 11, calculation unit 12, and estimation unit 13 for the displacement data at measurement time T1. Similarly, the extraction unit 11, calculation unit 12, and estimation unit 13 calculate probability distribution information representing a probability distribution (second probability distribution) corresponding to measurement time T2 from the displacement data at measurement time T2 according to a preset timing, and store the calculated information in the storage device 30.

[0062] The estimation of the probability distribution estimation process will be described using FIG. 8 . FIG. 8 is a diagram for explaining an example of a probability distribution. In the example of FIG. 8 , the vertical axis represents probability density, and the horizontal axis represents displacement ratio [%]. A histogram 81a in FIG. 8 shows a first frequency distribution representing the state of the structure 20 at measurement time T1. A curve 82a in FIG. 8 shows the first probability distribution representing the state of the structure 20 at measurement time T1. A histogram 81b in FIG. 8 shows a second frequency distribution representing the state of the structure 20 at measurement time T2. A curve 82b in FIG. 8 shows the second probability distribution representing the state of the structure 20 at measurement time T2.

[0063] The diagnoser 14 diagnoses the soundness of the state of the structure 20 at the measurement time T2 relative to the state of the structure 20 at the measurement time T1 using the first probability distribution at the measurement time T1 and the second probability distribution at the measurement time T2 (soundness diagnosis process). Next, the diagnoser 14 stores the soundness diagnosis result in the storage device 30.

[0064] In the health diagnosis process, the diagnosis unit 14 first performs statistical analysis processing on a first probability distribution at measurement time T1 and a second probability distribution at measurement time T2. The statistical analysis processing quantitatively indicates whether there is a difference in the state of the structure 20 at measurement times T1 and T2 by checking whether there is a statistical difference between the first probability distribution and the second probability distribution. A testing process may be used as one method for checking whether there is a statistical difference. Possible statistical quantities that can be subject to testing processing include the mean value, variance value, and probability distribution. An example of a testing process for the mean value is the t-test. An example of a testing process for the variance value is the F-test. An example of a testing process for the probability distribution is the Kolmogorov-Smirnov test.

[0065] The reason for performing the testing process is that it becomes possible to confirm whether the difference between the first probability distribution at measurement time T1 and the second probability distribution at measurement time T2 is statistically significant. In other words, if there is a statistically significant difference, it is recognized that the state of the structure 20 has changed between measurement time T1 and measurement time T2, and therefore, by comparing measurement time T2 with measurement time T1, it can be determined that an abnormality such as aging deterioration or damage is progressing.

[0066] It is desirable to use the Kolmogorov-Smirnov test as the test process. Next, the diagnosis unit 14 uses the p-value resulting from the test process to determine whether the difference between the states of the structure 20 at the measurement times T1 and T2 is statistically significant.

[0067] That is, if the resultant p-value is at or above the significance level of 1% (p-value ≥ 1%), it is determined that the state of the structure 20 at the measurement time T2 is healthy compared to the state of the structure 20 at the measurement time T1. However, the significance level is not limited to 1%.

[0068] In addition to the Kolmogorov-Smirnov test, other testing processes such as t-tests and F-tests may be used to diagnose soundness. For t-tests and F-tests, as with the Kolmogorov-Smirnov test, a significance level is set before the test (often 1% or 5%), and soundness is determined by comparing the p-value obtained in the test with the significance level. The t-test is a test to confirm statistical significance by determining whether the means of two distributions are different, and the F-test is a test to confirm whether the variances of two distributions are different. When the p-value is less than the significance level, the difference is deemed significant.

[0069] Therefore, for example, if the significance level is set to 1 [%] and a t-test is performed on the first probability distribution and the second probability distribution, and the result is a p-value of 0.0003, the difference in the means of the first and second probability distributions is recognized as statistically significant, and it can be detected that the state of the structure has changed between measurement times T1 and T2, and this can be used for health diagnosis.

[0070] The output information generation unit 16 generates output information used to output to the output device 40 the structure of the structure 20 (see FIG. 3 ), or the displacement data measured by each of the sensors 21 (see FIG. 4 ) and a graph of the displacement data (see FIG. 5 ), or the displacement data extracted by each of the sensors 21 (extracted displacement data) (see FIG. 7 ) and a graph of the extracted displacement data (see FIG. 6 ), or the probability distribution (see FIG. 8 ), or the diagnosis result, or two or more of these pieces of information. Then, the output information generation unit 16 outputs the generated output information to the output device 40.

[0071] [Device Operation] Next, the operation of the information processing device in the embodiment will be described with reference to FIG. 9. FIG. 9 is a diagram for explaining an example of the operation of the information processing device. In the following description, the diagram will be referenced as appropriate. Furthermore, in the embodiment, an information processing method is implemented by operating the information processing device. Therefore, the description of the information processing method in the embodiment will be replaced with the description of the operation of the information processing device below.

[0072] 9 , first, the converter 15 collects measurement data (displacement data) (step A1). Specifically, in step A2, the converter 15 collects measurement data (displacement data) transmitted from each of the multiple sensors 21 (21a to 21h) attached to the structure 20 via a network using wired communication, wireless communication, or the like, and stores the measurement data in the storage device 30. The converter 15 adds information indicating the collection time to the measurement data so that the time when the measurement data was collected can be identified.

[0073] Next, the extraction unit 11 extracts extracted displacement data to be used for diagnosing the soundness of the structure from each of the displacement data (step A2).

[0074] Specifically, in step A2, the extractor 11 first acquires from the storage device 30 displacement data (first displacement data and second displacement data) measured using the sensors 21 (first sensor and second sensor) at two locations at measurement time T1. Next, in step A2, the extractor 11 extracts extracted displacement data (first extracted displacement data and second extracted displacement data) to be used for diagnosing the soundness of the system, based on preset extraction conditions, for each of the acquired displacement data of the first sensor and the displacement data of the second sensor (extraction process). Next, in step A2, the extractor 11 stores the extracted displacement data in the storage device 30.

[0075] Next, for each movement of the measurement time T1, the calculation unit 12 calculates a displacement ratio for each corresponding element of the first array data and the second array data using first array data composed of the first extracted displacement data and second array data composed of the extracted second extracted displacement data corresponding to the second sensor (step A3).

[0076] Specifically, in step A3, the calculation unit 12 first acquires the extracted displacement data used for diagnosing the soundness from the storage device 30. Next, in step A3, the calculation unit 12 calculates, for each shift in measurement time T1, a displacement ratio for each corresponding element of the first array data and the second array data, using first array data configured from the extracted displacement data corresponding to the first sensor (first extracted displacement data) and second array data configured from the extracted displacement data corresponding to the second sensor (second extracted displacement data) (displacement ratio calculation process). Next, in step A3, the calculation unit 12 stores, in the storage device 30, displacement ratio array data configured from the displacement ratios calculated for each shift in measurement time T1.

[0077] Next, the estimation unit 13 calculates the probability distribution of the measurement time T1 using the displacement ratio array data configured by the displacement ratios calculated for each movement of the measurement time T1 (step A4).

[0078] Specifically, in step A4, the estimation unit 13 first acquires displacement ratio array data calculated for each movement of the measurement time T1. Next, in step A4, the estimation unit 13 inputs each displacement ratio array data into a probability distribution estimation model and estimates a first probability distribution corresponding to the measurement time T1 (probability distribution estimation process). Next, in step A4, the estimation unit 13 stores probability distribution information representing the probability distribution corresponding to the estimated measurement time T1 (distribution of probability density with respect to displacement ratio) in the storage device 30.

[0079] In the same manner as described above, in steps A2, A3, and A4, probability distribution information representing a second probability distribution corresponding to the displacement data at measurement time T2 is calculated and stored in the storage device 30. Next, the diagnosing unit 14 diagnoses the soundness of the state of the structure 20 at measurement time T2 relative to the state of the structure 20 at measurement time T1 through statistical analysis processing using the probability distributions at measurement times T1 and T2 (step A5).

[0080] Specifically, in step A5, the diagnosis unit 14 first performs a Kolmogorov-Smirnov test (statistical analysis process) on the first probability distribution at measurement time T1 and the second probability distribution at measurement time T2. Next, in step A5, the diagnosis unit 14 uses the results of the statistical analysis process to determine whether the states of the structure 20 at measurement times T1 and T2 are statistically significantly different. Next, in step A5, the diagnosis unit 14 stores the soundness diagnosis results in the storage device 30.

[0081] Next, the output information generation unit 16 generates output information and outputs the output information to the output device (step A6). Specifically, in step A6, the output information generation unit 16 generates output information to be used for outputting to the output device 40 the structure of the structure 20 (see FIG. 3), or the displacement data measured by each of the sensors 21 (see FIG. 4) and a graph of the displacement data (see FIG. 5), or the displacement data extracted by each of the sensors 21 (see FIG. 7) and a graph of the extracted displacement data (see FIG. 6), or a probability distribution (see FIG. 8), or a diagnosis result, or two or more of these pieces of information. Next, in step A6, the output information generation unit 16 outputs the generated output information to the output device 40.

[0082] [Effects of the Embodiments] As described above, according to the embodiments, the displacement ratio of displacements measured at two points on a structure is used, so that the health of the structure can be diagnosed without depending on the weight of the moving body. In other words, since the deflection of a structure is proportional to the weight of the moving body (live load), by using the displacement ratio at two points, the weight of the moving body can be ignored. Therefore, the health of the structure can be diagnosed without depending on the weight of the moving body. In reality, it is difficult to measure the weight of a moving body passing through a structure that is in general use, but in the embodiments, the health of the structure can be diagnosed even if the weight of the moving body is unknown.

[0083] In addition, in this embodiment, the speed of the moving object can be ignored. This is because the theoretical equation for the deflection of a simple beam supported at both ends, such as a bridge, does not depend on the speed of the moving object. Furthermore, realistic speeds of moving objects, when the moving object is a vehicle, are often 30 to 60 km / h (kilometers per hour) on ordinary roads and 80 to 100 km / h on expressways. This does not vary significantly compared to the weight of the moving object. Therefore, the impact of fluctuations in moving object speed on the probability distribution of the displacement ratio is sufficiently smaller than the impact on the structural integrity, so ignoring the speed does not have a significant impact. In fact, the probability distribution of the displacement ratio shown in Figure 8 includes measurements using two speed patterns for each of 82a and 82b.

[0084] (Modifications) In the above-described embodiment, the soundness of a structure is diagnosed by statistically checking the difference between the first and second probability distributions at the first measurement time and the second measurement time. However, a modification is also possible in which the soundness of a structure is diagnosed using only one of the first and second probability distributions, rather than using both. In other words, the presence or absence of an abnormality in the structure, such as aging deterioration or damage, may be diagnosed by estimating the structural parameters of the structure through statistical analysis processing that reproduces, through simulation, a probability distribution obtained from displacement data at a certain measurement time. Such a modification will now be described.

[0085] A common example of the above-mentioned statistical analysis process is the Markov chain Monte Carlo method. The Markov chain Monte Carlo method (MCMC) estimates the posterior probability distribution of θ, P(θ|X) = P(X|θ)P(θ) / P(X), expressed as the probability distribution P(X) of the observed data X, the conditional probability distribution P(X|θ) of the observed data X, and the prior probability distribution P(θ) of the unobserved parameter θ, by repeated random selection and simulation. P(X) is obtained from the observed data. P(θ) is set based on general knowledge about the observed object, and a uniform distribution is often used. On the other hand, P(X|θ) is calculated by simulating the observed object. This is because P(X|θ) is the probability distribution of the observed data X assuming a certain unobserved parameter θ, and it is not realistic to obtain it from the observed data.

[0086] Applying the above to a modified example, the observation target is a structure, the observation data X is displacement data, P(X) is a probability distribution calculated from the displacement ratio, the unobserved parameters θ are the structural parameters of the structure (such as the elastic coefficient, spring constant, and density of the components), and P(X|θ) is a probability distribution of the structural displacement ratio calculated by structural simulation. In other words, the posterior probability distribution of the structural parameters of the structure can be obtained by a statistical analysis process called MCMC, and the structural soundness can be diagnosed using this posterior probability distribution. For example, if the mean value of the posterior probability distribution of the structural parameter is smaller than the nominal value of the structural parameter, an abnormality can be diagnosed, or the posterior probability distributions of the structural parameters of components A and B can be compared and the one that is significantly smaller can be diagnosed as an abnormality.

[0087] When performing a structural simulation of the structure 20, a situation in which the moving body 22 moves on the structure 20 is simulated, and the displacements corresponding to the positions of the first sensor and the second sensor are calculated. In this calculation, a structure model that simulates the structural form of the structure 20 is used, and a load that simulates the moving body 22 is applied to the structure model. Furthermore, in order to make the structure model closer to the state of the structure 20, settings that represent aging deterioration, damage, etc. may be added.

[0088] The structural simulation may be performed, for example, inside the information processing device 10 or in another information processing device provided outside the information processing device 10 .

[0089] Next, the extraction unit 11, calculation unit 12, and estimation unit 13 of the modified example perform the same processing as in the above-described embodiment. The diagnosis unit 14 of the modified example diagnoses the soundness of the state of the structure by a statistical analysis processing called MCMC. The contents of the diagnosis have already been described.

[0090] Next, the output information generation unit 16 in the modified example generates output information to be used for outputting to the output device 40 the structure of the structure 20 (see FIG. 3 ), or the displacement data measured by each of the sensors 21 (see FIG. 4 ) and a graph of the displacement data (see FIG. 5 ), or the displacement data extracted by each of the sensors 21 (extracted displacement data) (see FIG. 7 ) and a graph of the extracted displacement data (see FIG. 6 ), or the probability distribution (see FIG. 8 ), or the diagnosis result, or two or more of these pieces of information. Then, the output information generation unit 16 outputs the generated output information to the output device 40.

[0091] Furthermore, the output information generation unit 16 of the modified example generates output information used to output to the output device 40 a structural model, or displacement data generated by the simulator and a graph of the displacement data, or extracted displacement data generated by the simulator and a graph of the extracted displacement data, or a probability distribution generated by the simulator, or a diagnostic result, or two or more of these pieces of information.

[0092] By using the modified example, it is possible to estimate the degree of deterioration of each component of a structure by selecting the method of structural simulation and the structural parameters to be estimated, which is an advantage that cannot be obtained in the above-described embodiment.

[0093] [Program] The program in the embodiment and the modified example may be a program that causes a computer to execute steps A1 to A6 shown in Fig. 9. By installing and executing this program on a computer, the information processing device and information processing method in the embodiment and the modified example can be realized. In this case, the processor of the computer functions as the conversion unit 15, extraction unit 11, calculation unit 12, estimation unit 13, diagnosis unit 14, and output information generation unit 16 and performs processing.

[0094] The programs in the embodiments and modifications may be executed by a computer system constructed by a plurality of computers, in which case, for example, each computer may function as one of the conversion unit 15, extraction unit 11, calculation unit 12, estimation unit 13, diagnosis unit 14, and output information generation unit 16.

[0095] [Physical Configuration] A computer that realizes an information processing device by executing a program in the embodiment and the modified example will now be described with reference to Fig. 10. Fig. 10 is a diagram for explaining an example of a computer that realizes an information processing device in the embodiment and the modified example.

[0096] 10 , the computer 110 includes a CPU 111, a main memory 112, a storage device 113, an input interface 114, a display controller 115, a data reader / writer 116, and a communication interface 117. These components are connected to each other via a bus 121 so as to be able to communicate data with each other. Note that the computer 110 may include a GPU or an FPGA in addition to or instead of the CPU 111.

[0097] The CPU 111 loads a program in the embodiment, which is composed of a group of codes and stored in the storage device 113, into the main memory 112 and executes each code in a predetermined order to perform various calculations. The main memory 112 is typically a volatile storage device such as a DRAM (Dynamic Random Access Memory).

[0098] The program in the embodiment is provided in a state stored in a computer-readable recording medium 120. The program in the embodiment may be distributed over the Internet connected via the communication interface 117.

[0099] Specific examples of the storage device 113 include a hard disk drive and a semiconductor storage device such as a flash memory. The input interface 114 mediates data transmission between the CPU 111 and input devices 118 such as a keyboard and a mouse. The display controller 115 is connected to a display device 119 and controls the display on the display device 119.

[0100] The data reader / writer 116 mediates data transmission between the CPU 111 and the recording medium 120, reads programs from the recording medium 120, and writes processing results from the computer 110 to the recording medium 120. The communication interface 117 mediates data transmission between the CPU 111 and other computers.

[0101] Specific examples of the recording medium 120 include general-purpose semiconductor storage devices such as CF (Compact Flash (registered trademark)) and SD (Secure Digital), magnetic recording media such as flexible disks, or optical recording media such as CD-ROMs (Compact Disk Read Only Memory).

[0102] The information processing device 10 in the embodiment may be realized not by a computer on which a program is installed, but by hardware corresponding to each unit, such as an electronic circuit. Furthermore, the information processing device 10 may be partially realized by a program and the remaining unit by hardware. In the embodiment, the computer is not limited to the computer shown in FIG. 10.

[0103] [Supplementary Note] The following supplementary note is further disclosed regarding the above-described embodiment. Part or all of the above-described embodiment can be expressed by (Supplementary Note 1) to (Supplementary Note 12) described below, but is not limited to the following description.

[0104] (Supplementary Note 1) An information processing device having: an extraction unit that acquires displacement data measured using a first sensor and a second sensor installed on a structure each time a moving body moves on the structure, and extracts first extracted displacement data and second extracted displacement data to be used for diagnosing the soundness of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; a calculation unit that calculates, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data, using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; an estimation unit that estimates a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement; and a diagnosis unit that diagnoses the soundness of the structure using the estimated probability distribution.

[0105] (Supplementary Note 2) The information processing device according to Supplementary Note 1, wherein the extraction unit detects a minimum value for each of the first displacement data and the second displacement data, and extracts the first extracted displacement data and the second extracted displacement data from the first displacement data and the second displacement data based on data in a predetermined range that includes the detected minimum value.

[0106] (Supplementary Note 3) The information processing device according to Supplementary Note 2, wherein the estimation unit obtains a frequency distribution of the displacement ratio, and estimates the probability distribution based on the frequency distribution.

[0107] (Supplementary Note 4) The information processing device according to Supplementary Note 3, wherein the diagnosing unit executes statistical analysis processing on a first probability distribution for a first measurement time point and a second probability distribution for a second measurement time point.

[0108] (Supplementary Note 5) An information processing method that executes processes in which an information processing device acquires displacement data measured using a first sensor and a second sensor installed on the structure, each time a mobile body moves on the structure, extracts first extracted displacement data and second extracted displacement data to be used for diagnosing the soundness of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions, calculates, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data, using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data, estimates a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement, and diagnoses the soundness of the structure using the estimated probability distribution.

[0109] (Appendix 6) The information processing method according to Appendix 5, wherein in the extraction, a minimum value is detected for each of the first displacement data and the second displacement data, and the first extracted displacement data and the second extracted displacement data are extracted from the first displacement data and the second displacement data based on data in a predetermined range that includes the detected minimum value.

[0110] (Supplementary Note 7) The information processing method according to claim 6, wherein the estimation comprises determining a frequency distribution of the displacement ratio, and estimating the probability distribution based on the frequency distribution.

[0111] (Supplementary Note 8) The information processing method according to Supplementary Note 7, wherein in the diagnosis, a statistical analysis process is performed on a first probability distribution for the first measurement time point and a second probability distribution for the second measurement time point.

[0112] (Supplementary Note 9) A computer-readable recording medium having recorded thereon a program including instructions to: acquire displacement data measured using a first sensor and a second sensor installed on a structure, each time a moving body moves on the structure; extract first extracted displacement data and second extracted displacement data to be used for diagnosing the health of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; calculate, for each movement, a displacement ratio for each element of the array data using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; estimate a probability distribution using displacement ratio array data constituted by the displacement ratios calculated for each movement; and diagnose the health of the structure using the estimated probability distribution.

[0113] (Supplementary Note 10) The computer-readable recording medium according to Supplementary Note 9, wherein in the extraction, a minimum value is detected for each of the first displacement data and the second displacement data, and the first extracted displacement data and the second extracted displacement data are extracted from the first displacement data and the second displacement data based on data in a predetermined range including the detected minimum value.

[0114] (Supplementary Note 11) The computer-readable recording medium according to Supplementary Note 10, wherein the estimation comprises determining a frequency distribution of the displacement ratio, and estimating the probability distribution based on the frequency distribution.

[0115] (Supplementary Note 12) The computer-readable recording medium according to Supplementary Note 11, wherein in the diagnosis, a statistical analysis process is performed on a first probability distribution for a first measurement time point and a second probability distribution for a second measurement time point.

[0116] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0117] This application claims priority based on Japanese Patent Application No. 2023-003342, filed on January 12, 2023, the disclosure of which is incorporated herein in its entirety.

[0118] According to the above description, the soundness of a structure can be diagnosed without depending on the weight of a moving object, and is useful in fields where the soundness of a structure needs to be diagnosed.

[0119] 10 Information processing device 11 Extraction unit 12 Calculation unit 13 Estimation unit 14 Diagnosis unit 15 Conversion unit 16 Output information generation unit 20 Structure 21, 21a, 21b, 21c, 21d, 21e, 21f, 21g, 21h Sensor 22 Vehicle (mobile body) 30 Storage device 40 Output device 100 System 110 Computer 111 CPU 112 Main memory 113 Storage device 114 Input interface 115 Display controller 116 Data reader / writer 117 Communication interface 118 Input device 119 Display device 120 Recording medium 121 Bus

Claims

1. an extraction means for acquiring displacement data measured by a first sensor and a second sensor installed on the structure each time a moving body moves on the structure, and extracting first extracted displacement data and second extracted displacement data to be used for diagnosing the soundness of the structure from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; a calculation means for calculating, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data, using first array data constituted by the first extracted displacement data and second array data constituted by the second extracted displacement data; an estimation means for estimating a probability distribution using displacement ratio sequence data configured by the displacement ratios calculated for each movement; a diagnostic means for diagnosing the soundness of the state of the structure using the estimated probability distribution; An information processing device having the above.

2. The extraction means Detecting a minimum value for each of the first displacement data and the second displacement data; extracting the first extracted displacement data and the second extracted displacement data from the first displacement data and the second displacement data based on data in a preset range including the detected minimum value; The information processing device according to claim 1 .

3. the estimation means calculates a frequency distribution of the displacement ratio and estimates the probability distribution based on the frequency distribution. The information processing device according to claim 2 .

4. the diagnostic means performs statistical analysis processing on a first probability distribution for the first measurement time point and a second probability distribution for the second measurement time point; The information processing device according to claim 3 .

5. The information processing device each time a moving body moves on a structure, displacement data measured using a first sensor and a second sensor installed on the structure is acquired, and first extracted displacement data and second extracted displacement data to be used for diagnosing the soundness of the structure are extracted from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; calculating, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data using first array data configured from the first extracted displacement data and second array data configured from the second extracted displacement data; Estimating a probability distribution using displacement ratio sequence data configured by the displacement ratios calculated for each movement; diagnosing the soundness of the state of the structure using the estimated probability distribution; An information processing method that performs processing.

6. In the extraction, Detecting a minimum value for each of the first displacement data and the second displacement data; extracting the first extracted displacement data and the second extracted displacement data from the first displacement data and the second displacement data based on data in a preset range including the detected minimum value; The information processing method according to claim 5 .

7. In the above estimation, determining a frequency distribution of the displacement ratio, and estimating the probability distribution based on the frequency distribution; The information processing method according to claim 6.

8. In the diagnosis, performing a statistical analysis process on the first probability distribution for the first measurement time and the second probability distribution for the second measurement time; The information processing method according to claim 7.

9. On the computer, each time a moving body moves on a structure, displacement data measured using a first sensor and a second sensor installed on the structure is acquired, and first extracted displacement data and second extracted displacement data to be used for diagnosing the soundness of the structure are extracted from the acquired first displacement data of the first sensor and second displacement data of the second sensor, respectively, based on preset extraction conditions; calculating, for each movement, a displacement ratio for each corresponding element of the first array data and the second array data using first array data configured from the first extracted displacement data and second array data configured from the second extracted displacement data; a probability distribution is estimated using displacement ratio sequence data configured by the displacement ratios calculated for each movement; diagnosing the soundness of the state of the structure using the estimated probability distribution; A program containing instructions.

10. In the extraction, detecting a minimum value for each of the first displacement data and the second displacement data; extracting the first extracted displacement data and the second extracted displacement data from the first displacement data and the second displacement data based on data in a preset range including the detected minimum value; The program according to claim 9.