Structure diagnosis system, structure diagnosis method, and structure diagnosis program

Abstract

To enable a quantitative abnormality diagnosis of a structure to be performed at high accuracy.SOLUTION: A structure diagnosis system has a diagnosis part for calculating an evaluation index being a ratio between a first periphery likelihood representing a probability distribution of a feature amount in the case of assuming that a structure is in a healthy state and a second periphery likelihood representing a probability distribution of a feature amount in the case of assuming that the structure is not in the healthy state about a feature amount showing a state of the structure generated from a time series of information about the structure to diagnose the state of the structure on the basis of the evaluation index. An autoregressive model represents sensor information acquired from a plurality of sensors attached to the structure at a certain time by a linear combination of time series of sensor information acquired before the certain time. A regression coefficient is a matrix obtained by being multiplied to each of the time series of sensor information linearly combined in the autoregressive model. The feature amount is information based on a coefficient matrix obtained by connecting matrixes.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to a structure diagnosis system, a structure diagnosis method, and a structure diagnosis program. [Background technology]

[0002] Conventionally, there has been technology that estimates characteristic quantities (vibration characteristics) such as the natural frequency, damping coefficient, and mode shape of vibration based on the acceleration of a structure such as a bridge, and diagnoses abnormalities in the structure based on changes in the estimated vibration characteristics.

[0003] For example, Patent Document 1 discloses the following technology. That is, independent component analysis (ICA) is performed on sensor signals indicating vibrations acquired from acceleration sensors installed at multiple locations on the bridge, and the natural frequency of the bridge is determined by performing spectral analysis on the independent vibration components obtained by the independent component analysis. Then, based on a comparison between the natural frequency of the bridge in a healthy state acquired in advance and the natural frequency of the bridge in its current state, an abnormality diagnosis is performed on the entire bridge and abnormal locations are identified. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2008-255571 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, the sensitivity to changes in response to damage varies depending on the location and vibration mode where the vibration is measured. Furthermore, in the prior art, the estimation varies depending on the environmental conditions (external force, temperature, etc.) at the time of vibration measurement. However, even an experienced person has difficulty in presetting the installation location of the acceleration sensor and the vibration mode appropriately. For this reason, in the case of abnormality diagnosis of a bridge, for example, based on the natural frequency, if the vibration mode is set incorrectly, it is not possible to distinguish between changes in vibration characteristics due to abnormalities in the bridge and accidental changes in vibration characteristics due to reasons other than abnormalities in the bridge, and there is a problem in that quantitative abnormality diagnosis cannot be performed with high accuracy.

[0006] In consideration of the above, an object of the present invention is to enable quantitative abnormality diagnosis of a structure with high accuracy. [Means for solving the problem]

[0007] In order to solve the above-mentioned problems, the present invention provides a structure diagnosis system comprising: a diagnosis unit that calculates an evaluation index for a feature quantity indicating a state of a structure, generated from a time series of information about the structure, between a first marginal likelihood representing a probability distribution of the feature quantity when it is assumed that the structure is in a healthy state and a second marginal likelihood representing a probability distribution of the feature quantity when it is assumed that the structure is in an unhealthy state, and diagnoses the state of the structure based on the evaluation index; an acquisition unit that acquires sensor information in time series from a plurality of sensors attached to the structure; an autoregressive model generation unit that generates an autoregressive model that expresses the sensor information acquired by the acquisition unit at a certain time as a linear combination of the time series of the sensor information acquired before the certain time; and a diagnosis unit that calculates an evaluation index for the structure at the certain time based on the regression coefficients of the autoregressive model. a sensor node including: a feature generation unit that generates the feature indicating a state; the acquisition unit, the autoregressive model generation unit, the feature generation unit, and a transmission unit that transmits the feature generated by the feature generation unit to the diagnosis unit, wherein the sensor information acquired from a plurality of the sensors at each time in a time series is a sensor information vector at each time with an order equal to the number of the sensors; the autoregressive model expresses the sensor information vector acquired at the certain time by the acquisition unit as a linear combination of a time series of the sensor information vector acquired before the certain time, the regression coefficients are matrices multiplied by each of the time series of the sensor information vectors linearly combined in the autoregressive model, and the feature is information based on a coefficient matrix combining the matrices. Effect of the Invention

[0008] According to the present invention, quantitative abnormality diagnosis of a structure can be performed with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing a schematic configuration of a diagnostic system according to a first embodiment. [Diagram 2]FIG. 2 is a block diagram showing the configuration of a sensor node according to the first embodiment. [Diagram 3] FIG. 1 is a block diagram showing the configuration of a diagnostic device according to a first embodiment. [Figure 4] FIG. 4 is a sequence diagram showing a reference time process in the diagnostic system of the first embodiment. [Diagram 5] FIG. 4 is a sequence diagram showing a diagnosis process in the diagnosis system of the first embodiment. [Figure 6] FIG. 3 is an explanatory diagram of a diagnosis process in the diagnosis system of the first embodiment. [Figure 7] FIG. 11 is a diagram showing a comparison of the data amounts of coefficient matrices and principal component matrices for each number of sensors in the first embodiment and the prior art. [Figure 8] 10 is a flowchart showing a diagnostic process in the diagnostic system of the second embodiment. [Figure 9A] FIG. 11 is a diagram for explaining a method of calculating a threshold value for determining an abnormality according to the second embodiment. [Figure 9B] 13 is a diagram for explaining another example of the abnormality determination method using a plurality of threshold values ​​according to the second embodiment. FIG. [Figure 10] 11A to 11C are diagrams for explaining the results of an experiment on abnormality determination carried out using the diagnosis system of the second embodiment. [Figure 11] FIG. 11 is a diagram showing the execution conditions of an experiment performed using the diagnostic system of the second embodiment. [Figure 12] FIG. 11 is a diagram showing the results of an experiment conducted using the diagnostic system of the second embodiment. [Figure 13] FIG. 11 is a diagram showing the change in the natural frequency of a bridge that differs depending on the vibration mode measured under the same conditions as in the experiment conducted using the diagnostic system of embodiment 2. [Figure 14] A graph showing the time-dependent changes in the outside temperature and Bayes factor values ​​for a certain girder of a bridge during a certain period of time. [Figure 15] A graph showing the change in deflection and Bayes factor values ​​over time for a bridge over a certain period of time. [Figure 16] A comparison of the Bayes Factor values ​​over time for two spans of a bridge. [Figure 17] FIG. 11 is an explanatory diagram of sequential updating of a coefficient matrix in the diagnostic system of the third embodiment. [Figure 18] 13 is a diagram showing the convergence of the probability distribution of the coefficient matrix by sequentially updating the coefficient matrix in the diagnostic system of the embodiment 3. FIG. [Figure 19] FIG. 2 is a block diagram showing the configuration of a sensor node terminal used as a sensor node according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. The following embodiment is an example for explaining the present invention sufficiently and appropriately, and appropriate omissions and simplifications are made. Not all of the configurations and processes described in the following embodiment are essential for carrying out the present invention, and can be omitted as appropriate. In addition to the following embodiment, the present invention can be carried out in various other forms that can achieve the object of the present invention. Furthermore, forms that combine part or all of each embodiment and modified example are also included in the embodiments of the present invention as long as they are consistent within the scope of the technical idea of ​​the present invention.

[0011] In the following embodiments, configurations and processes described later that are similar to configurations and processes already described may be given the same reference numerals, and descriptions thereof may be omitted, with only the differences being described.

[0012] In the following embodiment, a bridge will be described as an example of a structure to be diagnosed for the presence or absence of abnormalities such as cracks or other damage and deterioration. However, the present invention is not limited to bridges, and can be applied to any civil engineering or architectural structure that serves as social infrastructure, such as tunnels, road structures, river structures, port structures, water supply and sewerage systems, and buildings, to diagnose the presence or absence of abnormalities therein.

[0013] In addition, in the following description of the embodiments, an expression in which a first symbol is followed by a second symbol, such as “A^”, is the same as an expression in which the second symbol is written directly above the first symbol.

[0014] <Mathematical Background of the Invention> First, prior to describing the embodiments, the mathematical background of the present invention will be described. The present invention utilizes the fact that the system matrix of the state equation in the state space model of a structure can be approximated by a matrix of regression coefficients of an autoregressive model that expresses an observation signal at a certain time as a linear combination of a time series of observation signals prior to the certain time. The present invention focuses on the fact that the matrix of regression coefficients contains various information related to the state of the structure contained in the system matrix, and expresses the state of the structure using the matrix of regression coefficients, and evaluates the state of the structure by analyzing the matrix of regression coefficients.

[0015] In the following description, the sensor information acquired by the sensor is acceleration, but is not limited to acceleration and may be another physical quantity.

[0016] In general, the equation of motion of a structure is expressed as the following formula (1): n sensors (n is a natural number equal to or greater than 1) are installed at various positions on the structure, and the time series of n-th order observation vectors is acquired with the installation positions as observation points.

[0017]

number

[0018] The equation of motion (1) above can be converted into an equation of state as shown in the following equations (2-1) and (2-2).

[0019]

number

[0020] Here, y in the above formula (2-2) represents the observation vector, z in the above formula (2-3) represents the state variable vector, and A in the above formula (2-5) s and represent the system matrices that represent the state of the system (the structure to be diagnosed) in state space. In the above formula (2-2), C is a matrix that associates the observation vector y with the state of the system, and becomes a unit matrix when the measurement information at the observation point is regarded as the state of the system as it is.

[0021] It is known that the state equations of the above formulas (2-1) and (2-2) can be expressed by an autoregressive model, which is a linear combination of the time series of discretized observation signals, as shown in the following formula (3).

[0022]

number

[0023] In the above formula (3), k is the time index, y(k) is the sensor information vector at time k, p is the order of the autoregressive model, A i is the matrix of regression coefficients, and e(k) is the error term of the autoregressive model at time k. i is a regression coefficient by which each of the time series of the linearly combined sensor information vector y(ki) is multiplied in the autoregressive model.

[0024] Matrix A, which is the regression coefficient in the autoregressive model of the above formula (3), i Each element of the system matrix A in the above formula (2-1) s The matrix A is associated with the physical quantities of the structure included in the matrix A, and contains at least one of the following information: displacement, velocity, acceleration, mass matrix m, damping coefficient matrix c, and stiffness matrix k at the observation point where the sensor is installed. i By using the matrix A, the state of the structure can be expressed so as to include various information related to vibration. i By capturing changes in this, it becomes possible to capture changes in the condition of the structure.

[0025] However, when there is one sensor (n=1), the matrix A in the autoregressive model i is a scalar.

[0026] Here, matrix A i is an n-th order square matrix as shown in the following formula (4), where n is the number of sensors installed at each position of the structure.

[0027]

number

[0028] When the p-th order autoregressive model shown in the above formula (3) generated from the time series of the sensor information vector y(k) measured by n sensors is expressed as a determinant, it becomes as shown in the following formula (5).

[0029]

number

[0030] Here, Y on the left side of the above formula (5) f is the predicted state, and Y p represents the pth order past acceleration, and E in the second term on the right-hand side represents the error due to the uncertainty of the state observation of the structure. Also, the coefficient matrix A in the first term on the right-hand side of the above equation (5) is the matrix A for i from 1 to p. i and is expressed as the following equation (6).

[0031]

number

[0032] The coefficient matrix A is the system matrix A s For example, the natural frequency ω of the system at time k k and the damping coefficient h k The pole z of the system at time k is expressed using k ,z k * can be calculated from the above formula (5) as shown in the following formula (7).

[0033]

number

[0034] The posterior distribution of the coefficient matrix A is converted to the posterior distribution of the poles, and the natural frequency ω is calculated as shown in the above equation (7). kand damping coefficient h k can also be used for diagnosing structures. The natural frequency ω obtained in this way k and damping coefficient h k have the advantage that, compared with the prior art, vibration characteristics such as the natural frequency and damping coefficient can be identified considering variations. Also, by converting the posterior distribution of the coefficient matrix A into the posterior distribution of the poles and obtaining the vibration characteristics from the poles with small variances, the selection of physically meaningful vibration characteristics can be automated. Further, the selection of the model order p can be automated based on the BIC (Bayesian information criterion).

[0035] By transmitting the coefficient matrix A obtained as described above to the diagnostic device as a feature quantity representing the state of the structure, a time series having the vibration characteristics of the structure can be reproduced in the diagnostic device, and the state of the structure can be diagnosed.

[0036] However, the coefficient matrix A contains components of inferior-quality information that is irrelevant to the diagnostic result. By removing these components of inferior-quality information and transmitting the reconstructed matrix A^ to the diagnostic device, the amount of data transmission and reception can be reduced. This matrix A^ is obtained by performing principal component analysis on the coefficient matrix A, so it is called the principal component matrix.

[0037] For example, the coefficient matrix A estimated at the reference time (e.g., when the structure is sound) of the structure is subjected to singular value decomposition as in the following formula (8).

[0038]

Equation

[0039] The matrix U and the matrix P in the above formula (8) T (where P T is the transposed matrix of the matrix P) are orthogonal matrices, and the matrix Λ is the eigenvalue of the coefficient matrix A. And the right side of the above formula (8) is, as in the following formula (9), by principal component analysis, the matrix U is an n×N matrix U 1 (N < n) and an n×(n - N) matrix U 2 and decomposed into.

[0040]

number

[0041] Matrix U at this reference time (e.g., healthy time) 1 is a matrix that projects the coefficient matrix A in the probability space to the principal component space. As shown in the following formula (10), for the coefficient matrix A estimated at each time point after the reference time, the matrix U 1 Transpose of matrix U 1 T By applying the above formula, the principal component matrix A^ is generated, which is an N × np matrix from which components with poor quality information have been removed.

[0042]

number

[0043] As above, the system matrix A s By estimating a coefficient matrix A that inherits information from the matrix A, generating a principal component matrix A^ from the coefficient matrix A, and capturing changes in the principal component matrix A^, it is possible to detect abnormalities in the structure. In the present invention, as shown in the following formula (11), the probability distribution of the elements of the principal component matrix A^ is estimated by Bayesian estimation. Then, by using the estimated probability distribution for diagnosing the state of the structure, it is possible to detect abnormalities in the structure while taking into account the uncertainty included in the above formula (5).

[0044]

number

[0045] In the present invention, a probability distribution having a mean and variance is used as the evaluation index for evaluating the condition of a structure. This makes it possible to capture minute changes in the mean value of the evaluation index when the structure is damaged compared to when it is healthy, and also makes it possible to indicate the reliability of the evaluation index using the variance.

[0046] It should be noted that the condition of a structure can also be diagnosed by using the coefficient matrix A as a feature instead of the principal component matrix A^. In that case, the above formula (11) becomes a formula in which A^ is replaced with A.

[0047] <Embodiment 1> Hereinafter, the first embodiment will be described with reference to FIGS.

[0048] (Configuration of diagnostic system S of embodiment 1) Fig. 1 is a diagram showing a schematic configuration of a diagnostic system S of the first embodiment. The diagnostic system S includes a sensor node 1 and a diagnostic device 2. The sensor node 1 generates a feature quantity indicating the state of the bridge 4 based on sensor information acquired via wireless communication (or wired communication) from a sensor 3 installed on the bridge 4. The diagnostic device 2 acquires the feature quantity indicating the state of the bridge 4 generated by the sensor node 1 via wireless communication (or wired communication), and diagnoses the presence or absence of an abnormality in the bridge 4 using the feature quantity.

[0049] The sensor 3 is, for example, an acceleration sensor, and is installed at each location of the bridge 4. In this embodiment, the sensor 3 is a plurality of sensors installed at multiple locations of the bridge 4, but is not limited to this and may be a single sensor installed at one location. Also, in this embodiment, the sensor 3 is an acceleration sensor that detects acceleration, but is not limited to this and may be a sensor that can measure other physical quantities (for example, strain, displacement, speed, etc.).

[0050] In this embodiment, for ease of understanding, a configuration is described as an example in which the sensor node 1 processes sensor information acquired from the sensor 3 and transmits the processed result to the diagnostic device 2 as shown in Fig. 1. However, the present invention is not limited to this, and may be configured as a distributed cooperative system in which the sensors 3 form a sensor network and perform distributed cooperative processing to achieve functions equivalent to those of the sensor node 1. When there is only one sensor 3, the single sensor 3 achieves functions equivalent to those of the sensor node 1.

[0051] (Configuration of the sensor node 1 of the first embodiment) 2 is a block diagram showing the configuration of the sensor node 1 of the embodiment 1. The sensor node 1 performs edge processing to generate a coefficient matrix A (or a principal component matrix A^) as a feature representing the state of a bridge 4 from sensor information acquired from a sensor 3. The sensor node 1 has a processor 11, a memory 12, a storage 13, and a communication I / F (Inter / Face) unit 14.

[0052] The processor 11 is an arithmetic processing device such as a CPU (Central Processing Unit), a PLD (Programmable Logic Device), or a microprocessor. The memory 12 is a main storage device. The storage 13 is an auxiliary storage device. The communication I / F unit 14 is a communication interface for the sensor node 1 to perform wireless communication (or wired communication) with the sensor 3 and the diagnostic device 2.

[0053] The processor 11 executes a program in cooperation with the memory 12 to realize the following functional units: a sensor information acquisition unit 111, an autoregressive model generation unit 112, a feature generation unit 113, and a feature transmission unit 114.

[0054] The sensor information acquisition unit 111 acquires, in time series, observation signals observed by the sensors 3 at each installation position of the bridge 4 via the communication I / F unit 14, and stores the signals in the storage 13 as sensor information 131. In this embodiment, the sensor information 131 acquired by the sensor information acquisition unit 111 is time-series information at continuous time, but may be time-series information at discrete time. The sensor information 131 may be acquired continuously, or may be acquired for a fixed period of time in response to an acquisition instruction.

[0055] The autoregressive model generation unit 112 discretizes the sensor information 131 stored in the storage 13 by time. Then, as shown in the above formula (3), the autoregressive model generation unit 112 generates an autoregressive model that expresses the sensor information 131 at a certain time k as a linear combination of the time series of the sensor information 131 at p times ki (i=1, . . . , p) before the certain time k. Details of the processing by the autoregressive model generation unit 112 will be described later with reference to a flowchart.

[0056] The feature generation unit 113 generates a feature representing the state of the bridge 4 at a certain time k from the coefficient matrix A (the above formula (6)) obtained by combining the regression coefficients of the linear combination of the autoregressive models generated by the autoregressive model generation unit 112. The feature may be the coefficient matrix A itself, or may be a principal component matrix A^ (the above formula (10)) obtained by projecting the coefficient matrix A onto a principal component space based on principal component analysis. As described later, based on such feature, the surface and internal states of the bridge 4 can be represented as a probability distribution. Details of the processing by the feature generation unit 113 will be described later with reference to a flowchart.

[0057] The feature amount transmission unit 114 transmits the feature amount generated by the feature amount generation unit 113 to the diagnostic device 2 via the communication I / F unit 14.

[0058] (Configuration of diagnostic device 2 of embodiment 1) 3 is a block diagram showing the configuration of the diagnostic device 2 of the embodiment 1. The diagnostic device 2 has a processor 21, a memory 22, a storage 23, a communication I / F unit 24, and an output unit 25. The processor 21 cooperates with the memory 22 to execute a program, thereby realizing each functional unit of a feature receiving unit 211 and a diagnostic unit 212.

[0059] The processor 21 is an arithmetic processing device such as a CPU, PLD, or microprocessor. The memory 22 is a main storage device. The storage 23 is an auxiliary storage device. The communication I / F unit 24 is a communication interface for the diagnostic device 2 to perform wireless communication (or wired communication) with the sensor node 1. The output unit 25 is a monitor, display, or the like, and outputs various information.

[0060] The feature amount receiving unit 211 receives a feature amount 231 indicating the state of the bridge 4 at each time k from the sensor node 1 via the communication I / F unit 24. The feature amount receiving unit 211 stores the received feature amount 231 in the storage 23.

[0061] The diagnosis unit 212 uses Bayesian estimation to obtain a probability distribution (the above formula (11)) of the feature amount at each time k from the feature amount 231 stored in the storage 23 as an evaluation index. Then, the diagnosis unit 212 calculates the Mahalanobis distance MD of the probability distribution obtained as the evaluation index at each time k, as shown in the following formula (12).

[0062]

number

[0063] In the above formula (12), the matrix X is the coefficient matrix A (or the principal component matrix A^), and the matrix S is the covariance matrix of the matrix X. The diagnosis unit 212 calculates in advance the Mahalanobis distance MD of the coefficient matrix A (or the principal component matrix A^) of the bridge 4 at a reference time (e.g., when healthy) as a reference evaluation index 232 and stores it in the storage 23. The diagnosis unit 212 also calculates the Mahalanobis distance MD of the coefficient matrix A (or the principal component matrix A^) of the bridge 4 at the time of diagnosis, when the presence or absence and the degree of damage are unknown.

[0064] The diagnosis unit 212 then compares the Mahalanobis distance MD at the time of diagnosis with the reference evaluation index 232, and if a statistical distance such as a difference or ratio between them is equal to or greater than a certain value, diagnoses that an abnormality such as damage has occurred or progressed in the bridge 4 compared to the reference time. The diagnosis unit 212 outputs the diagnosis result to the output unit 25 such as a display.

[0065] In addition, the diagnosis unit 212 may diagnose the progression of abnormalities and deterioration of the bridge 4 by using a Z value or other statistical index instead of the Mahalanobis distance MD and determining a threshold value for the statistical distance between each statistical index at the reference time and the diagnosis time.

[0066] (Reference time processing in diagnostic system S of embodiment 1) 4 is a sequence diagram showing the reference time processing in the diagnostic system S of embodiment 1. In the reference time processing in the diagnostic system S, a coefficient matrix A and a principal component matrix A^ are generated from a time series of sensor information acquired from the sensor 3 at a reference time (for example, when the bridge 4 is in a healthy state), and a process of calculating a reference evaluation index 232 based on the principal component matrix A^ is performed.

[0067] First, in step S101, the sensor information acquisition unit 111 of the sensor node 1 acquires the sensor information 131 from the sensor 3 and stores it in the storage 13. Next, in step S102, the autoregressive model generation unit 112 generates a p-th order autoregressive model of the sensor information vector y(k) at a certain time k obtained by discretizing the sensor information 131 acquired in step S101 based on the above formula (3). The order p of the autoregressive model is appropriately determined, but may be automatically determined from the above formula (5) based on the BIC, for example, as described above.

[0068] Next, in step S103, the feature generator 113 calculates a matrix A representing the regression coefficients of the p-th order autoregressive model of the sensor information vector y(k) as shown in the above formula (6). i Next, in step S104, the feature generator 113 generates a principal component space matrix U 1 T Generate.

[0069] Next, in step S106, the feature generator 113 calculates the principal component space matrix U 1 T to the coefficient matrix A to generate a principal component matrix A^ as a feature. Next, in step S106, the feature transmitting unit 114 transmits the feature generated in step S105 to the diagnostic device 2.

[0070] Next, in step S201, the feature receiving unit 211 of the diagnostic device 2 receives the feature 231 from the sensor node 1 and stores it in the storage 23. Next, in step S202, the diagnostic unit 212 obtains the probability distribution p(A^|Σ,Y) of the feature 231 as in the above formula (11), and calculates the Mahalanobis distance MD of the probability distribution p(A^|Σ,Y) as the reference evaluation index 232. Next, in step S203, the diagnostic unit 212 stores the reference evaluation index 232 calculated in step S202 in the storage 23.

[0071] 4, in the reference time process, the steps executed by the sensor node 1 may be executed by the diagnostic device 2, and the steps executed by the diagnostic device 2 may be executed by the sensor node 1. In other words, it is not limited to whether the execution subject of each step shown in FIG. 4 is the sensor node 1 or the diagnostic device 2.

[0072] For example, the processes after any one of steps S102 to S105 may be performed by the diagnostic device 2 instead of the sensor node 1. Also, for example, the process of step S202 may be performed by the sensor node 1 instead of the diagnostic device 2, and the calculated reference evaluation index is transmitted to the diagnostic device 2 and used in the diagnostic device 2 for diagnosing the condition of the bridge 4.

[0073] (Diagnosis process in diagnostic system S of embodiment 1) Fig. 5 is a sequence diagram showing the diagnosis process in the diagnosis system S of embodiment 1. The diagnosis process in Fig. 5 differs from the reference time process in Fig. 4 only in that it handles sensor information and feature amounts at the time of diagnosis rather than at the reference time, and steps S111 to S116 are the same as steps S101 to S106 in Fig. 4.

[0074] In addition, in step S104 of the reference time process in FIG. 4, the principal component space matrix U 1 T When the above is generated, in the diagnosis process of FIG. 5, the principal component space matrix U 1 TIn the case where step S114 is omitted, in step S115 following step S113, the feature generator 113 generates the principal component space matrix U 1 T to the coefficient matrix A generated in step S113 to generate a principal component matrix A^ as a feature. Next, in step S116, the feature transmitting unit 114 transmits the feature generated in step S115 to the diagnostic device 2.

[0075] Next, in step S211, the feature receiving unit 211 of the diagnostic device 2 receives the feature from the sensor node 1. Next, in step S212, the diagnostic unit 212 calculates the probability distribution p(A^|Σ,Y) of the feature based on the feature received in step S211 using Bayesian estimation as in the above formula (11). Then, the diagnostic unit 212 calculates the Mahalanobis distance MD at the time of diagnosis as an evaluation index based on the above formula (12), compares the evaluation index with the reference evaluation index 232, and diagnoses that an abnormality such as damage has occurred or progressed in the bridge 4 compared to the reference time if the difference or ratio between them is equal to or greater than a certain value.

[0076] 5, like Fig. 4, there is no limitation as to whether each step is executed by the sensor node 1 or the diagnostic device 2. For example, the evaluation index may be calculated by the sensor node 1 instead of the diagnostic device 2. The evaluation index calculated in this manner is transmitted to the diagnostic device 2, and is used by the diagnostic device 2 to diagnose the condition of the bridge.

[0077] 4 and 5, the principal component matrix A^ is used as the feature, but the coefficient matrix A may be used as the feature. In this case, A^ is replaced with A in the above formula (11) to calculate the probability distribution p(A|Σ, Y).

[0078] Fig. 6 is an explanatory diagram of the diagnosis time processing in the diagnosis system S of the embodiment 1. The illustrated portion 601 in Fig. 6 shows an overview of the reference time processing (Fig. 4) in which feature amounts are extracted from observation data representing the vibration of the bridge 4 at the reference time, and a statistical index based on this feature amount is calculated as a reference evaluation index. Also, the illustrated portion 602 shows an overview of the diagnosis time processing (Fig. 5) in which feature amounts are extracted from observation data representing the vibration of the bridge 4 at the diagnosis time, and a statistical index based on this feature amount is calculated as a diagnosis time evaluation index.

[0079] Then, in the diagnosis process (FIG. 5), the presence or absence of an abnormality in the bridge 4 and its progression are judged based on the comparison result between the reference evaluation index and the diagnosis-time evaluation index. That is, as shown in the illustrated portion 603 of FIG. 6, in the probability space, an abnormality in the bridge 4 is diagnosed by comparing the reference evaluation index based on the probability distribution of the reference feature amount with the diagnosis-time evaluation index based on the probability distribution of the diagnosis-time feature amount. In the comparison between the reference evaluation index and the diagnosis-time evaluation index, a statistical index such as the Mahalanobis distance is used to evaluate the degree to which the diagnosis-time evaluation index deviates from the reference evaluation index. The presence or absence of an abnormality in the bridge 4 can be judged such that, when the statistical distance between the diagnosis-time evaluation index and the reference evaluation index is equal to or greater than a certain value, it is judged that the state of the bridge 4 at the time of diagnosis has changed from the reference time.

[0080] In this embodiment, the presence or absence of an abnormality in the bridge 4 is determined based on the statistical distance between the evaluation indexes at the reference time and the evaluation time, but this is not limited to the above. For example, the coefficient matrix A (or the principal component matrix A^) at each time is clustered, and if the coefficient matrix A based on new observation data is not classified into an existing cluster but into a new cluster, it is determined that the pattern of the feature quantities of the coefficient matrix A has changed, and it is determined that an abnormality has occurred in the bridge 4.

[0081] (Effects of the First Embodiment) In the above-mentioned first embodiment, the condition evaluation based on the feature quantity representing the state of the structure is performed using an evaluation index based on a probability distribution that includes various physical quantities of the structure and that can take into account the estimation error of the measurement value while absorbing the difference in sensitivity of the change in the measurement value to damage that differs depending on the measurement location. Therefore, according to the first embodiment, it is not necessary to set a vibration mode that is sensitive to damage, which requires a high level of specialized knowledge, and the state of the structure can be evaluated at low cost and with high accuracy without performing numerical analysis by using a probability distribution having a mean and variance based on the feature quantity that is sensitive to the damage of the structure. In addition, the validity of the evaluation can be expressed by the variance.

[0082] In addition, the evaluation index of the probability distribution used in embodiment 1 can capture minute changes that progress slowly as a result of damage to a structure and that are easily obscured by noise during measurement and forced vibrations such as live loads, making it possible to perform highly accurate condition diagnosis of the structure.

[0083] In the first embodiment, the coefficient matrix A representing the state of the structure is projected onto the principal component space to remove information of low quality, thereby generating a principal component matrix A^ of a lower order. Therefore, the feature quantity representing the state of the structure is compressed into a feature quantity capable of reproducing the state of the structure without reducing the quality of the information, so that the feature quantity can be transferred by a method using low-cost advanced technology such as low-power wide area wireless communication by edge processing, and the sensor and transfer system can be constructed inexpensively, which is expected to reduce management costs significantly.

[0084] More specifically, in the past, when evaluating such a vibration state, it was necessary to use acceleration data for several minutes, which required a large amount of communication. However, in this method, the only information required is the value of the principal component matrix A^, so that the principal component matrix A^ is obtained by edge processing in the measuring device, and by making the data small, it is possible to use inexpensive advanced technology such as specific low-power radio, and it is considered to have an advantage in terms of management costs as shown in FIG. 7. FIG. 7 is a diagram showing a comparison of the coefficient matrix A and the data amount of the principal component matrix A^ for each number of sensors in the first embodiment and the conventional technology. FIG. 7 shows a case where data measured for 60 seconds at a period of 5 ms is transmitted. According to FIG. 7, it can be seen that the amount of data transferred from the sensor node 1 can be significantly reduced by the principal component matrix A^ in any number of sensors, whether the number of sensors is 8, 4, or 1.

[0085] <Embodiment 2> In the first embodiment, abnormality diagnosis of the bridge 4 is performed using a statistical index such as the Mahalanobis distance of a probability distribution based on the feature amounts of the bridge 4 at the reference time and the diagnosis time, whereas in the second embodiment, abnormality diagnosis of the bridge 4 is performed using a Bayes factor based on the feature amounts of the bridge 4 as an evaluation index. Note that the configuration of the diagnosis system S in the second embodiment is similar to the configuration of the diagnosis system in the first embodiment, except that part of the processing of the diagnosis unit 212 of the diagnosis device 2 is different.

[0086] (Diagnosis process in diagnosis system S of embodiment 2) Fig. 8 is a flowchart showing diagnostic processing in the diagnostic system S of embodiment 2. The flowchart shown in Fig. 8 is another example of the processing of step S212 of the diagnostic processing of embodiment 1 shown in Fig. 5. That is, in embodiment 2, the diagnostic device 2 executes the diagnostic processing shown in Fig. 8 following step S211. Note that in embodiment 2, the diagnostic device 2 can execute the diagnostic processing of Fig. 5 without executing the reference time processing of Fig. 4.

[0087] First, in step S2121, the diagnosis unit 212 of the diagnosis device 2 calculates a Bayes factor B defined by the following formula (13) as an evaluation index based on the coefficient matrix A (or the principal component matrix A^) that is the feature amount received in step S211. The local Bayes factor B, which will be described later, j When distinguishing it from the above, Bayes Factor B is called the global Bayes Factor.

[0088]

number

[0089] In the above formula (13), H 0 is the null hypothesis (in this embodiment, the soundness of bridge 4), H 1 is the alternative hypothesis (in this embodiment, the abnormal / damaged state of bridge 4), Y t is the feature to be tested for hypothesis (in this embodiment, the coefficient matrix A or the principal component matrix A^), Φ t H 0 Or H 1 These are parameters under the hypothesis (e.g., the mean and standard deviation of the probability distribution of the feature).

[0090] In the Bayes factor B shown in the above formula (13), the denominator p(Y t |Φ t ,H 0 ) is the feature value Y t indicates the marginal likelihood, which is the same feature as the state (sound state) of Bridge 4 at the reference time, and the numerator p(Y t |Φ t ,H 1 ) is the feature value Y t represents the marginal likelihood, which is a feature that differs from the state of bridge 4 at the reference time. t |Φ t ,H 0 ) for p(Y t |Φ t ,H 1 When the Bayes factor B, which is the ratio of the feature values, exceeds a threshold value, it can be determined that an abnormality or damage has occurred in the bridge 4 based on a certain feature value.

[0091] Next, in step S2122, the diagnosis unit 212 determines whether the Bayes factor B calculated in step S2121 is greater than a threshold value. This threshold value is set to a category that an inspection engineer of the bridge 4 has determined to be abnormal based on past inspection data, etc. If the Bayes factor B is greater than the threshold value (Yes in step S2122), the diagnosis unit 212 determines that there is an abnormality in the bridge 4 (step S2123), and if the Bayes factor B is equal to or less than the threshold value (No in step S2122), the diagnosis unit 212 determines that the bridge 4 is normal (step S2124).

[0092] The diagnostic process shown in FIG. 8 may be performed by the sensor node 1 instead of the diagnostic device 2.

[0093] (Calculation method of threshold for abnormality judgment) Here, a method for calculating the threshold value for abnormality determination used in step S2122 of the diagnosis process (FIG. 8) will be described. FIG. 9A is a diagram for explaining a method for calculating the threshold value for abnormality determination in the second embodiment. In the graph (a) on the left side of FIG. 9A, the horizontal axis represents time and the vertical axis represents the logarithm of Bayes Factor B, and the values ​​of Bayes Factor B at each time are plotted. In the graph (b) on the right side of FIG. 9A, the horizontal axis represents frequency and the vertical axis represents the logarithm of Bayes Factor B, and the frequency distribution of each value of Bayes Factor B is shown. The calculation of the threshold value for abnormality determination may be performed by the diagnosis device 2 or another information processing device.

[0094] On an actual bridge, various situations occur that affect anomaly detection, such as the passing of a truck with a heavy load or braking on the bridge. Bayes Factor B is a value with variation that includes specific data under various situations. When calculating the threshold value of Bayes Factor B, specific data and data variation of multiple measurement data from a specified period in the past are not eliminated, but are included in the basis for calculating the threshold value, thereby making it possible to calculate a threshold value that takes into account various situations that occur on an actual bridge.

[0095] Among the past measurement data of the bridge 4, the measurement data for a reference predetermined period (for example, one year) (see graph (a) in Fig. 9A) is applied to the above formula (13) to create a distribution of the values of the Bayes factor B (see graph (b) in Fig. 9A). Based on the mean value μ and variance σ of the distribution of the values of the Bayes factor B, any value such as μ, μ + σ, μ + 2σ, etc. can be determined as a threshold value. In graph (b) of Fig. 9A, since the values of the Bayes factor B are normalized, it follows a normal distribution with a mean μ = 0, and the case where the threshold value is the mean μ is shown. The threshold value of the Bayes factor B can be quantitatively determined using the mean μ and variance σ based on the characteristics of the bridge 4, and index values such as usage conditions, geographical conditions, and meteorological conditions. In this way, the accuracy of anomaly determination can be improved by using a threshold value that takes into account various situations that occur in an actual bridge.

[0096] (Another example of the threshold value for anomaly diagnosis) Another example of the threshold value for anomaly diagnosis will be described. Fig. 9B is a diagram for explaining another example of the anomaly determination method using a plurality of threshold values according to Embodiment 2. In graph (a) of Fig. 9B, the horizontal axis represents the frequency distribution, the vertical axis represents the logarithm of the Bayes factor B, and the frequency distribution of each value of the Bayes factor B is shown. In graph (b) of Fig. 9B, the horizontal axis represents the day, the vertical axis represents the logarithm of the Bayes factor B, and each value of the Bayes factor B for each day is plotted.

[0097] When the value of the Bayes factor B exceeds the threshold value, it is determined as an anomaly. Therefore, among the distribution of the values of the Bayes factor B based on the measurement data described above with reference to Fig. 9A, for values greater than the mean μ, a plurality of threshold values can be determined using the mean μ and the standard deviation σ, and anomalies can be determined step by step. Based on the plurality of threshold values, ranges representing diagnostic levels, such as a "normal" range, a "caution required" range, and an "abnormal" range, may be defined.

[0098] For example, a plurality of values (μ, μ + σ, μ + 2σ, etc. in (graph a) of FIG. 9B) based on the mean value μ and variance σ of the distribution of the value of the Bayes factor B are determined as a plurality of stepwise thresholds for the abnormality diagnosis of the bridge 4 based on the Bayes factor B. As shown in (graph a) of FIG. 14, if the Bayes factor B is B ≤ μ + σ, it can be diagnosed as "normal", if μ + σ < B ≤ μ + 2σ, it can be diagnosed as "attention required", and if μ + 2σ < B, it can be diagnosed as "abnormal". In the example of FIG. 9B, the number of the plurality of stepwise thresholds for the abnormality diagnosis is "2", but it is not limited thereto. The stepwise thresholds of the Bayes factor B and the number thereof can be quantitatively determined using the mean μ and variance σ based on the characteristics of the bridge 4, index values such as usage conditions, geographical conditions, and meteorological conditions.

[0099] In this way, the accuracy of the abnormality determination can be improved by using a plurality of thresholds considering various situations occurring in an actual bridge. Further, by determining the thresholds for the abnormality diagnosis of the bridge 4 based on the Bayes factor B stepwise, the administrator of the bridge 4 can gradually capture the abnormality of the bridge 4 that progresses over time stepwise and can perform the maintenance of the bridge 4 systematically.

[0100] (Local Bayes factor B) Now, the Bayes factor B based on the above formula (13) is an evaluation index for detecting an abnormality by looking at the bridge 4 as a whole. On the other hand, an individual Bayes factor can also be calculated based on the feature amount obtained from the time series of the sensor information of each individual sensor 3 installed in the bridge 4. The individual Bayes factor is called the local Bayes factor. For example, the local Bayes factor B based on the feature amount of the time series of the sensor information of the j-th (j = 1, ···, n) sensor 3 among the plurality of sensors 3 installed in the bridge 4 j is defined by the following formula (14).

[0101] [Number]

[0102] Local Bayes factor B jBy replacing the Bayes factor B with the diagnosis process shown in Fig. 8, the local Bayes factor B j From the index j, it can be identified that an abnormality or damage has occurred in the bridge 4 at the location where the j-th sensor 3 is installed.

[0103] Also, the local Bayes factor B j can also be used as follows. The type of sensor information that can sensitively detect abnormalities using the Bayes factor may differ depending on the structure such as a bridge 4 and the type of abnormality or damage that occurs in the structure. Therefore, sensors 3 of multiple sensor types are installed on a structure such as a bridge 4, and a local Bayes factor B based on the feature amount generated for each sensor type is calculated. j A diagnosis is made based on:

[0104] In other words, sensors 3 that detect different physical quantities (different sensor types) are installed on bridge 4, and a local Bayes factor B j Calculate the local Bayes factor B j If anomalies are judged based on the local Bayes factor B j From the index j, it can be determined that an abnormality or damage has occurred based on the sensor information of the j-th sensor type, sensor 3. In this way, the local Bayes factor B j By using the above, it is possible to sense an abnormality in any one of the multiple physical quantities, thereby improving the sensitivity of abnormality detection.

[0105] (Abnormality determination in bridge diagnosis system S of embodiment 2) FIG. 10 is a diagram for explaining the results of an experiment on abnormality determination performed using the diagnosis system S of the second embodiment. In FIG. 10, the horizontal axis indicates time, and the vertical axis indicates the local Bayes factor B j On the binary logarithm axis, there are 10 types of local Bayes factors A1 to A10. j10 shows the time transition of the binary logarithm of . In Fig. 10, A1 to A10 show, as an example, the installation positions of the sensor 3. INT (initial stage), DMG1, and DMG2 in Fig. 10 represent the respective periods.

[0106] In the INT, since no damage was done to bridge 4, the local Bayes factor B based on the sensor information of sensor 3 at any installation position is j The local Bayes factor B j If the value of INT shown in Fig. 10 is similar to that of INT, it can be estimated that bridge 4 is in a sound state with no abnormalities or damage occurring.

[0107] In DMG1, which damages a part of bridge 4 near A6 following INT, the value of the local Bayes factor based on the sensor information of sensor 3 of A6, especially A1 to A10, exceeds the threshold and is larger than that of INT. j If DMG1 is a value similar to that of INT, it can be estimated that damage has occurred in the area near A6 of Bridge 4.

[0108] In addition, in DMG2, which added further damage to the area near A6 of bridge 4 following DMG1, the local Bayes factor B j is larger than that of DMG1. Conversely, the local Bayes factor B j If DMG2 is similar to DMG1, it can be estimated that the damage that occurred in the area near A6 of Bridge 4 has progressed further. In addition, the local Bayes factor B j The sum or average of and the local Bayes factor B of DMG2 j By comparing this with the sum or average, the degree of damage progression from DMG1 to DMG2 can be evaluated.

[0109] It should be noted that a similar evaluation to that shown in FIG. 10 can also be performed using the global Bayes factor.

[0110] Thus, Bayes factor B or local Bayes factor B j By using this, it is possible to detect when the bridge 4 changes from a healthy state to an abnormal state, and to evaluate the progression of damage that has already been discovered through inspections, etc.

[0111] (Experimental Results of the Second Embodiment) Fig. 11 is a diagram showing the execution conditions of an experiment carried out using the diagnostic system S of the embodiment 2. Fig. 12 is a diagram showing the results of an experiment carried out using the diagnostic system S of the embodiment 2.

[0112] Figure 11 shows the load pattern applied to the bridge over time, with the horizontal axis representing time and the vertical axis representing load. As shown in Figure 11, vibration was applied to the bridge at times t0-t1 (Stage 1), t2-t3 (Stage 2), t4-t5 (Stage 3), t6-t7 (Stage 4), t7-t8 (Stage 5), t9-t10 (Stage 6), t10-t11 (Stage 7), and t12- (Stage 8). At times t1-t2 (Loading 1), a crack load was applied to the bridge. At times t3-t4 (Loading 2), a yield load was applied to the bridge. At times t5-t6 (Loading 3), the load on the bridge continued. At times t8-t9 (Loading 4), a design load was applied to the bridge. At times t11-t12 (Loading 5), a maximum load was applied to the bridge.

[0113] As a result of conducting experiments under these execution conditions, it can be said that the Bayes factor generally tends to increase as the loading stage progresses, as shown in Figure 12. Therefore, a clear interpretation can be given to the observed results of changes in the Bayes factor, making it easy to detect abnormalities or damage that have occurred in the bridge.

[0114] In this way, the advantage of this embodiment, that abnormalities or damage occurring in a bridge can be easily detected regardless of an increase or decrease in the bridge's natural frequency, can be seen from Fig. 13. Fig. 13 is a diagram showing, as a comparative example, changes in the natural frequency of a bridge that differs depending on the vibration mode measured under the same conditions as in the experiment conducted using the diagnosis system S of the second embodiment shown in Fig. 12.

[0115] Graph 1101 in FIG. 13 shows the change in natural frequency of the first bending mode in Stage 1 to Stage 8. Graph 1102 in FIG. 13 shows the change in natural frequency of the second bending mode in Stage 1 to Stage 8. As shown in graphs 1101 and 1102, the natural frequency increases or decreases depending on the change in the condition of the bridge. Theoretically, the natural frequency decreases due to a decrease in rigidity caused by damage, but the natural frequency may increase if, for example, there is a change in the condition of the bridge's support parts. Also, as shown in graphs 1101 and 1102, the change in natural frequency differs depending on the mode.

[0116] In this way, in abnormality diagnosis based on the natural frequency, it is difficult to set an appropriate vibration mode and determine the presence or absence of damage and its location, because the manner in which the natural frequency changes varies depending on the location of the damage and the vibration mode. In this regard, abnormality diagnosis using the Bayes factor according to this embodiment does not require the setting of a vibration mode, and can quantitatively detect abnormalities and damage that have occurred in the bridge.

[0117] (Temperature and Bayes factor values ​​over time) Figure 14 is a diagram showing the change over time in the outside temperature and Bayes Factor values ​​for a certain girder of bridge 4 over a certain period of time. Graph a in Figure 14 is a graph showing the change over time in the outside temperature over a certain period of time, and graph b is a graph showing the change over time in the Bayes Factor B of the outside temperature. The solid line in graph b in Figure 14 indicates the threshold for determining an anomaly in Bayes Factor B, and if this threshold is exceeded, it is determined to be an anomaly.

[0118] Fig. 14 shows an example of data on changes in outside air temperature of the girders of a bridge 4, where it has been confirmed that there is no abnormality in the structure itself. The outside air temperature fluctuates in a yearly cycle, but when this embodiment is applied to the outside air temperature, the abnormality determination determines that the change in the outside air temperature during the period for which an abnormality is to be determined is not abnormal. That is, Fig. 14 shows that this embodiment makes it possible to determine an abnormality in a structure by taking into account the presence or absence of the influence of periodic fluctuations that occur in nature, such as temperature changes.

[0119] (Changes in the deflection and Bayes factor values ​​of Bridge 4 over time) Figure 15 shows the changes over time in the deflection and Bayes Factor values ​​of a bridge over a certain period of time. Deflection is detected using a connecting pipe. In Figure 15, one year from April to March of the following year is taken as one fiscal year, and (graph a) shows the changes over time in deflection over a certain period, while (graph b) shows the changes over time in the Bayes Factor B of deflection. The solid line in (graph b) of Figure 15 indicates the threshold for determining an abnormality in Bayes Factor B, and if this threshold is exceeded, it is determined to be an abnormality. The threshold for determining an abnormality is determined based on measurement data for one year in the base year.

[0120] Although the temperature fluctuates throughout the year, as shown in (graph a) of Fig. 15, the judgment results according to this embodiment show that abnormalities are judged to exist during periods when the amount of deflection is large (for example, from September of the fourth year to January of the following year). It is also clear that abnormalities are judged to exist from the fifth year onwards.

[0121] (Comparison of changes in Bayes factor values ​​over time for two spans of a bridge) Figure 16 shows a comparison of the changes over time in the Bayes factor values ​​of two spans of a bridge. In Figure 16, the fiscal year is from May to April of the following year. Bridge 4, whose data is shown in Figure 16, is the same as Bridge 4, whose data is shown in Figure 15.

[0122] In (graph a) and (graph b) of Fig. 16, the result of abnormality judgment is calculated based on the acceleration measurement results at two different points (the damaged first span and the relatively less damaged second span) of the same bridge 4. In Fig. 16, the threshold is set based on one year's worth of measurement data in the base year. However, since the base year, 1st year, 2nd year, and 3rd year in Fig. 16 are different from those in Fig. 15, they are distinguished by notating them as, for example, 1st year in Fig. 15 and 1st year in Fig. 16.

[0123] In the abnormality judgment according to this embodiment, an abnormality in the damaged first span was detected in September of the first year in Fig. 16, and deterioration over time was detected thereafter. On the other hand, the second span, which was relatively less damaged, was judged to be normal except for temporary abnormal values, even in the year in which an abnormality was detected in the first span in Fig. 16. This result for the first span is the same as the period when the fluctuation in the amount of deflection became large shown in Fig. 15 (from the fourth and fifth years in Fig. 15), and therefore it is believed that appropriate abnormal values ​​can be judged.

[0124] (Modification of the second embodiment) In this embodiment, the diagnosis device 2 uses the coefficient matrix A or the principal component matrix A^ of the bridge 4 as a feature representing the state of the bridge 4, and calculates a Bayes factor B or a local Bayes factor B based on the feature. j In the above, the bridge abnormality diagnosis is performed using the above. However, the present invention is not limited to this, and feature quantities may be extracted from time-series data that continuously measures one or more physical quantities of each part of the structure, and the structure abnormality diagnosis may be performed using a Bayes factor based on these feature quantities. The physical quantities include displacement, speed, acceleration, external force, strain, temperature, etc. For example, the structure abnormality diagnosis may be performed using a Bayes factor based on feature quantities extracted from data for a predetermined period of time-series data obtained by fixed-point observation of the temperature of the bridge 4.

[0125] Furthermore, the diagnosis unit may correct the Bayes factor using the results of an on-site inspection of the bridge 4 by an inspection worker, and diagnose the condition of the bridge 4 based on the corrected Bayes factor. For example, if an abnormality is determined based on the Bayes factor of a certain feature, but no abnormality is found as a result of an on-site inspection, the Bayes factor is corrected so that the same feature will not be determined to be abnormal thereafter. Alternatively, if an abnormality is found as a result of an on-site inspection, the threshold may be set or corrected by referring to the Bayes factor based on a sensor installed in the vicinity of the part where the abnormality was detected.

[0126] (Effects of the second embodiment) In the second embodiment, the condition of the structure is diagnosed based on a Bayes factor, which is the ratio of the probability of a healthy state to an abnormal state calculated from the time series of observation data of the structure in each time domain, and a threshold value set based on damage states that inspection engineers with advanced expertise have previously determined to be abnormal. Therefore, even a person without advanced expertise can perform a highly accurate evaluation of the health of the structure using quantitative evaluation indices without the need for costly processing such as numerical analysis, in the same way as an inspection engineer with advanced expertise.

[0127] <Embodiment 3> In the third embodiment, in the first or second embodiment, the coefficient matrix A, which is a feature representing the state of the bridge 4, is sequentially learned using Bayesian estimation, thereby improving the accuracy of detecting anomalies in the bridge 4. The sequential learning of the coefficient matrix A may be performed by the sensor node 1 (e.g., the feature generating unit 113) or the diagnostic device 2 (e.g., the diagnostic unit 212). Note that the same effect can be obtained by performing the same processing using the principal component matrix A^ instead of the coefficient matrix A.

[0128] FIG. 17 is an explanatory diagram of sequential updating of the coefficient matrix A in the diagnostic system S of the third embodiment. In FIG. 17, the vertical axis indicates the acceleration detected by the sensor 3, and the horizontal axis indicates the time. The posterior probability p(A, Σ|Y) of the coefficient matrix A at time i shown in FIG. i is calculated using Bayesian estimation as shown in the following formula (15-1). Here, the prior probability p(A,Σ) at time i isi is the posterior probability p(A,Σ|Y) at time (i-1), as shown in the following equation (15-2). i-1 By replacing i with i+1 in the following equations (15-1) and (15-2), the posterior probability p(A,Σ|Y) of the coefficient matrix A at time (i+1) can be calculated in the same way. i+1 is required.

[0129]

number

[0130] (Effects of the Third Embodiment) FIG. 18 is a diagram showing the convergence of the probability distribution of the coefficient matrix by sequentially updating the coefficient matrix in the diagnosis system of the third embodiment. In FIG. 18, the horizontal axis represents the values ​​that the elements of the feature (for example, the coefficient matrix A) can take, and the vertical axis represents the posterior probability at each value of the element. In the third embodiment, by sequentially learning the probability distribution of the coefficient matrix A, as shown in FIG. 18, the average value of the probability distribution approaches the true value and converges in a direction in which the variance becomes smaller (the probability distribution shown in FIG. 18 converges from the thin line to the dashed line and then to the thick line), so that the coefficient matrix A represents the state of the structure with higher accuracy. Then, the diagnosis unit 212 diagnoses the state of the structure using the coefficient matrix A or the principal component matrix A^ after the sequential learning as a feature. Therefore, it is possible to improve the accuracy of the abnormality estimation of the state of the structure. Since the coefficient matrix A is a feature including various features of the vibration data of the structure, it is possible to capture a more minute change in the state of the structure and perform an abnormality determination than the conventional technology that performs an abnormality determination using the natural frequency or the like.

[0131] (Other embodiments) In the above-described embodiment, the diagnostic system S has been described as having the sensor node 1 and the diagnostic device 2, but the embodiment is not limited to this. For example, the diagnostic system S may be configured without having the diagnostic device 2. In such a case, the diagnostic system S is configured to include the sensor node 1 having an acquisition unit, an autoregressive model generation unit, a feature generation unit, and a diagnosis unit. That is, the sensor node 1 has an acquisition unit that acquires sensor information in a time series from a sensor attached to the structure, an autoregressive model generation unit that generates an autoregressive model that expresses the sensor information acquired by the acquisition unit at a certain time as a linear combination of the time series of sensor information acquired before the certain time, a feature generation unit that generates features indicative of the state of the structure at a certain time based on the regression coefficients of the autoregressive model, and a diagnosis unit that calculates an evaluation index for the features indicative of the state of the structure generated from the time series of information about the structure, which is the ratio between a first marginal likelihood that represents the probability distribution of the feature when it is assumed that the structure is in a healthy state and a second marginal likelihood that represents the probability distribution of the feature when it is assumed that the structure is in an unhealthy state, and diagnoses the state of the structure based on the evaluation index.

[0132] In the above embodiment, a case has been described in which a feature quantity indicating the state of a structure at a certain time is generated based on the regression coefficients of an autoregressive model, but the embodiment is not limited to this. For example, a feature quantity indicating the state of a structure may be generated from something other than the regression coefficients of an autoregressive model.

[0133] (Example of sensor node 1 implementation) 19 is a block diagram showing the configuration of a sensor node terminal 1B used as the sensor node 1 of the embodiment. The sensor node terminal 1B implemented as the sensor node 1 further includes an acceleration sensor 15, in comparison with the configuration of the sensor node 1 (FIG. 2). Such a sensor node terminal 1B exerts the same functions as the sensor node 1 and the sensor 3 by executing a predetermined application. That is, the sensor node terminal 1B is installed on the bridge 4 in the same way as the sensor 3, generates feature amounts of the bridge 4 from the acquired acceleration data, and transmits them to the diagnostic device 2.

[0134] The diagnostic device 2 is constructed on, for example, a cloud server, and provides diagnostic results based on feature quantities as a cloud service. The diagnostic device 2 transmits the diagnostic results to the sensor node terminal 1B or other terminal devices. The user checks the diagnostic results by viewing the screen output of the sensor node terminal 1B or other terminal devices.

[0135] Furthermore, multiple sensor node terminals 1B may be implemented as multiple sensor nodes 1 and installed at multiple locations on the bridge 4, similar to the sensors 3. In this case, a feature amount of the bridge 4 is generated from the acceleration data acquired by all of the multiple sensor node terminals 1B through independent processing of one sensor node terminal 1B representing the multiple sensor node terminals 1B or cooperative processing of a predetermined number of sensor nodes 1, and is transmitted to the diagnostic device 2.

[0136] The present invention is not limited to the above-described embodiments, and the configurations of each embodiment can be added, deleted, replaced, integrated, or distributed. The configurations and processes shown in the embodiments can be appropriately distributed, integrated, or replaced based on the efficiency of processing or implementation. The programs for executing the processes of the diagnostic system described in the above-described embodiments are installed in one or more computers via a recording medium or a transmission medium, or are provided as embedded programs. [Explanation of symbols]

[0137] S: diagnostic system, 1: sensor node, 2: diagnostic device, 3: sensor, 4: bridge, 111: sensor information acquisition unit, 112: autoregressive model generation unit, 113: feature generation unit, 114: feature transmission unit, 131: sensor information, 211: feature reception unit, 212: diagnostic unit, 231: feature, 232: reference evaluation index

Claims

1. a diagnosis unit that calculates an evaluation index, which is a ratio between a first marginal likelihood representing a probability distribution of a feature quantity indicating a state of a structure, generated from a time series of information about the structure, when it is assumed that the structure is in a healthy state, and a second marginal likelihood representing a probability distribution of the feature quantity when it is assumed that the structure is not in the healthy state, and diagnoses the state of the structure based on the evaluation index; an acquisition unit that acquires sensor information in time series from a plurality of sensors attached to the structure; an autoregressive model generation unit that generates an autoregressive model that expresses the sensor information acquired by the acquisition unit at a certain time as a linear combination of a time series of the sensor information acquired before the certain time; a feature generating unit that generates the feature indicating a state of the structure at the certain time based on a regression coefficient of the autoregressive model; a sensor node including the acquisition unit, the autoregressive model generation unit, the feature generation unit, and a transmission unit that transmits the feature generated by the feature generation unit to the diagnosis unit; The sensor information acquired from the plurality of sensors at each time point in the time series is a sensor information vector at each time point, the vector having an order equal to the number of the sensors; the autoregressive model expresses the sensor information vector acquired by the acquisition unit at the certain time as a linear combination of a time series of the sensor information vector acquired before the certain time, the regression coefficient is a matrix multiplied by each of the time series of the sensor information vectors linearly combined in the autoregressive model; The feature amount is information based on a coefficient matrix obtained by combining the matrices. A structural diagnostic system comprising:

2. The feature generation unit generates, as the feature, a principal component matrix of the coefficient matrix based on singular value decomposition of the coefficient matrix.

2. A structure diagnosis system according to claim 1.

3. The feature generating unit is The feature is generated by sequential learning, which repeats a process of using a posterior distribution obtained by Bayesian estimation with the probability distribution of the previously generated feature as a prior distribution as the probability distribution of the currently generated feature.

3. A structure diagnostic system according to claim 1 or 2.

4. A structure diagnosis system as described in any one of claims 1 to 3, characterized in that the feature includes at least one of information on the displacement, velocity, acceleration, mass, stiffness, and damping coefficient of the structure at the observation point of the feature.

5. The diagnosis unit corrects the evaluation index using an inspection result of an on-site inspection of the structure, and diagnoses a state of the structure based on the corrected evaluation index.

5. A structure diagnosis system according to claim 1, wherein the structure diagnosis system comprises:

6. The diagnosis unit diagnoses a state of the structure based on a comparison between the evaluation index and a threshold value; The threshold value is determined based on the average and variance of a plurality of measurement data of the structure over a predetermined period of time in the past.

6. A structure diagnosis system according to claim 1, wherein the structure diagnosis system comprises:

7. A plurality of the thresholds are determined based on the average and the variance; The diagnosing unit diagnoses a state of the structure based on a comparison between the evaluation index and a range based on a plurality of the threshold values.

7. A structure diagnostic system according to claim 6.

8. A structure diagnosis method executed by a structure diagnosis system, comprising: The structural diagnostic system includes: A sensor node including an acquisition unit, an autoregressive model generation unit, a feature generation unit, a transmission unit, and a diagnosis unit, The acquisition unit acquires sensor information in time series from a plurality of sensors attached to a structure, the autoregressive model generation unit generates an autoregressive model that expresses the sensor information acquired by the acquisition unit at a certain time as a linear combination of a time series of the sensor information acquired before the certain time; the feature generation unit generates a feature indicating a state of the structure at the certain time based on a regression coefficient of the autoregressive model; the transmission unit transmits the feature amount generated by the feature amount generation unit to the diagnosis unit; The diagnosing unit calculates an evaluation index, which is a ratio between a first marginal likelihood representing a probability distribution of the feature amount when it is assumed that the structure is in a healthy state and a second marginal likelihood representing a probability distribution of the feature amount when it is assumed that the structure is not in the healthy state, and diagnoses a state of the structure based on the evaluation index. Each process has The sensor information acquired from the plurality of sensors at each time point in the time series is a sensor information vector at each time point, the vector having an order equal to the number of the sensors; the autoregressive model expresses the sensor information vector acquired by the acquisition unit at the certain time as a linear combination of a time series of the sensor information vector acquired before the certain time, the regression coefficient is a matrix multiplied by each of the time series of the sensor information vectors linearly combined in the autoregressive model; The feature amount is information based on a coefficient matrix obtained by combining the matrices. A structure diagnosis method comprising:

9. Computer, a diagnosis unit that calculates an evaluation index, which is a ratio between a first marginal likelihood representing a probability distribution of a feature quantity indicating a state of the structure, generated from a time series of information about the structure, when it is assumed that the structure is in a healthy state, and a second marginal likelihood representing a probability distribution of the feature quantity when it is assumed that the structure is not in the healthy state, and diagnoses the state of the structure based on the evaluation index; an acquisition unit that acquires sensor information in time series from a plurality of sensors attached to the structure; an autoregressive model generation unit that generates an autoregressive model that expresses the sensor information acquired by the acquisition unit at a certain time as a linear combination of a time series of the sensor information acquired before the certain time; a feature generating unit that generates the feature indicating a state of the structure at the certain time based on a regression coefficient of the autoregressive model; a sensor node including the acquisition unit, the autoregressive model generation unit, the feature generation unit, and a transmission unit that transmits the feature generated by the feature generation unit to the diagnosis unit. It is a structural diagnostic program to function as a The sensor information acquired from the plurality of sensors at each time point in the time series is a sensor information vector at each time point, the vector having an order equal to the number of the sensors; the autoregressive model expresses the sensor information vector acquired by the acquisition unit at the certain time as a linear combination of a time series of the sensor information vector acquired before the certain time, the regression coefficient is a matrix multiplied by each of the time series of the sensor information vectors linearly combined in the autoregressive model; The feature amount is information based on a coefficient matrix obtained by combining the matrices. A structure diagnosis program comprising:

Images