Deterioration detection device, deterioration detection system, deterioration detection method, weight measurement device, weight measurement method, and program

Abstract

To continuously detect deterioration in a bridge.SOLUTION: A deterioration detection device comprises: an acquisition unit for collecting time series data pertaining to a parameter that represents a travel-direction site on a subject portion of a bridge where a sensor is provided; an extraction unit for extracting, from the time series data, specific portion data from a time when a specific vehicle passes through a measured segment of the bridge on the basis of an assessment result indicating whether the specific vehicle has passed by, the assessment being made by a neural network that outputs the assessment result upon receiving input of the time series data; an amplitude calculation unit for calculating, on the basis of the specific portion data, an amplitude value pertaining to the amount of travel-direction expansion and contraction of the bridge at the time when the specific vehicle passes by; a deterioration assessment unit for assessing that the bridge has deteriorated when the amplitude value is greater than a preset criterion value; and a re-training command unit for determining whether to re-train the neural network on the basis of pre-established determination criteria, and outputting a re-training command that commands re-training of the neural network on the basis of the result of the determination as to whether to re-train the neural network.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to a deterioration detection device, a deterioration detection system, a deterioration detection method, a weight measurement device, a weight measurement method, and a program. [Background technology]

[0002] Traditionally, bridges have been visually inspected about once every five years. To further improve bridge safety, it is desirable to monitor bridges constantly, predict their future condition based on the results of the monitoring, and manage bridges systematically.

[0003] Patent Document 1 describes a technology that uses a strain gauge to measure the strain of a bridge deck when a vehicle passes over a bridge and detects the characteristics of the passing vehicle based on the measured strain. Patent Document 2 describes a technology that calculates the vehicle's axle ratio from the strain waveform measured by a strain gauge and compares the calculated axle ratio with the axle ratio registered in a database to identify the vehicle's wheelbase, speed, and vehicle type. Patent Document 3 describes a technology that calculates a provisional axle load value of a vehicle based on the strain of longitudinal ribs and transverse ribs when the vehicle passes over, and corrects the provisional axle load value using the vehicle weight value calculated based on the strain of the transverse ribs. Patent Document 4 describes a technology that detects the strain of a bridge deck when a vehicle passes over a bridge and calculates the vehicle's weight based on the detected strain. Non-Patent Document 1 describes a technology that installs an acceleration sensor under the rear wheel springs of a route bus to calculate the bridge's deflection characteristics. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-084404 [Patent Document 2] Japanese Patent Application Laid-Open No. 2009-237805 [Patent Document 3] Japanese Patent Application Laid-Open No. 2014-228480 [Patent Document 4] Japanese Patent Application Laid-Open No. 2017-106769 [Non-patent literature]

[0005] [Non-Patent Document 1] Fumio Miyamoto et al., "Demonstration Experiment of a Small and Medium-sized Bridge Monitoring System Using Route Buses," Yamaguchi University Faculty of Engineering Research Report, Vol. 66 No. 2, March 2015 Summary of the Invention [Problem to be solved by the invention]

[0006] As bridge deterioration progresses, strain increases when vehicles pass over the bridge. However, it is difficult to easily and continuously measure the degree of bridge strain due to deterioration without relying on personnel.

[0007] Another approach to bridge monitoring is to use a model that outputs values corresponding to multiple input values. However, bridge deterioration detection requires long-term monitoring, typically over several years. As a result, a divergence between the bridge characteristics and the model characteristics occurs over long periods of operation, making it impossible to accurately detect bridge deterioration.

[0008] The present invention has been made in consideration of the above, and aims to provide a deterioration detection device, a deterioration detection system, a deterioration detection method, a weight measuring device, a weight measuring method, and a program that can accurately detect bridge deterioration over a long period of time. [Means for solving the problem]

[0009] In order to solve the above-mentioned problems and achieve the object, the deterioration detection device of the present invention comprises an acquisition unit that collects time series data of parameters that represent displacement in the target portion of the bridge where the sensor is installed from a sensor installed on the bridge; an extraction unit that extracts specific portion data from the time series data when the specific vehicle passes through the measurement section of the bridge based on the judgment result obtained by a neural network that inputs the time series data and outputs a judgment result indicating whether the specific vehicle has passed; an amplitude calculation unit that calculates, based on the specific portion data, an amplitude value of the amount of expansion and contraction in the target portion of the bridge when the specific vehicle passes through; and a deterioration determination unit that determines that the bridge has deteriorated if the amplitude value is greater than a predetermined reference value. [Effects of the Invention]

[0010] According to the present invention, deterioration of a bridge can be detected with high accuracy over a long period of time. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing a deterioration detection system according to the first embodiment. [Figure 2] Figure 2 shows the layout of sensors when the bridge is viewed from the side. [Figure 3] FIG. 3 shows the layout of sensors when the bridge is viewed from above. [Figure 4] FIG. 4 is a diagram showing a sensor and a portion of the main girder of a bridge. [Figure 5] FIG. 5 is a diagram showing the displacement detection device together with the first member and the second member. [Figure 6] FIG. 6 is a diagram illustrating the functional configuration of the deterioration detection device. [Figure 7] FIG. 7 is a diagram showing an example of time-series data of the amount of expansion and contraction in the traveling direction when a route bus passes over a bridge. [Figure 8] FIG. 8 is a diagram showing the change over time of the amplitude value and the error range. [Figure 9]FIG. 9 is a diagram showing changes in amplitude values over time and threshold values for re-learning the first neural network. [Figure 10] FIG. 10 is a diagram illustrating a functional configuration of a deterioration detection device according to a modified example. [Figure 11] FIG. 11 is a flowchart showing the flow of processing by the deterioration detection device. [Figure 12] FIG. 12 is a diagram showing a weight measurement system according to the second embodiment. [Figure 13] FIG. 13 is a diagram illustrating the functional configuration of the weight measuring device. [Figure 14] FIG. 14 is a diagram showing the relationship between the amplitude value and the weight of the test vehicle. [Figure 15] FIG. 15 is a flowchart showing the flow of the process of correcting the related information by the weight measuring device. [Figure 16] FIG. 16 is a diagram illustrating the hardware configuration of the deterioration detection device and the weight measurement device. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment will be described with reference to the drawings.

[0013] (First embodiment) 1 is a diagram showing a deterioration detection system 10 according to the first embodiment. The deterioration detection system 10 outputs alarm information when a bridge deteriorates.

[0014] The deterioration detection system 10 includes a sensor 20 , a transmitting device 22 , and a deterioration detection device 30 .

[0015] The sensor 20 is installed at a predetermined target portion of the bridge. The sensor 20 detects a parameter that indicates displacement in the traveling direction at the target portion of the bridge where the sensor 20 is installed. In this embodiment, the sensor 20 measures the amount of expansion and contraction in the traveling direction at the target portion of the bridge. The amount of expansion and contraction is, for example, a change in distance of several nanometers to several hundred nanometers between two points that are several tens of centimeters apart.

[0016] Note that the sensor 20 may detect a physical quantity other than the expansion / contraction amount in the traveling direction, as long as it can detect a parameter representing displacement in the traveling direction. For example, the sensor 20 may be a strain meter that detects strain in the traveling direction of a target portion of a bridge. Also, for example, the sensor 20 may be a vibrometer that detects the magnitude of the natural frequency in the traveling direction of a target portion of the bridge or the magnitude of the natural frequency in the vertical direction of a target portion of the bridge.

[0017] The sensor 20 continuously detects a parameter representing a displacement of a target portion of the bridge in the traveling direction at predetermined time intervals. For example, the sensor 20 detects the parameter every few milliseconds. The sensor 20 continuously detects the parameter at predetermined time intervals, for example, while the power is on. The sensor 20 may continuously detect the parameter at predetermined time intervals at all times, for example, 24 hours a day.

[0018] The transmitting device 22 transmits the parameters detected by the sensor 20 to the deterioration detection device 30 via a network. The network may be wired, wireless, or a combination of wired and wireless. The network may be, for example, a local area network (LAN), a virtual private network (VPN), or a wide area network (WAN) in which LANs are connected via a router. The network may also include the Internet or a telephone communication line.

[0019] The deterioration detection device 30 receives time-series data of parameters that represent the displacement of a target portion of the bridge in the traveling direction, transmitted from the transmission device 22 via the network. The deterioration detection device 30 determines whether the bridge has deteriorated based on the received time-series data of the parameters. If the deterioration detection device 30 determines that the bridge has deteriorated, it outputs alarm information to, for example, an administrator or an information processing device held by the administrator.

[0020] The deterioration detection device 30 is a computer such as a server device that can be connected to a network. The deterioration detection device 30 may be a single computer, or may be configured by multiple computers like a cloud system.

[0021] The deterioration detection system 10 may be configured without the transmission device 22. In this case, the deterioration detection device 30 acquires parameters representing the displacement of the target portion of the bridge in the traveling direction directly from the sensor 20. In this case, the deterioration detection device 30 may be provided near the sensor 20, i.e., near the bridge.

[0022] FIG. 2 is a diagram showing the arrangement of the sensor 20 when the bridge is viewed from the side. FIG. 3 is a diagram showing the arrangement of the sensor 20 when the bridge is viewed from above. The sensor 20 is attached, for example, closer to the end of the bridge than the center in the travel direction. The sensor 20 is attached, for example, on the underside of the bridge, near the abutment. This allows workers to easily attach the sensor 20 to the bridge even after the bridge is completed. The sensor 20 may be attached at any position in the travel direction of the bridge. For example, the sensor 20 may be attached to the center of the bridge in the travel direction, although this may make installation more difficult for workers.

[0023] 4 is a diagram showing the sensor 20 and a portion of the bridge's main girder 54. The sensor 20 measures the change in distance between a first point 62 and a second point 64 on the underside 56 of the bridge's main girder 54 as the amount of expansion and contraction in the direction of travel.

[0024] The first point 62 and the second point 64 are at the same position in the width direction of the bridge but at different positions in the traveling direction. The distance between the first point 62 and the second point 64 is, for example, several tens of centimeters. In the example of FIG. 4, the distance between the first point 62 and the second point 64 is 35 centimeters. The sensor 20 measures the change in the distance in the traveling direction between the first point 62 and the second point 64 in units of, for example, several nanometers to several hundred nanometers.

[0025] The sensor 20 includes a first member 66, a second member 68, and a displacement detection device .

[0026] The first member 66 is a cantilever beam having a support portion 66a and a beam portion 66b. One end of the support portion 66a is a fixed end 66c fixed to the first point 62. The support portion 66a extends a predetermined distance downward from the first point 62 in a direction perpendicular to the underside 56 of the main girder 54. The beam portion 66b extends a predetermined distance from the end of the support portion 66a opposite the fixed end 66c toward the second point 64 in the running direction. The end of the beam portion 66b not connected to the support portion 66a is a free end 66d that is not connected to any member. In this embodiment, the free end 66d of the first member 66 is located near the approximate center of the line connecting the first point 62 and the second point 64.

[0027] The second member 68 is a cantilever beam having a support portion 68a and a beam portion 68b. One end of the support portion 68a is a fixed end 68c that is fixed to the second point 64. The support portion 68a extends a predetermined distance downward from the second point 64 in a direction perpendicular to the underside 56 of the main girder 54. The beam portion 68b extends a predetermined distance from the end of the support portion 68a opposite the fixed end 68c toward the first point 62 in the running direction. The end of the beam portion 68b that is not connected to the support portion 68a is a free end 68d that is not connected to any member. In this embodiment, the free end 68d of the second member 68 is located near the approximate center of the line connecting the first point 62 and the second point 64.

[0028] Here, the free end 66d of the first member 66 and the free end 68d of the second member 68 are positioned so as to overlap in the running direction without mechanical interference. As a result, the free end 66d of the first member 66 and the free end 68d of the second member 68 are positioned so as to face each other in a direction perpendicular to the underside 56 of the main girder 54. When the distance between the first point 62 and the second point 64 changes, the relative positions of the free end 66d of the first member 66 and the free end 68d of the second member 68 shift in the running direction.

[0029] In the sensor 20 shown in FIG. 4, both the first member 66 and the second member 68 are cantilevers. However, the second member 68 may be a cantilever and the first member 66 may not be a cantilever. In this case, the second member 68 is positioned so that its free end 68d overlaps with at least a portion of the first member 66 in the traveling direction without mechanically interfering with it. Even with this configuration, if the distance between the first point 62 and the second point 64 changes, the relative positions of the first member 66 and the free end 68d of the second member 68 will shift in the traveling direction.

[0030] The displacement detection device 70 is provided at a portion where the free end 66d of the first member 66 and the free end 68d of the second member 68 face each other. The displacement detection device 70 detects the displacement of the relative position between the free end 66d of the first member 66 and the free end 68d of the second member 68. The displacement detection device 70 then outputs the detected displacement as the amount of expansion and contraction between two points on the bridge in the traveling direction.

[0031] 5 is a diagram showing the displacement detection device 70 together with the first member 66 and the second member 68. The displacement detection device 70 includes an optical element 72 and a detector 74.

[0032] The optical element 72 is attached to one of the free end 66d of the first member 66 or the free end 68d of the second member 68. The detector 74 is attached to the other of the free end 66d of the first member 66 or the free end 68d of the second member 68 to which the optical element 72 is not attached.

[0033] The optical element 72 is an optical member whose reflected or transmitted light amount changes depending on the position of the light incident on it in the traveling direction. For example, the optical element 72 is a mirror whose surface is coated with a plurality of light-absorbing materials at predetermined intervals in the traveling direction. Alternatively, the optical element 72 may be a diffraction grating in which a plurality of optical slits are formed at predetermined intervals in the traveling direction.

[0034] The detector 74 includes a half mirror 76, a light emitting section 78, a light receiving section 80, and a detection circuit 82. The half mirror 76 reflects a part of the irradiated light and transmits the other part.

[0035] The light-emitting unit 78 irradiates the optical element 72 with light via the half mirror 76. The light-receiving unit 80 receives the light reflected by the optical element 72 via the half mirror 76. The detection circuit 82 outputs a signal representing the displacement of the relative position between the first member 66 and the second member 68 as the amount of expansion / contraction based on the change in the amount of light detected by the light-receiving unit 80.

[0036] The position of the light irradiated onto the optical element 72 shifts in the traveling direction depending on the shift in the relative positions of the first member 66 and the second member 68 in the traveling direction. Because the optical element 72 has a plurality of light-absorbing materials or a plurality of optical slits aligned in the traveling direction, the amount of light reflected from the optical element 72 increases or decreases depending on the shift in the traveling direction of the light irradiation position. Specifically, the amount of light reflected from the optical element 72 increases or decreases by one cycle when the position of the light irradiated onto the optical element 72 shifts by the spacing of the aligned light-absorbing materials or the plurality of optical slits. Therefore, for example, the detection circuit 82 can obtain the amount of change in the relative position between the first member 66 and the second member 68 by counting the increase or decrease in the signal output from the light-receiving unit 80.

[0037] Furthermore, the displacement detection device 70 may include two optical elements 72 that are shifted from each other by a quarter period with respect to the pitch of the light absorbing material or optical slit, and two light-emitting units 78 and two light-receiving units 80 that correspond to the two optical elements 72. This allows the two light-receiving units 80 to output two periodic signals that are shifted in phase by a quarter period in response to changes in the relative position between the first member 66 and the second member 68. Therefore, for example, the detection circuit 82 can detect, based on the values of the two signals, the direction of change in the relative position between the first member 66 and the second member 68 and the amount of change in the relative position between the first member 66 and the second member 68 at an interval shorter than the stripe period.

[0038] 5, the optical element 72 is configured to reflect light. Alternatively, the optical element 72 may be configured to transmit light. In this case, the amount of light transmitted through the optical element 72 changes depending on the position of the light irradiated in the traveling direction. For example, the optical element 72 may be made of glass or plastic, etc., with a surface coated with a plurality of light-absorbing materials at predetermined intervals in the traveling direction. In such a case, the light receiving unit 80 receives light that has transmitted through the optical element 72.

[0039] The detector 74 may not include the half mirror 76. Here, the detector 74 is provided on the first member 66. The optical element 72 is provided on the second member 68. The position on the first member 66 facing the center of the optical element 72 in the width direction is designated as P. In this case, the light-emitting unit 78 is disposed on the first member 66 at a position offset from P by a predetermined distance in the width direction. The light-receiving unit 80 is disposed at a position offset from P on the opposite side of the light-emitting unit 78 in the width direction by a predetermined distance. The light-emitting unit 78 emits light toward the center of the optical element 72 in the width direction. The light from the light-emitting unit 78 is incident on the optical element 72 at a predetermined angle, and the optical element 72 reflects the incident light toward the light-receiving unit 80. The light-receiving unit 80 receives the light reflected by the optical element 72. Such a detector 74 can have the same function as the configuration shown in FIG. 5.

[0040] The displacement detection device 70 configured in this way can be attached to the underside 56 of the main girder 54 of a bridge. For example, the displacement detection device 70 can be attached from the outside, without embedding an expansion member in the bridge as in the case of a strain gauge. This allows the displacement detection device 70 to be attached to a bridge after it has been completed. Furthermore, the displacement detection device 70 can be attached without reducing the strength of the bridge. Furthermore, the displacement detection device 70 can be easily maintained even after it has been installed.

[0041] Furthermore, the displacement detection device 70 configured as described above uses a cantilever beam to detect changes in distance between two points with an optical sensor. This allows the displacement detection device 70 to accurately detect very small expansion and contraction of a bridge using simple and inexpensive components.

[0042] 6 is a diagram showing the functional configuration of the deterioration detection device 30. The deterioration detection device 30 includes an acquisition unit 112, a time-series data storage unit 114, a clipping unit 116, an extraction unit 118, an amplitude calculation unit 120, a deterioration determination unit 122, an alarm output unit 124, a collection unit 132, a relearning data storage unit 134, a relearning instruction unit 136, and a relearning unit 138.

[0043] The acquisition unit 112 collects time series data of a parameter that indicates displacement in the traveling direction at the target portion of the bridge where the sensor 20 is installed, from the sensor 20 installed on the bridge. In this embodiment, the acquisition unit 112 acquires the time series data of the parameter via a network. In this embodiment, the parameter is the amount of expansion or contraction in the traveling direction at the target portion. The time series data of the parameter associates the detected time with the parameter.

[0044] The time-series data storage unit 114 stores the time-series data of the parameters collected by the acquisition unit 112.

[0045] The cutout unit 116 divides the time-series data of the parameters stored in the time-series data storage unit 114 into units of a predetermined time length to cut out partial data. The cutout unit 116 then sequentially supplies the cut-out partial data one by one to the extraction unit 118. The time length of the partial data is at least longer than the time from when a change in the expansion / contraction amount in the traveling direction starts as a result of a specific vehicle passing through the measurement section of the bridge to when the change ends.

[0046] The partial data is data of a predetermined number of samples. More specifically, the partial data is data of a number of samples to be input to the first neural network used in the extraction unit 118. In this embodiment, the extraction unit 116 extracts overlapping portions of two partial data adjacent in the time direction. That is, each partial data overlaps with the latter half of the partial data immediately preceding it and the former half of the partial data immediately following it. For example, the first half of each partial data may be the same as the latter half of the partial data immediately preceding it. Furthermore, the latter half of each partial data may be the same as the first half of the partial data immediately following it. In this way, when a specific vehicle passes over a bridge, the extraction unit 116 can include, in one of the plurality of partial data, the entire period from when the change in the expansion / contraction amount in the bridge's traveling direction due to the specific vehicle passing over the bridge begins to when the change ends.

[0047] The extraction unit 118 extracts specific partial data, which is partial data when a specific vehicle passed through a bridge, from the time-series data of parameters stored in the time-series data storage unit 114 based on the determination result by the first neural network. The first neural network inputs the target partial data and determines whether the specific vehicle passed through the measurement section in the target partial data. The first neural network acquires time-series data obtained when the specific vehicle passed through a bridge in advance and learns using the previously acquired time-series data as training data. In this embodiment, the first neural network is a convolutional neural network (CNN). By using the convolutional neural network, the extraction unit 118 can accurately detect that the specific vehicle has passed through a bridge, regardless of which time portion of the partial data contains data obtained when the specific vehicle passed through a bridge. Then, in response to the determination result obtained by the first neural network that the specific vehicle has passed through a bridge, the extraction unit 118 outputs the partial data input to the first neural network as specific partial data.

[0048] A specific vehicle is, for example, a vehicle that periodically passes over a bridge, passing over the bridge at approximately the same speed and weight each time. For example, a specific vehicle is a route bus. Route buses run according to a predetermined timetable each day. Therefore, route buses are scheduled to pass over a bridge at a predetermined time each day. Another specific vehicle may be, for example, a garbage truck. The route and time that a garbage truck travels are predetermined. Therefore, the garbage truck is scheduled to pass over a bridge at a predetermined time on a garbage collection day.

[0049] Each time the extraction unit 118 extracts specific partial data, the amplitude calculation unit 120 calculates, based on the extracted specific partial data, an amplitude value of the expansion / contraction amount of the bridge in the traveling direction when a specific vehicle passes. For example, when the parameter represents the expansion / contraction amount of the target portion, the amplitude calculation unit 120 calculates the difference between the maximum value and the minimum value of the extracted specific partial data as the amplitude value.

[0050] If the parameter is not the amount of expansion or contraction of the target portion, the amplitude calculation unit 120 may output a value correlated with the amplitude value of the amount of expansion or contraction of the target portion. For example, if the parameter is the magnitude of the natural frequency, the amplitude calculation unit 120 may calculate the difference between the maximum value and the minimum value in the extracted specific portion data as the amplitude value.

[0051] The deterioration determination unit 122 compares the calculated amplitude value with a preset reference value every time the amplitude calculation unit 120 calculates an amplitude value. If the amplitude value is greater than the reference value, the deterioration determination unit 122 determines that the bridge has deteriorated.

[0052] The deterioration determination unit 122 may calculate a moving average value of the amplitude values of a predetermined number of recent samples, and determine that the bridge has deteriorated when the moving average value is greater than a reference value. Alternatively, the deterioration determination unit 122 may perform a predetermined filtering process, such as a noise removal process, on the amplitude values of a plurality of samples, and determine that the bridge has deteriorated when the result of the filtering process is greater than a reference value. Note that a plurality of different reference values may be set in advance for the deterioration determination unit 122. Then, the deterioration determination unit 122 may determine that the bridge has deteriorated each time the amplitude value becomes greater than each reference value.

[0053] When it is determined that the bridge has deteriorated, the alarm output unit 124 outputs alarm information indicating that the bridge has deteriorated. Note that, when a plurality of different reference values are set in advance in the deterioration determination unit 122, the alarm output unit 124 may acquire alarm information including level information indicating the magnitude of the reference value each time the amplitude value becomes larger than each reference value. In this way, the alarm output unit 124 can notify the administrator or the like of the level of deterioration of the bridge.

[0054] The collection unit 132 collects the extracted specific partial data every time the extraction unit 118 extracts specific partial data. The re-learning data storage unit 134 stores the specific partial data collected by the collection unit 132.

[0055] Re-learning instruction unit 136 determines whether to re-learn the first neural network based on predetermined criteria, and outputs a re-learning instruction to instruct the first neural network to be re-learned based on the result of the determination of whether to re-learn the first neural network. For example, re-learning instruction unit 136 determines whether to re-learn the first neural network based on predetermined criteria every time amplitude calculation unit 120 calculates an amplitude value.

[0056] When a relearning instruction is output from relearning instruction unit 136, relearning unit 138 re-learns the first neural network using the specific partial data collected by collection unit 132 as training data. That is, relearning unit 138 re-learns the first neural network that has already been trained. For example, relearning unit 138 may perform relearning using a backpropagation algorithm or the like, with network parameters such as weights and biases set immediately before relearning as initial values, or may perform relearning using a backpropagation algorithm or the like, after changing the network parameters set immediately before relearning to random values or predetermined values.

[0057] The re-learning unit 138 re-learns the first neural network using the specific partial data collected after the last re-learning as training data. If re-learning has not yet been performed since the start of the deterioration assessment, the re-learning unit 138 may re-learn the first neural network using the specific partial data collected after the start as training data. This allows the re-learning unit 138 to re-train the first neural network so as to perform appropriate assessment processing according to the nearest bridge condition. Note that the re-learning unit 138 may re-learn the first neural network using time-series data collected in advance as training data in addition to the specific partial data collected by the collection unit 132.

[0058] 7 is a diagram showing an example of time-series data of the amount of expansion and contraction in the traveling direction when a route bus passes over a bridge. When the vehicle passes over a bridge, the bridge expands in the traveling direction, expands to a maximum value, then contracts, contracts to a minimum value, and then returns to its original state.

[0059] When vehicles of the same type pass over a bridge with approximately the same weight and speed, the waveforms of the expansion and contraction amounts of the target portion of the bridge will be approximately the same if the bridge has the same level of deterioration. For example, when vehicles of the same type pass over a bridge with approximately the same weight and speed, the amplitude value (difference between the maximum and minimum values) of the expansion and contraction amount waveform and the change time (the period from the start time of the change to the end time of the change) will be approximately the same if the bridge has the same level of deterioration. Note that FIG. 7 shows an example in which sensor 20 is installed at the end of the bridge on the vehicle's approach side. Sensor 20 may also be installed at the end of the bridge on the vehicle's exit side. In this case, the bridge changes in the opposite direction to that shown in FIG. 7. That is, in this case, the bridge contracts relative to the direction of travel, contracts to its minimum value, then expands, expands to its maximum value, and then returns to its original state.

[0060] FIG. 8 is a diagram showing changes in amplitude values over time and error ranges of amplitude values.

[0061] Bridges deteriorate over time. As bridge deterioration progresses, the amplitude of the expansion / contraction increases even when the same type of vehicle passes over the bridge with approximately the same weight and speed. In other words, when the same type of vehicle passes over the bridge with approximately the same weight and speed, the amplitude of the expansion / contraction of the target portion of the bridge increases over time.

[0062] Furthermore, even when the same type of vehicle passes over a bridge at approximately the same weight and speed, errors will occur in the amplitude value of the expansion / contraction amount depending on the surrounding environment and measurement conditions. Furthermore, if the specific vehicle is a route bus, the number of passengers and passing speed will also vary from day to day. The amplitude value of the expansion / contraction amount calculated when a specific vehicle passes over a bridge will also include errors due to weight and passing speed.

[0063] However, for example, referring to the experimental results in Non-Patent Document 1, it is predicted that the amount of change in amplitude value due to aging of the bridge is much larger than the error distribution range of the amplitude value calculated when a route bus passes over the bridge, as shown in Figure 8. Therefore, if the amplitude value of the expansion / contraction amount of the target section becomes larger than a preset reference value when a specific vehicle such as a route bus passes over the bridge, and the reference value is set to be much larger than the error distribution range of the amplitude value at the start of measurement, it can be said that the bridge has deteriorated since the start of measurement.

[0064] Therefore, the deterioration detection device 30 can determine that the bridge has deteriorated if the amplitude value of the expansion and contraction amount in the traveling direction of the bridge when a specific vehicle passes becomes larger than a reference value.

[0065] FIG. 9 is a diagram showing changes in amplitude values over time and threshold values for re-learning the first neural network.

[0066] When the data input to a machine learning model changes over time, neural networks have the problem of their accuracy deteriorating over long periods of operation. This is thought to be due to a discrepancy between the situation when the neural network was trained and the situation after a long period of time has passed. For this reason, neural networks are retrained if their prediction accuracy deteriorates. However, it is difficult to determine the extent to which prediction accuracy has deteriorated during operation.

[0067] When a bridge deteriorates, the amplitude value of the expansion / contraction amount of the bridge in the traveling direction when a vehicle passes increases over time. Therefore, it is considered that the accuracy of the first neural network to which the expansion / contraction amount of the bridge in the traveling direction is input will deteriorate in accordance with the change in the amplitude value of the expansion / contraction amount. Therefore, the re-learning instruction unit 136 outputs a re-learning instruction, for example, when the amplitude value of the expansion / contraction amount of the bridge in the traveling direction becomes larger than a threshold value.

[0068] This allows the deterioration detection device 30 to appropriately determine when to re-train the first neural network without determining the degree to which the prediction accuracy has deteriorated. Therefore, the deterioration detection device 30 can accurately detect bridge deterioration over a long period of time.

[0069] For example, the relearning instruction unit 136 is set with one or more thresholds that are different from each other. The one or more thresholds are values between an initial value, which is the amplitude value at the start of the deterioration assessment, and a reference value for determining that the bridge has deteriorated. In this case, the relearning instruction unit 136 outputs a relearning instruction every time the amplitude value calculated by the amplitude calculation unit 120 becomes larger than one or more thresholds. Alternatively, the relearning instruction unit 136 may calculate a moving average of the amplitude values of a predetermined number of recent samples, and output a relearning instruction every time the moving average becomes larger than one or more thresholds.

[0070] Furthermore, if multiple different reference values are set in advance and the deterioration determination unit 122 determines that the bridge has deteriorated each time the amplitude value exceeds a corresponding reference value, the relearning instruction unit 136 may set each of the multiple different reference values to the threshold value. In this case, the relearning instruction unit 136 may further set one or more threshold values between the reference values.

[0071] Furthermore, for example, if the calculated amplitude value changes according to a predetermined pattern, the relearning instruction unit 136 may determine that the neural network should be relearned and output a relearning instruction. For example, the relearning instruction unit 136 outputs a relearning instruction if the amplitude value calculated by the amplitude calculation unit 120 has changed beyond a predetermined range since the last relearning. Note that if relearning has not yet been performed since the start of the deterioration determination, the relearning instruction unit 136 outputs a relearning instruction if the amplitude value calculated by the amplitude calculation unit 120 has changed beyond a predetermined range since the start.

[0072] For example, the relearning instruction unit 136 may output a relearning instruction when the amplitude value calculated by the amplitude calculation unit 120 has changed by a predetermined percentage since the start or the last relearning. In this case, the relearning instruction unit 136 may output a relearning instruction when the amplitude value has changed by more than a predetermined percentage in the increasing direction, or when the amplitude value has changed by more than a predetermined percentage in the decreasing direction.

[0073] The relearning instruction unit 136 may output a relearning instruction when a predetermined time has elapsed since the last relearning. If relearning has not yet been performed since the start of the deterioration determination, the relearning instruction unit 136 outputs a relearning instruction when a predetermined time has elapsed since the start.

[0074] FIG. 10 is a diagram showing the functional configuration of a deterioration detection device 30 according to a modified example.

[0075] The deterioration detection device 30 may further include one or more of a passage time acquisition unit 142, a passage detection information acquisition unit 144, a scheduled time estimation unit 146, a date acquisition unit 148, a passage speed acquisition unit 152, and a weight acquisition unit 154.

[0076] If the specific vehicle is scheduled to pass over the bridge at the same first time every day, the passing time acquisition unit 142 acquires information indicating the first time, which is the passing time of the specific vehicle, from an external device or the like. For example, if the specific vehicle is a route bus, route bus timetable information or the like may be acquired and the first time may be calculated based on the acquired timetable information. Then, when the passing time acquisition unit 142 acquires the first time, the extraction unit 118 extracts specific partial data from the parameter time-series data based on the acquired first time. For example, the extraction unit 118 extracts a predetermined time range before and after the first time from the parameter time-series data and extracts specific partial data from the extracted range. As a result, the extraction unit 118 only needs to perform extraction processing on partial data for a portion of the time period in the parameter time-series data, thereby enabling accurate extraction of specific partial data with a small amount of processing.

[0077] The passage detection information acquisition unit 144 acquires a detection signal detected by a passage detection device that detects that a specific vehicle is passing through a bridge. For example, the passage detection device acquires image data from a camera that captures images of vehicles passing through a bridge and analyzes the acquired image data to determine whether the specific vehicle is passing through the bridge. If the passage detection device determines that the specific vehicle is passing through the bridge, it provides a detection signal indicating that the specific vehicle is passing through the bridge to the deterioration detection device 30. Furthermore, for example, the passage detection device may be a receiving device that receives identification information identifying the specific vehicle via a wireless signal from a wireless communication device provided in the specific vehicle. In this case, the passage detection device is provided near the bridge, and upon receiving identification information from the specific vehicle, it provides a detection signal indicating that the specific vehicle is passing through the bridge to the deterioration detection device 30.

[0078] Then, when the passage detection information acquisition unit 144 receives detection information indicating that a specific vehicle is passing over a bridge from the passage detection device, it provides time information indicating the time at which the detection information was received to the extraction unit 118. The extraction unit 118 extracts specific partial data from the parameter time-series data based on the received time information. For example, the extraction unit 118 extracts a predetermined time range before and after the time indicated in the received time information from the parameter time-series data, and extracts specific partial data from the extracted range. As a result, the extraction unit 118 only needs to perform extraction processing on partial data during a partial time period in the parameter time-series data, and therefore can extract specific partial data with high accuracy and a small amount of processing.

[0079] The scheduled time estimation unit 146 acquires passage information indicating that a specific vehicle has passed a predetermined first position. For example, if the specific vehicle is a route bus, the first position is a bus stop immediately before a bridge on the bus route or a specific bus stop. If the specific vehicle is a route bus, the scheduled time estimation unit 146 receives passage information indicating that the specific vehicle has passed the first position. The passage information is transmitted, for example, from a transmitter provided at a bus stop, a transmitter provided on the route bus, or a management device that manages route bus operation information.

[0080] When the passing information is received, the scheduled time estimation unit 146 estimates the scheduled time when the specific vehicle will pass the bridge based on the passing information and the predicted traveling time of the specific vehicle from the first position to the bridge. For example, the scheduled time estimation unit 146 calculates the scheduled time by adding the predicted traveling time to the time when the passing information is received.

[0081] Then, the scheduled time estimation unit 146 provides the estimated scheduled time to the extraction unit 118. The extraction unit 118 extracts specific partial data from the time-series data of parameters based on the received scheduled time. For example, the extraction unit 118 extracts a predetermined time range before and after the time indicated by the scheduled time from the time-series data of parameters, and extracts specific partial data from the extracted range. As a result, the extraction unit 118 only needs to perform extraction processing on partial data in a partial time period in the time-series data of parameters, and can extract specific partial data with high accuracy and a small amount of processing.

[0082] The date acquisition unit 148 acquires date information indicating a preset date. The date acquisition unit 148 may acquire a day of the week as the date. In this case, the specific vehicle is a vehicle that is scheduled to pass the bridge at the same time every day. The date acquisition unit 148 provides the acquired date information to the amplitude calculation unit 120.

[0083] When date information is acquired, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from the time-series data for the date indicated in the acquired date information. For example, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from the time-series data for a weekday date, but does not calculate an amplitude value based on specific partial data extracted from the time-series data for a holiday date. For example, if the specific vehicle is a route bus, the number of passengers may differ significantly between weekdays and holidays, resulting in a significant difference in weight. Furthermore, if the specific vehicle is a route bus, the degree of traffic congestion may differ between weekdays and holidays, resulting in a significant difference in the speed at which the bus passes over a bridge. Therefore, if the specific vehicle is a route bus, the waveform characteristics of the expansion / contraction amplitude value may differ significantly between weekdays and holidays.

[0084] Therefore, by calculating the amplitude value based on specific partial data extracted from the time-series data on a preset date, the amplitude calculation unit 120 can output the amplitude value of the expansion / contraction amount when the same type of vehicle passes by with approximately the same weight and approximately the same speed, which allows the deterioration detection device 30 to accurately determine whether the bridge has deteriorated.

[0085] The time period acquiring unit 150 acquires time period information indicating a preset time period within a day. The time period acquiring unit 150 may acquire information such as 5:00 AM to 7:00 AM as the time period. The time period acquiring unit 150 provides the acquired time period information to the amplitude calculating unit 120.

[0086] When time zone information is acquired, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from time series data for the time zone indicated in the acquired time zone information. For example, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from time series data for a specified time zone, and does not calculate an amplitude value based on specific partial data extracted from time series data for a time zone other than the specified time zone. For example, the degree of traffic congestion may vary depending on the time zone within a day, and the passing speed of a specific vehicle across a bridge may vary significantly. Therefore, the waveform characteristics of the amplitude value of the expansion / contraction amount may vary significantly depending on the time zone within a day.

[0087] Therefore, by calculating the amplitude value based on specific partial data extracted from time-series data for a preset time period, the amplitude calculation unit 120 can output the amplitude value of the expansion / contraction amount when the same type of vehicle passes by with approximately the same weight and approximately the same speed. This allows the deterioration detection device 30 to accurately determine whether the bridge has deteriorated.

[0088] The passing speed acquisition unit 152 acquires the speed of the specific vehicle when passing through the bridge. For example, the passing speed acquisition unit 152 may acquire log data measured by a speedometer provided in the specific vehicle. Then, the passing speed acquisition unit 152 may acquire the speed of the specific vehicle at the time of passing through the bridge from the log data. The passing speed acquisition unit 152 provides speed information indicating the acquired speed to the amplitude calculation unit 120.

[0089] When speed information is acquired, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from the time-series data in which the speed of a specific vehicle passing over the bridge is within a preset range. This allows the amplitude calculation unit 120 to output an amplitude value of the amount of expansion and contraction when vehicles of the same type pass over the bridge at approximately the same speed. Therefore, the deterioration detection device 30 can more accurately determine whether the bridge has deteriorated.

[0090] The weight acquisition unit 154 acquires the weight of the specific vehicle when it passes over a bridge. For example, a garbage truck is generally equipped with a weighing scale that measures its own weight. The weight acquisition unit 154 may acquire log data measured by a weighing scale provided on the specific vehicle, such as a garbage truck. The weight acquisition unit 154 may then acquire the weight of the specific vehicle at the time it passed over the bridge from the log data. Furthermore, if the specific vehicle is a route bus, the weight acquisition unit 154 may acquire, for example, the number of passengers at a bus stop immediately before the bridge on the bus route or at a specific bus stop, and estimate the weight based on the acquired number of passengers. The weight acquisition unit 154 then provides weight information indicating the acquired weight to the amplitude calculation unit 120.

[0091] When weight information is acquired, the amplitude calculation unit 120 calculates an amplitude value based on specific partial data extracted from the time-series data in which the weight of a specific vehicle passing over the bridge is within a preset range. This allows the amplitude calculation unit 120 to output an amplitude value of the amount of expansion and contraction when vehicles of the same type pass over the bridge with approximately the same weight. Therefore, the deterioration detection device 30 can more accurately determine whether the bridge has deteriorated.

[0092] 11 is a flowchart showing the flow of processing by the deterioration detection device 30. The deterioration detection device 30 executes processing according to the flow shown in FIG.

[0093] First, in S11, the deterioration detection device 30 determines whether a route bus, which is a specific vehicle, has passed the bus stop (or a specific bus stop) immediately before the bridge on the bus route. If the bus has not passed the immediately before bus stop (No in S11), the deterioration detection device 30 waits in S11. If the bus has passed the immediately before bus stop (Yes in S11), the deterioration detection device 30 proceeds to S12.

[0094] In S12, the deterioration detection device 30 estimates the scheduled time to cross the bridge. Subsequently, in S13, the deterioration detection device 30 determines whether or not it is a predetermined time before the scheduled time. If it is not a predetermined time before the scheduled time (No in S13), the deterioration detection device 30 puts the process on hold in S13. If it is a predetermined time before the scheduled time (Yes in S13), the deterioration detection device 30 advances the process to S14.

[0095] In S14, the deterioration detection device 30 turns on the power of the sensor 20. For example, the deterioration detection device 30 sends an instruction signal to the sensor 20 via wireless communication or the like to turn on the power.

[0096] Next, in S15, the deterioration detection device 30 receives and stores time series data of the parameters detected by the sensor 20. For example, the deterioration detection device 30 receives and stores time series data of the expansion / contraction amount of a target portion of a bridge.

[0097] Next, in S16, the deterioration detection device 30 determines whether or not it is now a predetermined time after the scheduled time. If it is not now a predetermined time after the scheduled time (No in S16), the deterioration detection device 30 puts the process on hold in S16. If it is now a predetermined time after the scheduled time (Yes in S16), the deterioration detection device 30 proceeds to S17.

[0098] In S17, the deterioration detection device 30 turns off the power supply to the sensor 20. For example, the deterioration detection device 30 sends an instruction signal to the sensor 20 by wireless communication or the like to turn off the power supply.

[0099] Next, in S18, the deterioration detection device 30 extracts specific partial data, which is partial data when a specific vehicle, a route bus, passes over the bridge, from the stored time-series data of the parameters. Next, in S19, the deterioration detection device 30 calculates, from the extracted specific partial data, an amplitude value of the expansion / contraction amount of the bridge in the traveling direction when the specific vehicle, a route bus, passes over. For example, if the parameter represents the expansion / contraction amount of the target portion, the deterioration detection device 30 calculates the difference between the maximum value and the minimum value of the extracted specific partial data as the amplitude value. Next, in S20, the deterioration detection device 30 stores the calculated amplitude value.

[0100] Next, in S21, the deterioration detection device 30 determines whether the calculated amplitude value is greater than the reference value. If the amplitude value is not greater than the reference value (No in S21), the deterioration detection device 30 returns the process to S11 and repeats the process from S11. If the amplitude value is greater than the reference value (Yes in S21), the deterioration detection device 30 proceeds to S22.

[0101] In S22, the deterioration detection device 30 outputs alarm information indicating that the bridge has deteriorated to, for example, the administrator or an information processing device held by the administrator. When S22 ends, the deterioration detection device 30 ends this flow. Note that after S22, the deterioration detection device 30 may increase the reference value by a predetermined amount and return the process to S11.

[0102] As described above, the deterioration detection system 10 according to the first embodiment calculates the amplitude value of the expansion and contraction of the bridge in the traveling direction when a specific vehicle, such as a route bus, passes over the bridge based on specific portion data when the specific vehicle passes over the bridge. If the calculated amplitude value exceeds a preset reference value, the system determines that the bridge has deteriorated and outputs alarm information indicating that the bridge has deteriorated. In this way, the deterioration detection system 10 according to the first embodiment can easily and continuously detect bridge deterioration over a long period of time. Therefore, the deterioration detection system 10 according to the first embodiment can constantly monitor the condition of a bridge at low cost and manage the bridge in a planned manner.

[0103] Furthermore, the deterioration detection system 10 according to the first embodiment re-learns the first neural network used to detect specific vehicles at appropriate times, and therefore can accurately detect bridge deterioration over a long period of time.

[0104] (Second embodiment) Next, a weight measurement system 210 according to a second embodiment will be described. In the description of the second embodiment, elements having substantially the same configuration as those in the first embodiment will be denoted by the same reference numerals, and detailed description will be omitted except for the differences.

[0105] 12 is a diagram showing a weight measurement system 210 according to the second embodiment. The weight measurement system 210 accurately measures the weight of a vehicle passing over a bridge while correcting related information in accordance with the deterioration of the bridge.

[0106] The weight measurement system 210 includes a sensor 20 , a transmitting device 22 , and a weight measurement device 230 .

[0107] The weight measuring device 230 receives time-series data of parameters representing the displacement of a target portion of a bridge in the traveling direction, transmitted from the transmitting device 22 via the network. Based on the received time-series data of parameters, the weight measuring device 230 calculates a vehicle amplitude value representing the amplitude value of the amount of expansion and contraction of the bridge in the traveling direction when a vehicle passes. The weight measuring device 230 then calculates the weight of the vehicle based on the calculated vehicle amplitude value and relationship information representing the correspondence between the amplitude value and weight. Furthermore, if the weight measuring device 230 determines that the bridge has deteriorated, it corrects the relationship information representing the correspondence between the amplitude value and weight.

[0108] The weight measuring device 230 is a computer such as a server device connectable to a network. The weight measuring device 230 may be a single computer, or may be configured by multiple computers such as a cloud system.

[0109] The weight measurement system 210 may not include the transmitter 22. In this case, the weight measurement device 230 acquires parameters representing the displacement of the target portion of the bridge in the traveling direction directly from the sensor 20. In this case, the weight measurement device 230 may be provided near the sensor 20, i.e., near the bridge.

[0110] 13 is a diagram showing the functional configuration of weight measuring device 230. Weight measuring device 230 includes acquisition unit 112, time-series data storage unit 114, clipping unit 116, vehicle extraction unit 242, vehicle amplitude calculation unit 244, related information storage unit 246, weight calculation unit 248, extraction unit 118, amplitude calculation unit 120, correction unit 250, vehicle collection unit 262, vehicle relearning data storage unit 264, collection unit 132, relearning data storage unit 134, relearning instruction unit 136, relearning unit 138, and vehicle relearning unit 266.

[0111] The acquisition unit 112, the time-series data storage unit 114, and the cut-out unit 116 have the same functions and configurations as those in the first embodiment.

[0112] Based on the determination result by the vehicle determination neural network, the vehicle extraction unit 242 extracts vehicle partial data, which is partial data when a vehicle passes over a bridge, from the time-series data of parameters stored in the time-series data storage unit 114. Here, the vehicle is not limited to a specific vehicle such as a route bus, but may be any type of vehicle.

[0113] The vehicle determination neural network receives target partial data and determines whether a vehicle has passed over a bridge based on the target partial data. The vehicle determination neural network acquires time-series data obtained when a vehicle has passed over a bridge in advance and trains using the acquired time-series data as training data. In this embodiment, the vehicle determination neural network is a convolutional neural network (CNN). By using the convolutional neural network, the vehicle extraction unit 242 can accurately detect that a vehicle has passed over a bridge, regardless of which time portion of the partial data contains waveform data obtained when the vehicle has passed over a bridge. Then, in response to the vehicle determination neural network's determination result that the vehicle has passed over a bridge, the vehicle extraction unit 242 outputs the partial data input to the vehicle determination neural network as vehicle partial data. Note that the vehicle determination neural network may be a neural network with the same configuration as the first neural network. However, in this case, the parameters included in the vehicle determination neural network will have different values from the parameters included in the first neural network as a result of training.

[0114] Each time the vehicle extraction unit 242 extracts vehicle part data, the vehicle amplitude calculation unit 244 calculates a vehicle amplitude value that represents the amplitude value of the amount of expansion / contraction of the bridge in the traveling direction when a vehicle passes, based on the extracted vehicle part data. For example, when the parameter represents the amount of expansion / contraction of the target part, the vehicle amplitude calculation unit 244 calculates the difference between the maximum value and the minimum value in the extracted vehicle part data as the vehicle amplitude value.

[0115] If the parameter is not the amount of expansion / contraction of the target portion, the vehicle amplitude calculation unit 244 may output a value correlated to the amplitude value of the amount of expansion / contraction of the target portion as the vehicle amplitude value. For example, if the parameter is the magnitude of the natural frequency, the vehicle amplitude calculation unit 244 may calculate the difference between the maximum value and the minimum value in the extracted vehicle part data as the vehicle amplitude value.

[0116] The relationship information storage unit 246 stores relationship information that indicates the correspondence between the amplitude value and the weight of the vehicle.

[0117] The amplitude value of the expansion / contraction amount of the bridge in the traveling direction when a vehicle passes over the bridge correlates with the weight of the vehicle. More specifically, the amplitude value of the expansion / contraction amount of the bridge in the traveling direction when a vehicle passes over the bridge increases according to the weight of the vehicle. Therefore, the administrator or the like generates relationship information in advance that indicates the correspondence between the amplitude value and the weight of the vehicle passing over the bridge, and stores the information in the relationship information storage unit 246.

[0118] The administrator may generate the relationship information by, for example, running test vehicles of various weights on the bridge and measuring the correspondence between the vehicle weights and the amplitude values. The administrator may also generate the relationship information by further utilizing simulation results. The administrator may also generate the relationship information for the bridge by utilizing relationship information applied to other bridges.

[0119] The relationship information storage unit 246 may store, as the relationship information, a table associating each of a plurality of amplitude values with the corresponding weight. The relationship information storage unit 246 may also store, as the relationship information, a function or an arithmetic expression that outputs a weight when an amplitude value is input.

[0120] The weight calculation unit 248 calculates the weight of the vehicle each time the vehicle amplitude calculation unit 244 calculates the vehicle amplitude value. More specifically, the weight calculation unit 248 calculates the weight of the vehicle based on the relationship information that indicates the correspondence between the amplitude value and the weight stored in the relationship information storage unit 246 and the calculated vehicle amplitude value. The weight calculation unit 248 outputs the calculated weight to, for example, an information processing device or a server held by an administrator. In this case, the weight calculation unit 248 may also output the time when the vehicle passed over the bridge, etc. This allows the administrator or the like to associate the vehicle that passed over the bridge with the weight.

[0121] The extraction unit 118 has the same function and configuration as in the first embodiment, and extracts specific partial data, which is partial data when a specific vehicle passes through a bridge, from the time series data of parameters stored in the time series data storage unit 114 based on the determination result by the first neural network.

[0122] The amplitude calculation unit 120 has the same function and configuration as in the first embodiment, and calculates a specific vehicle amplitude value that represents the amplitude value of the expansion and contraction amount of the bridge in the traveling direction when a specific vehicle passes, based on the specific part data, each time the extraction unit 118 extracts specific part data.

[0123] The correction unit 250 compares the calculated specific vehicle amplitude value with a preset reference value every time the amplitude calculation unit 120 calculates the specific vehicle amplitude value. Then, when the specific vehicle amplitude value is greater than the reference value, the correction unit 250 corrects the correspondence relationship stored in the relationship information storage unit 246.

[0124] The correction unit 250 may calculate a moving average value of the specific vehicle amplitude value of a predetermined number of most recent samples, and correct the related information when the moving average value becomes larger than a reference value. Alternatively, the correction unit 250 may execute a predetermined filtering process such as a noise removal process on the specific vehicle amplitude value of a plurality of samples, and correct the related information when the result of the filtering process becomes larger than a reference value.

[0125] The vehicle collection unit 262 collects the extracted vehicle part data every time the vehicle extraction unit 242 extracts the vehicle part data. The vehicle re-learning data storage unit 264 stores the vehicle part data collected by the vehicle collection unit 262.

[0126] The collection unit 132 has the same function and configuration as in the first embodiment, and collects the extracted specific partial data every time the extraction unit 118 extracts the specific partial data. The re-learning data storage unit 134 has the same function and configuration as in the first embodiment, and stores the specific partial data collected by the collection unit 132.

[0127] Relearning instruction unit 136 determines whether or not to relearn the first neural network and the vehicle-determination neural network based on the same predetermined criteria as in the first embodiment, and outputs a relearning instruction based on the determination result of whether or not to relearn the first neural network and the vehicle-determination neural network. Relearning instruction unit 136 supplies the relearning instruction to vehicle relearning unit 266 and relearning unit 138.

[0128] When a relearning instruction is output from the relearning instruction unit 136, the vehicle relearning unit 266 re-learns the vehicle determination neural network using the vehicle part data collected by the vehicle collection unit 262 as training data. That is, the vehicle relearning unit 266 re-learns the vehicle determination neural network that has already been trained. For example, the vehicle relearning unit 266 may perform relearning using a backpropagation method or the like, using network parameters such as weights and biases set immediately before relearning as initial values, or may perform relearning using a backpropagation method or the like after changing the network parameters set immediately before relearning to random values or predetermined values.

[0129] The vehicle re-learning unit 266 re-learns the vehicle determination neural network using the vehicle part data collected after the last re-learning as training data. If re-learning has not yet been performed since the start of the deterioration determination, the vehicle re-learning unit 266 may re-learn the vehicle determination neural network using the vehicle part data collected after the start as training data. This allows the vehicle re-learning unit 266 to re-learn the vehicle determination neural network so that it performs appropriate determination processing according to the condition of the nearest bridge. Note that the vehicle re-learning unit 266 may re-learn the vehicle determination neural network using time-series data collected in advance as training data in addition to the vehicle part data collected by the vehicle collection unit 262.

[0130] The re-learning unit 138 has the same configuration as in the first embodiment, and when a re-learning instruction is output from the re-learning instruction unit 136, it re-learns the first neural network using the specific partial data collected by the collection unit 132 as training data.

[0131] In addition, the weight measuring device 230 may be configured to further include one or more of the passage time acquisition unit 142, passage detection information acquisition unit 144, scheduled time estimation unit 146, date acquisition unit 148, time zone acquisition unit 150, passage speed acquisition unit 152, and weight acquisition unit 154 shown in Figure 10.

[0132] Fig. 14 shows the relationship between the weight of the test vehicle and the amplitude of the bridge expansion and contraction amount. In Fig. 14, the graph with black circles shows the relationship when the bridge deterioration is small, and the graph with white squares shows the relationship when the bridge deterioration becomes larger than a predetermined standard value.

[0133] As the deterioration of a bridge increases, the amplitude of the expansion / contraction amount of the bridge in the traveling direction when a vehicle passes over it increases. Therefore, as shown in FIG. 14 , the relationship between the vehicle weight and the amplitude of the expansion / contraction amount of the bridge in the traveling direction when a vehicle passes over it differs between when the deterioration of the bridge is greater than, for example, a reference value and when the deterioration is less than the reference value. Therefore, for example, the administrator generates first relationship information when the deterioration of the bridge is equal to or less than the reference value and second relationship information when the deterioration of the bridge is greater than the reference value, and stores these in the relationship information storage unit 246.

[0134] Then, when the specific vehicle amplitude value is equal to or less than the reference value, the correction unit 250 outputs the first relationship information from the relationship information storage unit 246 to the weight calculation unit 248. Furthermore, when the specific vehicle amplitude value is greater than the reference value, the correction unit 250 outputs the second relationship information from the relationship information storage unit 246 to the weight calculation unit 248. This allows the correction unit 250 to measure the weight of the vehicle with high accuracy, regardless of the degree of deterioration of the bridge.

[0135] The correction unit 250 may be configured with a plurality of different reference values set in advance. Then, the correction unit 250 may adjust the amount of correction to the related information in accordance with the magnitude of the reference value each time the specific vehicle amplitude value becomes larger than the respective reference value. This allows the correction unit 250 to appropriately correct the related information in accordance with the level of bridge deterioration.

[0136] 15 is a flowchart showing the flow of the process of correcting the related information by the weight measuring device 230. The weight measuring device 230 executes the process according to the flow shown in FIG.

[0137] 15 are the same as those performed by the deterioration detection device 30 in FIG. 11. However, in the weight measurement system 210, the power of the sensor 20 is always on to measure the weight of vehicles passing over a bridge. Therefore, if the sensor 20 used to measure the weight is the same as the sensor 20 used when a specific vehicle passes over, the weight measurement device 230 does not need to perform the processes of S13, S14, S16, and S17. In this case, however, in S18, the weight measurement device 230 extracts from the time-series data of the parameters a range from a predetermined time before the scheduled time to a predetermined time after the scheduled time, and extracts specific partial data from the extracted range.

[0138] In S21, the weight measuring device 230 determines whether the calculated amplitude value is greater than the reference value. If the amplitude value is greater than the reference value (Yes in S21), the weight measuring device 230 advances the process to S31.

[0139] In S31, the weight measuring device 230 corrects the correspondence stored in the relationship information storage unit 246. When S31 ends, the weight measuring device 230 ends this flow. Note that after S31, the weight measuring device 230 may increase the reference value by a predetermined amount and return the process to S11.

[0140] The weight measurement system 210 according to the second embodiment calculates a vehicle amplitude value that represents the amplitude value of the amount of expansion and contraction of the bridge in the traveling direction when a vehicle passes over it, and calculates the weight of the vehicle based on the calculated vehicle amplitude value and relationship information that represents the correspondence between the amplitude value and the vehicle weight. Therefore, the weight measurement system 210 can accurately measure the weight of a vehicle passing over a bridge.

[0141] Furthermore, the weight measurement system 210 corrects the related information when the specific vehicle amplitude value, which represents the amplitude value of the expansion / contraction amount of the bridge in the traveling direction when the specific vehicle passes, becomes larger than the reference value. Therefore, the weight measurement system 210 can correct the related information according to the deterioration of the bridge.

[0142] As described above, the weight measurement system 210 according to the second embodiment can accurately measure the weight of a vehicle passing over a bridge while correcting related information in accordance with deterioration of the bridge.

[0143] (Hardware configuration of the deterioration detection device 30 and the weight measurement device 230) 16 is a diagram showing the hardware configuration of the deterioration detection device 30 and the weight measurement device 230. As an example, the deterioration detection device 30 and the weight measurement device 230 are realized by a hardware configuration similar to that of a general computer. The deterioration detection device 30 and the weight measurement device 230 include a CPU (Central Processing Unit) 301, an operation device 302, a display device 303, a ROM (Read Only Memory) 304, a RAM (Random Access Memory) 305, a storage device 306, a communication device 307, and a bus 309. Each unit is connected via the bus 309.

[0144] The CPU 301 uses a predetermined area of the RAM 305 as a working area to execute various processes in cooperation with various programs stored in advance in the ROM 304 or the storage device 306, and comprehensively controls the operation of each part constituting the deterioration detection device 30 or the weight measuring device 230. The CPU 301 also operates the operation device 302, the display device 303, the communication device 307, etc. in cooperation with the programs stored in advance in the ROM 304 or the storage device 306.

[0145] The operation device 302 is an input device such as a touch panel, a mouse, or a keyboard, and receives information input by a user as an instruction signal, and outputs the instruction signal to the CPU 301 .

[0146] The display device 303 is a display unit such as an LCD (Liquid Crystal Display), etc. The display device 303 displays various information based on a display signal from the CPU 301.

[0147] The ROM 304 non-rewritably stores programs and various setting information used to control the deterioration detection device 30 or the weight measurement device 230. The RAM 305 is a volatile storage medium such as an SDRAM (Synchronous Dynamic Random Access Memory). The RAM 305 functions as a work area for the CPU 301.

[0148] The storage device 306 is a rewritable storage device such as a semiconductor storage medium such as a flash memory, or a magnetically or optically recordable storage medium. The storage device 306 stores a program used to control the deterioration detection device 30 or the weight measurement device 230.

[0149] The communication device 307 transmits and receives data to and from other devices. The communication device 307 may also transmit and receive data to and from a server or the like via a network.

[0150] The programs executed by the deterioration detection device 30 and the weight measuring device 230 are stored on a computer connected to a network such as the Internet and are provided by being downloaded via the network. Alternatively, the programs executed by the deterioration detection device 30 and the weight measuring device 230 may be provided in advance by being stored in a portable storage medium or the like.

[0151] The program executed by the deterioration detection device 30 has a modular configuration including a collection module, a cutout module, an extraction module, an amplitude calculation module, a deterioration determination module, an alarm output module, a collection module, a relearning instruction module, and a relearning module. The CPU 301 reads such a program from a storage medium or the like and loads each of the above modules into the RAM 305. By executing such a program, the CPU 301 functions as the acquisition unit 112, the cutout unit 116, the extraction unit 118, the amplitude calculation unit 120, the deterioration determination unit 122, the alarm output unit 124, the collection unit 132, the relearning instruction unit 136, and the relearning unit 138. Note that some or all of the acquisition unit 112, the extraction unit 118, the amplitude calculation unit 120, the deterioration determination unit 122, the alarm output unit 124, the collection unit 132, the relearning instruction unit 136, and the relearning unit 138 may be configured by hardware.

[0152] The program executed by the weight measuring device 230 has a modular configuration including a collection module, a cutout module, a vehicle extraction module, a vehicle amplitude calculation module, a weight calculation module, an extraction module, an amplitude calculation module, a correction module, a vehicle collection module, a collection module, a relearning instruction module, a vehicle relearning module, and a relearning module. The CPU 301 reads such programs from a storage medium or the like and loads each of the above modules into the RAM 305. By executing such programs, the CPU 301 functions as the acquisition unit 112, the cutout unit 116, the vehicle extraction unit 242, the vehicle amplitude calculation unit 244, the weight calculation unit 248, the extraction unit 118, the amplitude calculation unit 120, the correction unit 250, the vehicle collection unit 262, the collection unit 132, the relearning instruction unit 136, the vehicle relearning unit 266, and the relearning unit 138. Note that some or all of the acquisition unit 112, vehicle extraction unit 242, vehicle amplitude calculation unit 244, weight calculation unit 248, extraction unit 118, amplitude calculation unit 120, and correction unit 250 may be configured by hardware.

[0153] Although the embodiments of the present invention have been described above, these embodiments are presented as examples and are not intended to limit the scope of the invention. Various modifications can be made to the embodiments. [Explanation of symbols]

[0154] 10 Deterioration detection system 20 sensors 22 Transmitting device 30 Deterioration detection device 54 Main digit 56 Bottom side 62 1st point 64 Second point 66 First member 68 Second member 70 Displacement detection device 72 Optical Elements 74 detectors 76 Half Mirror 78 Light-emitting part 80 Light receiving section 82 Detection circuit 112 Acquisition Department 114 Time series data storage unit 118 Extraction part 120 Amplitude calculation unit 122 Deterioration determination section 124 Alarm output section 132 Collection Department 134 Re-learning data storage unit 136 Relearning Instructions 138 Re-learning Section 142 Passage time acquisition section 144 Passage detection information acquisition unit 146 Scheduled Time Estimation Unit 148 Date Acquisition Section 150 Time Zone Acquisition Section 152 Passing speed acquisition section 154 Weight acquisition part 210 Weight Measurement System 230 Weight measuring device 242 Vehicle Extraction Unit 244 Vehicle amplitude calculation unit 246 Related Information Storage Unit 248 Weight calculation section 250 Correction Unit 262 Vehicle Collection Department 264 Vehicle re-learning data storage unit 266 Vehicle Relearning Unit

Claims

1. an acquisition unit that collects, from a sensor installed on a bridge, time series data of a parameter that represents a displacement of a target portion of the bridge where the sensor is installed; an extraction unit that extracts, from the time-series data, specific partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time-series data and outputs a determination result indicating whether or not the specific vehicle passed; an amplitude calculation unit that calculates an amplitude value of the expansion / contraction amount of the target portion of the bridge when the specific vehicle passes based on the specific portion data; a deterioration determination unit that determines that the bridge has deteriorated when the amplitude value becomes larger than a preset reference value; A deterioration detection device comprising:

2. an alarm output unit that outputs alarm information indicating that the bridge has deteriorated when the bridge is determined to have deteriorated; The deterioration detection device according to claim 1 , further comprising:

3. a re-learning instruction unit that determines whether or not to re-learn the neural network based on a predetermined determination criterion, and outputs a re-learning instruction that instructs the neural network to be re-learned based on the result of the determination whether or not to re-learn the neural network; The deterioration detection device according to claim 1 or 2, further comprising:

4. a sensor provided at a target portion of a bridge to detect a parameter representing a displacement of the target portion of the bridge; an acquisition unit that collects time series data of the parameters from the sensors; an extraction unit that extracts, from the time-series data, specific partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time-series data and outputs a determination result indicating whether or not the specific vehicle passed; an amplitude calculation unit that calculates an amplitude value of the expansion / contraction amount of the target portion of the bridge when the specific vehicle passes based on the specific portion data; a deterioration determination unit that determines that the bridge has deteriorated when the amplitude value becomes larger than a preset reference value; A deterioration detection system comprising:

5. collecting, from a sensor provided on a bridge, time series data of a parameter representing a displacement at a target portion of the bridge where the sensor is provided; extracting, from the time series data, specific portion data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time series data and outputs a determination result indicating whether or not a specific vehicle passed; Calculating an amplitude value of the expansion / contraction amount of the target portion of the bridge when the specific vehicle passes based on the specific portion data; If the amplitude value is greater than a preset reference value, it is determined that the bridge has deteriorated. Degradation detection methods.

6. A program for causing an information processing device to function as a deterioration detection device, The information processing device an acquisition unit that collects, from a sensor installed on a bridge, time series data of a parameter that represents a displacement of a target portion of the bridge where the sensor is installed; an extraction unit that extracts, from the time-series data, specific partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time-series data and outputs a determination result indicating whether or not the specific vehicle passed; an amplitude calculation unit that calculates an amplitude value of the expansion / contraction amount of the target portion of the bridge when the specific vehicle passes based on the specific portion data; a deterioration determination unit that determines that the bridge has deteriorated when the amplitude value becomes larger than a preset reference value; A program that makes it work.

7. an acquisition unit that collects, from a sensor installed on a bridge, time series data of a parameter that represents a displacement of a target portion of the bridge where the sensor is installed; a vehicle extraction unit that extracts vehicle partial data from the time series data, which is partial data when the vehicle passed through the measurement section of the bridge, based on the determination result by a vehicle determination neural network that inputs the time series data and outputs a determination result indicating whether or not a vehicle has passed; a vehicle amplitude calculation unit that calculates a vehicle amplitude value that represents an amplitude value of an amount of expansion and contraction of the target portion of the bridge when the vehicle passes, based on the vehicle portion data; a weight calculation unit that calculates the weight of the vehicle based on relationship information that indicates a correspondence relationship between an amplitude value and a vehicle weight and the calculated vehicle amplitude value; an extraction unit that extracts specific partial data from the time series data, which is partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time series data and outputs a determination result indicating whether or not the specific vehicle passed; an amplitude calculation unit that calculates a specific vehicle amplitude value that represents an amplitude value of the amount of expansion and contraction of the target portion of the bridge when the specific vehicle passes, based on the specific portion data; a correction unit that corrects the related information when the specific vehicle amplitude value becomes larger than a predetermined reference value; A weight measuring device comprising:

8. collecting, from a sensor provided on a bridge, time series data of a parameter representing a displacement at a target portion of the bridge where the sensor is provided; extracting vehicle partial data from the time series data, which is partial data when the vehicle passed through the measurement section of the bridge, based on the determination result by a vehicle determination neural network that inputs the time series data and outputs a determination result indicating whether or not a vehicle has passed; calculating a vehicle amplitude value representing an amplitude value of the amount of expansion and contraction of the target portion of the bridge when the vehicle passes based on the vehicle portion data; Calculating the weight of the vehicle based on relationship information indicating a correspondence relationship between amplitude values and vehicle weights and the calculated vehicle amplitude value; an extraction unit that extracts specific partial data from the time series data, which is partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time series data and outputs a determination result indicating whether or not the specific vehicle passed; calculating a specific vehicle amplitude value representing an amplitude value of the expansion / contraction amount of the target portion of the bridge when the specific vehicle passes based on the specific portion data; When the specific vehicle amplitude value becomes larger than a preset reference value, the related information is corrected. Weight measurement method.

9. A program for causing an information processing device to function as a weight measuring device, The information processing device an acquisition unit that collects, from a sensor installed on a bridge, time series data of a parameter that represents a displacement of a target portion of the bridge where the sensor is installed; a vehicle extraction unit that extracts vehicle partial data from the time series data, which is partial data when the vehicle passed through the measurement section of the bridge, based on the determination result by a vehicle determination neural network that receives the time series data and outputs a determination result indicating whether or not a vehicle has passed; a vehicle amplitude calculation unit that calculates a vehicle amplitude value that represents an amplitude value of an amount of expansion and contraction of the target portion of the bridge when the vehicle passes, based on the vehicle portion data; a weight calculation unit that calculates the weight of the vehicle based on relationship information that indicates a correspondence relationship between an amplitude value and a vehicle weight and the calculated vehicle amplitude value; an extraction unit that extracts specific partial data from the time series data, which is partial data when the specific vehicle passed through the measurement section of the bridge, based on the determination result by a neural network that inputs the time series data and outputs a determination result indicating whether or not the specific vehicle passed; an amplitude calculation unit that calculates a specific vehicle amplitude value that represents an amplitude value of the amount of expansion and contraction of the target portion of the bridge when the specific vehicle passes, based on the specific portion data; a correction unit that corrects the related information when the specific vehicle amplitude value becomes larger than a predetermined reference value; A program that makes it work.

Images