JP7503284B2 - Vibration evaluation device and vibration evaluation system - Google Patents

Description

The present invention relates to a vibration evaluation device and a vibration evaluation system.

Conventionally, a building evaluation system such as that disclosed in Patent Document 1 has been proposed as a means for evaluating the soundness of buildings and other structures.

The building evaluation system of Patent Document 1 includes an acceleration sensor that is installed in a building and obtains acceleration caused in the building due to an earthquake, and a processing unit that is connected to the acceleration sensor and evaluates the soundness of the building using the acceleration data output from the acceleration sensor. Patent Document 1 discloses that the processing unit includes a main earthquake displacement acquisition unit that obtains displacement data using the acceleration data, a main earthquake stress acquisition unit that obtains stress data related to stress caused in the building using a first stiffness matrix indicating the structural characteristics of the building and the displacement data, and a main earthquake damage evaluation unit that performs an evaluation of damage to the building using the stress data.

JP 2019-144031 A

The technology disclosed in Patent Document 1 is premised on evaluating soundness using displacement data on horizontal displacement for each floor. As a result, as the number of floors in a building increases, the number of sensors (acceleration sensors) that must be installed in advance also increases, raising concerns about a decrease in the accuracy of evaluation results due to insufficient maintenance of the sensors and damage to the sensors due to earthquakes, etc.

The present invention was devised in consideration of the above-mentioned problems, and its purpose is to provide a vibration evaluation device and a vibration evaluation system that can obtain highly accurate evaluation results.

The vibration evaluation device according to the first invention is a vibration evaluation device that evaluates the state of a structure based on the vibration of the structure, and includes a laser detector that measures the vibration using a laser, an acquisition unit that acquires evaluation target information including first data based on vibration data measured by the laser detector, a reference database that stores associations between multiple pieces of past evaluation target information acquired in advance and multiple pieces of reference information linked to the multiple pieces of past evaluation target information, a generation unit that references the reference database and generates evaluation data for the evaluation target information, and an output unit that outputs an evaluation result based on the evaluation data, wherein the reference information includes soundness information regarding an evaluation of the soundness of the past evaluation target information, and the evaluation result includes, from the soundness information, first soundness information linked to the evaluation target information.

The vibration evaluation device according to the second invention is the first invention, characterized in that the acquisition unit acquires the first data from the result of Fourier transforming a first signal pattern included in the vibration data.

The vibration evaluation device according to the third invention is the first invention, characterized in that the laser detector uses the laser to measure an impact temporarily applied to a part of the structure, and the acquisition unit acquires the evaluation target information including the first data and second data based on the impact data measured by the laser detector.

The vibration evaluation device according to the fourth invention is the third invention, characterized in that the evaluation target information and the past evaluation target information include hammering information regarding the method of applying the impact to a part of the structure in order to measure the impact data.

The vibration evaluation device according to the fifth invention is the third invention, characterized in that the reference information includes shape information relating to the shape of cracks occurring inside the structure, and the evaluation result includes, from the shape information, first shape information linked to the evaluation target information.

The vibration evaluation system according to the sixth aspect of the present invention is a vibration evaluation system that evaluates the state of a structure based on the vibration of the structure, and includes a laser detector that measures the vibration using a laser, an acquisition means that acquires evaluation target information including first data based on the vibration data measured by the laser detector, a reference database that stores associations between a plurality of pieces of past evaluation target information acquired in advance and a plurality of pieces of reference information linked to the plurality of pieces of past evaluation target information, a generation means that refers to the reference database and generates evaluation data for the evaluation target information, and an output means that outputs an evaluation result based on the evaluation data, wherein the reference information includes soundness information regarding an evaluation of the soundness of the past evaluation target information, and the evaluation result includes, from the soundness information, first soundness information linked to the evaluation target information.

According to the first to fifth inventions, the laser detector uses a laser to measure the vibration of the structure. Therefore, there is no need to increase the number of laser detectors in proportion to the number of floors of the structure, and there is no need to install them in the structure in advance. Therefore, compared to sensors that need to be installed in advance, there is an extremely low possibility of the accuracy of the evaluation results decreasing due to lack of maintenance or damage due to earthquakes, etc. This makes it possible to obtain highly accurate evaluation results. In addition, vibration data can be obtained without contacting the structure. This makes it possible to suppress the decrease in evaluation accuracy caused by the measurer, etc., without having to consider the variation in the measurement results due to the contact state, compared to contact-type measurement methods. In addition, compared to measuring the vibration of a structure due to an earthquake, measurements can be taken at any time. This makes it possible to carry out regular evaluations.

Furthermore, according to the first to fifth inventions, the generation unit refers to the reference database and generates evaluation data for the evaluation target information. The evaluation result includes, among the health information, the first health information linked to the evaluation target information. Therefore, it is possible to generate evaluation data based on past results, and even when a complex signal pattern is included in the vibration data, it is possible to output evaluation results including first health information that is optimal for the evaluation target information. This makes it possible to improve the accuracy of the evaluation result.

In particular, according to the second invention, the acquisition unit acquires the first data from the result of Fourier transforming the first signal pattern. Therefore, it is possible to output an evaluation result even for slight differences in the signal pattern that accompany differences in the state of the building. This makes it possible to easily generate optimal evaluation data even for evaluation target information that indicates a complex state of the building.

In particular, according to the third invention, the acquisition unit acquires evaluation target information including the first data and the second data based on the impact data measured by the laser detector. Therefore, it is possible to obtain an evaluation result including a combination of the soundness of the entire structure and the condition of a part of the structure. This makes it possible to easily identify the part that affects the soundness of the structure.

In particular, according to the fourth invention, the evaluation target information and the past evaluation target information include hammering sound information on the method of applying an impact to a part of a structure in order to measure the impact data. Therefore, optimal evaluation data can be generated for each of the various hammering sound methods for applying an impact to a part of a structure. This makes it possible to further improve the accuracy of the evaluation results obtained.

In particular, according to the fifth invention, the evaluation result includes the first shape information linked to the evaluation target information. Therefore, the internal condition of the structure can be quantitatively evaluated. This makes it possible to obtain an evaluation result that eliminates the subjectivity of each measurer.

According to the sixth aspect of the invention, the laser detector uses a laser to measure the vibration of the building. Therefore, there is no need to increase the number of laser detectors in proportion to the number of floors of the building, and there is no need to install them in the building in advance. Therefore, compared to sensors that need to be installed in advance, there is an extremely low possibility of the accuracy of the evaluation results decreasing due to lack of maintenance or damage caused by earthquakes, etc. This makes it possible to obtain highly accurate evaluation results. In addition, vibration data can be obtained without contacting the building. This makes it possible to suppress the decrease in evaluation accuracy caused by the measurer, etc., without having to consider the variation in the measurement results due to the contact state, compared to contact-type measurement methods. In addition, compared to measuring the vibration of a building due to an earthquake, measurements can be taken at any time. This makes it possible to carry out regular evaluations.

According to the sixth aspect of the present invention, the generating means refers to the reference database and generates evaluation data for the evaluation target information. The evaluation result includes, among the health information, the first health information linked to the evaluation target information. Therefore, it is possible to generate evaluation data based on past results, and even when a complex signal pattern is included in the vibration data, it is possible to output an evaluation result including the first health information that is optimal for the evaluation target information. This makes it possible to improve the accuracy of the evaluation result.

FIG. 1 is a schematic diagram showing an example of an overview of a vibration evaluation system and a vibration evaluation device according to a first embodiment. FIG. 2 is a schematic diagram showing an example of the operation of the vibration evaluation system and the vibration evaluation device in the first embodiment. FIG. 3A is a graph showing an example of vibration data, and FIG. 3B is a graph showing an example of the result of Fourier transform of the first signal pattern. FIG. 4 is a schematic diagram showing an example of the reference database. FIG. 5 is a schematic diagram showing another example of the reference database. FIG. 6( a ) is a schematic diagram showing an example of the configuration of the vibration evaluation device in the first embodiment, and FIG. 6( b ) is a schematic diagram showing an example of the function of the vibration evaluation device in the first embodiment. FIG. 7 is a flowchart showing an example of the operation of the vibration evaluation system in the first embodiment. FIG. 8 is a schematic diagram showing an example of the operation of the vibration evaluation system and the vibration evaluation device in the second embodiment. FIG. 9A is a graph showing an example of impact data, and FIG. 9B is a graph showing an example of the result of Fourier transform of the second signal pattern. FIG. 10 is a schematic diagram showing yet another example of the reference database. FIG. 11A is a schematic diagram showing an example of a result of comparing the evaluation data with the reference evaluation data, and FIG. 11B is a schematic diagram showing an example of image information.

Below, an example of a vibration evaluation device and a vibration evaluation system according to an embodiment of the present invention will be described with reference to the drawings.

First Embodiment
An example of a vibration evaluation system 100 and a vibration evaluation device 1 in the first embodiment will be described with reference to Fig. 1 and Fig. 2. Fig. 1 is a schematic diagram showing an example of an outline of the vibration evaluation system 100 and the vibration evaluation device 1 in the present embodiment. Fig. 2 is a schematic diagram showing an example of the operation of the vibration evaluation system 100 and the vibration evaluation device 1 in the present embodiment.

(Vibration evaluation system 100)
The vibration evaluation system 100 is used to evaluate the state of the structure 9 based on the vibration of the structure 9. By using the vibration evaluation system 100, it is possible to perform evaluation of the structure 9 including its soundness, for example.

The structure 9 includes, for example, buildings made of wood or reinforced concrete, as well as structures such as embankments and bridges. The vibration evaluation system 100 evaluates the state of the structure 9 based on vibrations (e.g., natural vibrations) that occur throughout the entire structure 9. Vibrations of the structure 9 are generated by, for example, wind and the surrounding environment, such as the passing of vehicles.

The vibration evaluation system 100 uses a laser to measure the vibrations of the structure 9. The vibration evaluation system 100 also uses information from previous evaluations. Therefore, compared to methods that measure by contacting the structure 9, such as ultrasonic methods, it is possible to obtain vibration data without contact, and it is possible to obtain vibration data with less variation due to measurement conditions.

The vibration evaluation system 100 includes a vibration evaluation device 1, as shown in FIG. 1, for example. The vibration evaluation device 1 includes a laser detector 2. The vibration evaluation device 1 may be connected to, for example, an imaging device 7, or may be connected to a terminal 5 or a server 6 via a communication network 4. In addition to controlling the laser detector 2, the vibration evaluation device 1 may also control the imaging device 7, or may include the functions of the laser detector 2 and the imaging device 7.

As shown in FIG. 2, the vibration evaluation system 100 may target the outer wall of the building 9, or may target the inner wall, etc. For example, the vibration evaluation system 100 uses a laser detector 2 to measure the vibration of the building 9. At this time, the laser detector 2 measures the vibration by emitting a laser and receiving the laser reflected by the building 9.

Then, the vibration evaluation device 1 acquires the evaluation target information. The evaluation target information includes first data based on vibration data measured by the laser detector 2. The vibration evaluation device 1 then refers to the reference database, generates evaluation data for the evaluation target information, and outputs an evaluation result based on the evaluation data. This makes it possible to output an index indicating the state of the structure 9, such as soundness, as the evaluation result. Note that the evaluation result may display one item regarding the state of the structure 9, such as "Inspection required (soundness)", or may display multiple candidates and probabilities, such as "Safe: 30%, Inspection required: 60%, Danger: 10%".

The following describes the vibration data, evaluation target information, and reference database used in the vibration evaluation system 100.

<Vibration data>
The vibration data includes a signal pattern (first signal pattern) of a time waveform expressed by velocity (Velocity (m/s)) with respect to time (Time (s)), as shown in FIG. 3A for example. The vibration data may be a known vibration measurement result. The vibration data includes a signal pattern from 1 second to 300 seconds after an arbitrary timing, for example, and may be set arbitrarily according to the situation.

The signal pattern obtained differs depending on the state of the structure 9 (e.g., the presence or absence of cracks, the shape of the cracks, the balance of the loads acting on, etc.). In this regard, the vibration evaluation system 100 can perform evaluation based on the signal pattern. Therefore, it is possible to obtain highly accurate evaluation results even when cracks or cavities in the structure 9 due to deterioration over time or earthquakes have only occurred inside the structure 9 and have not reached the surface of the structure 9, or when the balance of the loads acting on the entire structure has deteriorated.

The vibration data indicates, for example, the result of measuring the vibration in the depth direction on the irradiation surface of the laser emitted from the laser detector 2. Therefore, it is possible to obtain vibration data that reflects the state inside the structure 9, which is important for evaluating the soundness of the structure 9. This makes it possible to improve the accuracy of the evaluation results.

The vibration data indicates, for example, the results of measuring vibrations in the depth direction, as well as in at least one of the width direction, height direction, and torsion direction, on the irradiation surface of the laser emitted from the laser detector 2. Therefore, vibration data can be obtained that takes into account the structure of the entire building 9. This makes it possible to output evaluation results that reflect the structural characteristics of the building 9, making it possible to further improve accuracy.

<Information to be evaluated>
The evaluation target information includes first data based on the vibration data. The first data is obtained, for example, from the result of Fourier transform of the signal pattern included in the vibration data (for example, FIG. 3B). The Fourier transformed data can be expressed, for example, as the magnitude with respect to the frequency (Hz). In this case, for example, multiple characteristic values are extracted from the result of the Fourier transform and obtained as the evaluation target information. Therefore, compared to the case where the signal pattern of the time waveform is directly evaluated, the characteristics of the entire superimposed vibration can be the evaluation target. As a result, the evaluation result can be output even for slight differences in the vibration data due to differences in the state of the building 9.

In addition to the above, for example, multiple characteristic values may be extracted from the signal pattern of the time waveform and acquired as the first data included in the evaluation target information. In this case, there is no need to perform processing such as Fourier transform, and an increase in the data processing process can be suppressed. Note that a publicly known technique such as principal component analysis can be used as a method for extracting the above-mentioned "characteristic values." This makes it possible to reduce the amount of data required for evaluation without including the subjectivity of the measurer, etc. Also, by deleting unnecessary data (noise), it is possible to improve accuracy.

The first data included in the evaluation target information may be obtained, for example, from data converted from a signal pattern into a Mel frequency spectrum, or from Mel Frequency Cepstrum Coefficients (MFCC). As the first data, data in a matrix (e.g., vector) format may be obtained, or data in an image format such as a spectrogram may be obtained.

The evaluation target information may include, for example, attribute information related to the characteristics of the building 9. The attribute information may include, for example, the type of structure of the building 9 (e.g., wood, reinforced concrete, embankment, bridge, height, number of floors, area, volume, material occupancy rate, etc.), and may also include, for example, at least one of the age of the building, the construction company, the measurement location, and the measurement conditions. By including attribute information in the evaluation target information, it becomes possible to obtain appropriate evaluation results when, for example, similar first data are obtained for different attribute information.

The evaluation target information may include, for example, excitation information. The excitation information indicates information related to the factor that caused vibration (excited) in the structure 9. The excitation information may include identification information related to factors such as wind and vehicles, and may also include detailed information such as wind direction, wind speed, vehicle traffic, and vehicle noise volume. By including excitation information in the evaluation target information, slight differences in signal patterns resulting from differences in the excitation factors can be reflected in the evaluation results, and different evaluations can be made for each excitation information, for example.

<Reference database>
The reference database stores associations between a plurality of pieces of past evaluation target information acquired in advance and a plurality of pieces of reference information each associated with a plurality of pieces of past evaluation target information. The associations are constructed by known machine learning using a plurality of pieces of learning data, for example, with the past evaluation target information and the reference information as a set of learning data. As the machine learning, deep learning such as a convolutional neural network may be used, or known techniques such as a random forest or an SVM (Support Vector Machine) may be used.

In this case, for example, the correlation is constructed based on the degree of connection between many-to-many information (multiple past evaluation target information vs. multiple reference information). The correlation is appropriately updated during the machine learning process, and indicates, for example, a function (classifier) optimized based on past evaluation target information and reference information. Therefore, evaluation data for the evaluation target information is generated using the correlation that takes into account all past evaluation results of the state of the structure 9. This makes it possible to generate optimal evaluation data even when complex signal patterns are included in the vibration data. Furthermore, optimal evaluation data can be quantitatively generated not only when the evaluation target information is the same as or similar to past evaluation target information, but also when it is dissimilar. Note that by improving the generalization ability when performing machine learning, the evaluation accuracy for unknown signal patterns can be improved.

The reference database may store, for example, past evaluation target information and reference information used in machine learning learning data. The association may have, for example, multiple association degrees indicating the degree of connection between each piece of information. For example, when the reference database is constructed using a neural network, the association degrees can correspond to weight variables.

The past evaluation target information indicates information of the same type as the evaluation target information described above. When the past evaluation target information includes attribute information, the first data based on the vibration data and the attribute information can be used as a set of input data for machine learning. In addition to the above, for example, machine learning may be performed using the first data separated for each attribute information as input data. In this case, for example, multiple trained models separated for each attribute information may be stored in the reference database. Note that, even when the past evaluation target information includes excitation information instead of attribute information, or when it includes attribute information and excitation information, it can be used as a set of input data for machine learning in the same manner as described above, and multiple trained models separated for each excitation information may be stored in the reference database.

The reference information is linked to past evaluation target information and indicates information regarding the state of the structure 9. The reference information includes, for example, soundness information regarding an evaluation of the soundness of the past evaluation target information. The soundness information includes information indicating a three-level degree of soundness, such as "safe", "requires inspection", and "dangerous", and may also include information indicating a three-level or higher level of soundness (for example, a 10-level evaluation in which the safest state is "10" and the most dangerous state is "1").

The reference information may include, for example, attribute information corresponding to health. The reference information may also include information indicating different levels of health for each piece of attribute information. In these cases, the reference information may include a health level appropriate for each piece of attribute information.

As shown in FIG. 4, for example, correlation may indicate the degree of connection between multiple pieces of past evaluation target information and multiple pieces of reference information. In this case, correlation can be used to link and store the degree of relationship between multiple pieces of reference information ("Reference A" to "Reference C" in FIG. 4) and each piece of past evaluation target information ("Target A" to "Target C" in FIG. 4). Therefore, for example, correlation can be used to link multiple pieces of reference information to one piece of past evaluation target information, enabling the generation of multifaceted evaluation data.

The association has multiple associations that link each piece of past evaluation target information with each piece of reference information. The association is shown in three or more levels, such as a percentage, a 10-level scale, or a 5-level scale, and is shown, for example, by the characteristics of the line (for example, thickness, etc.). For example, "Subject A" included in the past evaluation target information shows an association AA of "62%" with "Reference A" included in the reference information, and an association AB of "26%" with "Reference B" included in the reference information. In other words, the "association" indicates the degree of connection between each piece of data, and for example, the higher the association, the stronger the connection between each piece of data. Note that when constructing associations by the above-mentioned machine learning, the association may be set to have three or more levels of association.

As shown in FIG. 5, for example, the degree of association may be linked to multiple reference information by treating two or more combinations of past evaluation target information (dashed lines in FIG. 5) as one target data. For example, the combination of "target A" and "target D" included in the past evaluation target information shows an association degree ADA of "25%" with "reference A" and an association degree ADB of "17%" with "reference B". In this case, a quantitative evaluation can be performed even when the evaluation target information evaluated with reference to the reference database is similar to both "target A" and "target D". The associations shown in FIG. 4 and FIG. 5 may be constructed, for example, by the machine learning described above.

By using the above-mentioned correlation, it is possible to express the complex relationship between the past evaluation target information, each of which has multiple data, and the reference information with high accuracy. Therefore, even when the vibration data contains a complex signal pattern, it is possible to generate optimal evaluation data. It is also possible to achieve high-accuracy evaluation of unknown signal patterns contained in the vibration data.

The reference database may store, for example, reference evaluation data. The reference evaluation data is acquired in advance as a standard for evaluating the evaluation data, and is stored in the reference database. As the reference evaluation data, for example, data corresponding to the sound state of the structure 9 is used.

The reference database may store, for example, image information. The image information indicates an image of the surface of the structure 9, and may plot, for example, the measurement positions. The image information is captured in advance, for example, by the imaging device 7, and stored in the reference database.

(Vibration evaluation device 1)
Next, an example of the vibration evaluation device 1 in this embodiment will be described with reference to Fig. 6. Fig. 6(a) is a schematic diagram showing an example of the configuration of the vibration evaluation device 1 in this embodiment, and Fig. 6(b) is a schematic diagram showing an example of the function of the vibration evaluation device 1 in this embodiment.

An electronic device such as a laptop (notebook) PC or a desktop PC is used as the vibration evaluation device 1. As shown in FIG. 6(a), for example, the vibration evaluation device 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and I/Fs 105 to 107. The components 101 to 107 are connected by an internal bus 110.

The CPU 101 controls the entire vibration evaluation device 1. The ROM 102 stores the operation code of the CPU 101. The RAM 103 is a working area used when the CPU 101 is operating. The storage unit 104 stores various information such as a reference database and evaluation target information. As the storage unit 104, for example, a data storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) is used. For example, the vibration evaluation device 1 may have a GPU (Graphics Processing Unit) not shown.

The I/F 105 is an interface for transmitting and receiving various information to and from the laser detector 2, etc., as necessary, via a data communication means, and may be used, for example, to transmit and receive various information to and from the terminal 5, etc., via the communication network 4. The I/F 106 is an interface for transmitting and receiving information to and from the input section 108. For example, a keyboard is used as the input section 108, and a measurer of the vibration evaluation device 1 inputs various information or control commands for the vibration evaluation device 1 or the laser detector 2, etc., via the input section 108. The I/F 107 is an interface for transmitting and receiving various information to and from the output section 109. The output section 109 outputs various information stored in the storage section 104, or the processing status of the vibration evaluation device 1 or the laser detector 2, etc. A display is used as the output section 109, and may be, for example, a touch panel type.

Fig. 6(b) is a schematic diagram showing an example of the functions of the vibration evaluation device 1. The vibration evaluation device 1 includes an acquisition unit 11, a generation unit 12, an output unit 13, a storage unit 14, and a control unit 15, and may also include, for example, an update unit 16. Each function shown in Fig. 6(b) is realized by the CPU 101 using the RAM 103 as a working area to execute a program stored in the storage unit 104 or the like, and may be controlled by, for example, artificial intelligence.

<Acquisition Unit 11>
The acquisition unit 11 acquires evaluation target information including first data based on vibration data. The acquisition unit 11 acquires vibration data measured by the laser detector 2, processes a signal pattern included in the vibration data by Fourier transform or the like, and acquires the processing result as the first data. The acquisition unit 11 may acquire at least one of attribute information and excitation information input in advance by a measurer or the like as part of the evaluation target information.

The acquisition unit 11 may acquire image information, for example, of an image of the surface of the structure 9. The image information may be input in advance by, for example, a measurer, or may be received from a terminal 5, for example. The acquisition unit 11 may also acquire image information captured by, for example, an imaging device 7 having an imaging function. The acquisition unit 11 may acquire, for example, the irradiation position (measurement position) of the laser emitted from the laser detector 2, which is included in the image information.

The measurement position can be identified by the spot of the laser emitted from the laser detector 2 to acquire vibration data. Therefore, the measurement position may be acquired by, for example, the imaging device 7, in addition to being acquired from the laser detector 2, or may be directly input by, for example, a person making a measurement. Note that the acquisition unit 11 may acquire, for example, the measurement position as part of the evaluation target information. In this case, an evaluation can be performed using the information on the measurement position as an auxiliary parameter, making it possible to further improve accuracy.

<Generation Unit 12>
The generating unit 12 refers to the reference database and generates evaluation data for the evaluation target information. The generating unit 12 selects one or more pieces of reference information linked to the evaluation target information, for example, via association (classifier), and generates evaluation data reflecting the selected reference information.

The generation unit 12 extracts, for example, from among the multiple selected reference information, the reference information with the highest degree of association linked to the evaluation target information, and generates it as evaluation data. Note that multiple pieces of reference information may be extracted, and in this case, for example, reference information linked to a degree of association equal to or greater than a preset threshold may be extracted.

When the generation unit 12 refers to a reference database such as that shown in FIG. 4, for example, it selects past evaluation target information that is identical or similar to the evaluation target information (for example, "target A": first target data). As the past evaluation target information, target data that partially or completely matches the evaluation target information is selected, as well as similar target data, for example. The degree of similarity to be selected can be set arbitrarily. Furthermore, multiple target data (for example, "target A" and "target C") may be selected as the first target data.

The generating unit 12 selects reference information (first reference data) linked to the selected first target data, and the degree of association between the first target data and the first reference data (e.g., degree of association AA: first degree of association). For example, the generating unit 12 selects the first reference data "Reference A" linked to the first target data "Target A", and the first degree of association "62%" between "Target A" and "Reference A", and generates evaluation data including each selected data.

Furthermore, when multiple reference data and correlations are selected, in addition to the above-mentioned "Reference A" and "62%", the first reference data "Reference B" linked to the first target data "Target A" and the first correlation "26%" between "Target A" and "Reference B" may be selected as the first reference data and first correlation. In this way, the generation unit 12 generates evaluation data including the selected first reference data and first correlation.

<Output Unit 13>
The output unit 13 outputs an evaluation result based on the evaluation data. The output unit 13 generates and outputs an evaluation result by converting the evaluation data into a character string or the like that can be understood by a person performing measurement, for example, using a display format previously stored in the storage unit 104. The output unit 13 transmits the evaluation result to the output section 109 via the I/F 107, and also transmits the evaluation result to the terminal 5 or the like, for example, via the I/F 105.

The output unit 13 outputs an evaluation result that includes, for example, health information (first health information) that is linked to the evaluation target information. In this case, the output unit 13 outputs the evaluation result by including the first health information included in the first reference data selected by the generation unit 12.

<Storage unit 14>
The storage unit 14 retrieves various data such as the reference database stored in the storage unit 104 as necessary. The storage unit 14 stores various data acquired or generated by each of the components 11 to 13, 15, and 16 in the storage unit 104 as necessary.

<Control Unit 15>
The control unit 15 controls the laser detector 2. The control unit 15 controls the conditions of the laser emitted from the laser detector 2 and the conditions of the measurement, for example, based on the contents input by a measurer or the like. The control unit 15 controls the laser detector 2 using, for example, a known technique, and may also control, for example, the imaging device 7, etc.

<Update unit 16>
The update unit 16 updates, for example, the reference database. When the update unit 16 acquires a new relationship between past evaluation target information and reference information, the update unit 16 reflects the relationship in the correlation. For example, when a measurer or the like considers the accuracy of the evaluation result based on the evaluation result output by the output unit 13 and the vibration evaluation device 1 acquires the consideration result, the update unit 16 updates the correlation included in the reference database based on the consideration result. The correlation is updated using, for example, machine learning.

<Laser detector 2>
The laser detector 2 is used to measure vibrations occurring in the structure 9 by using a laser. The laser detector 2 generates vibration data from the vibrations occurring in the structure 9 by using, for example, an interference laser light. The laser detector 2 transmits the generated vibration data to the vibration evaluation device 1. The laser detector 2 may have, for example, a function of Fourier transforming a signal pattern included in the generated vibration data.

The laser detector 2 may be directly connected to the vibration evaluation device 1, or may be connected via a communication network 4, for example. As the laser detector 2, for example, a known laser interferometer or the like is used. The laser detector 2 is controlled, for example, by a control unit 15.

<Communication Network 4>
The communication network 4 is, for example, an Internet network to which the vibration evaluation device 1 is connected via a communication circuit. The communication network 4 may be configured as a so-called optical fiber communication network. The communication network 4 may be realized by a known communication network such as a wired communication network or a wireless communication network.

<Terminal 5>
The terminal 5 is provided, for example, at a location away from the measurement location, and is connected to the vibration evaluation device 1 via a communication network 4. The terminal 5 is, for example, an electronic device such as a personal computer or a tablet terminal. The terminal 5 may have at least a part of the functions of the vibration evaluation device 1, for example.

<Server 6>
The server 6 is provided, for example, at a location away from the measurement location, and is connected to the vibration evaluation device 1 via the communication network 4. The server 6 stores various types of data measured in the past, and various types of data are transmitted from the vibration evaluation device 1 as necessary.

<Imaging device 7>
The imaging device 7 is used to capture an image of the surface of the structure 9. The imaging device 7 transmits the captured image to the vibration evaluation device 1. The imaging device 7 may be connected to the vibration evaluation device 1 directly, for example, or may be connected to the vibration evaluation device 1 via the communication network 4. As the imaging device 7, a known imaging device such as a digital camera may be used.

(Example of Operation of Vibration Evaluation System 100)
Next, a description will be given of an example of the operation of the vibration evaluation system 100 in this embodiment. Fig. 7 is a flowchart showing an example of the operation of the vibration evaluation system 100 in this embodiment.

As shown in FIG. 7, the vibration evaluation system 100 includes an acquisition means S110, a generation means S120, and an output means S130, and may also include, for example, an update means S140.

<Acquisition Means S110>
The acquiring means S110 acquires evaluation target information including first data based on vibration data. The acquiring unit 11 acquires vibration data measured by, for example, the laser detector 2, and acquires the first data based on a signal pattern included in the vibration data. The acquiring unit 11 may acquire one piece of evaluation target information based on, for example, one signal pattern, or may acquire one piece of evaluation target information based on, for example, multiple signal patterns. The acquiring unit 11 stores the acquired evaluation target information, etc. in the saving unit 104, for example via the memory unit 14.

The vibration data is measured, for example, based on at least one of the vibrations in the depth direction, width direction, height direction, and torsional direction of the structure 9. When the vibration data is measured based on two or more of the vibrations in the above directions, the acquisition unit 11 may acquire, for example, first data divided into components for each direction, or may acquire, for example, first data including components in multiple directions.

For example, the vibration data may include multiple measurements based on vibrations in different directions. In this case, the acquisition unit 11 may recognize the data measured at different times as one piece of vibration data and acquire the first data based on the vibration data.

For example, the control unit 15 may control the laser detector 2. In this case, the control unit 15 may cause the laser detector 2 to emit a laser and control the laser detector 2 to receive the laser reflected by the structure 9, thereby causing the laser detector 2 to measure vibration data.

<Generation Means S120>
The generating means S120 refers to the reference database and generates evaluation data for the evaluation target information. The generating unit 12 extracts reference information (first reference data) that has a high degree of relationship with the evaluation target information, for example, based on the associations stored in the reference database. The generating unit 12 generates evaluation data including the extracted first reference data. The generating unit 12 stores the generated evaluation data in the saving unit 104, for example, via the memory unit 14.

In addition to the above, for example, the generation unit 12 selects first target data that includes information identical or similar to the evaluation target information from among the past evaluation target information stored in the reference database. The generation unit 12 selects first reference data that is linked to the selected first target data from among the reference information stored in the reference database, and selects a first degree of association between the first target data and the first reference data.

For example, if the evaluation target information is acquired based on vibration data corresponding to vibrations in two or more directions in the structure 9, the generation unit 12 may generate evaluation data corresponding to each of the vibrations in each direction, and may also generate evaluation data corresponding to the vibration of the entire structure 9 taking into account the vibrations in each direction.

<Output Means S130>
The output means S130 outputs an evaluation result based on the evaluation data. The output unit 13 generates and outputs an evaluation result by, for example, converting the evaluation data into a character string that can be understood by a person who measures the object. The output unit 13 generates the evaluation result by including, for example, the first soundness information included in the first reference data.

This completes the operation of the vibration evaluation system 100 in this embodiment.

<Update Means S140>
For example, when a relationship between past evaluation target information and reference information is newly acquired, the relationship may be reflected in the association (update means S140). The update unit 16 updates the association contained in the reference database based on the results of the evaluation results by the measurer, etc. The timing and frequency of the update unit 16 are arbitrary.

According to this embodiment, the laser detector 2 measures the vibration of the structure 9 using a laser. Therefore, there is no need to increase the number of laser detectors 2 in proportion to the number of floors of the structure 9, and there is no need to install them in the structure 9 in advance. Therefore, compared to sensors that need to be installed in advance, there is an extremely low possibility of a decrease in the accuracy of the evaluation results due to lack of maintenance or damage caused by earthquakes, etc. This makes it possible to obtain highly accurate evaluation results. In addition, vibration data can be obtained without contacting the structure 9. As a result, compared to contact-type measurement methods, there is no need to consider variations in the measurement results due to the contact state, and it is possible to suppress a decrease in evaluation accuracy due to the measurer, etc. In addition, compared to measuring the vibration of the structure 9 due to an earthquake, measurements can be made at any time. This makes it possible to carry out periodic evaluations.

Furthermore, according to this embodiment, the generation unit 12 refers to the reference database and generates evaluation data for the evaluation target information. The evaluation result includes, from among the health information, the first health information linked to the evaluation target information. Therefore, it is possible to generate evaluation data based on past results, and even when a complex signal pattern is included in the vibration data, it is possible to output evaluation results including first health information that is optimal for the evaluation target information. This makes it possible to improve the accuracy of the evaluation result.

In addition, according to this embodiment, the acquisition unit 11 acquires the first data from the result of Fourier transforming the first signal pattern. Therefore, it is possible to output an evaluation result even for slight differences in the signal pattern due to differences in the state of the structure 9. This makes it possible to easily generate optimal evaluation data even for evaluation target information that indicates a complex state of the structure 9.

According to this embodiment, the generating means S120 refers to the reference database and generates evaluation data for the evaluation target information. The evaluation result includes, from among the health information, the first health information linked to the evaluation target information. Therefore, it is possible to generate evaluation data based on past results, and even when the vibration data contains a complex signal pattern, it is possible to output an evaluation result including the first health information that is optimal for the evaluation target information. This makes it possible to improve the accuracy of the evaluation result.

Second Embodiment
Next, a vibration evaluation system 100 and a vibration evaluation device 1 in a second embodiment will be described. The difference between the above-mentioned embodiment and the second embodiment is that the evaluation target information includes the second data. Note that the description of the same contents as those in the above-mentioned embodiment will be omitted.

In the vibration evaluation system 100 of this embodiment, as shown in FIG. 8, for example, the laser detector 2 uses a laser to measure an impact temporarily applied to a part of the structure 9. For this reason, the acquisition unit 11 acquires evaluation target information including first data and second data based on the impact data measured by the laser detector 2. In this case, for example, the evaluation result may include information regarding the shape of a crack 91 that occurs in the structure 9.

The laser detector 2 may measure, for example, vibration and impact at the same time. In this case, the acquisition unit 11 extracts the first data and the second data from the measurement data including, for example, vibration data and impact data, and acquires them as evaluation target information.

In addition to the above, the laser detector 2 may measure, for example, vibration and impact separately. In this case, the acquisition unit 11 may acquire, for example, first data based on vibration data and second data based on impact data at different times.

When acquiring impact data, the vibration evaluation system 100 uses, for example, a laser remote sensing method. In the laser remote sensing method, an impact is generated on the structure 9 by a striking method using a pulsed laser or the like. The impact generated on the structure 9 is then measured as impact data using a laser detector 2. In other words, the impact data can be measured while maintaining non-contact with the structure 9. For this reason, it is possible to suppress variation in the impact data due to contact, compared to, for example, a method in which impact data is measured by contacting the structure 9.

In addition, as a method for generating an impact on the structure 9, a non-contact method may be used, or a contact method may be used. For example, as a method for generating an impact on the structure 9 by striking the structure 9, a method using a known item such as a hammer, a speaker, gas, or a water jet may be used in addition to using the pulse laser described above.

The vibration evaluation system 100 may include, for example, an impact generating device 3. The impact generating device 3 generates an impact on the structure 9. As the impact generating device 3, for example, a pulse laser generator may be used, or a known impact generating device such as a hammering device, a speaker, a gas generator, a water jet device, etc. may be used. The impact generating device 3 may be connected to, for example, the vibration evaluation device 1 and controlled by the vibration evaluation device 1. In this case, for example, the control unit 15 controls the impact generating device 3.

The impact data includes a time waveform signal pattern (second signal pattern) represented by velocity (Velocity (m/s)) versus time (Time (s)), as shown in FIG. 9(a), for example. The impact data can be based on known impact (vibration) measurement results. The impact data includes the second signal pattern from about 10 to 50 milliseconds after the timing of the impact, for example, and can be set arbitrarily depending on the situation.

The second signal pattern shows a complex shape due to the superposition of surface waves that mainly pass through the surface of the structure 9 and internal elastic waves that pass through the inside of the structure 9. Therefore, the content of the second signal pattern obtained differs depending on the state of the structure 9 (for example, the presence or absence of cracks and the shape of the cracks). In this regard, the vibration evaluation system 100 can perform evaluation based on the second signal pattern. Therefore, even if cracks or cavities in the structure 9 occur only inside and do not reach the surface of the structure 9, it is possible to obtain highly accurate evaluation results.

The evaluation target information includes the first data and second data described above. The second data is obtained, for example, from the result of Fourier transforming the second signal pattern included in the impact data (for example, FIG. 9(b)). The Fourier transformed data can be expressed, for example, as magnitude versus frequency (Hz). In this case, for example, multiple characteristic values are extracted from the Fourier transform result and obtained as the evaluation target information. Therefore, compared to directly evaluating the signal pattern of the time waveform, the characteristics of the entire superimposed impact can be the evaluation target. This makes it possible to output evaluation results even for slight differences in impact data due to differences in the condition of the building 9.

In addition to the above, for example, multiple characteristic values may be extracted from the second signal pattern and acquired as the second data included in the evaluation target information. In this case, there is no need to perform processing such as a Fourier transform, and an increase in the number of data processing steps can be suppressed.

The second data included in the evaluation target information may be obtained, for example, from data converted from the second signal pattern into a Mel frequency spectrum, or from Mel frequency cepstral coefficients. As the second data, data in a matrix (e.g., vector) format may be obtained, or data in an image format such as a spectrogram may be obtained.

The evaluation target information and the past evaluation target information include, for example, hammering information. The hammering information indicates information on the method by which an impact was applied to the structure 9 (i.e., the hammering method) in order to measure the impact data. The hammering information includes identification information that differs for each hammering method, such as a pulsed laser, a hammer, a speaker, gas, or a water jet that applies an impact to the structure 9, and may also include information on the hammering conditions, such as the oscillation conditions and irradiation angle of the pulsed laser, the type of hammer, and the time it takes to apply the impact. By including the hammering information in the evaluation target information, it is possible to evaluate slight differences in the second signal pattern due to differences in the hammering method, and it is also possible to perform different evaluations for different hammering methods, for example.

When the past evaluation target information includes hammering sound information, the second data based on the second signal pattern and the hammering sound information can be used as a set of input data for machine learning. In addition to the above, machine learning may be performed using evaluation target information separated for each hammering sound information as input data, or ensemble learning may be performed for each hammering sound information.

The reference information includes, for example, shape information on the shape of cracks 91 occurring in the structure 9. The shape information includes at least any of the depth of the crack 91 in the structure 9, the angle in the thickness direction of the structure 9, the width, the taper angle, the porosity, the moisture content, and the number of branches, and indicates a state that cannot be determined from the surface image of the structure 9 alone. The shape information includes values indicating constant values such as "depth 15 mm" and "width 13 mm," as well as values indicating ranges such as "depth 10-20 mm" and "width 5-10 mm," and the method of displaying the values is arbitrary.

The reference information may include, for example, classification information that classifies the state of the building 9. The classification information may include, for example, definitive classifications such as "sound (normal)" and "defective (abnormal)", as well as classifications of the characteristics and judgment indicators of the cracks 91, such as "crack depth is xx mm or more" and "possibly wide range of impact". The reference information may include, for example, specific examples of past evaluation results, such as aging and treatment history, such as "similar to evaluation of xx building on March 3, 2015", "cracks in xx building expanded to xx mm on September 5, 2015", and "repaired on December 1, 2015", and the combination of contents may be set arbitrarily.

For example, as shown in FIG. 10, the reference database may link reference information to data that combines information based on each signal pattern included in past evaluation target information ("Feature A" to "Feature C" in FIG. 10) and tapping sound information ("Tapping Sound A" to "Tapping Sound C" in FIG. 10).

The reference database may link reference information to data that combines, for example, past first data and past second data. In this case, for example, the data shown as "Feature A" to "Feature C" in FIG. 10 corresponds to past first data, and the data shown as "Hit Sound A" to "Hit Sound C" corresponds to past second data. This makes it possible to reduce the amount of learning data (input data) used when constructing the reference database.

The acquisition unit 11 may acquire, for example, at least one of the measurement position of the impact data in the image information and the impact position where the impact was applied to the structure 9 in the image information.

When a pulsed laser is used to deliver an impact to the structure 9, the impact position can be identified by the laser spot output from the impact generator 3. For this reason, the impact position may be acquired from the impact generator 3, or may be acquired by, for example, the imaging device 7. Note that when an impact is delivered to the structure 9 using a hammer or the like, the impact position may be input directly by, for example, a measurer. Note that the acquisition unit 11 may acquire at least one of the measurement position and the impact position, for example, as part of the evaluation target information. In this case, an evaluation can be performed using the information on each position as an auxiliary parameter, making it possible to further improve accuracy.

For example, if the reference information includes shape information, the output unit 13 generates an evaluation result that includes shape information (e.g., first shape information) that is linked to the evaluation target information from among the shape information. This makes it possible to quantitatively evaluate the internal state of the structure 9.

The output unit 13 outputs an evaluation result including, for example, the result of comparing the evaluation data with the reference evaluation data. For example, as shown in FIG. 11(a), the output unit 13 uses Pearson's product-moment correlation coefficient to calculate the comparison result of each target evaluation data (the first evaluation data to the fifth evaluation data in FIG. 11(a)) against the reference evaluation data, and outputs the result by including it in the evaluation result. The output unit 13 may output, for example, a classification result such as color coding, "sound", or "high possibility of defect" based on the comparison result.

The output unit 13 outputs, for example, an evaluation result linked to at least one of the measurement positions of the impact data in the image information and the impact position in the image information where an impact was applied to the structure 9. The output unit 13 outputs the evaluation result including the impact positions (e.g., positions ref, positions s1 to s5) and image information in which the impact positions (e.g., position int) are plotted, as shown in FIG. 11(b). The output unit 13 may output, for example, numerical values such as X-Y coordinates corresponding to each position in the image (positions ref, positions s1 to s5, position int) including in the evaluation result.

This embodiment can achieve the same effects as the above-mentioned embodiment.

Furthermore, according to this embodiment, the acquisition unit 11 acquires evaluation target information including second data based on impact data. Therefore, it is not necessary to include the measurement position and the like as the minimum parameters required for evaluation. This makes it possible to prevent a decrease in accuracy due to measurement variation between individuals.

Furthermore, according to this embodiment, the acquisition unit 11 acquires evaluation target information including the first data and the second data based on the impact data measured by the laser detector 2. Therefore, an evaluation result including a combination of the soundness of the entire structure 9 and the state of a part of the structure 9 can be obtained. This makes it possible to easily identify the part that affects the soundness of the structure 9.

Furthermore, according to this embodiment, the evaluation target information and past evaluation target information include hammering information on the method of applying an impact to a part of the structure 9 in order to measure the impact data. Therefore, optimal evaluation data can be generated for each of the various hammering methods of applying an impact to a part of the structure 9. This makes it possible to further improve the accuracy of the evaluation results obtained.

Furthermore, according to this embodiment, the evaluation result includes the first shape information linked to the evaluation target information. Therefore, the internal state of the structure 9 can be quantitatively evaluated. This makes it possible to obtain an evaluation result that eliminates the subjectivity of each measurer.

Furthermore, according to this embodiment, for example, the output unit 13 may output an evaluation result including a result of comparing the evaluation data with the reference evaluation data. In this case, it is possible to output an evaluation result that takes into account various conditions such as the installation environment of the structure 9 and the measurement environment. This makes it possible to suppress the variation in the signal pattern that accompanies various conditions.

Furthermore, according to this embodiment, for example, the output unit 13 may output an evaluation result linked to at least one of the measurement position and the impact position. Therefore, when evaluating changes over time, the previous measurement conditions, etc. can be easily understood. This makes it possible to easily carry out measurements, analyses, etc. based on the evaluation results.

The vibration evaluation device 1 and vibration evaluation system 100 described above can evaluate the condition of structures 9, such as instrumentation piping, gas tanks, airplanes, ships, fences, walls, water pipes, and gas pipes. Therefore, it is possible to obtain highly accurate evaluation results even for structures 9 that have been difficult to evaluate or difficult to improve accuracy in the past.

Although embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the gist of the invention. These embodiments and their modifications are included within the scope and gist of the invention, and are included in the scope of the invention and its equivalents described in the claims.

1: Vibration evaluation device 10: Housing 11: Acquisition unit 12: Generation unit 13: Output unit 14: Storage unit 15: Control unit 16: Update unit 101: CPU
102: ROM
103: RAM
104: Storage unit 105: I/F
106: I/F
107: I/F
108: Input section 109: Output section 110: Internal bus 2: Laser detector 3: Impact generator 4: Communication network 5: Terminal 6: Server 7: Imaging device 9: Building 100: Vibration evaluation system S110: Acquisition means S120: Generation means S130: Output means S140: Update means

Claims (5)

A vibration evaluation device that evaluates a state of a structure based on vibration of the structure,
a laser detector that measures the vibration using a laser;
an acquisition unit that acquires evaluation target information including first data based on vibration data measured by the laser detector;
A reference database in which associations between a plurality of pieces of previously acquired past evaluation target information and a plurality of pieces of reference information each associated with the plurality of pieces of previously acquired evaluation target information are stored;
a generation unit that references the reference database and generates evaluation data for the evaluation target information;
an output unit that outputs an evaluation result based on the evaluation data;
Equipped with
The reference information includes soundness information regarding an evaluation of soundness of the past evaluation target information,
The evaluation result includes, among the soundness information, first soundness information linked to the evaluation target information.
Furthermore, the reference information includes shape information regarding the shape of a crack occurring inside the structure,
The evaluation result includes first shape information associated with the evaluation target information among the shape information.
A vibration evaluation device comprising: 2. The vibration evaluation device according to claim 1, wherein the acquisition unit acquires the first data from a result of Fourier transforming a first signal pattern included in the vibration data. the laser detector includes measuring a temporary impact applied to a portion of the structure using the laser;
The acquisition unit is
The first data;
Second data based on impact data measured by the laser detector;
2. The vibration evaluation device according to claim 1, wherein the evaluation object information includes: 4. The vibration evaluation device according to claim 3, wherein the evaluation target information and the past evaluation target information include hammering sound information regarding a method for applying the impact to a part of the structure in order to measure the impact data. A vibration evaluation system for evaluating a state of a structure based on vibration of the structure, comprising:
a laser detector that measures the vibration using a laser;
an acquisition means for acquiring evaluation target information including first data based on vibration data measured by the laser detector;
A reference database in which associations between a plurality of pieces of past evaluation target information acquired in advance and a plurality of pieces of reference information each linked to the plurality of pieces of past evaluation target information are stored;
a generating means for generating evaluation data for the evaluation target information by referring to the reference database;
an output means for outputting an evaluation result based on the evaluation data;
Equipped with
The reference information includes soundness information regarding an evaluation of soundness of the past evaluation target information,
The evaluation result includes, among the soundness information, first soundness information linked to the evaluation target information.
Furthermore, the reference information includes shape information regarding a shape of a crack occurring inside the structure,
The evaluation result includes first shape information associated with the evaluation target information among the shape information.
A vibration evaluation system characterized by:

Images