JP6913571B2 - Vibration mode prediction device and vibration mode prediction model learning device - Google Patents

Description

The present invention relates to a vibration mode prediction device and a vibration mode prediction model learning device.

Conventionally, a technique for predicting vibration of a building is known (see, for example, Patent Documents 1 to 3). In the technique described in Patent Document 1, acceleration information indicating acceleration for each frequency of vibration generated in the vibration source according to the vibration force applied to the vibration source located outside the building, vibration. Damping factor information showing the damping rate for each frequency of vibration due to the ground between the source and the building, loss rate information showing the loss rate for each frequency of vibration when inputting to the building through the ground, and in the building Resonance amplification factor information indicating the resonance amplification factor for each vibration frequency is acquired, and a physical quantity indicating the state of vibration generated inside the building is derived according to the exciting force.

Further, in the technique described in Patent Document 2, the vibration level prediction in the building is classified by the presence or absence of resonance between the ground vibration and the building in the building having the same structural system as the building, and the two-step average vibration level amplification is performed. Either one of the quantities and the vibration level of the ground measured by vibration measurement are added.

Further, in the technique described in Patent Document 3, the vibration level of the ground on which the building is constructed is measured and the vibration level is analyzed for each frequency, and the range of the frequency expected as the natural frequency of the building is assumed. By calculating the vibration level of the building for all the values of the natural frequencies of the building in the assumed range, the vibration level of each natural frequency assumed for the building is predicted.

Japanese Unexamined Patent Publication No. 2008-117089 Japanese Unexamined Patent Publication No. 2001-215167 Japanese Unexamined Patent Publication No. 2001-349776

However, the techniques described in Patent Documents 1 to 3 do not consider vibration caused by an event around the building.

An object of the present invention is to accurately predict the vibration mode of a building according to a surrounding event in consideration of the above facts.

The vibration mode prediction device according to the present invention has an event information receiving unit that receives future event information around the building to be predicted, and learning to predict the vibration mode at the time of the event of the building to be predicted from the event information. It is configured to include a prediction unit that predicts the vibration mode of the building to be predicted at the time of the event indicated by the event information received by the event information reception unit using the completed model.

According to the vibration mode prediction device according to the present invention, the event information reception unit receives future event information around the building to be predicted. Then, the prediction unit uses a learned model for predicting the vibration mode at the time of the event of the building to be predicted from the event information, and the event information received by the event information reception unit indicates the event time. Predict the vibration mode of the building to be predicted.

In this way, by predicting the vibration mode of the building at the time of the event using the trained model for predicting the vibration mode at the time of the event from the event information, the vibration mode of the building according to the surrounding event can be accurately determined. Can be predicted.

The building to be predicted according to the present invention is a building in which a vibration control device is installed, and the vibration mode is any one of a plurality of vibration modes controlled by the vibration control device. Thereby, the vibration mode to be controlled by the vibration control device at the time of the event can be adjusted in advance.

The vibration mode prediction model learning device according to the present invention predicts based on a sensor data acquisition unit that acquires sensor data output by a sensor installed in a building to be predicted and sensor data acquired by the sensor data acquisition unit. Event information that receives event information related to events around the building to be predicted when the sensor outputs sensor data acquired by the vibration mode determination unit that determines the vibration mode of the target building and the sensor data acquisition unit. At the time of the event of the building to be predicted from the event information, the set of the reception unit, the vibration mode determined by the vibration mode determination unit, and the event information received by the event information reception unit is used as learning data. It is configured to include a model learning unit that learns a model for predicting the vibration mode of.

According to the vibration mode prediction model learning device according to the present invention, the sensor data acquisition unit acquires the sensor data output by the sensor installed in the building to be predicted. The vibration mode determination unit determines the vibration mode of the building to be predicted based on the sensor data acquired by the sensor data acquisition unit. The event information reception unit receives event information related to an event around the building to be predicted when the sensor outputs the sensor data acquired by the sensor data acquisition unit. Then, the model learning unit uses the set of the vibration mode determined by the vibration mode determination unit and the event information received by the event information reception unit as learning data, and the building to be predicted from the event information. Learn a model for predicting the vibration mode at the time of the event.

In this way, based on the vibration mode of the building to be predicted determined from the sensor data and the received event information regarding the event around the building to be predicted, the event information of the building to be predicted is used. By learning the model for predicting the vibration mode at the time of an event, it is possible to learn the model for accurately predicting the vibration mode of the building according to the surrounding event.

The building to be predicted according to the present invention is a building in which a vibration control device is installed, and the vibration mode is any one of a plurality of vibration modes controlled by the vibration control device. This makes it possible to learn in advance a model that predicts the vibration mode in order to adjust the vibration mode to be controlled by the vibration control device at the time of an event.

As described above, according to the vibration mode prediction device of the present invention, the vibration mode of the building at the time of the event is predicted by using the learned model for predicting the vibration mode at the time of the event from the event information. The effect of being able to accurately predict the vibration mode of a building according to surrounding events can be obtained.

Further, according to the vibration mode prediction model learning device of the present invention, based on the vibration mode of the building to be predicted determined from the sensor data and the received event information regarding the event around the building to be predicted. By learning a model for predicting the vibration mode of the building to be predicted at the time of the event from the event information, learning a model for accurately predicting the vibration mode of the building according to the surrounding event. The effect of being able to do is obtained.

It is the schematic which shows the structure of the vibration mode prediction system which concerns on 1st Embodiment of this invention. It is a figure which shows the example of the arrangement of a sensor. It is a block diagram which shows the server which concerns on 1st Embodiment of this invention. It is a functional block diagram which shows the server which concerns on 1st Embodiment of this invention. It is a figure for demonstrating the method of determining the main vibration mode. It is a figure which shows the example of the control mode determined for each event. It is a flowchart which shows the content of the learning data creation processing routine of the server which concerns on 1st Embodiment of this invention. It is a flowchart which shows the content of the learning processing routine of the server which concerns on 1st Embodiment of this invention. It is a flowchart which shows the content of the vibration mode prediction processing routine of the server which concerns on 1st Embodiment of this invention. It is a flowchart which shows the content of the learning data creation processing routine of the server which concerns on 2nd Embodiment of this invention. It is a figure which shows the state that a building vibrates by a traffic event. It is a figure which shows the example which does not arrange a sensor at the time of vibration mode prediction.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

<Outline of Embodiment of the present invention>
Synchronized mass dampers (hereinafter also referred to as TMDs (tuned mass dampers)) install weights with springs and dampers on the rooftop floor and other parts of the building, and absorb the vibration energy of the building by resonating the weights. .. In order to move the TMD efficiently and absorb the vibration energy, it is necessary to resonate with the vibration mode (generally the primary vibration mode) of the building so that the weight easily swings. Therefore, in a passive type vibration control device represented by TMD (a type in which the vibration control device is driven without requiring external supply energy such as electric power), a device that performs optimum control for the vibration mode to be controlled in advance. Need to be adjusted.

However, disturbances (hereinafter referred to as events) that excite the vibration mode to be controlled do not always occur, and especially in large-scale buildings such as skyscrapers, higher-order modes (secondary and third-order vibration modes). ) May impair comfort and cause discomfort. In order to control a plurality of vibration modes with a passive type vibration control device, a plurality of control devices are required, but there are concerns about the installation location and cost.

Therefore, in the embodiment of the present invention, event information (disturbance input information) and vibration of the controlled building (output information) are observed by using a sensor in a building in which a passive vibration control device is installed. , Accumulate data. Regarding event information, not only numerical information measured by sensors, but also, for example, if the event is a movement of people due to a concert (jumping, vertical, etc.), the number of spectators, seating arrangement, music genre, etc. The information that determines the characteristics of the vibration caused by the above is also accumulated.

Based on this information, the vibration mode of the building is predicted for the event that is predicted to occur in the future, and the vibration control device is adjusted in advance so as to be the optimum control, thereby suppressing the vibration of the building.

[First Embodiment]
<Structure of Vibration Mode Prediction System of First Embodiment of the Present Invention>
As shown in FIG. 1, the vibration mode prediction system 100 according to the embodiment of the present invention includes a server 10, a sensor 60, and a building-side terminal 70, and the server 10, the sensor 60, and the building-side terminal 70 are provided. , The Internet and the like, are connected to each other via a network 78. The server 10 is an example of a vibration mode prediction device.

As shown in FIG. 2, the sensor 60 is attached to the building 90 in which the passive vibration control device 80 is installed, detects the vibration acceleration of the building 90, and sequentially transmits the sensor data to the server 10. Here, the vibration control device 80 is, for example, a TMD, has a plurality of vibration modes to be controlled, and is manually switched so as to be a control mode for controlling the vibration of any of the plurality of vibration modes. ..

The building side terminal 70 is a terminal installed on the building 90 side, and is, for example, a computer terminal, a mobile phone, a PDA (Personal Digital Assistants) terminal, or the like. The building side terminal 70 receives the event information regarding the event around the building 90 input by the operator and transmits it to the server 10. The event information includes, for example, the type of event, the number of spectators, the seating arrangement, and the like.

As shown in FIG. 3, the server 10 includes a CPU 62, a ROM 64, a RAM 66, an HDD 68, a communication interface 71, and a bus 73 for connecting them to each other.

The CPU 62 executes various programs. The RAM 66 is used as a work area or the like when the CPU 62 executes various programs. The HDD 68 as a recording medium stores various programs and various data including a program for executing a learning data creation processing routine, a learning processing routine, and a vibration mode prediction processing routine, which will be described later.

The server 10 in the present embodiment is represented by a functional block according to a program for executing a learning data creation processing routine, a learning processing routine, and a vibration mode prediction processing routine, as shown in FIG. The server 10 includes an input unit 12, a calculation unit 20, and an output unit 50.

The input unit 12 receives the sensor data received from the sensor 60 and the event information received from the building side terminal 70. Further, the input unit 12 receives the event information of the prediction target event received from the building side terminal 70.

The calculation unit 20 includes an event information acquisition unit 22, a sensor data acquisition unit 24, a learning data creation unit 26, a learning data storage unit 28, a model learning unit 30, a model storage unit 32, a prediction target event information acquisition unit 34, and a vibration mode prediction. A unit 36 and a control mode determination unit 38 are provided. The event information acquisition unit 22 is an example of an event information reception unit, and the learning data creation unit 26 is an example of a vibration mode determination unit.

The event information acquisition unit 22 acquires the event information received from the building side terminal 70.

The sensor data acquisition unit 24 sequentially acquires the sensor data received from the sensor 60.

The learning data creation unit 26 performs frequency analysis on the time series of the sensor data received from the sensor 60, and based on the result of the frequency analysis, among the plurality of vibration modes controlled by the vibration control device 80, among the plurality of vibration modes to be controlled. Determine the main vibration mode. For example, as shown in FIG. 5, the vibration waveform obtained from the time series of the sensor data received from the sensor 60 is subjected to frequency analysis and the waveform in the frequency domain of each vibration mode (primary mode to tertiary mode). Is filtered to determine the main vibration mode (secondary mode in the example of FIG. 5).

Further, the learning data creation unit 26 creates a pair of the determined main vibration mode and the corresponding event information as learning data, and stores the pair in the learning data storage unit 28.

The learning data storage unit 28 stores a plurality of created learning data.

The model learning unit 30 learns a model for predicting the vibration mode at the time of an event of the building to be predicted from the event information by using a plurality of learning data stored in the learning data storage unit 28. The model is, for example, a neural network that inputs a vector representing event information (event type, number of spectators, seat arrangement, music genre) and outputs a vector representing the probability of each vibration mode. , Learn the model.

The model storage unit 32 stores the parameters of the model learned by the model learning unit 30.

The prediction target event information acquisition unit 34 acquires the event information of the prediction target event received from the building side terminal 70.

The vibration mode prediction unit 36 predicts the vibration mode at the time of the event to be predicted based on the event information of the event to be predicted and the model learned by the model learning unit 30. For example, a vector representing the event information of the event to be predicted is input to the model, and the vibration mode having the highest probability is predicted as the vibration mode at the time of the event to be predicted from the output probabilities of each vibration mode.

The control mode determination unit 38 determines the control mode of the vibration control device 80 corresponding to the predicted vibration mode based on the correspondence relationship between the vibration mode and the control mode, which is predetermined for the vibration control device 80.

The output unit 50 transmits the determined control mode of the vibration control device 80 to the building side terminal 70.

On the building side terminal 70, the control mode of the vibration control device 80 determined by the server 10 is displayed. The operator manually switches the control mode of the vibration control device 80 so as to be the displayed control mode, and prepares for the occurrence of the event to be predicted. As a result, as shown in FIG. 6, when the control mode of the vibration control device 80 is determined for each prediction target event, the control mode of the vibration control device 80 is manually switched before the occurrence of each prediction target event. ..

<Operation of vibration mode prediction system>
Next, the operation of the vibration mode prediction system 100 according to the first embodiment of the present invention will be described.

First, the operator manually sets the control mode of the vibration control device 80 to a specific control mode, and when the sensor data is sequentially transmitted to the server 10 by the sensor 60, the server 10 shows the figure 7 in FIG. The training data creation processing routine shown is executed.

First, in step S102, it is determined whether or not vibration is generated in the building 90 based on the sensor data received from the sensor 60. For example, when the vibration acceleration of the building 90 represented by the sensor data is equal to or greater than the threshold value, it is determined that the building 90 is vibrating.

If it is determined that the building 90 is not vibrating, the step S102 is repeated, and if it is determined that the building 90 is vibrating, the process proceeds to step S104.

In step S104, the sensor data received from the sensor 60 is acquired and stored in a memory (not shown).

In step S106, it is determined whether or not the vibration generated in the building 90 has ended based on the sensor data received from the sensor 60. For example, when the vibration acceleration of the building 90 represented by the sensor data is less than the threshold value, it is determined that the vibration generated in the building 90 has ended.

If it is determined that the vibration generated in the building 90 has not been completed, the process returns to step S104. On the other hand, if it is determined that the vibration generated in the building 90 has ended, the process proceeds to step S108.

In step S108, frequency analysis is performed on the time series of the sensor data acquired in step S104. In step S110, the main vibration mode among the plurality of vibration modes controlled by the vibration control device 80 is determined based on the result of the frequency analysis in step S108.

In step S112, a message requesting event information regarding an event that has occurred immediately before the building 90 is transmitted to the building side terminal 70, and screen data for inputting the event information is transmitted. Then, the input screen indicated by the screen data is displayed on the building side terminal 70, and when the event information is input by the operator, the input event information is transmitted to the server 10, and the server 10 acquires the event information. ..

In step S114, a pair of the main vibration mode determined in step S108 and the event information acquired in step S112 is created as learning data and stored in the learning data storage unit 28. Then, the process returns to step S102.

By the above-mentioned learning data creation processing routine, every time the building 90 vibrates due to an event around the building 90, the server 10 creates the learning data, so that the learning data is accumulated.

Further, the server 10 periodically executes the learning processing routine shown in FIG.

First, in step S120, the learning data stored in the learning data storage unit 28 is read.

Then, in step S122, based on the learning data acquired in step S120, a model for predicting the vibration mode at the time of the event of the building to be predicted is learned from the event information, and the model storage unit 32 learns. Stores model parameters and ends the learning process routine.

Then, when the event information of the event to be predicted is input by the operator at the terminal 70 on the building side, the input event information is transmitted to the server 10, and the server 10 executes the vibration mode prediction processing routine shown in FIG. Will be done.

First, in step S130, the event information of the prediction target event received from the building side terminal 70 is received.

In step S132, the vibration mode at the time of the event to be predicted is predicted based on the event information of the event to be predicted obtained in step S130 and the model learned by the learning processing routine.

In step S134, the control mode of the vibration control device 80 corresponding to the predicted vibration mode based on the correspondence relationship between the vibration mode and the control mode, which is predetermined for the vibration control device 80, is set as the optimum control mode. The determined and determined control mode of the vibration control device 80 is transmitted to the building side terminal 70, and the vibration mode prediction processing routine is terminated.

Then, on the building side terminal 70, the control mode of the vibration control device 80 determined by the server 10 is displayed. The operator manually switches the control mode of the vibration control device 80 so as to be the displayed control mode, and prepares for the occurrence of the event to be predicted.

As described above, according to the vibration mode prediction system according to the first embodiment of the present invention, the vibration mode of the building to be predicted and the periphery of the received building to be predicted are determined from the sensor data. By learning a model for predicting the vibration mode of the building to be predicted at the time of the event from the event information based on the event information related to the event of, the vibration mode of the building according to the surrounding event is accurately predicted. You can learn the model for.

In addition, by predicting the vibration mode of the building at the time of the event using the trained model for predicting the vibration mode at the time of the event from the event information, the vibration mode of the building according to the surrounding event is accurately predicted. be able to. Further, by adjusting the vibration control device according to the predicted vibration mode before the event occurs, the vibration due to the event occurrence can be appropriately suppressed.

In addition, event information and measured building response are linked to create and accumulate learning data. By accumulating data through long-term measurement, the probability of occurrence of unexpected events can be reduced and more accurate control can be performed.

Further, by adjusting the passive type vibration control device before the event occurs and performing pseudo control, it is possible to perform optimum vibration control for the vibration of the building. In addition, the introduction and operation costs can be reduced as compared with the active type vibration control device.

[Second Embodiment]
Next, the vibration mode prediction system according to the second embodiment will be described. Since the vibration mode prediction system according to the second embodiment has the same configuration as that of the first embodiment, the same reference numerals are given and the description thereof will be omitted.

The second embodiment is different from the first embodiment in that when the learning data is created, the event information is received in advance and then the sensor data at the time of the event occurrence is acquired.

The learning data creation processing routine according to the second embodiment will be described with reference to FIG. A detailed description of the same processing as that of the first embodiment will be omitted.

When the operator inputs the event information including the event occurrence period of the event to be generated in the building side terminal 70, the input event information is transmitted to the server 10, and when the server 10 receives the event information, the input event information is transmitted. The server 10 executes the learning data creation processing routine shown in FIG.

First, in step S200, the event information received from the building side terminal 70 is received.

Then, in step S202, it is determined whether or not the event has been started based on the event occurrence period included in the received event information. If it is determined that the event has not started, step S202 is repeated, and if it is determined that the event has started, the process proceeds to step S204.

In step S204, the sensor data received from the sensor 60 is acquired and stored in a memory (not shown).

In step S206, it is determined whether or not the event has ended based on the event occurrence period included in the received event information. If it is determined that the event has not ended, the process returns to step S204, and if it is determined that the event has ended, the process proceeds to step S108.

In step S108, frequency analysis is performed on the time series of the sensor data acquired in step S204. In step S110, the main vibration mode among the plurality of vibration modes controlled by the vibration control device 80 is determined based on the result of the frequency analysis in step S108.

In step S114, a pair of the main vibration mode determined in step S108 and the event information acquired in step S200 is created as learning data, stored in the learning data storage unit 28, and a learning data creation processing routine. To finish.

By the above-mentioned learning data creation processing routine, the learning data is created by the server 10 every time the event information is input in the building side terminal 70, so that the learning data is accumulated.

Since the configuration and other operations of the vibration mode prediction system according to the second embodiment are the same as those of the first embodiment, the description thereof will be omitted.

The present invention is not limited to the above-described embodiment, and various modifications and applications are possible without departing from the gist of the present invention.

For example, in the above embodiment, the case where the building vibrates due to an event such as a concert has been described as an example, but the present invention is not limited to this. For example, it can be applied when the building vibrates due to a traffic event in which a train or truck passes around the building (Fig. 11). In this case, the type of vehicle passing through, the number of occupants, and the like may be input as the event information.

It can also be applied when a building vibrates due to a meteorological event such as a strong wind. In this case, the wind direction, wind speed, etc. may be input as the event information.

Further, when the model has been trained, it is not necessary to install the sensor in the building 90 as shown in FIG. This is because the server has a learning function, so that if vibration measurement for an event is performed, optimum control can be performed without a sensor.

Further, before the event occurs, the manager and the residents in the vicinity may be provided with the vibration information by using the predicted vibration mode.

Further, the case where the model learning and the vibration mode prediction are realized by one device has been described as an example, but the present invention is not limited to this, and the model learning is performed by a vibration mode prediction model learning device different from the server. It may be configured to be realized by. In this case, the vibration mode prediction model learning device includes an event information acquisition unit 22, a sensor data acquisition unit 24, a learning data creation unit 26, a learning data storage unit 28, a model learning unit 30, and a model storage unit 32. Just do it.

Further, the program of the present invention may be stored in a storage medium and provided.

10 Server 12 Input unit 20 Calculation unit 22 Event information acquisition unit 24 Sensor data acquisition unit 26 Learning data creation unit 28 Learning data storage unit 30 Model learning unit 32 Model storage unit 34 Prediction target event information acquisition unit 36 Vibration mode prediction unit 38 Control Mode determination unit 50 Output unit 60 Sensor 70 Building side terminal 78 Network 80 Vibration control device 90 Building 100 Vibration mode prediction system

Claims (4)

The event information reception department that accepts future event information around the building to be predicted,
Using a trained model for predicting the vibration mode of the building to be predicted at the time of the event from the event information, the vibration of the building to be predicted at the time of the event indicated by the event information received by the event information reception unit. Predictor that predicts the mode and
Vibration mode predictor including. The building to be predicted is a building in which a vibration control device is installed.
The vibration mode prediction device according to claim 1, wherein the vibration mode is any one of a plurality of vibration modes controlled by the vibration control device. A sensor data acquisition unit that acquires sensor data output by sensors installed in the building to be predicted,
Based on the sensor data acquired by the sensor data acquisition unit, the vibration mode determination unit that determines the vibration mode of the building to be predicted, and the vibration mode determination unit.
An event information reception unit that receives event information related to an event around the building to be predicted when the sensor outputs sensor data acquired by the sensor data acquisition unit.
Using the set of the vibration mode determined by the vibration mode determination unit and the event information received by the event information reception unit as learning data, the vibration mode at the time of the event of the building to be predicted is determined from the event information. A model learning department that learns a model for prediction,
Vibration mode prediction model learning device including. The building to be predicted is a building in which a vibration control device is installed.
The vibration mode prediction model learning device according to claim 3, wherein the vibration mode is one of a plurality of vibration modes controlled by the vibration control device.

Images