JP2023095030A - Abnormality detecting system and abnormality detecting method - Google Patents

Abstract

To efficiently and appropriately detect abnormality of a sound generation device.SOLUTION: An abnormality detection system 1 moves to sound collection positions of sound generation devices SG1 to SG4 which convert a sound signal from a sound source SS into a sound and emit the sound. The system includes: an unmanned aerial vehicle 50 for acquiring sound data including sound components of the sound generators SG1 to SG4; and an abnormality determination device 10 for performing determination for abnormality of the sound generators SG1 to SG4 by analyzing the sound data acquired by the unmanned aerial vehicle 50.SELECTED DRAWING: Figure 6

Description

The present disclosure relates to an abnormality detection system for detecting an abnormality in a sound generator that emits sound, and an abnormality detection method for detecting an abnormality in the sound generator.

2. Description of the Related Art It is known to use a moving object such as a drone to detect whether or not there is an abnormality in a structure (for example, a building, a bridge, etc.) or equipment located in a place that is difficult for humans to access. For example, in Patent Document 1, a flying object is used to hit the wall surface of a structure to be investigated that is placed at a high position, and based on the sound generated by hitting the wall surface, it is possible to determine whether there is damage inside the structure. It is disclosed to detect whether or not

Japanese Patent Application Laid-Open No. 2020-139929

On the other hand, in a facility that amplifies important public broadcasts such as disaster broadcasts using a sound generator such as a speaker (called a loudspeaker system), the sound emitted from the sound generator is collected and collected. It is known to determine whether or not there is an abnormality in a sound generator from sound. Conventionally, a worker has gone to the vicinity of the sound generator to collect the sound. In the conventional method, in a facility with many sound generators, it was necessary to move workers to each sound generator.

As a method of detecting an abnormality in the sound generator, a method of detecting whether or not the sound signal from the sound source is appropriately transmitted to the sound generator is also conceivable. This method eliminates the need to send workers to the sound generator. However, even if the sound signal is properly transmitted from the sound source to the sound generating device, an abnormality exists in the sound generating mechanism of the sound generating device (for example, a diaphragm (cone paper) if the sound generating device is a speaker). sound may not be emitted properly. In this way, it is not possible to appropriately determine whether the sound generator is abnormal depending on whether or not the sound signal is being transmitted.

In view of the above viewpoints, an object of the present disclosure is to efficiently and appropriately detect an abnormality in a sound generating device.

In order to solve the above problems, according to one aspect of the present disclosure, an abnormality detection system that detects an abnormality in a sound generating device that converts a sound signal from a sound source into sound and emits sound is provided up to a sound collecting position of the sound generating device. A moving object that moves and acquires sound data including sound components of the sound generating device, and an abnormality determination device that analyzes the sound data acquired by the moving object to determine whether the sound generating device is abnormal. Prepare.

According to another aspect of the present disclosure, an anomaly detection method for detecting an anomaly in a sound generating device that converts a sound signal from a sound source into sound and emits sound includes the steps of: moving a moving object to a sound collecting position of the sound generating device; a step of causing a moving object that has moved to a sound collecting position of the sound generating device to acquire sound data including the sound component of the sound generating device; and C. making an anomaly determination.

In the anomaly detection system and anomaly detection method according to the present disclosure, the moving body is moved to the sound collection position of the sound generation device, and the sound of the sound generation device is collected by the moving body, so sound data can be efficiently acquired. Therefore, the abnormality of the sound generator can be determined efficiently and appropriately.

FIG. 1 shows a configuration example of a public address system. FIG. 2 shows an overall configuration example of an anomaly detection system according to the present disclosure. FIG. 3 shows a configuration example of an abnormality determination device and a control terminal according to the present disclosure. FIG. 4 shows a front appearance of an unmanned air vehicle according to the present disclosure. FIG. 5 shows a configuration example of an unmanned air vehicle according to the present disclosure. FIG. 6 is a flow chart showing the operation of the anomaly detection system according to the first embodiment.

Hereinafter, embodiments will be described in detail with reference to the drawings as appropriate. However, more detailed description than necessary may be omitted. For example, detailed descriptions of well-known matters and redundant descriptions of substantially the same configurations may be omitted. This is to avoid unnecessary verbosity in the following description and to facilitate understanding by those skilled in the art. It should be noted that the accompanying drawings and the following description are provided to enable those skilled in the art to fully understand the present disclosure and are not intended to limit the claimed subject matter thereby.

In the following description, a "sound generator" is a device that converts a sound signal, which is an electrical signal output from a sound source, into sound and emits it to the outside. Specifically, the sound generating device is a speaker. In this case, the sound generator mainly includes an electromagnetic coil that converts sound signals into vibrations, and a diaphragm (cone paper) that generates sound by vibrating due to the vibrations generated by the electromagnetic coil. The sound source includes, for example, a device that automatically outputs pre-recorded voice as a sound signal, a device such as a microphone that converts sound into an electrical signal, or both. A sound source may include a device that amplifies an electrical signal, such as an amplifier.

"Abnormality of the sound generator" means, for example, when the sound signal is output but the sound generator does not emit sound, the sound signal is output and the sound is emitted from the sound generator, but the sound is emitted. Means if the sound does not correspond to the sound signal. "When the emitted sound does not correspond to the sound signal" means, for example, when the emitted sound includes a loud noise sound other than the sound corresponding to the sound signal, the emitted sound is higher or lower than the sound signal (i.e., The frequency of the emitted sound is higher or lower than the frequency of the sound corresponding to the sound signal).

Each embodiment of the present invention will be described below.

1. Embodiment 1
The anomaly detection system 1 described below is a system for detecting an anomaly of sound generators SG1 to SG4 provided in the public address system 100 shown in FIG. 1, for example. The loudspeaker equipment 100 transmits various kinds of information to a large number of people by voice, for example, equipment for amplifying publically important broadcasts such as disaster broadcasts in urban areas, etc., and equipment for amplifying advertisements, store information, etc. in commercial facilities. Equipment.

The sound generating devices SG1 to SG4 of the public address system 100 are devices that convert sound signals from the sound source SS into sounds and emit them, and are devices for amplifying voices to people in the installation area A of the public address system 100. be. The sound generators SG1-SG4 are, for example, speakers. The sound source SS is, for example, owned by the public address system 100 or the manager of the installation area A, and is a device that converts pre-recorded sounds into sound signals and outputs them to the sound generators SG1 to SG4. Also, the sound source SS can convert voice input from a microphone or the like into a sound signal and output the sound signal to the sound generators SG1 to SG4.

In the public address system 100, predetermined sounds are emitted from the sound generators SG1 to SG4 at predetermined times. The anomaly detection system 1 detects an anomaly of the sound generators SG1 to SG4 using the sounds emitted from the sound generators SG1 to SG4 at predetermined times.

Note that the number of sound generators SG1 to SG4 provided in the public address system 100 is not limited to four, and can be any number according to the size of the installation area A and the like.

In the public address system 100, a large number of sound generators SG1 to SG4 are generally arranged. Therefore, the anomaly detection system 1 described below aims to efficiently collect sounds from a large number of sound generators SG1 to SG4. Specifically, the moving body is moved to the sound collecting positions of the sound generators SG1 to SG4, and the sound is efficiently collected by the moving body. Further, the abnormality detection system 1 aims to appropriately determine abnormality of the sound generators SG1 to SG4 using collected sound data.

The sound generators SG1 to SG4 of the public address system 100 are arranged at high positions such as the wall of a building or the top of a pole. Also, in order to collect sounds of sufficient volume from the sound generators SG1 to SG4, it is preferable that the sound collection positions be in the vicinity of the installation positions of the sound generators SG1 to SG4. Therefore, in the anomaly detection system 1 described below, the unmanned flying object 50 is used as a moving object that collects the sounds of the sound generators SG1 to SG4.

1-1. Configuration 1-1-1. Configuration of Anomaly Detection System FIG. 2 schematically shows an overall configuration of an anomaly detection system 1 according to the present embodiment. The anomaly detection system 1 includes an anomaly determination device 10, a control terminal 30 capable of communicating with the anomaly determination device 10 via a network N, and an unmanned aircraft capable of wireless communication with the control terminal 30 and whose flight is controlled by the control terminal 30. and a flying body 50 (an example of a moving body). The network N includes a wired LAN (Local Area Network), a wireless LAN, a WAN (Wide Area Network), and/or the Internet.

The abnormality determination device 10 commands the unmanned flying object 50 to move to the sound collecting positions of the sound generating devices SG1 to SG4 whose abnormality is to be detected, and to collect the sounds of the sound generating devices SG1 to SG4 into the unmanned flying object 50. (referred to as a sound collection command) is transmitted to the control terminal 30 . In addition, the abnormality determination device 10 analyzes the sound collected by the unmanned flying object 50 and determines abnormality of each of the sound generation devices SG1 to SG4.

The control terminal 30 receives the sound collection command from the abnormality determination device 10 and causes the unmanned air vehicle 50 to perform an operation according to the sound collection command. Specifically, for example, automatically or manually, the unmanned flying object 50 is made to fly close to the target sound generating devices SG1 to SG4 whose abnormality is to be detected, and then the sound generating devices SG1 to SG1 to SG4 near the unmanned flying object 50 The sound of SG4 is collected, and the collected sound data is transmitted to the abnormality determination device 10 via the control terminal 30. - 特許庁

1-1-2. Configuration of Abnormality Determination Device The abnormality determination device 10 shown in FIG. The control unit 11 is an electronic circuit such as a CPU (Central Processing Unit). The control unit 11 operates as an arithmetic processing device and a control device, and controls the abnormality determination device 10 according to various programs in order to execute functions to be described later. The storage unit 12 is ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), SSD (Solid State Drive), FeRAM (Ferroelectric Random Access Memory), or the like. The ROM, HDD, SSD, FeRAM, and the like store programs used by the control unit 11, calculation parameters, calculation results, and the like. The RAM temporarily stores programs used in executing the functions of the control unit 11, parameters that change as appropriate during the execution, and the like. The communication unit 19 is, for example, a network interface card for connecting to a wired LAN or the Internet. The communication unit 19 may be a wireless communication interface for connecting to a base station or a communication interface compatible with a wireless LAN.

The control unit 11 executes the functions of the command unit 111 , the reception unit 112 , and the determination unit 113 by executing a program read from the storage unit 12 .

The command unit 111 transmits a command (sound collection command) for the unmanned air vehicle 50 to collect the sounds of the sound generators SG1 to SG4 to the control terminal 30 via the communication unit 19 . The sound collection command includes, for example, a flight route to the sound collection positions of the sound generators SG1 to SG4 and a command to collect the sound of each of the sound generators SG1 to SG4.

The flight route included in the sound collection command may include information about the order in which the plurality of sound generators SG1 to SG4 should be moved. For example, when moving in the order of sound generator SG1, sound generator SG2, sound generator SG3, and sound generator SG4, the flight route is, for example, the flight route from the current position of unmanned flying object 50 to sound generator SG1. , flight route from sound generator SG1 to sound generator SG2, flight route from sound generator SG2 to sound generator SG3, flight route from sound generator SG3 to sound generator SG4, unmanned flight from sound generator SG4 Includes the flight route to the tarmac of body 50.

Moreover, in order to appropriately detect an abnormality in the sound generators SG1 to SG4, it is preferable that the sounds collected from the sound generators SG1 to SG4 are always the same or similar. The same sound means, for example, sounds included in speech and/or music of the same content. On the other hand, similar sounds mean, for example, sounds that differ in speech and/or music content but have the same or similar features (for example, frequency patterns) included in the sounds.

Therefore, the command to collect sound included in the sound collection command may include information (for example, time) representing the timing at which the same or similar sounds are emitted from the sound generators SG1 to SG4. . This makes it possible to control the unmanned flying object 50, for example, to wait until a specific sound is emitted from the sound generators SG1 to SG4, and then start collecting the sound.

Furthermore, the command to collect sound may include information regarding the length of time for which sound is to be collected. As a result, it is possible to obtain sound data that includes an amount of information that allows appropriate detection of anomalies and that does not increase the data size.

The receiving unit 112 receives collected sound data from the unmanned air vehicle 50 via the control terminal 30 and the wireless communication unit 39 . The receiving unit 112 stores the received sound data in the storage unit 12 . The sound data may be deleted from the storage unit 12 after being used to determine whether the sound generators SG1 to SG4 are abnormal, or may be stored in the storage unit 12 after the determination. By storing the sound data even after the abnormality determination, the sound data can be used as teacher data for the determining unit 113, for example.

The determination unit 113 analyzes the sound data received by the reception unit 112 and makes determinations regarding the abnormality of the sound generators SG1 to SG4. In the present embodiment, the determination unit 113 has an input layer to which information about sound data is input, and an output for outputting a determination result regarding abnormality of the sound generators SG1 to SG4 from which the sound data input to the input layer is obtained. It is composed of a neural network having layers. An intermediate layer may be included between the input layer and the output layer of the neural network. In addition, the intermediate layer may further include a plurality of layers (so-called deep neural network).

Information about sound data input to the input layer includes, for example, sound data itself without any processing, data obtained by extracting specific frequency components from sound data, and data obtained by Fourier transforming sound data. can. Data obtained by Fourier transforming sound data can be data representing, for example, the frequency included in the sound data and the magnitude of the frequency component.

The judgment result output from the output layer is, for example, whether the sound generating devices SG1 to SG4 to be detected are abnormal or normal. Specifically, for example, the output layer outputs "1" when the sound generating devices SG1 to SG4 to be detected are abnormal, and outputs "0" when they are normal. Alternatively, conversely, "0" is output from the output layer when the sound generators SG1 to SG4 to be detected are abnormal, and "1" is output from the output layer when they are normal. good too.

The output layer of the neural network can also output numerical values other than '0' or '1'. Using this characteristic, the output layer of the determination unit 113 may output, for example, numerical values (scores) regarding abnormalities of the sound generators SG1 to SG4. Specifically, for example, the greater the degree of abnormality of the sound generators SG1 to SG4, the greater the numerical value that can be output from the output layer. In this case, for example, when the numerical value output from the output layer becomes equal to or greater than a predetermined threshold value, it can be determined that an abnormality requiring investigation exists in the sound generators SG1 to SG4.

The output layer can also output multiple types of numerical values. For example, the output layer can output the presence or absence of a plurality of abnormalities that can occur in the sound generators SG1 to SG4, or a score indicating the degree of a plurality of abnormalities.

The determination unit 113 configured by a neural network is trained in advance before use. That is, the determination unit 113 is a trained model of a neural network.

As will be described later, the sound data acquired by the unmanned air vehicle 50 includes sound components of the sound generators SG1 to SG4 and operating sound components of the unmanned air vehicle 50 (mainly, wing sounds of the rotor blades 55). ,It is included. Therefore, in the present embodiment, the learning of the determination unit 113 is performed using, for example, sound data containing sound components of normal sound generators SG1 to SG4 and operation sound components of the unmanned air vehicle 50 as teacher data. using As a result, even if the acquired sound data is input as it is to the input layer, an appropriate determination result regarding abnormality is output from the output layer.

Note that the teacher data may be sound data including sound components of the sound generators SG1 to SG4 having an abnormality and operation sound components of the unmanned flying object 50 . The teacher data may be sound data actually acquired by the unmanned flying object 50, or a model of sound components from the sound generators SG1 to SG4 and operation sound components of the unmanned flying object 50. It may also be theoretical sound data generated by converting the sound data.

Furthermore, the teacher data may contain only sound components from the sound generators SG1 to SG4. In this case, the input layer may be input with sound data including components of the operation sound of the unmanned flying object 50, or may be input with the operation sound removed from the sound data.

1-1-3. Configuration of Control Terminal The control terminal 30 shown in FIG. 3 is a computer device for executing control of the unmanned air vehicle 50 by wireless communication. 39. The control unit 31 is an electronic circuit such as a CPU, and operates as an arithmetic processing device and a control device. The control unit 31 controls the control terminal 30 according to various programs in order to execute functions to be described later. The storage unit 32 is a semiconductor memory such as a ROM, a RAM, or a flash memory. The ROM and flash memory store programs used by the control unit 31, calculation parameters, calculation results, and the like. The RAM temporarily stores programs used in executing the functions of the control unit 31, parameters that change as appropriate during execution, and the like. The input unit 36 includes a joystick, buttons, a touch panel, or the like, and controls the flight of the unmanned air vehicle 50 according to the operator's input operations. The input unit 36 also receives input for controlling the direction of the speaker, microphone, and camera mounted on the unmanned air vehicle 50 . The display unit 37 is configured by a liquid crystal display device or an organic EL display device. The display unit 37 displays information about the sound collection command received from the abnormality determination device 10 and the flight route. The display unit 37 also displays videos and images captured by the camera of the unmanned air vehicle 50 .

The wireless communication unit 39 may be, for example, a wireless communication interface for connecting to a base station. Also, the wireless communication unit 39 may be a communication interface compatible with a wireless LAN.

The control unit 31 executes the functions of the flight instruction unit 311 and the sound collection instruction unit 312 by executing a program read from the storage unit 32 . The flight instruction unit 311 extracts the flight route of the unmanned flying object 50 from the sound collection command received from the abnormality determination device 10 and transmits flight instructions to the unmanned flying object 50 according to the extracted flight route. The sound collection instruction unit 312 extracts a command to collect the sound of each of the sound generators SG1 to SG4 from the sound collection command received from the abnormality determination device 10, and issues a sound collection command in accordance with the command to collect the sound. Send to unmanned air vehicle 50 .

When the command for collecting sound received from the abnormality determination device 10 includes information indicating the timing at which the same or similar sounds are emitted from the sound generators SG1 to SG4, the sound collection instruction unit 312 receives this information. A sound collection instruction is transmitted to the unmanned flying object 50 at the timing shown in .

1-1-4. Configuration of Unmanned Aerial Vehicle FIG. 4 shows a front appearance of the unmanned aerial vehicle 50 , and FIG. 5 shows an example of the overall configuration of the unmanned aerial vehicle 50 . The unmanned flying object 50 is an unmanned aircraft capable of remote control and automatic control, and performs flight operations such as ascending, advancing, rotating, and descending according to flight instructions from the control terminal 30 . The unmanned air vehicle 50 includes a body 50a, a plurality of arms 50b extending horizontally and radially from the body 50a, a plurality of legs 50c extending downward, and a rotor 55 attached to the upper end of each leg 50c. . The unmanned air vehicle 50 flies by lift generated by rotating the rotor blades 55 by rotating the motor 56 . The unmanned air vehicle 50 also changes the direction of rotation of some of the rotor blades 55 to generate reaction and prevent the main body 50a itself from rotating. A microphone 64 is attached to the main body 50 a of the unmanned air vehicle 50 . The microphone 64 collects the sounds of the sound generators SG1 to SG4 when the unmanned flying object 50 approaches. The direction of sound collection of the microphone 64 can be changed by changing the angle in the vertical direction by the microphone direction control mechanism 63 .

As shown in FIG. 5, the unmanned air vehicle 50 includes a control device 51, a storage device 52, a sensor group 53, a GPS receiver 54, a battery 58, and a wireless communication device 59 as components for flight. Prepare. The control device 51 is an electronic circuit such as a CPU, and functions as an arithmetic processing device and a control device. The control device 51 controls the unmanned flying object 50 according to various programs in order to execute functions to be described later. The storage device 52 is a memory such as a ROM, a RAM, or a flash memory. The ROM and flash memory store programs used by the control device 51, calculation parameters, calculation results, and the like. The RAM temporarily stores programs used in executing the functions of the control device 51, parameters that change as appropriate during execution, and the like.

The sensor group 53 includes an acceleration sensor and an angular velocity sensor for detecting acceleration and angular velocity for attitude control of the unmanned flying object 50, an air pressure sensor for detecting the altitude of the unmanned flying object 50, and a direction for detecting the direction of the unmanned flying object 50. including geomagnetic sensors, etc. GPS receiver 54 includes an antenna and a signal processing unit to receive signals from GPS satellites for detecting position information of unmanned air vehicle 50 . A battery 58 stores electric power necessary for the operation of the unmanned air vehicle 50 and supplies it to each part. The wireless communication device 59 includes a wireless communication interface for wirelessly communicating with the control terminal 30 .

Unmanned air vehicle 50 further comprises camera orientation control mechanism 65 and camera 66 . A camera 66 photographs the surroundings of the unmanned flying object 50 or the situation in the traveling direction. The camera 66 can change the photographing direction by changing the angle in the vertical direction using the camera direction control mechanism 65 .

The control device 51 executes the functions of the flight control unit 511 , the sound collection control unit 512 , and the image control unit 513 by executing programs read from the storage device 52 . The flight control unit 511 controls the number of rotations and rotation speed of the motor 56 in accordance with flight instructions from the control terminal 30 to cause the unmanned air vehicle 50 to fly. The flight control unit 511 acquires the inclination and rotation direction of the main body 50a shown in FIG. Get location information including azimuth. A storage device 52 stores programs in which algorithms for controlling the attitude and basic flight motions of the unmanned air vehicle 50 during flight are implemented. The program causes the unmanned air vehicle 50 to fly while correcting the attitude and position of the main body 50a in accordance with the flight instructions transmitted from the control terminal 30. The unmanned air vehicle 50 may be manually operated by an operator using the control terminal 30 or may be autonomously flown along a flight route transmitted from the control terminal 30 .

The sound collection control unit 512 collects the sounds of the sound generators SG1 to SG4 as sound data using the microphone 64 in accordance with the sound collection instructions transmitted from the control terminal 30 and received via the wireless communication device 59, and performs wireless communication. It is transmitted to the control terminal 30 via the device 59 . The sound collection control unit 512 may use the data collected by the microphone 64 as sound data without compression, or may compress the collected sound data and use it as sound data. Further, the sound collection control unit 512 may extract only the feature portion used for abnormality detection from the data collected by using the microphone 64 and use it as sound data.

The image control unit 513 temporarily stores videos and images captured by the camera 66 in the storage device 52 and transmits them to the control terminal 30 via the wireless communication device 59 .

1-2. Operation The operation of the abnormality detection system 1 shown in FIGS. 1 to 5 will be described with reference to FIG.
First, the command unit 111 of the abnormality determination device 10 determines whether or not it is time to move the unmanned flying object 50 to the target sound generators SG1 to SG4 for abnormality determination (S101). Specifically, the command unit 111 determines whether or not it is time to emit a predetermined sound to be collected from the sound generating devices SG1 to SG4 for which abnormality determination is to be performed. The predetermined sounds to be collected are, for example, sounds of the same content or similar sounds periodically emitted from the sound generators SG1 to SG4.

If it is determined that it is not the timing to move the unmanned air vehicle 50 ("No" in S101), the process waits until the timing arrives.

On the other hand, when it is determined that it is time to move the unmanned air vehicle 50 (“Yes” in S101), the command unit 111 outputs the above sound collection command to the control terminal 30. FIG. Upon receiving the sound collection command, the control terminal 30 moves the unmanned air vehicle 50 to the target sound generators SG1 to SG4 for abnormality determination according to the flight route included in the sound collection command (S102).

After the unmanned flying object 50 arrives at the sound collection positions of the sound generators SG1 to SG4 for which an abnormality is to be determined, the control terminal 30 follows the sound collection command and unmannedly operates at the sound collection positions of the sound generators SG1 to SG4. With the flying object 50 hovering, the microphone 64 of the unmanned flying object 50 is used to collect sounds from the sound generators SG1 to SG4 (S103). In this way, the unmanned flying object 50 is hovering when the sounds of the sound generators SG1 to SG4 are collected. In other words, the unmanned flying object 50 is also operating while the sounds of the sound generators SG1 to SG4 are being collected. Therefore, the sound data collected using the microphone 64 includes the sound components of the sound generators SG1 to SG4 and the components of the operation sound of the unmanned flying object 50 (mainly the sound of the rotor blades 55). be

After collecting the sounds of the sound generating devices SG1 to SG4 for which abnormality is to be judged, the unmanned flying object 50 transmits the collected sounds as sound data to the abnormality judgment device 10 via the control terminal 30 (S104). ). After receiving the sound data transmitted from the unmanned air vehicle 50 , the reception unit 112 of the abnormality determination device 10 stores the sound data in the storage unit 12 .

Next, the control terminal 30 determines whether or not the sounds of all the sound generators SG1 to SG4 provided in the public address system 100 (or all the sound generators SG1 to SG4 for which abnormality determination is to be performed) have been collected. It judges (S105). If the sounds of all the sound generators SG1 to SG4 have not been collected ("No" in S105), the control terminal 30 collects sounds from the current sound generators SG1 to SG4 in accordance with the sound collection command. The unmanned flying object 50 is moved to the target sound generators SG1 to SG4, and the sounds of the sound generators SG1 to SG4 are collected (S102 to S104).

After collecting the sounds of all the sound generators SG1 to SG4 ("Yes" in S105), the determination unit 113 of the abnormality determination device 10 sequentially inputs the sound data stored in the storage unit 12, and SG1 to SG4 are judged to be abnormal. The determination unit 113 stores in the storage unit 12 the determination results regarding the abnormality of each of the sound generators SG1 to SG4.

If the judgment result of any of the sound generators SG1 to SG4 indicates the existence of an abnormality, the terminal (for example, personal computer, smartphone, tablet terminal) connected to the abnormality judgment device 10 has an abnormality. You may notify that it exists. This notification may be sent to the terminal by e-mail, may be displayed as a pop-up on the terminal, or may be notification by generating a predetermined alarm sound on the terminal.

1-3. Features The abnormality detection system 1 and the abnormality detection method for detecting an abnormality in the sound generators SG1 to SG4 using the unmanned flying object 50 according to the above-described embodiment can The unmanned flying object 50 is moved to the sound position to collect the sounds of the sound generators SG1 to SG4. Also, by analyzing the sound data acquired by the unmanned flying object 50, the abnormality of the sound generators SG1 to SG4 is determined. By causing the unmanned flying object 50 to collect the sounds of the sound generators SG1 to SG4 in this manner, the sound data of the sound generators SG1 to SG4 can be efficiently obtained.

Further, in the abnormality detection system 1 according to the above-described embodiment, the neural network (learned model thereof) determines the abnormality of the sound generators SG1 to SG4 based on the sound data. As a result, it is possible to appropriately determine whether the sound generating devices SG1 to SG4 are abnormal without designing a logical model, algorithm, or the like for analyzing the sound data and calculating the determination result regarding the abnormality.

2. Other Embodiments As described above, each embodiment has been described as an example of the technology disclosed in the present application. However, the technology in the present disclosure is not limited to this, and can be applied to embodiments in which modifications, replacements, additions, omissions, etc. are made as appropriate. Further, it is also possible to combine the constituent elements described in the above embodiments to form a new embodiment. For example, the following embodiments are conceivable.

(1) In the above-described embodiment, the abnormality is determined after acquiring the sound data from all the sound generators SG1 to SG4. This is not the only option, and the abnormality may be determined each time the sound data of one of the sound generators SG1 to SG4 is obtained.

(2) If there is an appropriate model and/or algorithm for judging an abnormality from sound data, the judging unit 113 may be realized as software or hardware that implements this model and/or algorithm.

For example, the determination unit 113 compares the reference value data regarding the sounds of normal sound generators SG1 to SG4 with the sound data acquired by the unmanned air vehicle 50, and if the sound data is outside the range of the reference value data, It can be realized as an algorithm for judging that the sound generating devices SG1 to SG4 are abnormal. The reference value data is data representing characteristics of sounds emitted from normal sound generators SG1 to SG4. The reference value data includes, for example, frequency components containing sounds emitted from normal sound generators SG1 to SG4, setting information (for example, volume of sounds to be emitted, equalizer settings, etc.) regarding the sound generators SG1 to SG4. .

For example, if the sound components other than the sound generators SG1 to SG4 included in the sound data such as the operation sound of the unmanned flying object 50 are constant, the sound components other than the sound generators SG1 to SG4 are removed by frequency filtering or the like. can. In this case, the determination unit 113 can appropriately detect an abnormality in the sound generators SG1 to SG4 based on the sound data (from which sound components other than the sound generators SG1 to SG4 are removed) using the above algorithm. .

(3) For example, when the sound generators SG1 to SG4 need to amplify important content such as an emergency broadcast during sound collection, the unmanned flying object 50 should be positioned away from the sound generators SG1 to SG4. (for example, far above the sound generators SG1 to SG4). This prevents important contents from being drowned out by the operating sound of the unmanned flying object 50 and being inaudible to people.

(4) The determination unit 113 configured by a neural network may be a software implementation of the neural network algorithm, or may be a hardware implementation of the neural network.

(5) The unmanned flying object 50 that collects sound is not limited to one, and the anomaly detection system 1 may have a plurality of them.

(6) In the above embodiment, the unmanned flying object 50 collects sounds from the single sound generators SG1 to SG4. However, the present invention is not limited to this, and one unmanned flying object 50 may hover at an intermediate point between the plurality of sound generators SG1 to SG4 and collect the sounds of the plurality of sound generators SG1 to SG4 all at once. . That is, the sound collection position may be an intermediate point between the plurality of sound generators SG1 to SG4. In this case, the unmanned flying object 50 may have a sound collector provided with a plurality of microphones, such as an array microphone, as the microphone 64 for collecting sound.

As a result, for example, the unmanned flying object 50 hovers at the midpoint between the two sound generators SG1 to SG4 and collects the sounds of the two sound generators SG1 to SG4 at the same time, so that the sound can be collected efficiently. . Further, for example, it is possible to simultaneously determine an abnormality such that any one of the plurality of sound generators SG1 to SG4 does not emit sound.

(7) The anomaly detection system 1 according to the above embodiment includes the control terminal 30, but is not limited to this. The anomaly detection system 1 may have a configuration in which the anomaly determination device 10 directly transmits a sound collection command to the unmanned flying object 50 . Specifically, the abnormality determination device 10 is arranged as part of the control system of the unmanned flying object 50, and the unmanned flying object 50 automatically flies and collects sounds by remote communication via the communication unit 19. good too.

(8) The unmanned flying object 50 may have a speaker for amplifying the sound from the unmanned flying object 50 and a speaker direction adjustment mechanism for adjusting the orientation of the speaker.

(9) In the above embodiments, each device or system can have a cloud computing configuration in which one function is shared by a plurality of devices via a network and processed jointly.

(10) When the sound generator is placed at a relatively low position, instead of the unmanned flying object 50, an autonomous mobile robot equipped with a microphone for collecting sound and moving autonomously on the ground is used. The sound of the sound generator may be collected.

(11) In the above embodiments, the device or system includes a set of multiple components (devices, modules (parts), etc.), and whether or not all the components are in the same housing. does not matter. A plurality of devices housed in separate housings and connected via a network, and a single device housing a plurality of modules in one housing are both referred to as a system. In some cases.

Each step described in the flowchart above can be executed by a single device, or can be shared and executed by a plurality of devices. Furthermore, when one step includes a plurality of processes, the plurality of processes included in the one step can be executed by one device or shared by a plurality of devices.

In the above embodiments, the control section or control device of each device or device is configured with a dedicated electronic circuit designed to achieve a predetermined function according to the function required for each device or device. may include a processor that Also, the control unit or control device can be realized by various processors or electronic circuits such as MPU, GPU, DSP, FPGA, ASIC, etc., in addition to CPU. A controller or controller may be comprised of one or more processors.

Depending on the functions required for each device or device, any computer-readable recording medium, such as an optical disk, a magnetic disk, or a magneto-optical disk , magnetic tape, HDD, SD card, SSD, or the like.

The computer program is not limited to being recorded on a recording medium, and may be obtained via an electric communication line, a wireless or wired communication line, a network represented by the Internet, or the like.

The communication unit or communication device of each device or device may use any communication interface, such as wireless LAN, wired LAN, 3G (3rd Generation), LTE (Long Term Evolution), depending on the function required for each device or device. ), 4G (4th Generation), 5G (5th Generation), and millimeter wave wireless communication interfaces.

Each process of the above embodiment may be realized by hardware, or may be realized by software (including cases where it is realized together with an OS (operating system), middleware, or a predetermined library). Furthermore, each process may be realized by mixed processing of software and hardware.

The execution order of the operations of the system, device, or device in the above embodiments is not necessarily limited to the description of the above embodiments, and the execution order can be changed or multiple operations can be performed without departing from the spirit of the invention. Actions can be performed simultaneously.

The present disclosure is widely applicable to sound generator routing systems, routing devices, and routing methods.

1: Anomaly detection system 10: Anomaly judgment device 11: Control unit 111: Command unit 112: Reception unit 113: Judgment unit 12: Storage unit 19: Communication unit 30: Control terminal 31: Control unit 311: Flight instruction unit 312: Collection Sound instruction unit 32 : Storage unit 36 : Input unit 37 : Display unit 39 : Wireless communication unit 50 : Unmanned flying object 50a : Main body 50b : Arm 50c : Leg 51 : Control device 511 : Flight control unit 512 : Sound collection control unit 513: Image control unit 52: Storage device 53: Sensor group 54: GPS receiver 55: Rotary blade 56: Motor 58: Battery 59: Wireless communication device 63: Microphone direction control mechanism 64: Microphone 65: Camera direction control mechanism 66: Camera N: Network 100: Public Address Equipment A: Installation Areas SG1 to SG4: Sound Generator SS: Sound Source

Claims (8)

An anomaly detection system for detecting an anomaly in a sound generator that converts a sound signal from a sound source into sound and emits sound,
a moving body that moves to a sound collecting position of the sound generating device and acquires sound data including sound components of the sound generating device;
an abnormality determination device that determines an abnormality of the sound generator by analyzing sound data acquired by the moving body;
anomaly detection system. The abnormality determination device is
an input layer into which information about the sound data is input;
an output layer for outputting a determination result regarding an abnormality of the sound generating device from which the sound data input to the input layer is acquired;
2. The anomaly detection system according to claim 1, comprising a determination unit configured by a neural network having 3. The abnormality detection system according to claim 2, wherein said output layer outputs whether said sound generator is abnormal or whether said sound generator is normal as said determination result. 3. The anomaly detection system according to claim 2, wherein said output layer outputs a numerical value relating to an anomaly of said sound generator as said determination result. The abnormality determination device compares the sound data with reference value data relating to the sound of the sound generator that is normal, and determines that the sound generator is abnormal if the sound data is outside the range of the reference value data. 2. The anomaly detection system of claim 1, wherein the anomaly detection system determines. 6. The anomaly detection system according to claim 1, wherein said sound data includes a sound component of said sound generator and an operation sound component of said moving body. The abnormality detection system according to any one of claims 1 to 6, wherein said moving body moves to said sound generating device at a timing when said sound generating device for which abnormality is to be determined emits a predetermined sound. An anomaly detection method for detecting an anomaly in a sound generating device that converts a sound signal from a sound source into sound and emits sound,
a step of moving a moving body to a sound collecting position of the sound generating device;
a step of causing the moving object that has moved to a sound collecting position of the sound generating device to acquire sound data including sound components of the sound generating device;
a step of analyzing the sound data acquired by the moving object to determine whether the sound generating device is abnormal;
An anomaly detection method comprising:

Images