JPWO2018198315A1 - Computer system, equipment abnormal sound judging method and program - Google Patents

Abstract

The present invention aims to provide a computer system, an equipment abnormal sound judging method, and a program that make it easy to execute machine learning by machine learning normal sound and detecting abnormal sound when different. A computer system that determines the abnormal sound of the facility in the facility, acquires a normal sound when the facility is normal, machine-learns the waveform of the normal sound, and the facility is normal or abnormal An unknown unknown sound is acquired, an abnormal point of the waveform of the unknown sound different from the machine-learned result is detected, and an abnormal sound is generated at the abnormal point when the abnormal point satisfies a predetermined condition judge.

Description

  The present invention relates to a computer system that determines an abnormal sound of equipment in a facility, a method of determining an abnormal sound, and a program.

  In recent years, when part or all of the equipment in a facility breaks down, correlation between the abnormal noise and the location where the fault occurs is created by specifying the abnormal noise and the location of the fault. Furthermore, in addition to this correlation, determination of abnormality is performed based on external factors (temperature, pressure, humidity, speed, acceleration, pressure, tension, load, etc.).

  As a configuration for determining such an abnormality, an external factor of the target device is acquired as sensing data, and based on the reference sound data generated based on this and the sound data generated by the target device, an abnormality of the target device Patent Document 1 discloses a configuration for diagnosing

JP, 2013-200143, A

  However, in the configuration of Patent Document 1, it is difficult to perform machine learning because the types and patterns of failure targets are diverse. This is because it is necessary to find out the malfunctioning device when making machine learning with the abnormal noise of the malfunctioning device as the correct data, and to record the abnormal noise generated by this device and learn it as the correct data. It was because it took a lot of time to acquire.

  An object of the present invention is to provide a computer system, an equipment abnormal sound judging method, and a program that make it easy to execute machine learning by machine learning normal sound and detecting abnormal sound when different. I assume.

  The present invention provides the following solutions.

The present invention is a computer system for determining abnormal noise of equipment in a facility, comprising:
Normal sound acquisition means for acquiring a normal sound when the equipment is normal;
Machine learning means for machine learning the waveform of the normal sound;
Unknown sound acquisition means for acquiring an unknown sound that is normal or abnormal or unknown in the equipment;
Detection means for detecting an abnormal point of the waveform of the unknown sound different from the machine-learned result;
A determination unit that determines that an abnormal sound is generated at the abnormal point when the abnormal point satisfies a predetermined condition;
Providing a computer system characterized by comprising:

  According to the present invention, the computer system that determines the abnormal sound of the facility in the facility acquires a normal sound when the facility is normal, machine-learns the waveform of the normal sound, and the facility is normal. If an unknown or unknown unknown sound is acquired, an abnormal point of the waveform of the unknown sound different from the machine-learned result is detected, and the abnormal point satisfies a predetermined condition, an abnormality is detected at the abnormal point. It is determined that a sound has occurred.

  The present invention is a category of computer system, but also exerts the same operation / effect according to the category in other categories such as an equipment abnormal sound judging method and a program.

  According to the present invention, it is possible to provide a computer system, an equipment abnormal sound judging method and a program that make it easy to execute machine learning.

FIG. 1 is a diagram showing an outline of a facility abnormality sound determination system 1. FIG. 2 is an entire configuration diagram of the equipment abnormal sound determination system 1. FIG. 3 is a functional block diagram of the computer 10 and the portable terminal 100. FIG. 4 is a flowchart showing normal sound learning processing performed by the computer 10 and the portable terminal 100. FIG. 5 is a flowchart showing the unknown sound determination process performed by the computer 10 and the portable terminal 100. FIG. 6 is a flowchart showing the unknown sound determination process performed by the computer 10 and the portable terminal 100.

  Hereinafter, the best mode for carrying out the present invention will be described with reference to the drawings. Note that these are merely examples, and the technical scope of the present invention is not limited to these.

[Outline of Equipment Abnormality Sound Determination System 1]
An outline of a preferred embodiment of the present invention will be described based on FIG. FIG. 1 is a view for explaining an outline of a facility abnormal sound determination system 1 according to a preferred embodiment of the present invention. The facility abnormal sound determination system 1 is a computer system that includes a computer 10 and a portable terminal 100 and determines abnormal noise of facilities in a facility.

  In FIG. 1, the number of computers 10 and portable terminals 100 can be changed as appropriate. The computer 10 and the portable terminal 100 may be virtual devices as well as existing devices. In addition, each process described later may be realized by either or both of the computer 10 and the portable terminal 100.

  The computer 10 is a computer device connected so as to be capable of data communication with the portable terminal 100.

  The portable terminal 100 is a terminal device connected so as to be capable of data communication with the computer 10. The mobile terminal 100 is, for example, a mobile phone, a portable information terminal, a tablet terminal, a personal computer, an electric appliance such as a netbook terminal, a slate terminal, an electronic book terminal, a portable music player, a smart glass, a head mounted display, etc. Wearable terminals and other goods.

  First, the portable terminal 100 acquires a normal sound which is a sound of a normal time of equipment (pipes, various devices, etc.) (step S01). The portable terminal 100 collects normal sound with a microphone or the like that it has. The portable terminal 100 collects, for example, the sound of equipment that is considered to be normal, such as a newly installed equipment, as the normal sound.

  The portable terminal 100 transmits normal sound data indicating the acquired normal sound to the computer 10 (step S02).

  The computer 10 receives normal sound data. The computer 10 acquires the normal sound by receiving the normal sound data.

  The computer 10 machine-learns the waveform of the normal sound based on the normal sound data (step S03). The computer 10 learns, for example, whether the waveform is normal to rise or fall at a predetermined point. As a result of machine learning, the computer 10 can stochastically determine which of the rising and falling of the waveform at a predetermined point is normal.

  The portable terminal 100 acquires an unknown sound whose facility is normal or abnormal or unknown (step S04). Similar to the normal sound, the portable terminal 100 collects an unknown sound with a microphone or the like that it has. The portable terminal 100 collects, as an unknown sound, a sound of equipment that is considered to be normal, abnormal, or unknown, such as the equipment currently used.

  The portable terminal 100 transmits unknown sound data indicating the acquired unknown sound to the computer 10 (step S05).

  The computer 10 receives unknown sound data. The computer 10 acquires an unknown sound by receiving unknown sound data.

  The computer 10 extracts the waveform of the acquired unknown sound (step S06). The computer 10 extracts unknown sound data by excluding an environmental sound (for example, a natural sound, a voice emitted by a user or the like) included in the unknown sound data from the unknown sound data. This environmental sound is excluded based on known sound data stored in advance by the computer 10.

  The computer 10 compares the machine-learned normal sound waveform with the extracted unknown sound waveform to detect an abnormal point of the unknown sound waveform (step S07). The computer 10 compares the machine-learned result with the extracted unknown sound waveform to determine whether there is an unknown sound waveform different from the machine-learned waveform result. Detect an abnormal point in the waveform of an unknown sound. As a result of machine learning, the computer 10 determines whether the waveform of the normal sound at this point coincides with either rising or falling when either rising or falling occurs at a predetermined point as a result of machine learning. Based on it, it is determined whether it is normal or abnormal. That is, if the waveform of the unknown sound rises at the point where the waveform of the normal sound rises, the computer 10 determines that it is normal, and if the waveform of the unknown sound falls at the point where the waveform of the normal sound rises. Judge that it is abnormal. Further, when the waveform of the unknown sound rises at the point where the waveform of the normal sound goes down, the computer 10 determines that it is abnormal, and when the waveform of the unknown sound goes down at the point where the waveform of the normal sound goes down. Judge that it is normal. In addition, the computer 10 detects the abnormal point of the waveform of the unknown sound by the difference between the time when the change occurs in the waveform of the unknown sound and the time when the change similar to the waveform of the unknown sound occurs in the waveform of the machine-learned normal sound. To detect

  The computer 10 determines whether the abnormal sound generated at the abnormal point satisfies a predetermined condition, and determines that the abnormal sound is generated at the abnormal point when the predetermined condition is satisfied (step S08). The computer 10 determines that an abnormal sound is generated at the abnormal point, for example, when an abnormal point is equal to or more than a predetermined number of times as a predetermined condition, and when an abnormal point is equal to or more than a predetermined period.

  The above is the outline of the equipment abnormal sound determination system 1.

[System Configuration of Equipment Abnormal Sound Determination System 1]
The system configuration of the equipment abnormal sound determination system 1 according to the preferred embodiment of the present invention will be described based on FIG. FIG. 2 is a diagram showing a system configuration of a facility abnormal sound determination system 1 according to a preferred embodiment of the present invention. The facility abnormal sound determination system 1 includes a computer 10, a portable terminal 100, and a public network (Internet network, third and fourth generation communication networks, etc.) 5, and is a computer for determining abnormal noise of facilities in a facility. It is a system.

  In addition, the number and the kind of each apparatus which comprise the installation abnormality sound determination system 1 can be changed suitably. Moreover, the installation abnormal sound determination system 1 may be implement | achieved not only with the existing apparatus but virtual apparatuses. Moreover, each process mentioned later may be implement | achieved by either or both of each apparatuses which comprise the installation abnormal sound determination system 1. FIG.

  The computer 10 is the above-described computer device having the functions described later.

  The portable terminal 100 is the above-described terminal device having a function described later.

[Description of each function]
Based on FIG. 3, the function of the installation abnormal sound determination system 1 according to the preferred embodiment of the present invention will be described. FIG. 3 is a functional block diagram of the computer 10 and the portable terminal 100. As shown in FIG.

  The computer 10 includes a central processing unit (CPU), a random access memory (RAM), a read only memory (ROM), and the like as the control unit 11, and a device for enabling communication with other devices as the communication unit 12. For example, a device compatible with Wi-Fi (Wireless-Fidelity) compliant with IEEE 802.11 is provided. In addition, the computer 10 includes, as the storage unit 13, a storage unit of data such as a hard disk, a semiconductor memory, a recording medium, and a memory card. The computer 10 also includes, as the processing unit 14, various devices and the like that execute various calculations, processes, machine learning, and the like.

  In the computer 10, the control unit 11 reads a predetermined program to realize the data reception module 20 and the abnormality notification transmission module 21 in cooperation with the communication unit 12. In addition, in the computer 10, the control unit 11 reads a predetermined program to realize the storage module 30 in cooperation with the storage unit 13. Further, in the computer 10, the control unit 11 reads a predetermined program to cooperate with the processing unit 14 to form the waveform extraction module 40, the machine learning module 41, the point detection module 42, the abnormality determination module 43, and the analysis module 44. To achieve.

  Similar to the computer 10, the portable terminal 100 includes a CPU, a RAM, a ROM, and the like as the control unit 110, and a device for enabling communication with another device as the communication unit 120. In addition, the portable terminal 100 includes, as the input / output unit 140, a display unit for outputting and displaying data or an image controlled by the control unit 110, an input unit such as a touch panel or a keyboard that receives an input from the user, a mouse, It is equipped with various devices such as sound collection devices that make sounds.

  In the portable terminal 100, the control unit 110 reads a predetermined program to realize the data transmission module 150 and the abnormality notification reception module 151 in cooperation with the communication unit 120. In addition, in the portable terminal 100, the control unit 110 reads a predetermined program to realize the sound collection module 170, the input receiving module 171, and the display module 172 in cooperation with the input / output unit 140.

Normal sound learning process
The normal sound learning process performed by the facility abnormal sound determination system 1 will be described based on FIG. 4. FIG. 4 is a diagram showing a flowchart of normal sound learning processing executed by the computer 10 and the portable terminal 100. As shown in FIG. The process executed by the module of each device described above will be described together with this process.

  First, the sound collection module 170 collects a normal sound which is a sound of a normal time of equipment (pipes, various devices, etc.) (step S10). In step S10, the sound collection module 170 collects normal sound with a sound collection device such as a microphone that it has. The sound collection module 170 collects, as a normal sound, a sound of equipment that is considered to be normal, such as a newly installed device or a device that has just been maintained. The portable terminal 100 acquires a normal sound by collecting a normal sound.

  The input receiving module 171 receives an input of the identifier of the facility collected this time (step S11). In step S11, the input receiving module 171 receives an input using, for example, a name, an installation place, and a model as an identifier.

  The data transmission module 150 transmits the acquired normal sound and the identifier of the facility that has acquired the normal sound to the computer 10 as normal sound data (step S12).

  The data receiving module 20 receives normal sound data. The computer 10 acquires the normal sound of the facility by receiving the normal sound data.

  The waveform extraction module 40 extracts the waveform of the normal sound from the acquired normal sound (step S13). In step S13, the waveform extraction module 40 extracts the waveform of the normal sound of the facility by excluding the environmental sound, noise and the like included in the normal sound. The environmental sound is, for example, natural sound, noise in the facility, or voice emitted by the user. The waveform extraction module 40 refers to, for example, the waveforms and frequencies of the sounds stored in advance by the storage module 30 and excludes the waveforms and frequencies of the sounds included in the normal sound data, thereby removing the waveforms and frequencies from the normal sound data. , Exclude environmental sounds and noise.

  The machine learning module 41 performs machine learning as the extracted normal sound as teacher data (step S14). In step S14, the machine learning module 41 machine-learns the waveform of the normal sound and the time of this waveform. The machine learning module 41 machine-learns whether the waveform of the normal sound rises or falls from a particular point. Normal sound when the equipment is normal, although a slight difference occurs, but it will be similar waveforms, so a predetermined point (for example, 10 seconds after the start of sound collection, 15 seconds after, 20 seconds after, 31 After a second), it is possible to determine probabilistically whether the waveform rises or falls. The machine learning module 41 machine-learns the change in the waveform that is considered to be probabilistically high as being normal. For example, if the probability that the waveform has risen at a predetermined point is 95% and the probability that it has dropped is 5%, then it is machine-learned that it is normal for the waveform to rise at this point. The machine learning module 41 machine-learns the change of the waveform of the normal sound at each point based on this probability.

  The storage module 30 stores the learning result (step S15). In step S15, the storage module 30 associates and stores the change of the waveform of the normal sound at each point obtained as the learning result and the identifier of the facility from which the normal sound is acquired.

  The above is the normal sound learning process.

[Unknown sound judgment processing]
Based on FIG. 5 and FIG. 6, the unknown sound determination process performed by the equipment abnormal sound determination system 1 will be described. FIG.5 and FIG.6 is a figure which shows the flowchart of the unknown sound determination process which the computer 10 and the portable terminal 100 perform. The process executed by the module of each device described above will be described together with this process.

  First, the sound collection module 170 collects an unknown sound of equipment (step S20). In step S20, the sound collection module 170 collects an unknown sound of the equipment because the equipment is normal or abnormal or unknown. The portable terminal 100 acquires an unknown sound by collecting an unknown sound.

  The input receiving module 171 receives an input of the identifier of the facility collected this time (step S21). In step S21, the input reception module 171 inputs, for example, a name, an installation place, and a model as an identifier.

  The data transmission module 150 transmits the acquired unknown sound and the identifier of the facility from which the unknown sound is acquired to the computer 10 as unknown sound data (step S22).

  The data receiving module 20 receives unknown sound data. The computer 10 acquires the unknown sound of the facility by receiving the unknown sound data.

  The waveform extraction module 40 extracts the waveform of this unknown sound from the acquired unknown sound (step S23). In step S23, the waveform extraction module 40 extracts the waveform of the unknown sound of the facility by excluding the environmental sound, noise and the like included in the unknown sound. The waveform extraction module 40 refers to, for example, a waveform or frequency such as environmental sound or noise stored in advance in the storage module 30, and excludes the waveform or frequency of these sounds included in the unknown sound data to obtain an unknown sound. Exclude environmental noise and noise from the data.

  The point detection module 42 detects an abnormal point of the waveform of the unknown sound from the result of machine learning of the normal sound and the waveform of the extracted unknown sound (step S24). In step S24, the point detection module 42 detects, as an abnormal point, a point at which a change in waveform different from the machine-learned result has occurred among the unknown sound waveforms. For example, as a result of machine learning, the point detection module 42 detects the point as an abnormal point when the waveform of the unknown sound does not rise at a point where the sound should rise if the sound is normal. In addition, as a result of machine learning, the point detection module 42 detects the point as an abnormal point when the waveform of the unknown sound does not fall at a point that should fall if it is a normal sound as a result of machine learning. In addition, the point detection module 42 detects the point as an abnormal point when the waveform of the unknown sound is rising or falling at a point where neither normal sound nor rise or fall as a result of machine learning.

  When a change occurs in the waveform of the unknown sound at a time different from the time at the point where the change in the waveform of the normal sound occurs as a result of machine learning, the point detection module 42 detects this point as an abnormal point, A difference between the time when a change occurs in the waveform of the normal sound and the time when a change occurs in the waveform of the unknown sound at this time is detected as a shifted period.

  The abnormality determination module 43 determines whether the detected abnormal point satisfies a predetermined condition (e.g., whether a predetermined number of times or more, a predetermined period of time or more has occurred) (step S25). In step S25, for example, when the abnormality determination module 43 detects that the number of occurrences of the abnormal point is a predetermined number or more (for example, three or more, five or more, ten or more), the predetermined condition is satisfied. It is determined that In addition, when the occurrence time of the abnormal point is deviated from the occurrence time of the change of the waveform in the normal sound by a predetermined period or more (for example, 3 seconds or more, 5 seconds or more, 10 seconds or more), the abnormality determination module 43 It is determined that a predetermined condition is satisfied.

  In step S25, when the abnormality determination module 43 determines that the predetermined condition is not satisfied (NO in step S25), the process ends.

  On the other hand, when the abnormality determination module 43 determines in step S25 that the predetermined condition is satisfied (YES in step S25), it determines that an abnormal sound is generated at the detected abnormality point (step S26).

  The analysis module 44 analyzes the content of the abnormal sound generated at the abnormal point based on the determination result (step S27). In step S27, the analysis module 44 analyzes the content of the abnormal sound based on the change and the frequency of the unknown sound waveform at the abnormal point. The analysis module 44 analyzes, for example, the location, symptoms, response method, safety, and urgency as the content of the abnormality. The analysis module 44 analyzes the content of the abnormality based on the amount of change in the waveform, the frequency per unit time, and the like.

  The analysis module 44 may analyze the content of the abnormal sound by another method.

  The abnormality notification transmission module 21 transmits the content of the abnormal sound obtained as a result of the analysis and the identifier of the facility in which the abnormal sound is generated to the portable terminal 100 as an abnormality notification (step S28). The abnormality notification may be only the content of the abnormal sound.

  The abnormality notification receiving module 151 receives an abnormality notification. The display module 172 displays the content of the abnormal sound generated in the facility and the identifier of the facility in which the abnormal sound is generated as the abnormality notification based on the received abnormality notification (step S29). The display module 151 may display only the content of the abnormal sound when the abnormality notification includes only the content of the abnormal sound.

  In the processing of steps S27 to S29 described above, the computer 10 may be configured to notify the portable terminal 100 that an abnormal sound is generated. In this case, the portable terminal 100 may display that the abnormal sound is generated in the facility.

  The above-described means and functions are realized by a computer (including a CPU, an information processing device, and various terminals) reading and executing a predetermined program. The program is provided, for example, in the form of being provided from a computer via a network (SaaS: software as a service). Also, the program is provided in the form of being recorded in a computer readable recording medium such as, for example, a flexible disk, a CD (such as a CD-ROM), and a DVD (such as a DVD-ROM or a DVD-RAM). In this case, the computer reads the program from the recording medium, transfers the program to an internal storage device or an external storage device, stores it, and executes it. Alternatively, the program may be recorded in advance in a storage device (recording medium) such as, for example, a magnetic disk, an optical disk, or a magneto-optical disk, and may be provided from the storage device to the computer via a communication line.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to these embodiment mentioned above. Further, the effects described in the embodiments of the present invention only list the most preferable effects resulting from the present invention, and the effects according to the present invention are limited to those described in the embodiments of the present invention is not.

  1 Equipment abnormal sound judgment system, 10 computers, 100 mobile terminals

Claims (6)

A computer system for determining abnormal noise of equipment in a facility, comprising:
Normal sound acquisition means for acquiring a normal sound when the equipment is normal;
Machine learning means for machine learning the waveform of the normal sound;
Unknown sound acquisition means for acquiring an unknown sound that is normal or abnormal or unknown in the equipment;
Detection means for detecting an abnormal point of the waveform of the unknown sound different from the machine-learned result;
A determination unit that determines that an abnormal sound is generated at the abnormal point when the abnormal point satisfies a predetermined condition;
A computer system comprising: The machine learning means uses the normal sound as teacher data to perform machine learning as to whether the waveform rises or falls from a specific point.
The computer system according to claim 1, characterized in that: The determination means determines that an abnormal sound has occurred at the abnormal point, when the abnormal point has occurred a predetermined number of times or more.
The computer system according to claim 1, characterized in that: The determination unit determines that an abnormal sound is generated at the abnormal point, when the abnormal point is greater than or equal to a predetermined period.
The computer system according to claim 1, characterized in that: An equipment abnormal sound judging method executed by a computer system which judges an abnormal sound of equipment in a facility, comprising:
Obtaining a normal sound when the equipment is normal;
Machine learning the waveform of the normal sound;
Acquiring the unknown sound of the equipment which is normal, abnormal or unknown;
Detecting an abnormal point of the waveform of the unknown sound different from the machine-learned result;
Determining that an abnormal sound is generated at the abnormal point when the abnormal point satisfies a predetermined condition;
The equipment abnormal sound judging method characterized by having. In a computer system for determining abnormal noise of equipment in a facility,
Obtaining a normal sound when the equipment is normal,
Machine learning the waveform of the normal sound,
Acquiring the unknown sound of the equipment which is normal or abnormal or unknown;
Detecting an abnormal point of the waveform of the unknown sound different from the machine-learned result;
Determining that an abnormal sound is generated at the abnormal point when the abnormal point satisfies a predetermined condition;
A program to run a program.

Images