WO2021176568A1 - Equipment diagnostic system and equipment diagnostic method - Google Patents

Equipment diagnostic system and equipment diagnostic method Download PDF

Info

Publication number
WO2021176568A1
WO2021176568A1 PCT/JP2020/008962 JP2020008962W WO2021176568A1 WO 2021176568 A1 WO2021176568 A1 WO 2021176568A1 JP 2020008962 W JP2020008962 W JP 2020008962W WO 2021176568 A1 WO2021176568 A1 WO 2021176568A1
Authority
WO
WIPO (PCT)
Prior art keywords
equipment
infrared
state
diagnostic
imaging means
Prior art date
Application number
PCT/JP2020/008962
Other languages
French (fr)
Japanese (ja)
Inventor
浩一郎 森田
勉 遠藤
邦幸 奥山
Original Assignee
日本電気株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電気株式会社 filed Critical 日本電気株式会社
Priority to JP2022504822A priority Critical patent/JP7375909B2/en
Priority to PCT/JP2020/008962 priority patent/WO2021176568A1/en
Publication of WO2021176568A1 publication Critical patent/WO2021176568A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
    • G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
    • G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring

Definitions

  • the present invention relates to an equipment diagnosis system and an equipment diagnosis method.
  • Patent Document 1 discloses a patrol inspection support system for patrol inspection of an object to be inspected based on image data taken by a camera mounted on an aircraft. This system detects the image data of the abnormal part where the abnormality has occurred in the inspected object from the captured image data. Then, this system determines the abnormal state based on the image data of the abnormal part, and outputs the inspection result including the abnormal state of the abnormal part.
  • Patent Document 2 discloses a ground-based monitoring type pillar inspection vehicle equipped with an infrared monitoring device for monitoring an abnormality of a transmission line or a distribution line in a live-line state in a vehicle.
  • the partition wall of the vehicle in the direction facing the monitoring device is composed of a partition wall member formed of infrared transmissive crystals in order to enhance the monitoring effect of the monitoring device.
  • Patent Document 3 discloses an automatic inspection device for an overhead line having a function of identifying and detecting an accessory with respect to the overhead line based on the brightness distribution of an image obtained by taking an image by an imaging means. ing. This device makes an inspection judgment for an abnormality on the identified overhead line and its accessories, and outputs the inspection judgment result.
  • the equipment that constitutes the social infrastructure and is the target of diagnosis is set in various places. For example, there is a problem that the cost required for diagnosing a huge number of power supply equipment, communication equipment, etc. installed in a place where workers cannot easily reach, such as on a pillar, is very high.
  • the techniques described in Patent Documents 1 to 3 described above cannot be said to be sufficient to solve this problem.
  • a main object of the present invention is to perform equipment diagnosis with high accuracy and efficiency.
  • the equipment diagnosis system is obtained by an imaging means for imaging equipment in the near infrared band, a moving means equipped with the imaging means and moving the equipment to a place where imaging is possible, and the imaging means.
  • a diagnostic means for diagnosing the state of the equipment based on the obtained near-infrared image is provided.
  • a moving means equipped with an imaging means moves to a place where the equipment can be imaged, and the imaging means causes a near-infrared band.
  • the equipment is imaged, and the state of the equipment is diagnosed by the information processing device based on the near-infrared image obtained by the imaging means.
  • the present invention makes it possible to perform equipment diagnosis with high accuracy and efficiency.
  • FIG. 1 is a block diagram showing a configuration of the equipment diagnosis system 1 according to the first embodiment of the present invention.
  • the equipment diagnosis system 1 according to the present embodiment is a system that collects information (images) representing the state of the equipment 30 installed on the upper part of the pillar 31 and diagnoses the state of the equipment 30 based on the collected images. ..
  • the equipment 30 is, for example, power supply equipment, communication equipment, and the like that constitute social infrastructure. Although one equipment 30 and a pillar 31 are shown in FIG. 1 for convenience of explanation, the number of equipment 30 to be diagnosed by the equipment diagnosis system 1 may be plural.
  • the equipment diagnosis system 1 is roughly classified into an equipment diagnosis device 10, cameras 21 and 22, a vehicle 23, and a management terminal 40.
  • the cameras 21 and 22 are examples of the first and second imaging means, and the vehicle 23 is an example of the moving means.
  • the vehicle 23 is equipped with the cameras 21 and 22, and moves to a place where the equipment 30 can be imaged by the cameras 21 and 22. When there are a plurality of facilities 30, the vehicle 23 patrols a place where each facility 30 can be imaged.
  • the vehicle 23 may be moved by a driving operation by a worker, or may be moved by providing an automatic driving function. However, when the vehicle 23 is provided with the automatic driving function, it is assumed that the vehicle 23 is provided with map information indicating the position of the equipment 30.
  • the camera 21 acquires a near-infrared image 210 that images the equipment 30 with near-infrared rays.
  • Infrared rays are roughly classified into near infrared rays, middle infrared rays, and far infrared rays according to their wavelengths.
  • Near infrared rays are electromagnetic waves having a wavelength of about 0.7-2.5 ⁇ m (micrometers) and have a wavelength close to that of red visible light.
  • Mid-infrared rays are electromagnetic waves having a wavelength of about 2.5-4 ⁇ m, and may be classified as a part of near-infrared rays.
  • Far-infrared rays are electromagnetic waves having a wavelength of about 4-1000 ⁇ m, and are also called heat rays.
  • near-infrared rays have absorption characteristics and reflection characteristics peculiar to near-infrared rays
  • the state of the surface of the equipment 30 which is difficult to distinguish from an image captured by visible light or the like can be determined. It becomes possible to do.
  • By imaging the equipment 30 using near infrared rays for example, it is possible to determine the state of adhesion of salt, water, oil, etc. in the equipment 30.
  • FIG. 2 is a diagram showing a first example showing the difference between an image captured by visible light and an image captured by near infrared light.
  • the image captured by visible light A1 shown in FIG. 2A and the image captured by near infrared ray B1 shown in FIG. 2B are one of two insulators placed in a wooden box (upper side in the image). It is an image taken after spraying salt water on an insulator). In this example, the concentration of salt water is 3.5% (percent), which corresponds to seawater. Further, the captured image illustrated in FIG. 2 is an image captured after repeating spraying and drying of salt water about 10 times.
  • the contrast between the salt-attached place and the non-salt-attached place is clear in the near-infrared image captured image B1 as compared with the visible light-captured image A1. This is because ceramic insulators absorb near-infrared rays (ie, appear blacker in the image), whereas salts do not absorb near-infrared rays (ie, appear whiter in the image).
  • the substances adhering to the object to be imaged should be identified from the images captured by the near-infrared rays. Is also possible.
  • the camera 22 shown in FIG. 1 acquires a far-infrared image 220, which is an image of the equipment 30 by far-infrared rays.
  • the far-infrared image 220 represents, for example, the temperature of the surface of the equipment 30.
  • the near-infrared image 210 obtained by the camera 21 and the far-infrared image 220 obtained by the camera 22 are input to the equipment diagnostic apparatus 10.
  • the cameras 21 and 22 and the equipment diagnostic device 10 are communicably connected via a communication network (not shown) or the like, the near-infrared image 210 and the far-infrared image 220 are connected via the communication network. It is input to the equipment diagnostic device 10. Further, the near-infrared image 210 and the far-infrared image 220 may be input to the equipment diagnostic apparatus 10 via a non-volatile recording medium in which the near-infrared image 210 and the far-infrared image 220 are stored.
  • the equipment diagnosis device 10 is, for example, an information processing device such as a server, and includes a diagnosis unit 11, a prediction unit 12, and a storage unit 13.
  • the diagnostic unit 11, the prediction unit 12, and the storage unit 13 are examples of the diagnostic means, the prediction means, and the storage means in order.
  • the management terminal 40 is an information processing device such as a personal computer, and is communicably connected to the equipment diagnosis device 10.
  • the management terminal 40 is used as a user interface, for example, when a worker inputs information to the equipment diagnostic device 10 or when a worker confirms the content of information output from the equipment diagnostic device 10. It is a device.
  • the storage unit 13 is a non-volatile storage device such as an electronic memory or a magnetic disk, and stores an image captured image 131, a state information 132, a failure record 133, a learning model 134 for diagnosis, and a learning model 135 for prediction, which will be described later. doing.
  • the storage unit 13 stores the near-infrared image 210 and the far-infrared image 220 obtained in the inspection work for the equipment 30 so far as the image 131.
  • the state information 132 is information representing the state of the surface of the equipment 30 (state of deposits, etc.) obtained so far.
  • the state information 132 is information input to the equipment diagnosis device 10 by the worker via, for example, the management terminal 40.
  • the storage unit 13 stores the captured image 131 and the state information 132 in association with each other. That is, the storage unit 13 stores the state of the surface of the equipment 30 represented by a certain captured image 131.
  • the diagnostic unit 11 performs machine learning using the captured image 131 and the state information 132 associated as described above as teacher data, and generates or updates a diagnostic learning model 134 representing the result of the machine learning. That is, the diagnostic learning model 134 is a learning model used by the diagnostic unit 11 when diagnosing the state of the surface of the equipment 30 based on the near-infrared image 210 and the near-infrared image 210.
  • the diagnostic unit 11 when the diagnostic unit 11 is given an image such as the captured image B1 illustrated in FIG. 2B as teacher data, a criterion for diagnosing that salt is attached to the insulator contained in the equipment 30.
  • the diagnostic learning model 134 is generated or updated.
  • the diagnostic unit 11 uses the insulator included in the equipment 30 based on the diagnostic learning model 134. Diagnose that the insulator is attached to the insulator.
  • the diagnostic unit 11 indicates, for example, that the near-infrared image 210 represents moisture or oil adhering to the wall of the equipment 30, and the far-infrared image 220 indicates heat generation on the wall of the equipment 30. It is diagnosed that water or oil is leaking from the inside of the wall in the heat generating portion of the wall in the equipment 30.
  • the diagnosis unit 11 inputs the result of diagnosing the state of the equipment 30 into the prediction unit 12 and transmits it to the management terminal 40.
  • the diagnosis unit 11 may also store the result of diagnosing the state of the equipment 30 in the storage unit 13 so that it can be referred to from the management terminal 40.
  • the prediction unit 12 predicts a failure that occurs in the equipment 30 based on the diagnosis result input from the diagnosis unit 11 and the learning model 135 for prediction. For example, as illustrated in FIG. 2, the prediction unit 12 inputs the diagnosis result that salt is attached to the insulator included in the equipment 30 by the diagnosis unit 11, and insulates using the prediction learning model 135. Predict the occurrence of power outages due to the decrease in
  • the prediction unit 12 also has a function of performing machine learning to generate a learning model 135 for prediction.
  • the storage unit 13 stores the failure record 133, which represents the record of failures that have occurred in the equipment 30 so far.
  • the failure record 133 is information input to the equipment diagnosis device 10 by the worker via, for example, the management terminal 40.
  • the storage unit 13 stores the state information 132 and the failure record 133 in association with each other. That is, the storage unit 13 stores information representing a failure that may occur in the equipment 30 when the equipment 30 is in a certain state.
  • the prediction unit 12 performs machine learning using a plurality of sample data related to the diagnosis result as input data and teacher data using the failure record 133 as a label, and generates or updates a prediction learning model 135 representing the result of the machine learning. .. That is, the prediction learning model 135 is a learning model used by the prediction unit 12 when predicting a failure that occurs in the equipment 30 based on the diagnosis result of the state of the equipment 30 by the diagnosis unit 11.
  • the prediction unit 12 After generating the prediction learning model 135, the prediction unit 12 inputs the diagnosis result by the diagnosis unit 11, and outputs the result of predicting the failure occurring in the equipment 30 using the prediction learning model 135. The prediction unit 12 outputs the result of predicting the failure to the management terminal 40.
  • the prediction unit 12 may also store the result of predicting a failure occurring in the equipment 30 in the storage unit 13 so that the management terminal 40 can refer to it.
  • the vehicle 23 moves to a place where the equipment 30 can be imaged (step S101).
  • the camera 21 acquires a near-infrared image 210 that images the equipment 30, and the camera 22 acquires a far-infrared image 220 that images the equipment 30 (step S102).
  • the camera 21 inputs the near-infrared image 210 to the equipment diagnostic device 10, and the camera 22 inputs the far-infrared image 220 to the equipment diagnostic device 10 (step S103).
  • the diagnostic unit 11 in the equipment diagnostic apparatus 10 diagnoses the state of the equipment 30 based on the near-infrared image 210, the far-infrared image 220, and the diagnostic learning model 134 (step S104).
  • the prediction unit 12 in the equipment diagnosis device 10 predicts a failure occurring in the equipment 30 based on the diagnosis result of the state of the equipment 30 by the diagnosis unit 11 and the learning model 135 for prediction (step S105), and the entire process is performed. finish.
  • the equipment diagnosis system 1 can perform equipment diagnosis with high accuracy and efficiency.
  • the reason is that in the equipment diagnosis system 1, the vehicle 23 equipped with the camera 21 that images the equipment 30 in the near-infrared band moves to a place where the equipment 30 can be imaged, and the diagnosis unit 11 is obtained by the camera 21. This is because the state of the equipment 30 is diagnosed based on the infrared captured image 210.
  • the equipment that constitutes the social infrastructure and is the target of diagnosis is set in various places. For example, a huge number of power supply equipment and communication equipment installed in places that are difficult for workers to reach, such as on pillars, are diagnosed. The cost to do so is very high. Therefore, it is an issue to perform equipment diagnosis with high accuracy and efficiency.
  • the equipment diagnosis system 1 includes a camera 21, a vehicle 23, and a diagnosis unit 11, and operates as described above with reference to, for example, FIGS. 1 to 3. That is, the camera 21 images the equipment 30 in the near infrared band.
  • the vehicle 23 is equipped with the camera 21 and moves to a place where the equipment 30 can be imaged.
  • the diagnosis unit 11 diagnoses the state of the equipment 30 based on the near-infrared image captured image 210 obtained by the camera 21.
  • the vehicle 23 equipped with the camera 21 that captures images by near infrared rays goes to a place where the equipment 30 to be diagnosed can be imaged, and the equipment 30 is photographed by near infrared rays from that place. do.
  • the near-infrared image 210 that utilizes the absorption characteristics and reflection characteristics peculiar to near-infrared rays clearly represents the state of the equipment 30, and is therefore imaged from a place some distance from the equipment 30. It is possible to diagnose the state of the equipment 30 from the image even if it is an infrared image.
  • the equipment diagnosis system 1 uses the camera 21 that captures images by near-infrared rays, so that the equipment diagnosis system 1 has high accuracy based on the near-infrared image captured image 210 imaged from the vehicle 23 traveling on the road without going to the immediate vicinity of the equipment 30, for example. Diagnosis can be made.
  • the equipment diagnosis system 1 further includes a camera 22 mounted on the vehicle 23 for imaging by far infrared rays, and a near infrared image captured image 210 obtained by the camera 21 and a far infrared ray image obtained by the camera 22.
  • the state of the equipment 30 is diagnosed based on both the infrared captured image 220 and the infrared image 220. Since the near-infrared image 210 represents the state of deposits on the surface of the equipment 30 and the far-infrared image 220 represents the temperature of the surface of the equipment 30, the equipment diagnostic system 1 is based on these two types of captured images. The state of the equipment 30 can be performed with higher accuracy.
  • the camera 21 or the camera 22 captures the characters displayed on the equipment 30, and the diagnostic unit 11 identifies the information represented by the characters included in the near-infrared image 210 or the far-infrared image 220. Then, the state of the equipment 30 may be diagnosed based on the character identification result. In this case, the diagnostic unit 11 can recognize the characters included in the image by using the existing character recognition technique.
  • the diagnosis unit 11 identifies the character by the character identification process. Then, when the diagnosis unit 11 detects the adhesion of salt in the equipment 30 from the near-infrared image captured image 210, the diagnosis unit 11 diagnoses that the problem of salt adhesion in the equipment 30 has occurred. When the word "Caution for salt adhesion" is not displayed on the equipment 30, the diagnosis unit 11 may diagnose that the equipment 30 has no particular problem even if the equipment 30 detects the adhesion of salt.
  • the diagnostic unit 11 identifies the character by character identification processing. Then, when the heat generation in the equipment 30 is detected from the far-infrared image captured image 220, the diagnosis unit 11 diagnoses that the problem of heat generation in the equipment 30 has occurred. If the word "high temperature caution” is not displayed on the equipment 30, even if the diagnostic unit 11 detects heat generation in the equipment 30, the equipment 30 has no particular problem as long as it is within the predetermined temperature range specified by the user. May be diagnosed.
  • the equipment diagnosis system 1 can more accurately diagnose the state of the equipment 30 based on the information represented by the characters contained in the near-infrared image 210 or the far-infrared image 220.
  • the equipment diagnosis system 1 diagnoses the state of the equipment 30 while generating and updating the learning learning model 134 for diagnosis, and generates and updates the learning model 135 for prediction while generating and updating the equipment 30. Predict the obstacles to be made. As a result, the equipment diagnosis system 1 can improve the accuracy of diagnosing the state of the equipment 30 and the accuracy of predicting failures that occur in the equipment 30.
  • the equipment diagnosis system 1 does not necessarily have to include the learning model 134 for diagnosis and the learning model 135 for prediction, and may be provided with information that serves as a reference for performing diagnosis and prediction.
  • the equipment diagnosis system 1 uses a flying object such as a drone or a helicopter instead of the vehicle 23 as a means of moving the equipment 30 by mounting the cameras 21 and 22 to a place where the equipment 30 can be imaged. You may use it.
  • a flying object such as a drone or a helicopter instead of the vehicle 23 as a means of moving the equipment 30 by mounting the cameras 21 and 22 to a place where the equipment 30 can be imaged. You may use it.
  • the equipment 30 to be diagnosed by the equipment diagnosis system 1 is not limited to the equipment on the pillar installed above the pillar 31.
  • the installation location of the equipment 30 may be any place where the equipment 30 can be imaged from a place where the moving means such as the vehicle 23 can move.
  • FIG. 4 is a block diagram showing the configuration of the equipment diagnosis system 5 according to the second embodiment of the present invention.
  • the equipment diagnosis system 5 includes an imaging unit 51, a moving unit 52, and a diagnostic unit 53.
  • the imaging unit 51, the moving unit 52, and the diagnostic unit 53 are, in order, examples of the imaging means, the moving means, and the diagnostic means.
  • the imaging unit 51 images the equipment 50 in the near infrared band.
  • the imaging unit 51 is, for example, a device such as the camera 21 according to the first embodiment.
  • the moving unit 52 mounts the imaging unit 51 and moves the equipment 50 to a place where imaging is possible.
  • the moving unit 52 is a moving means such as the vehicle 23 according to the first embodiment.
  • the diagnosis unit 53 diagnoses the state of the equipment 50 based on the near-infrared image captured image 510 obtained by the imaging unit 51.
  • the diagnosis unit 53 can be realized by, for example, an information processing device such as the equipment diagnosis device 10 according to the first embodiment.
  • the diagnosis unit 53 generates a learning model representing the result of machine learning using the teacher data related to the diagnosis of the equipment 50, and uses the learning model, as in the diagnosis unit 11 according to the first embodiment.
  • the condition of the equipment 50 may be diagnosed.
  • the equipment diagnosis system 5 can perform equipment diagnosis with high accuracy and efficiency.
  • the moving unit 52 equipped with the imaging unit 51 that images the equipment 50 in the near infrared band moves to a place where the equipment 50 can be imaged, and the diagnostic unit 53 obtains the image by the imaging unit 51. This is because the state of the equipment 50 is diagnosed based on the obtained near-infrared image 510.
  • each part of the equipment diagnostic apparatus 10 shown in FIG. 1 or the diagnostic unit 53 shown in FIG. 4 can be realized by a dedicated HW (HardWare) (electronic circuit). Further, in FIGS. 1 and 4, at least the following configuration can be regarded as a function (processing) unit (software module) of the software program. ⁇ Diagnosis departments 11 and 53, ⁇ Forecasting unit 12, -Memory control function in the storage unit 13.
  • FIG. 5 is a diagram illustrating an example of a configuration of an information processing device 900 (computer) capable of executing the equipment diagnostic device 10 according to the first embodiment of the present invention or the diagnostic unit 53 according to the second embodiment. be. That is, FIG. 5 is a configuration of a computer (information processing device) capable of realizing the equipment diagnostic device 10 shown in FIG. 1 and the diagnostic unit 53 shown in FIG. 4, and each function in the above-described embodiment can be realized. Represents a hardware environment.
  • the information processing apparatus 900 shown in FIG. 5 includes the following components, but may not include some of the following components.
  • -CPU Central_Processing_Unit
  • -ROM Read_Only_Memory
  • RAM Random_Access_Memory
  • -Hard disk storage device
  • -Communication interface 905 with an external device ⁇ Bus 906 (communication line)
  • a reader / writer 908 that can read and write data stored in a recording medium 907 such as a CD-ROM (Compact_Disc_Read_Only_Memory), -Input / output interface 909 for monitors, speakers, keyboards, etc.
  • CD-ROM Compact_Disc_Read_Only_Memory
  • -Input / output interface 909 for monitors, speakers, keyboards, etc.
  • the information processing device 900 including the above components is a general computer in which these components are connected via the bus 906.
  • the information processing device 900 may include a plurality of CPUs 901 or may include a CPU 901 configured by a multi-core processor.
  • the information processing device 900 may include a GPU (Graphical_Processing_Unit) (not shown) in addition to the CPU 901.
  • the present invention described by taking the above-described embodiment as an example supplies the computer program capable of realizing the following functions to the information processing apparatus 900 shown in FIG.
  • the function is the above-described configuration in the block configuration diagrams (FIGS. 1 and 4) referred to in the description of the embodiment, or the function of the flowchart (FIG. 3).
  • the present invention is then achieved by reading, interpreting, and executing the computer program in the CPU 901 of the hardware.
  • the computer program supplied in the device may be stored in a readable / writable volatile memory (RAM 903) or a non-volatile storage device such as a ROM 902 or a hard disk 904.
  • the procedure for example, there are a method of installing in the device via various recording media 907 such as a CD-ROM, a method of downloading from the outside via a communication line such as the Internet, and the like. Then, in such a case, the present invention can be regarded as being composed of a code constituting the computer program or a recording medium 907 in which the code is stored.
  • the first imaging means for imaging equipment in the near-infrared band A moving means equipped with the first imaging means and moving the equipment to a place where imaging is possible, and A diagnostic means for diagnosing the state of the equipment based on the near-infrared image captured by the first imaging means, and Equipment diagnostic system equipped with.
  • the first imaging means acquires the near-infrared captured image showing a state in which a substance adheres to the surface of the equipment.
  • the equipment diagnostic system according to Appendix 1.
  • the first imaging means acquires the near-infrared captured image showing a state in which water, oil, and salt are attached to the surface of the equipment.
  • the first imaging means captures characters displayed on the equipment and obtains images.
  • the diagnostic means diagnoses the state of the equipment based on the character image obtained by the first imaging means.
  • the equipment diagnosis system according to any one of Appendix 1 to Appendix 3.
  • a second imaging means for imaging the equipment in the far infrared band is provided.
  • the moving means is equipped with the second imaging means.
  • the second imaging means acquires a far-infrared image that represents heat generation in the equipment, and obtains a far-infrared image.
  • the diagnostic means diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
  • the equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 4.
  • a prediction means for predicting a failure occurring in the facility from the diagnosis result of the facility by the diagnostic means and generating a second learning model used for predicting the failure is further provided.
  • the storage means stores information representing the state of the equipment in association with a record of failures that have occurred in the equipment.
  • the means of transportation is a vehicle or a flying object.
  • the equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 7.
  • the moving means equipped with the first imaging means moves to a place where the equipment can be imaged,
  • the equipment is imaged in the near infrared band by the first imaging means.
  • the information processing device diagnoses the state of the equipment based on the near-infrared image captured by the imaging means. Equipment diagnosis method.
  • the moving means is equipped with a second imaging means.
  • the second imaging means acquires a far-infrared image that represents heat generation in the equipment that images the equipment in the far-infrared band.
  • the information processing device diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
  • the equipment diagnosis method according to Appendix 10.
  • Equipment Diagnostic System 10 Equipment Diagnostic Device 11 Diagnostic Unit 12 Prediction Unit 13 Storage Unit 131 Captured Image 132 Status Information 133 Failure Record 134 Diagnostic Learning Model 135 Predictive Learning Model 21 Camera 210 Near Infrared Captured Image 22 Camera 220 Far Infrared Captured Image 23 Vehicle 30 Equipment 31 Pillar 40 Management terminal 5 Equipment diagnostic system 50 Equipment 51 Imaging unit 510 Near infrared imaging image 52 Mobile unit 53 Diagnosis unit 900 Information processing device 901 CPU 902 ROM 903 RAM 904 hard disk (storage device) 905 Communication interface 906 Bus 907 Recording medium 908 Reader / writer 909 Input / output interface

Abstract

This equipment diagnostic system 5 is provided with an imaging unit 51 that images equipment 50 in an infrared band, a mobile unit 52 that carries the imaging unit 51 and moves to a location where the equipment 50 can be imaged, and a diagnosing unit 53 that diagnoses the state of the equipment 50 on the basis of captured infrared images 510 obtained by the imaging unit 51, whereby a diagnosis of the equipment is performed accurately and efficiently.

Description

設備診断システム、及び、設備診断方法Equipment diagnosis system and equipment diagnosis method
　本発明は、設備診断システム、及び、設備診断方法に関する。 The present invention relates to an equipment diagnosis system and an equipment diagnosis method.
　電力設備等の社会インフラにおいて障害が発生した場合、人々の生活に多大な影響を及ぼすおそれがある。したがって、このような障害が発生しないように、社会インフラの点検、診断を着実に行うことが重要である。しかしながら、診断の対象となる設備の数は膨大であることから、設備の診断を、高い精度で、かつ効率的に行う技術に対する期待が高まってきている。 If a failure occurs in social infrastructure such as electric power equipment, it may have a great impact on people's lives. Therefore, it is important to steadily inspect and diagnose social infrastructure so that such obstacles do not occur. However, since the number of equipment to be diagnosed is enormous, expectations are increasing for a technique for diagnosing equipment with high accuracy and efficiency.
　このような技術に関連する技術として、特許文献１には、航空機に搭載されたカメラにより撮影された画像データをもとに被点検物について巡視点検する巡視点検支援システムが開示されている。このシステムは、撮影した画像データから被点検物に異常が生じた異常箇所の画像データを検出する。そして、このシステムは、その異常箇所の画像データをもとに異常状態を判別し、当該異常箇所の異常状態を含む点検結果を出力する。 As a technique related to such a technique, Patent Document 1 discloses a patrol inspection support system for patrol inspection of an object to be inspected based on image data taken by a camera mounted on an aircraft. This system detects the image data of the abnormal part where the abnormality has occurred in the inspected object from the captured image data. Then, this system determines the abnormal state based on the image data of the abnormal part, and outputs the inspection result including the abnormal state of the abnormal part.
　また、特許文献２には、車両内に活線状態にある送電線あるいは配電線等の異常を監視するための赤外線による監視装置を搭載した地上監視型装柱点検車が開示されている。この点検車では、当該監視装置で臨む方向の車両の隔壁部は、当該監視装置の監視効果を高めるために赤外線透過結晶により形成した隔壁部材により構成されている。 Further, Patent Document 2 discloses a ground-based monitoring type pillar inspection vehicle equipped with an infrared monitoring device for monitoring an abnormality of a transmission line or a distribution line in a live-line state in a vehicle. In this inspection vehicle, the partition wall of the vehicle in the direction facing the monitoring device is composed of a partition wall member formed of infrared transmissive crystals in order to enhance the monitoring effect of the monitoring device.
　また、特許文献３には、撮像手段により撮影して得られた画像の輝度分布をもとに、架空線に対し付属物を識別して検出する機能を有する架空線の自動点検装置が開示されている。この装置は、識別した当該架空線やその付属物に対し、異常についての検査判定を行い、その検査判定結果を出力する。 Further, Patent Document 3 discloses an automatic inspection device for an overhead line having a function of identifying and detecting an accessory with respect to the overhead line based on the brightness distribution of an image obtained by taking an image by an imaging means. ing. This device makes an inspection judgment for an abnormality on the identified overhead line and its accessories, and outputs the inspection judgment result.
特開２０１９－００９９１９号公報Japanese Unexamined Patent Publication No. 2019-0099919 実開平０６－００５３１２号公報Jikkenhei 06-005312 Gazette 特開平１０－１１７４１５号公報Japanese Unexamined Patent Publication No. 10-117415
　社会インフラを構成する診断の対象となる設備は、様々な場所に設定されている。例えば、柱上など作業員が行きにくい場所に設置された、膨大な数の電源設備や通信設備等を診断するのに要するコストは非常に高いという問題がある。上述した特許文献１乃至３が示すような技術は、この課題を解決するのに十分であるとは言えない。 The equipment that constitutes the social infrastructure and is the target of diagnosis is set in various places. For example, there is a problem that the cost required for diagnosing a huge number of power supply equipment, communication equipment, etc. installed in a place where workers cannot easily reach, such as on a pillar, is very high. The techniques described in Patent Documents 1 to 3 described above cannot be said to be sufficient to solve this problem.
　本発明の主たる目的は、設備の診断を、高い精度で、かつ効率的に行うことである。 A main object of the present invention is to perform equipment diagnosis with high accuracy and efficiency.
　本発明の一態様に係る設備診断システムは、近赤外線帯域において設備を撮像する撮像手段と、前記撮像手段を搭載し、前記設備を撮像可能な場所に移動する移動手段と、前記撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する診断手段と、を備える。 The equipment diagnosis system according to one aspect of the present invention is obtained by an imaging means for imaging equipment in the near infrared band, a moving means equipped with the imaging means and moving the equipment to a place where imaging is possible, and the imaging means. A diagnostic means for diagnosing the state of the equipment based on the obtained near-infrared image is provided.
　上記目的を達成する他の見地において、本発明の一態様に係る設備診断方法は、撮像手段を搭載した移動手段が、前記設備を撮像可能な場所に移動し、前記撮像手段によって、近赤外線帯域において前記設備を撮像し、情報処理装置によって、前記撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する。 From another viewpoint of achieving the above object, in the equipment diagnosis method according to one aspect of the present invention, a moving means equipped with an imaging means moves to a place where the equipment can be imaged, and the imaging means causes a near-infrared band. The equipment is imaged, and the state of the equipment is diagnosed by the information processing device based on the near-infrared image obtained by the imaging means.
　本発明は、設備の診断を、高い精度で、かつ効率的に行うことを可能とする。 The present invention makes it possible to perform equipment diagnosis with high accuracy and efficiency.
本発明の第１の実施形態に係る設備診断システム１の構成を示すブロック図である。It is a block diagram which shows the structure of the equipment diagnosis system 1 which concerns on 1st Embodiment of this invention. 可視光線による撮像画像と近赤外線による撮像画像との違いを示す例を表す図である。It is a figure which shows the example which shows the difference between the image which image | photographed by a visible light, and the image image | photographed by a near infrared ray. 本発明の第１の実施形態に係る設備診断システム１の動作を示すフローチャートである。It is a flowchart which shows the operation of the equipment diagnosis system 1 which concerns on 1st Embodiment of this invention. 本発明の第２の実施形態に係る設備診断システム５の構成を示すブロック図である。It is a block diagram which shows the structure of the equipment diagnosis system 5 which concerns on 2nd Embodiment of this invention. 本発明の第１の実施形態に係る設備診断装置１０あるいは第２の実施形態に係る診断部５３を実行可能な情報処理装置９００の構成を示すブロック図である。It is a block diagram which shows the structure of the information processing apparatus 900 which can execute the equipment diagnostic apparatus 10 which concerns on 1st Embodiment of this invention, or the diagnostic unit 53 which concerns on 2nd Embodiment.
　以下、本発明の実施の形態について図面を参照して詳細に説明する。 Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.
　＜第１の実施形態＞
　図１は、本発明の第１の実施の形態に係る設備診断システム１の構成を示すブロック図である。本実施形態に係る設備診断システム１は、柱３１の上部に設置された設備３０の状態を表す情報（画像）を収集し、収集した画像に基づいて、設備３０の状態を診断するシステムである。設備３０は、例えば、社会インフラを構成する電源設備や通信設備等である。尚、図１には説明の便宜上１つの設備３０及び柱３１を示しているが、設備診断システム１が診断の対象とする設備３０の数は複数でもよい。 <First Embodiment>
FIG. 1 is a block diagram showing a configuration of the equipment diagnosis system 1 according to the first embodiment of the present invention. The equipment diagnosis system 1 according to the present embodiment is a system that collects information (images) representing the state of the equipment 30 installed on the upper part of the pillar 31 and diagnoses the state of the equipment 30 based on the collected images. .. The equipment 30 is, for example, power supply equipment, communication equipment, and the like that constitute social infrastructure. Although one equipment 30 and a pillar 31 are shown in FIG. 1 for convenience of explanation, the number of equipment 30 to be diagnosed by the equipment diagnosis system 1 may be plural.
　設備診断システム１は、大別して、設備診断装置１０、カメラ２１及び２２、車両２３、及び、管理端末４０を含んでいる。カメラ２１及び２２は、第一及び第二の撮像手段の一例であり、車両２３は移動手段の一例である。 The equipment diagnosis system 1 is roughly classified into an equipment diagnosis device 10, cameras 21 and 22, a vehicle 23, and a management terminal 40. The cameras 21 and 22 are examples of the first and second imaging means, and the vehicle 23 is an example of the moving means.
　車両２３は、カメラ２１及び２２を搭載し、カメラ２１及び２２によって設備３０を撮像可能な場所に移動する。車両２３は、設備３０が複数である場合、各設備３０を撮像可能な場所を巡回する。車両２３は、作業員による運転操作によって移動してもよいし、あるいは、自動運転機能を備えることによって移動してもよい。但し、車両２３が自動運転機能を備える場合、車両２３には、設備３０の位置を表す地図情報が与えられていることとする。 The vehicle 23 is equipped with the cameras 21 and 22, and moves to a place where the equipment 30 can be imaged by the cameras 21 and 22. When there are a plurality of facilities 30, the vehicle 23 patrols a place where each facility 30 can be imaged. The vehicle 23 may be moved by a driving operation by a worker, or may be moved by providing an automatic driving function. However, when the vehicle 23 is provided with the automatic driving function, it is assumed that the vehicle 23 is provided with map information indicating the position of the equipment 30.
　カメラ２１は、近赤外線によって設備３０を撮像した近赤外線撮像画像２１０を取得する。 The camera 21 acquires a near-infrared image 210 that images the equipment 30 with near-infrared rays.
　ここで近赤外線による撮像について説明する。赤外線は、その波長によって、近赤外線、中赤外線、遠赤外線に大別される。近赤外線は、その波長が０．７－２．５μｍ（マイクロメートル）程度の電磁波であり、赤色の可視光線に近い波長を持つ。中赤外線は、その波長が約２．５－４μｍ程度の電磁波で、近赤外線の一部として分類されることもある。遠赤外線はその波長が約４－１０００μｍ程度の電磁波であり、熱線とも呼ばれる。 Here, the imaging by near infrared rays will be described. Infrared rays are roughly classified into near infrared rays, middle infrared rays, and far infrared rays according to their wavelengths. Near infrared rays are electromagnetic waves having a wavelength of about 0.7-2.5 μm (micrometers) and have a wavelength close to that of red visible light. Mid-infrared rays are electromagnetic waves having a wavelength of about 2.5-4 μm, and may be classified as a part of near-infrared rays. Far-infrared rays are electromagnetic waves having a wavelength of about 4-1000 μm, and are also called heat rays.
　近赤外線は、近赤外線に特有の吸光特性や反射特性を有するので、近赤外線を用いて設備３０を撮像することによって、可視光線等による撮像画像では判別が困難な設備３０の表面の状態を判別することが可能となる。近赤外線を用いて設備３０を撮像することによって、例えば、設備３０における、塩分や水分や油分の付着状態等を判別することができる。 Since near-infrared rays have absorption characteristics and reflection characteristics peculiar to near-infrared rays, by imaging the equipment 30 using the near-infrared rays, the state of the surface of the equipment 30 which is difficult to distinguish from an image captured by visible light or the like can be determined. It becomes possible to do. By imaging the equipment 30 using near infrared rays, for example, it is possible to determine the state of adhesion of salt, water, oil, etc. in the equipment 30.
　図２は、可視光線による撮像画像と近赤外線による撮像画像との違いを示す第一の例を表す図である。図２の（ａ）に示す可視光線による撮像画像Ａ１、及び、図２の（ｂ）に示す近赤外線による撮像画像Ｂ１は、木箱に置いた２つの碍子のうちの一方（画像における上側の碍子）に対して塩水を噴霧したのちに撮像した画像である。この例において、塩水の濃度は、海水に相当する３．５％（パーセント）である。また、図２に例示する撮像画像は、塩水の噴霧と乾燥とを１０回程度繰り返したのちに撮像した画像である。 FIG. 2 is a diagram showing a first example showing the difference between an image captured by visible light and an image captured by near infrared light. The image captured by visible light A1 shown in FIG. 2A and the image captured by near infrared ray B1 shown in FIG. 2B are one of two insulators placed in a wooden box (upper side in the image). It is an image taken after spraying salt water on an insulator). In this example, the concentration of salt water is 3.5% (percent), which corresponds to seawater. Further, the captured image illustrated in FIG. 2 is an image captured after repeating spraying and drying of salt water about 10 times.
　図２に示す通り、近赤外線による撮像画像Ｂ１は、可視光線による撮像画像Ａ１と比較して、塩分が付着している場所と塩分が付着していない場所とのコントラストがはっきりしている。これは、セラミックスの碍子が近赤外線を吸収する（即ち画像においてより黒く見える）のに対して、塩分は近赤外線を吸収しない（即ち画像においてより白く見える）からである。 As shown in FIG. 2, the contrast between the salt-attached place and the non-salt-attached place is clear in the near-infrared image captured image B1 as compared with the visible light-captured image A1. This is because ceramic insulators absorb near-infrared rays (ie, appear blacker in the image), whereas salts do not absorb near-infrared rays (ie, appear whiter in the image).
　また、近赤外線は、撮像対象物に付着した物質（塩分、水分、油分等）によって、吸光特性や反射特性が異なるので、近赤外線による撮像画像から、撮像対象物に付着した物質を判別することも可能である。 In addition, since near-infrared rays have different absorption characteristics and reflection characteristics depending on the substances (salt, water, oil, etc.) adhering to the object to be imaged, the substances adhering to the object to be imaged should be identified from the images captured by the near-infrared rays. Is also possible.
　図１に示すカメラ２２は、遠赤外線によって設備３０を撮像した遠赤外線撮像画像２２０を取得する。遠赤外線撮像画像２２０は、例えば、設備３０の表面の温度を表している。 The camera 22 shown in FIG. 1 acquires a far-infrared image 220, which is an image of the equipment 30 by far-infrared rays. The far-infrared image 220 represents, for example, the temperature of the surface of the equipment 30.
　カメラ２１によって得られた近赤外線撮像画像２１０、及び、カメラ２２によって得られた遠赤外線撮像画像２２０は、設備診断装置１０へ入力される。カメラ２１及び２２と設備診断装置１０とが通信ネットワーク（不図示）等を介して通信可能に接続されている場合、近赤外線撮像画像２１０及び遠赤外線撮像画像２２０は、当該通信ネットワークを介して、設備診断装置１０へ入力される。また、近赤外線撮像画像２１０及び遠赤外線撮像画像２２０が記憶された不揮発性の記録媒体を介して、近赤外線撮像画像２１０及び遠赤外線撮像画像２２０が設備診断装置１０へ入力されてもよい。 The near-infrared image 210 obtained by the camera 21 and the far-infrared image 220 obtained by the camera 22 are input to the equipment diagnostic apparatus 10. When the cameras 21 and 22 and the equipment diagnostic device 10 are communicably connected via a communication network (not shown) or the like, the near-infrared image 210 and the far-infrared image 220 are connected via the communication network. It is input to the equipment diagnostic device 10. Further, the near-infrared image 210 and the far-infrared image 220 may be input to the equipment diagnostic apparatus 10 via a non-volatile recording medium in which the near-infrared image 210 and the far-infrared image 220 are stored.
　設備診断装置１０は、例えばサーバ等の情報処理装置であり、診断部１１、予測部１２、及び、記憶部１３を備える。診断部１１、予測部１２、及び、記憶部１３は、順に、診断手段、予測手段、及び、記憶手段の一例である。 The equipment diagnosis device 10 is, for example, an information processing device such as a server, and includes a diagnosis unit 11, a prediction unit 12, and a storage unit 13. The diagnostic unit 11, the prediction unit 12, and the storage unit 13 are examples of the diagnostic means, the prediction means, and the storage means in order.
　管理端末４０は、例えばパーソナルコンピュータ等の情報処理装置であり、設備診断装置１０と通信可能に接続されている。管理端末４０は、例えば、作業員が設備診断装置１０に対して情報を入力する場合、あるいは、作業員が設備診断装置１０から出力された情報の内容を確認する場合に、ユーザインタフェースとして使用される装置である。 The management terminal 40 is an information processing device such as a personal computer, and is communicably connected to the equipment diagnosis device 10. The management terminal 40 is used as a user interface, for example, when a worker inputs information to the equipment diagnostic device 10 or when a worker confirms the content of information output from the equipment diagnostic device 10. It is a device.
　記憶部１３は、例えば電子メモリや磁気ディスク等の不揮発性の記憶デバイスであり、後述する撮像画像１３１、状態情報１３２、障害実績１３３、診断用学習モデル１３４、及び、予測用学習モデル１３５を記憶している。 The storage unit 13 is a non-volatile storage device such as an electronic memory or a magnetic disk, and stores an image captured image 131, a state information 132, a failure record 133, a learning model 134 for diagnosis, and a learning model 135 for prediction, which will be described later. doing.
　記憶部１３は、これまでの設備３０に対する点検作業において得られた近赤外線撮像画像２１０及び遠赤外線撮像画像２２０を、撮像画像１３１として記憶している。 The storage unit 13 stores the near-infrared image 210 and the far-infrared image 220 obtained in the inspection work for the equipment 30 so far as the image 131.
　状態情報１３２は、これまでに得られた、設備３０の表面の状態（付着物の状態等）を表す情報である。状態情報１３２は、例えば管理端末４０を介して、作業員により設備診断装置１０に入力された情報である。尚、記憶部１３は、撮像画像１３１と状態情報１３２とを関連付けて記憶している。即ち、記憶部１３は、ある撮像画像１３１が表す設備３０の表面の状態を記憶している。 The state information 132 is information representing the state of the surface of the equipment 30 (state of deposits, etc.) obtained so far. The state information 132 is information input to the equipment diagnosis device 10 by the worker via, for example, the management terminal 40. The storage unit 13 stores the captured image 131 and the state information 132 in association with each other. That is, the storage unit 13 stores the state of the surface of the equipment 30 represented by a certain captured image 131.
　診断部１１は、上述の通りに関連付けされた撮像画像１３１及び状態情報１３２を教師データとして機械学習を行い、当該機械学習の結果を表す診断用学習モデル１３４を生成あるいは更新する。即ち、診断用学習モデル１３４は、診断部１１が、近赤外線撮像画像２１０及び近赤外線撮像画像２１０に基づいて、設備３０の表面の状態等を診断する際に用いる学習モデルである。 The diagnostic unit 11 performs machine learning using the captured image 131 and the state information 132 associated as described above as teacher data, and generates or updates a diagnostic learning model 134 representing the result of the machine learning. That is, the diagnostic learning model 134 is a learning model used by the diagnostic unit 11 when diagnosing the state of the surface of the equipment 30 based on the near-infrared image 210 and the near-infrared image 210.
　診断部１１は、例えば、教師データとして、図２の（ｂ）に例示する撮像画像Ｂ１のような画像を与えられた場合、設備３０に含まれる碍子に塩分が付着していると診断する基準となる診断用学習モデル１３４を生成あるいは更新する。そしてそののち、診断部１１は、近赤外線撮像画像２１０が図２の（ｂ）に例示する撮像画像Ｂ１のような画像である場合、診断用学習モデル１３４に基づいて、設備３０に含まれる碍子に塩分が付着していると診断する。 For example, when the diagnostic unit 11 is given an image such as the captured image B1 illustrated in FIG. 2B as teacher data, a criterion for diagnosing that salt is attached to the insulator contained in the equipment 30. The diagnostic learning model 134 is generated or updated. After that, when the near-infrared image 210 is an image like the image B1 illustrated in FIG. 2B, the diagnostic unit 11 uses the insulator included in the equipment 30 based on the diagnostic learning model 134. Diagnose that the insulator is attached to the insulator.
　診断部１１は、例えば、近赤外線撮像画像２１０が設備３０の壁に水分あるいは油分が付着していることを表しており、遠赤外線撮像画像２２０が設備３０の壁における発熱を表している場合、設備３０における壁の発熱している部分において、壁の内部から水分あるいは油分が漏れていると診断する。 The diagnostic unit 11 indicates, for example, that the near-infrared image 210 represents moisture or oil adhering to the wall of the equipment 30, and the far-infrared image 220 indicates heat generation on the wall of the equipment 30. It is diagnosed that water or oil is leaking from the inside of the wall in the heat generating portion of the wall in the equipment 30.
　診断部１１は、設備３０の状態を診断した結果を、予測部１２に入力するとともに、管理端末４０に送信する。診断部１１は、また、設備３０の状態を診断した結果を、管理端末４０から参照可能に、記憶部１３に格納してもよい。 The diagnosis unit 11 inputs the result of diagnosing the state of the equipment 30 into the prediction unit 12 and transmits it to the management terminal 40. The diagnosis unit 11 may also store the result of diagnosing the state of the equipment 30 in the storage unit 13 so that it can be referred to from the management terminal 40.
　予測部１２は、診断部１１から入力された診断結果と予測用学習モデル１３５とに基づいて、設備３０において発生する障害を予測する。例えば、図２に例示するように、予測部１２は、診断部１１による設備３０に含まれる碍子に塩分が付着しているとの診断結果を入力し、予測用学習モデル１３５を用いて、絶縁の低下に伴う停電の発生を予測する。 The prediction unit 12 predicts a failure that occurs in the equipment 30 based on the diagnosis result input from the diagnosis unit 11 and the learning model 135 for prediction. For example, as illustrated in FIG. 2, the prediction unit 12 inputs the diagnosis result that salt is attached to the insulator included in the equipment 30 by the diagnosis unit 11, and insulates using the prediction learning model 135. Predict the occurrence of power outages due to the decrease in
　予測部１２は、また、予測用学習モデル１３５を生成する機械学習を行う機能を有する。記憶部１３にはこれまでに設備３０において発生した障害の実績を表す障害実績１３３が記憶されている。障害実績１３３は、例えば管理端末４０を介して、作業員により設備診断装置１０に入力された情報である。尚、記憶部１３は、状態情報１３２と障害実績１３３とを関連付けて記憶している。即ち、記憶部１３は、設備３０がある状態にある場合に、設備３０において発生する可能性がある障害を表す情報を記憶している。 The prediction unit 12 also has a function of performing machine learning to generate a learning model 135 for prediction. The storage unit 13 stores the failure record 133, which represents the record of failures that have occurred in the equipment 30 so far. The failure record 133 is information input to the equipment diagnosis device 10 by the worker via, for example, the management terminal 40. The storage unit 13 stores the state information 132 and the failure record 133 in association with each other. That is, the storage unit 13 stores information representing a failure that may occur in the equipment 30 when the equipment 30 is in a certain state.
　予測部１２は、診断結果に関する複数のサンプルデータを入力データとし障害実績１３３をラベルとする教師データを用いて機械学習を行い、当該機械学習の結果を表す予測用学習モデル１３５を生成あるいは更新する。即ち、予測用学習モデル１３５は、予測部１２が、診断部１１による設備３０の状態の診断結果に基づいて、設備３０において発生する障害を予測する際に用いる学習モデルである。 The prediction unit 12 performs machine learning using a plurality of sample data related to the diagnosis result as input data and teacher data using the failure record 133 as a label, and generates or updates a prediction learning model 135 representing the result of the machine learning. .. That is, the prediction learning model 135 is a learning model used by the prediction unit 12 when predicting a failure that occurs in the equipment 30 based on the diagnosis result of the state of the equipment 30 by the diagnosis unit 11.
　予測部１２は、予測用学習モデル１３５を生成後、診断部１１による診断結果を入力し、予測用学習モデル１３５を用いて、設備３０において発生する障害を予測した結果を出力する。予測部１２は、障害を予測した結果を、管理端末４０に出力する。予測部１２は、また、設備３０において発生する障害を予測した結果を、管理端末４０から参照可能に、記憶部１３に格納してもよい。 After generating the prediction learning model 135, the prediction unit 12 inputs the diagnosis result by the diagnosis unit 11, and outputs the result of predicting the failure occurring in the equipment 30 using the prediction learning model 135. The prediction unit 12 outputs the result of predicting the failure to the management terminal 40. The prediction unit 12 may also store the result of predicting a failure occurring in the equipment 30 in the storage unit 13 so that the management terminal 40 can refer to it.
　次に図３のフローチャートを参照して、本実施形態に係る設備診断システム１の動作（処理）について詳細に説明する。 Next, the operation (processing) of the equipment diagnosis system 1 according to the present embodiment will be described in detail with reference to the flowchart of FIG.
　車両２３は、設備３０を撮像可能な場所に移動する（ステップＳ１０１）。カメラ２１は、設備３０を撮像した近赤外線撮像画像２１０を取得し、カメラ２２は、設備３０を撮像した遠赤外線撮像画像２２０を取得する（ステップＳ１０２）。カメラ２１は、近赤外線撮像画像２１０を設備診断装置１０へ入力し、カメラ２２は、遠赤外線撮像画像２２０を、設備診断装置１０へ入力する（ステップＳ１０３）。 The vehicle 23 moves to a place where the equipment 30 can be imaged (step S101). The camera 21 acquires a near-infrared image 210 that images the equipment 30, and the camera 22 acquires a far-infrared image 220 that images the equipment 30 (step S102). The camera 21 inputs the near-infrared image 210 to the equipment diagnostic device 10, and the camera 22 inputs the far-infrared image 220 to the equipment diagnostic device 10 (step S103).
　設備診断装置１０における診断部１１は、近赤外線撮像画像２１０と遠赤外線撮像画像２２０と診断用学習モデル１３４とに基づいて、設備３０の状態を診断する（ステップＳ１０４）。設備診断装置１０における予測部１２は、診断部１１による設備３０の状態の診断結果と予測用学習モデル１３５とに基づいて、設備３０において発生する障害を予測し（ステップＳ１０５）、全体の処理は終了する。 The diagnostic unit 11 in the equipment diagnostic apparatus 10 diagnoses the state of the equipment 30 based on the near-infrared image 210, the far-infrared image 220, and the diagnostic learning model 134 (step S104). The prediction unit 12 in the equipment diagnosis device 10 predicts a failure occurring in the equipment 30 based on the diagnosis result of the state of the equipment 30 by the diagnosis unit 11 and the learning model 135 for prediction (step S105), and the entire process is performed. finish.
　本実施形態に係る設備診断システム１は、設備の診断を、高い精度で、かつ効率的に行うことができる。その理由は、設備診断システム１では、近赤外線帯域において設備３０を撮像するカメラ２１を搭載した車両２３が設備３０を撮像可能な場所に移動し、診断部１１が、カメラ２１によって得られた近赤外線撮像画像２１０に基づいて、設備３０の状態を診断するからである。 The equipment diagnosis system 1 according to the present embodiment can perform equipment diagnosis with high accuracy and efficiency. The reason is that in the equipment diagnosis system 1, the vehicle 23 equipped with the camera 21 that images the equipment 30 in the near-infrared band moves to a place where the equipment 30 can be imaged, and the diagnosis unit 11 is obtained by the camera 21. This is because the state of the equipment 30 is diagnosed based on the infrared captured image 210.
　以下に、本実施形態に係る設備診断システム１によって実現される効果について、詳細に説明する。 The effects realized by the equipment diagnosis system 1 according to the present embodiment will be described in detail below.
　社会インフラを構成する診断の対象となる設備は、様々な場所に設定されており、例えば、柱上など作業員が行きにくい場所に設置された、膨大な数の電源設備や通信設備等を診断するのに要するコストは非常に高い。従って、設備の診断を、高い精度で、かつ効率的に行うことが課題である。 The equipment that constitutes the social infrastructure and is the target of diagnosis is set in various places. For example, a huge number of power supply equipment and communication equipment installed in places that are difficult for workers to reach, such as on pillars, are diagnosed. The cost to do so is very high. Therefore, it is an issue to perform equipment diagnosis with high accuracy and efficiency.
　このような課題に対して、本実施形態に係る設備診断システム１は、カメラ２１と、車両２３と、診断部１１とを備え、例えば図１乃至図３を参照して上述した通り動作する。即ち、カメラ２１は、近赤外線帯域において設備３０を撮像する。車両２３は、カメラ２１を搭載し、設備３０を撮像可能な場所に移動する。そして、診断部１１は、カメラ２１によって得られた近赤外線撮像画像２１０に基づいて、設備３０の状態を診断する。 For such a problem, the equipment diagnosis system 1 according to the present embodiment includes a camera 21, a vehicle 23, and a diagnosis unit 11, and operates as described above with reference to, for example, FIGS. 1 to 3. That is, the camera 21 images the equipment 30 in the near infrared band. The vehicle 23 is equipped with the camera 21 and moves to a place where the equipment 30 can be imaged. Then, the diagnosis unit 11 diagnoses the state of the equipment 30 based on the near-infrared image captured image 210 obtained by the camera 21.
　即ち、本実施形態に係る設備診断システム１では、近赤外線により撮像するカメラ２１を搭載した車両２３が、診断対象の設備３０を撮像可能な場所まで行き、その場所から近赤外線により設備３０を撮影する。近赤外線に特有の吸光特性や反射特性を利用した近赤外線撮像画像２１０は、図２に例示する通り、設備３０の状態を明確に表しているので、設備３０からある程度離れた場所からの撮像された画像であっても、その画像から設備３０の状態を診断可能である。したがって、設備診断システム１は、近赤外線により撮像するカメラ２１を用いることで、例えば設備３０のすぐ近くまで行かなくとも、道路を走行する車両２３から撮像した近赤外線撮像画像２１０に基づく高い精度の診断を行うことができる。 That is, in the equipment diagnosis system 1 according to the present embodiment, the vehicle 23 equipped with the camera 21 that captures images by near infrared rays goes to a place where the equipment 30 to be diagnosed can be imaged, and the equipment 30 is photographed by near infrared rays from that place. do. As illustrated in FIG. 2, the near-infrared image 210 that utilizes the absorption characteristics and reflection characteristics peculiar to near-infrared rays clearly represents the state of the equipment 30, and is therefore imaged from a place some distance from the equipment 30. It is possible to diagnose the state of the equipment 30 from the image even if it is an infrared image. Therefore, the equipment diagnosis system 1 uses the camera 21 that captures images by near-infrared rays, so that the equipment diagnosis system 1 has high accuracy based on the near-infrared image captured image 210 imaged from the vehicle 23 traveling on the road without going to the immediate vicinity of the equipment 30, for example. Diagnosis can be made.
　また、本実施形態に係る設備診断システム１は、車両２３に搭載した、遠赤外線により撮像するカメラ２２をさらに備え、カメラ２１により得られた近赤外線撮像画像２１０と、カメラ２２により得られた遠赤外線撮像画像２２０との両方に基づいて設備３０の状態を診断する。近赤外線撮像画像２１０は設備３０の表面における付着物の状態を表し、遠赤外線撮像画像２２０は設備３０の表面の温度を表すので、設備診断システム１はこれらの２種類の撮像画像に基づいて、設備３０の状態をより高い精度で行うことができる。 Further, the equipment diagnosis system 1 according to the present embodiment further includes a camera 22 mounted on the vehicle 23 for imaging by far infrared rays, and a near infrared image captured image 210 obtained by the camera 21 and a far infrared ray image obtained by the camera 22. The state of the equipment 30 is diagnosed based on both the infrared captured image 220 and the infrared image 220. Since the near-infrared image 210 represents the state of deposits on the surface of the equipment 30 and the far-infrared image 220 represents the temperature of the surface of the equipment 30, the equipment diagnostic system 1 is based on these two types of captured images. The state of the equipment 30 can be performed with higher accuracy.
　また、本実施形態に係るカメラ２１あるいはカメラ２２は、設備３０に表示された文字を撮像し、診断部１１は、近赤外線撮像画像２１０あるいは遠赤外線撮像画像２２０に含まれる文字が表す情報を識別し、文字の識別結果をふまえて、設備３０の状態を診断してもよい。この場合、診断部１１は、既存の文字認識技術を用いることによって、画像に含まれる文字を認識可能である。 Further, the camera 21 or the camera 22 according to the present embodiment captures the characters displayed on the equipment 30, and the diagnostic unit 11 identifies the information represented by the characters included in the near-infrared image 210 or the far-infrared image 220. Then, the state of the equipment 30 may be diagnosed based on the character identification result. In this case, the diagnostic unit 11 can recognize the characters included in the image by using the existing character recognition technique.
　例えば、診断部１１は、設備３０に塩分の付着に対する注意を喚起する「塩分付着注意」という文字が表示されている場合において、その文字を文字識別処理によって識別する。そして、診断部１１は、設備３０における塩分の付着を近赤外線撮像画像２１０から検出した場合、設備３０において塩分が付着している問題が生じていると診断する。設備３０に「塩分付着注意」という文字が表示されていない場合、診断部１１は、設備３０における塩分の付着を検出したとしても、設備３０は特に問題ないと診断してもよい。 For example, when the character "Caution for salt adhesion" is displayed on the equipment 30 to call attention to the adhesion of salt, the diagnosis unit 11 identifies the character by the character identification process. Then, when the diagnosis unit 11 detects the adhesion of salt in the equipment 30 from the near-infrared image captured image 210, the diagnosis unit 11 diagnoses that the problem of salt adhesion in the equipment 30 has occurred. When the word "Caution for salt adhesion" is not displayed on the equipment 30, the diagnosis unit 11 may diagnose that the equipment 30 has no particular problem even if the equipment 30 detects the adhesion of salt.
　あるいは例えば、診断部１１は、設備３０に高温に対する注意を喚起する「高温注意」という文字が表示されている場合において、その文字を文字識別処理によって識別する。そして、診断部１１は、設備３０における発熱を遠赤外線撮像画像２２０から検出した場合、設備３０において発熱している問題が生じていると診断する。設備３０に「高温注意」という文字が表示されていない場合、診断部１１は、設備３０における発熱を検出したとしても、ユーザが指定する既定の温度範囲内であれば、設備３０は特に問題ないと診断してもよい。 Alternatively, for example, when the character "high temperature caution" that calls attention to high temperature is displayed on the equipment 30, the diagnostic unit 11 identifies the character by character identification processing. Then, when the heat generation in the equipment 30 is detected from the far-infrared image captured image 220, the diagnosis unit 11 diagnoses that the problem of heat generation in the equipment 30 has occurred. If the word "high temperature caution" is not displayed on the equipment 30, even if the diagnostic unit 11 detects heat generation in the equipment 30, the equipment 30 has no particular problem as long as it is within the predetermined temperature range specified by the user. May be diagnosed.
　このように、設備診断システム１は、近赤外線撮像画像２１０あるいは遠赤外線撮像画像２２０に含まれる文字が表す情報をふまえて、設備３０の状態をより正確に診断することができる。 As described above, the equipment diagnosis system 1 can more accurately diagnose the state of the equipment 30 based on the information represented by the characters contained in the near-infrared image 210 or the far-infrared image 220.
　また、本実施形態に係る設備診断システム１は、診断用学習モデル１３４を生成及び更新しながら、設備３０の状態を診断するとともに、予測用学習モデル１３５を生成及び更新しながら、設備３０において発生する障害を予測する。これにより設備診断システム１は、設備３０の状態の診断精度や、設備３０において発生する障害の予測精度を向上させることができる。尚、設備診断システム１は、診断用学習モデル１３４や予測用学習モデル１３５を必ずしも備える必要はなく、診断や予測を行うための基準となる情報が与えられればよい。また、本実施形態に係る設備診断システム１は、カメラ２１及び２２を搭載して設備３０を撮像可能な場所に移動する移動手段として、車両２３の代わりに、例えばドローンやヘリコプター等の飛翔体を用いるようにしてもよい。 Further, the equipment diagnosis system 1 according to the present embodiment diagnoses the state of the equipment 30 while generating and updating the learning learning model 134 for diagnosis, and generates and updates the learning model 135 for prediction while generating and updating the equipment 30. Predict the obstacles to be made. As a result, the equipment diagnosis system 1 can improve the accuracy of diagnosing the state of the equipment 30 and the accuracy of predicting failures that occur in the equipment 30. The equipment diagnosis system 1 does not necessarily have to include the learning model 134 for diagnosis and the learning model 135 for prediction, and may be provided with information that serves as a reference for performing diagnosis and prediction. Further, the equipment diagnosis system 1 according to the present embodiment uses a flying object such as a drone or a helicopter instead of the vehicle 23 as a means of moving the equipment 30 by mounting the cameras 21 and 22 to a place where the equipment 30 can be imaged. You may use it.
　また、本実施形態に係る設備診断システム１が診断対象とする設備３０は、柱３１の上部に設置された柱上設備に限定されない。設備３０の設置場所は、車両２３等の移動手段が移動可能な場所から設備３０を撮像できるような場所であればよい。 Further, the equipment 30 to be diagnosed by the equipment diagnosis system 1 according to the present embodiment is not limited to the equipment on the pillar installed above the pillar 31. The installation location of the equipment 30 may be any place where the equipment 30 can be imaged from a place where the moving means such as the vehicle 23 can move.
　＜第２の実施形態＞
　図４は、本発明の第２の実施形態に係る設備診断システム５の構成を示すブロック図である。設備診断システム５は、撮像部５１、移動部５２、及び、診断部５３を備えている。但し、撮像部５１、移動部５２、及び、診断部５３は、順に、撮像手段、移動手段、及び、診断手段の一例である。 <Second embodiment>
FIG. 4 is a block diagram showing the configuration of the equipment diagnosis system 5 according to the second embodiment of the present invention. The equipment diagnosis system 5 includes an imaging unit 51, a moving unit 52, and a diagnostic unit 53. However, the imaging unit 51, the moving unit 52, and the diagnostic unit 53 are, in order, examples of the imaging means, the moving means, and the diagnostic means.
　撮像部５１は、近赤外線帯域において設備５０を撮像する。但し、撮像部５１は、例えば第１の実施形態に係るカメラ２１のような機器である。 The imaging unit 51 images the equipment 50 in the near infrared band. However, the imaging unit 51 is, for example, a device such as the camera 21 according to the first embodiment.
　移動部５２は、撮像部５１を搭載し、設備５０を撮像可能な場所に移動する。但し、移動部５２は、例えば第１の実施形態に係る車両２３のような移動手段である。 The moving unit 52 mounts the imaging unit 51 and moves the equipment 50 to a place where imaging is possible. However, the moving unit 52 is a moving means such as the vehicle 23 according to the first embodiment.
　診断部５３は、撮像部５１によって得られた近赤外線撮像画像５１０に基づいて、設備５０の状態を診断する。診断部５３は、例えば、第１の実施形態に係る設備診断装置１０のような情報処理装置によって実現可能である。診断部５３は、例えば、第１の実施形態に係る診断部１１と同様に、設備５０の診断に関する教師データを用いて機械学習をおこなった結果を表す学習モデルを生成し、当該学習モデルを用いて、設備５０の状態を診断してもよい。 The diagnosis unit 53 diagnoses the state of the equipment 50 based on the near-infrared image captured image 510 obtained by the imaging unit 51. The diagnosis unit 53 can be realized by, for example, an information processing device such as the equipment diagnosis device 10 according to the first embodiment. For example, the diagnosis unit 53 generates a learning model representing the result of machine learning using the teacher data related to the diagnosis of the equipment 50, and uses the learning model, as in the diagnosis unit 11 according to the first embodiment. The condition of the equipment 50 may be diagnosed.
　本実施形態に係る設備診断システム５は、設備の診断を、高い精度で、かつ効率的に行うことができる。その理由は、設備診断システム５では、近赤外線帯域において設備５０を撮像する撮像部５１を搭載した移動部５２が設備５０を撮像可能な場所に移動し、診断部５３が、撮像部５１によって得られた近赤外線撮像画像５１０に基づいて、設備５０の状態を診断するからである。 The equipment diagnosis system 5 according to the present embodiment can perform equipment diagnosis with high accuracy and efficiency. The reason is that in the equipment diagnosis system 5, the moving unit 52 equipped with the imaging unit 51 that images the equipment 50 in the near infrared band moves to a place where the equipment 50 can be imaged, and the diagnostic unit 53 obtains the image by the imaging unit 51. This is because the state of the equipment 50 is diagnosed based on the obtained near-infrared image 510.
　＜ハードウェア構成例＞
　上述した各実施形態において図１に示した設備診断装置１０における各部、あるいは、図４に示した診断部５３は、専用のＨＷ（ＨａｒｄＷａｒｅ）（電子回路）によって実現することができる。また、図１及び図４において、少なくとも、下記構成は、ソフトウェアプログラムの機能（処理）単位（ソフトウェアモジュール）と捉えることができる。
・診断部１１及び５３、
・予測部１２、
・記憶部１３における記憶制御機能。 <Hardware configuration example>
In each of the above-described embodiments, each part of the equipment diagnostic apparatus 10 shown in FIG. 1 or the diagnostic unit 53 shown in FIG. 4 can be realized by a dedicated HW (HardWare) (electronic circuit). Further, in FIGS. 1 and 4, at least the following configuration can be regarded as a function (processing) unit (software module) of the software program.
・ Diagnosis departments 11 and 53,
・ Forecasting unit 12,
-Memory control function in the storage unit 13.
　但し、これらの図面に示した各部の区分けは、説明の便宜上の構成であり、実装に際しては、様々な構成が想定され得る。この場合のハードウェア環境の一例を、図５を参照して説明する。 However, the division of each part shown in these drawings is a configuration for convenience of explanation, and various configurations can be assumed at the time of mounting. An example of the hardware environment in this case will be described with reference to FIG.
　図５は、本発明の第１の実施形態に係る設備診断装置１０あるいは第２の実施形態に係る診断部５３を実行可能な情報処理装置９００（コンピュータ）の構成を例示的に説明する図である。即ち、図５は、図１に示した設備診断装置１０及び図４に示した診断部５３を実現可能なコンピュータ（情報処理装置）の構成であって、上述した実施形態における各機能を実現可能なハードウェア環境を表す。 FIG. 5 is a diagram illustrating an example of a configuration of an information processing device 900 (computer) capable of executing the equipment diagnostic device 10 according to the first embodiment of the present invention or the diagnostic unit 53 according to the second embodiment. be. That is, FIG. 5 is a configuration of a computer (information processing device) capable of realizing the equipment diagnostic device 10 shown in FIG. 1 and the diagnostic unit 53 shown in FIG. 4, and each function in the above-described embodiment can be realized. Represents a hardware environment.
　図５に示した情報処理装置９００は、構成要素として下記を備えているが、下記のうちの一部の構成要素を備えない場合もある。
・ＣＰＵ（Ｃｅｎｔｒａｌ＿Ｐｒｏｃｅｓｓｉｎｇ＿Ｕｎｉｔ）９０１、
・ＲＯＭ（Ｒｅａｄ＿Ｏｎｌｙ＿Ｍｅｍｏｒｙ）９０２、
・ＲＡＭ（Ｒａｎｄｏｍ＿Ａｃｃｅｓｓ＿Ｍｅｍｏｒｙ）９０３、
・ハードディスク（記憶装置）９０４、
・外部装置との通信インタフェース９０５、
・バス９０６（通信線）、
・ＣＤ－ＲＯＭ（Ｃｏｍｐａｃｔ＿Ｄｉｓｃ＿Ｒｅａｄ＿Ｏｎｌｙ＿Ｍｅｍｏｒｙ）等の記録媒体９０７に格納されたデータを読み書き可能なリーダライタ９０８、
・モニターやスピーカ、キーボード等の入出力インタフェース９０９。 The information processing apparatus 900 shown in FIG. 5 includes the following components, but may not include some of the following components.
-CPU (Central_Processing_Unit) 901,
-ROM (Read_Only_Memory) 902,
・ RAM (Random_Access_Memory) 903,
-Hard disk (storage device) 904,
-Communication interface 905 with an external device,
・ Bus 906 (communication line),
A reader / writer 908 that can read and write data stored in a recording medium 907 such as a CD-ROM (Compact_Disc_Read_Only_Memory),
-Input / output interface 909 for monitors, speakers, keyboards, etc.
　即ち、上記構成要素を備える情報処理装置９００は、これらの構成がバス９０６を介して接続された一般的なコンピュータである。情報処理装置９００は、ＣＰＵ９０１を複数備える場合もあれば、マルチコアにより構成されたＣＰＵ９０１を備える場合もある。情報処理装置９００は、ＣＰＵ９０１に加えてＧＰＵ（Ｇｒａｐｈｉｃａｌ＿Ｐｒｏｃｅｓｓｉｎｇ＿Ｕｎｉｔ）（不図示）を備えてもよい。 That is, the information processing device 900 including the above components is a general computer in which these components are connected via the bus 906. The information processing device 900 may include a plurality of CPUs 901 or may include a CPU 901 configured by a multi-core processor. The information processing device 900 may include a GPU (Graphical_Processing_Unit) (not shown) in addition to the CPU 901.
　そして、上述した実施形態を例に説明した本発明は、図５に示した情報処理装置９００に対して、次の機能を実現可能なコンピュータプログラムを供給する。その機能とは、その実施形態の説明において参照したブロック構成図（図１及び図４）における上述した構成、或いはフローチャート（図３）の機能である。本発明は、その後、そのコンピュータプログラムを、当該ハードウェアのＣＰＵ９０１に読み出して解釈し実行することによって達成される。また、当該装置内に供給されたコンピュータプログラムは、読み書き可能な揮発性のメモリ（ＲＡＭ９０３）、または、ＲＯＭ９０２やハードディスク９０４等の不揮発性の記憶デバイスに格納すれば良い。 Then, the present invention described by taking the above-described embodiment as an example supplies the computer program capable of realizing the following functions to the information processing apparatus 900 shown in FIG. The function is the above-described configuration in the block configuration diagrams (FIGS. 1 and 4) referred to in the description of the embodiment, or the function of the flowchart (FIG. 3). The present invention is then achieved by reading, interpreting, and executing the computer program in the CPU 901 of the hardware. Further, the computer program supplied in the device may be stored in a readable / writable volatile memory (RAM 903) or a non-volatile storage device such as a ROM 902 or a hard disk 904.
　また、前記の場合において、当該ハードウェア内へのコンピュータプログラムの供給方法は、現在では一般的な手順を採用することができる。その手順としては、例えば、ＣＤ－ＲＯＭ等の各種記録媒体９０７を介して当該装置内にインストールする方法や、インターネット等の通信回線を介して外部よりダウンロードする方法等がある。そして、このような場合において、本発明は、係るコンピュータプログラムを構成するコード或いは、そのコードが格納された記録媒体９０７によって構成されると捉えることができる。 Further, in the above case, as the method of supplying the computer program into the hardware, a general procedure can be adopted now. As the procedure, for example, there are a method of installing in the device via various recording media 907 such as a CD-ROM, a method of downloading from the outside via a communication line such as the Internet, and the like. Then, in such a case, the present invention can be regarded as being composed of a code constituting the computer program or a recording medium 907 in which the code is stored.
　以上、上述した実施形態を模範的な例として本発明を説明した。しかしながら、本発明は、上述した実施形態には限定されない。即ち、本発明は、本発明のスコープ内において、当業者が理解し得る様々な態様を適用することができる。 The present invention has been described above using the above-described embodiment as a model example. However, the present invention is not limited to the above-described embodiments. That is, the present invention can apply various aspects that can be understood by those skilled in the art within the scope of the present invention.
　尚、上述した各実施形態の一部又は全部は、以下の付記のようにも記載されうる。しかしながら、上述した各実施形態により例示的に説明した本発明は、以下には限られない。 Note that some or all of the above-described embodiments can also be described as described in the following appendices. However, the present invention exemplified by each of the above-described embodiments is not limited to the following.
　（付記１）
　近赤外線帯域において設備を撮像する第一撮像手段と、
　前記第一撮像手段を搭載し、前記設備を撮像可能な場所に移動する移動手段と、
　前記第一撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する診断手段と、
　を備える設備診断システム。 (Appendix 1)
The first imaging means for imaging equipment in the near-infrared band,
A moving means equipped with the first imaging means and moving the equipment to a place where imaging is possible, and
A diagnostic means for diagnosing the state of the equipment based on the near-infrared image captured by the first imaging means, and
Equipment diagnostic system equipped with.
　（付記２）
　前記第一撮像手段は、前記設備の表面に物質が付着した状態を表す前記近赤外線撮像画像を取得する、
　付記１に記載の設備診断システム。 (Appendix 2)
The first imaging means acquires the near-infrared captured image showing a state in which a substance adheres to the surface of the equipment.
The equipment diagnostic system according to Appendix 1.
　（付記３）
　前記第一撮像手段は、前記設備の表面に、水分、油分、塩分が付着した状態を表す前記近赤外線撮像画像を取得する、
　付記２に記載の設備診断システム。 (Appendix 3)
The first imaging means acquires the near-infrared captured image showing a state in which water, oil, and salt are attached to the surface of the equipment.
The equipment diagnostic system described in Appendix 2.
　（付記４）
　前記第一撮像手段は、前記設備に表示された文字を撮像し、
　前記診断手段は、前記第一撮像手段によって得られた文字画像に基づいて、前記設備の状態を診断する、
　付記１乃至付記３のいずれか一項に記載の設備診断システム。 (Appendix 4)
The first imaging means captures characters displayed on the equipment and obtains images.
The diagnostic means diagnoses the state of the equipment based on the character image obtained by the first imaging means.
The equipment diagnosis system according to any one of Appendix 1 to Appendix 3.
　（付記５）
　遠赤外線帯域において前記設備を撮像する第二撮像手段を備え、
　前記移動手段は、前記第二撮像手段を搭載し、
　前記第二撮像手段は前記設備における発熱を表す遠赤外線撮像画像を取得し、
　前記診断手段は、前記遠赤外線撮像画像と前記近赤外線撮像画像とに基づいて、前記設備の状態を診断する、
　付記１乃至付記４のいずれか一項に記載の設備診断システム。 (Appendix 5)
A second imaging means for imaging the equipment in the far infrared band is provided.
The moving means is equipped with the second imaging means.
The second imaging means acquires a far-infrared image that represents heat generation in the equipment, and obtains a far-infrared image.
The diagnostic means diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
The equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 4.
　（付記６）
　前記近赤外線撮像画像と前記設備の状態を表す情報とを関連付けて記憶する記憶手段をさらに備え、
　前記診断手段は、前記近赤外線撮像画像から前記設備の状態を診断する際に用いる第一の学習モデルを生成する、
　をさらに備える、付記１乃至付記５のいずれか一項に記載の設備診断システム。 (Appendix 6)
Further provided with a storage means for associating and storing the near-infrared image and the information representing the state of the equipment.
The diagnostic means generates a first learning model used when diagnosing the state of the equipment from the near-infrared image.
The equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 5, further comprising.
　（付記７）
　前記診断手段による前記設備の診断結果から前記設備において発生する障害を予測するとともに、前記障害を予測する際に用いる第二の学習モデルを生成する予測手段を更に備え、
　前記記憶手段は、前記設備の状態を表す情報と、前記設備において発生した障害の実績とを関連付けて記憶する、
　付記６に記載の設備診断システム。 (Appendix 7)
A prediction means for predicting a failure occurring in the facility from the diagnosis result of the facility by the diagnostic means and generating a second learning model used for predicting the failure is further provided.
The storage means stores information representing the state of the equipment in association with a record of failures that have occurred in the equipment.
The equipment diagnostic system according to Appendix 6.
　（付記８）
　前記移動手段は、車両あるいは飛翔体である、
　付記１乃至付記７のいずれか一項に記載の設備診断システム。 (Appendix 8)
The means of transportation is a vehicle or a flying object.
The equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 7.
　（付記９）
　前記設備は柱上に設置されている、
　付記１乃至付記８のいずれか一項に記載の設備診断システム。 (Appendix 9)
The equipment is installed on a pillar,
The equipment diagnosis system according to any one of Supplementary note 1 to Supplementary note 8.
　（付記１０）
　第一撮像手段を搭載した移動手段が、設備を撮像可能な場所に移動し、
　前記第一撮像手段によって、近赤外線帯域において前記設備を撮像し、
　情報処理装置によって、前記撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する、
　設備診断方法。 (Appendix 10)
The moving means equipped with the first imaging means moves to a place where the equipment can be imaged,
The equipment is imaged in the near infrared band by the first imaging means.
The information processing device diagnoses the state of the equipment based on the near-infrared image captured by the imaging means.
Equipment diagnosis method.
　（付記１１）
　前記移動手段は、第二撮像手段を搭載し、
　前記第二撮像手段によって、遠赤外線帯域において前記設備を撮像した前記設備における発熱を表す遠赤外線撮像画像を取得し、
　前記情報処理装置によって、前記遠赤外線撮像画像と前記近赤外線撮像画像とに基づいて、前記設備の状態を診断する、
　付記１０に記載の設備診断方法。 (Appendix 11)
The moving means is equipped with a second imaging means.
The second imaging means acquires a far-infrared image that represents heat generation in the equipment that images the equipment in the far-infrared band.
The information processing device diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
The equipment diagnosis method according to Appendix 10.
　１　　設備診断システム
　１０　　設備診断装置
　１１　　診断部
　１２　　予測部
　１３　　記憶部
　１３１　　撮像画像
　１３２　　状態情報
　１３３　　障害実績
　１３４　　診断用学習モデル
　１３５　　予測用学習モデル
　２１　　カメラ
　２１０　　近赤外線撮像画像
　２２　　カメラ
　２２０　　遠赤外線撮像画像
　２３　　車両
　３０　　設備
　３１　　柱
　４０　　管理端末
　５　　設備診断システム
　５０　　設備
　５１　　撮像部
　５１０　　近赤外線撮像画像
　５２　　移動部
　５３　　診断部
　９００　　情報処理装置
　９０１　　ＣＰＵ
　９０２　　ＲＯＭ
　９０３　　ＲＡＭ
　９０４　　ハードディスク（記憶装置）
　９０５　　通信インタフェース
　９０６　　バス
　９０７　　記録媒体
　９０８　　リーダライタ
　９０９　　入出力インタフェース 1 Equipment Diagnostic System 10 Equipment Diagnostic Device 11 Diagnostic Unit 12 Prediction Unit 13 Storage Unit 131 Captured Image 132 Status Information 133 Failure Record 134 Diagnostic Learning Model 135 Predictive Learning Model 21 Camera 210 Near Infrared Captured Image 22 Camera 220 Far Infrared Captured Image 23 Vehicle 30 Equipment 31 Pillar 40 Management terminal 5 Equipment diagnostic system 50 Equipment 51 Imaging unit 510 Near infrared imaging image 52 Mobile unit 53 Diagnosis unit 900 Information processing device 901 CPU
902 ROM
903 RAM
904 hard disk (storage device)
905 Communication interface 906 Bus 907 Recording medium 908 Reader / writer 909 Input / output interface

Claims (11)

  1. 　近赤外線帯域において設備を撮像する第一撮像手段と、
    　前記第一撮像手段を搭載し、前記設備を撮像可能な場所に移動する移動手段と、
    　前記第一撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する診断手段と、
    　を備える設備診断システム。     The first imaging means for imaging equipment in the near-infrared band,
    A moving means equipped with the first imaging means and moving the equipment to a place where imaging is possible, and
    A diagnostic means for diagnosing the state of the equipment based on the near-infrared image captured by the first imaging means, and
    Equipment diagnostic system equipped with.
  2. 　前記第一撮像手段は、前記設備の表面に物質が付着した状態を表す前記近赤外線撮像画像を取得する、
    　請求項１に記載の設備診断システム。     The first imaging means acquires the near-infrared captured image showing a state in which a substance adheres to the surface of the equipment.
    The equipment diagnostic system according to claim 1.
  3. 　前記第一撮像手段は、前記設備の表面に、水分、油分、塩分が付着した状態を表す前記近赤外線撮像画像を取得する、
    　請求項２に記載の設備診断システム。     The first imaging means acquires the near-infrared captured image showing a state in which water, oil, and salt are attached to the surface of the equipment.
    The equipment diagnostic system according to claim 2.
  4. 　前記第一撮像手段は、前記設備に表示された文字を撮像し、
    　前記診断手段は、前記第一撮像手段によって得られた文字画像に基づいて、前記設備の状態を診断する、
    　請求項１乃至請求項３のいずれか一項に記載の設備診断システム。     The first imaging means captures characters displayed on the equipment and obtains images.
    The diagnostic means diagnoses the state of the equipment based on the character image obtained by the first imaging means.
    The equipment diagnosis system according to any one of claims 1 to 3.
  5. 　遠赤外線帯域において前記設備を撮像する第二撮像手段を備え、
    　前記移動手段は、前記第二撮像手段を搭載し、
    　前記第二撮像手段は前記設備における発熱を表す遠赤外線撮像画像を取得し、
    　前記診断手段は、前記遠赤外線撮像画像と前記近赤外線撮像画像とに基づいて、前記設備の状態を診断する、
    　請求項１乃至請求項４のいずれか一項に記載の設備診断システム。     A second imaging means for imaging the equipment in the far infrared band is provided.
    The moving means is equipped with the second imaging means.
    The second imaging means acquires a far-infrared image that represents heat generation in the equipment, and obtains a far-infrared image.
    The diagnostic means diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
    The equipment diagnosis system according to any one of claims 1 to 4.
  6. 　前記近赤外線撮像画像と前記設備の状態を表す情報とを関連付けて記憶する記憶手段をさらに備え、
    　前記診断手段は、前記近赤外線撮像画像から前記設備の状態を診断する際に用いる第一の学習モデルを生成する、
    　をさらに備える、請求項１乃至請求項５のいずれか一項に記載の設備診断システム。     Further provided with a storage means for associating and storing the near-infrared image and the information representing the state of the equipment.
    The diagnostic means generates a first learning model used when diagnosing the state of the equipment from the near-infrared image.
    The equipment diagnosis system according to any one of claims 1 to 5, further comprising.
  7. 　前記診断手段による前記設備の診断結果から前記設備において発生する障害を予測するとともに、前記障害を予測する際に用いる第二の学習モデルを生成する予測手段を更に備え、
    　前記記憶手段は、前記設備の状態を表す情報と、前記設備において発生した障害の実績とを関連付けて記憶する、
    　請求項６に記載の設備診断システム。     A prediction means for predicting a failure occurring in the facility from the diagnosis result of the facility by the diagnostic means and generating a second learning model used for predicting the failure is further provided.
    The storage means stores information representing the state of the equipment in association with a record of failures that have occurred in the equipment.
    The equipment diagnostic system according to claim 6.
  8. 　前記移動手段は、車両あるいは飛翔体である、
    　請求項１乃至請求項７のいずれか一項に記載の設備診断システム。     The means of transportation is a vehicle or a flying object.
    The equipment diagnosis system according to any one of claims 1 to 7.
  9. 　前記設備は柱上に設置されている、
    　請求項１乃至請求項８のいずれか一項に記載の設備診断システム。     The equipment is installed on a pillar,
    The equipment diagnosis system according to any one of claims 1 to 8.
  10. 　第一撮像手段を搭載した移動手段が、設備を撮像可能な場所に移動し、
    　前記第一撮像手段によって、近赤外線帯域において前記設備を撮像し、
    　情報処理装置によって、前記第一撮像手段によって得られた近赤外線撮像画像に基づいて、前記設備の状態を診断する、
    　設備診断方法。     The moving means equipped with the first imaging means moves to a place where the equipment can be imaged,
    The equipment is imaged in the near infrared band by the first imaging means.
    The information processing device diagnoses the state of the equipment based on the near-infrared image captured by the first imaging means.
    Equipment diagnosis method.
  11. 　前記移動手段は、第二撮像手段を搭載し、
    　前記第二撮像手段によって、遠赤外線帯域において前記設備を撮像した前記設備における発熱を表す遠赤外線撮像画像を取得し、
    　前記情報処理装置によって、前記遠赤外線撮像画像と前記近赤外線撮像画像とに基づいて、前記設備の状態を診断する、
    　請求項１０に記載の設備診断方法。     The moving means is equipped with a second imaging means.
    The second imaging means acquires a far-infrared image that represents heat generation in the equipment that images the equipment in the far-infrared band.
    The information processing device diagnoses the state of the equipment based on the far-infrared image and the near-infrared image.
    The equipment diagnosis method according to claim 10.
PCT/JP2020/008962 2020-03-03 2020-03-03 Equipment diagnostic system and equipment diagnostic method WO2021176568A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022504822A JP7375909B2 (en) 2020-03-03 2020-03-03 Equipment diagnosis system and equipment diagnosis method
PCT/JP2020/008962 WO2021176568A1 (en) 2020-03-03 2020-03-03 Equipment diagnostic system and equipment diagnostic method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/008962 WO2021176568A1 (en) 2020-03-03 2020-03-03 Equipment diagnostic system and equipment diagnostic method

Publications (1)

Publication Number Publication Date
WO2021176568A1 true WO2021176568A1 (en) 2021-09-10

Family

ID=77613199

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/008962 WO2021176568A1 (en) 2020-03-03 2020-03-03 Equipment diagnostic system and equipment diagnostic method

Country Status (2)

Country Link
JP (1) JP7375909B2 (en)
WO (1) WO2021176568A1 (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003012122A (en) * 2001-06-28 2003-01-15 Nisshin Seifun Group Inc Storage and retrieval managing system
WO2010046968A1 (en) * 2008-10-21 2010-04-29 西日本高速道路エンジニアリング四国株式会社 Diagnostic device and diagnostic method for concrete structure
JP2016218813A (en) * 2015-05-22 2016-12-22 株式会社日立製作所 Inspection system of sewer line facility
JP2017087917A (en) * 2015-11-09 2017-05-25 株式会社日立製作所 Flight vehicle for pipeline facility inspection and pipeline facility inspection system using the same
JP2017224935A (en) * 2016-06-14 2017-12-21 株式会社日立ソリューションズ Object detection/evaluation system and object detection/evaluation method
JP2018037078A (en) * 2016-08-26 2018-03-08 伊達　博 Power generation monitoring system with failure detection function
JP2019009919A (en) * 2017-06-26 2019-01-17 株式会社東芝 Patrol inspection support system and patrol inspection support control program
US20190204814A1 (en) * 2016-05-24 2019-07-04 Siemens Aktiengesellschaft System and Method for Visualizing and Validating Process Events
US20190256208A1 (en) * 2017-03-13 2019-08-22 General Electric Company System and method for integrating flight path and site operating data
JP2019141909A (en) * 2012-03-09 2019-08-29 株式会社トヨコー Deposit removal method and deposit removal apparatus

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012242252A (en) * 2011-05-20 2012-12-10 Hitachi Kokusai Electric Inc Rail paving stone caving detection device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2003012122A (en) * 2001-06-28 2003-01-15 Nisshin Seifun Group Inc Storage and retrieval managing system
WO2010046968A1 (en) * 2008-10-21 2010-04-29 西日本高速道路エンジニアリング四国株式会社 Diagnostic device and diagnostic method for concrete structure
JP2019141909A (en) * 2012-03-09 2019-08-29 株式会社トヨコー Deposit removal method and deposit removal apparatus
JP2016218813A (en) * 2015-05-22 2016-12-22 株式会社日立製作所 Inspection system of sewer line facility
JP2017087917A (en) * 2015-11-09 2017-05-25 株式会社日立製作所 Flight vehicle for pipeline facility inspection and pipeline facility inspection system using the same
US20190204814A1 (en) * 2016-05-24 2019-07-04 Siemens Aktiengesellschaft System and Method for Visualizing and Validating Process Events
JP2017224935A (en) * 2016-06-14 2017-12-21 株式会社日立ソリューションズ Object detection/evaluation system and object detection/evaluation method
JP2018037078A (en) * 2016-08-26 2018-03-08 伊達　博 Power generation monitoring system with failure detection function
US20190256208A1 (en) * 2017-03-13 2019-08-22 General Electric Company System and method for integrating flight path and site operating data
JP2019009919A (en) * 2017-06-26 2019-01-17 株式会社東芝 Patrol inspection support system and patrol inspection support control program

Also Published As

Publication number Publication date
JP7375909B2 (en) 2023-11-08
JPWO2021176568A1 (en) 2021-09-10

Similar Documents

Publication Publication Date Title
US11449379B2 (en) Root cause and predictive analyses for technical issues of a computing environment
US10585773B2 (en) System to manage economics and operational dynamics of IT systems and infrastructure in a multi-vendor service environment
JP7080266B2 (en) AI-based inspection in transportation
US8959007B2 (en) Monitoring system
US20190294883A1 (en) Best image grab from video with digital grid assistance for aviation engine borescope inspection
CN109032102A (en) Automatic driving vehicle test method, device, equipment and storage medium
CN112669316B (en) Power production abnormality monitoring method, device, computer equipment and storage medium
JP2017199342A (en) Aircraft maintenance and inspection with data analytics enhancement
US20070129009A1 (en) Fault management system using satellite telemetering technology and method thereof
CN101999101B (en) The defining method of system cloud gray model prediction
CN113874889A (en) Self-maintenance autonomous vehicle procedure
US10885727B2 (en) Vehicular implemented inspection
WO2021176568A1 (en) Equipment diagnostic system and equipment diagnostic method
Michala et al. Vibration edge computing in maritime IoT
US11656328B2 (en) Validating object detection hardware and algorithms
RU2487023C1 (en) Method of maintenance and current repair of railway rolling stock
US11899527B2 (en) Systems and methods for identifying machine anomaly root cause based on a selected reduced order model and a selected fault model
EP4047550A1 (en) Train inspection system
CN114104329A (en) Automated prediction of fixes based on sensor data
US20210248681A1 (en) Detecting vehicle identity and damage status using single video analysis
CN113353072A (en) Driving control method, device, server and medium
Holland et al. Health ready components-unlocking the potential of IVHM
JP2021057957A (en) Patrol inspection system and patrol inspection method
Pecht A PHM Roadmap for Electronics‐Rich Systems
WO2024071317A1 (en) Sound recording device and abnormal sound analysis system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20922661

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022504822

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20922661

Country of ref document: EP

Kind code of ref document: A1