Anomaly detection system

Abstract

To improve abnormality inspection technology.SOLUTION: An abnormality detection system 100 includes an unmanned photographing device 1 which photographs an image of a facility to be inspected, a communication terminal 4 which acquires a photographed image from the unmanned photographing device 1, and an abnormality specifying device 6 which acquires a photographed image from the communication terminal 4 and specifies the abnormality of the inspection target from the photographed image. The unmanned photographing device 1 and the communication terminal 4 can communicate wirelessly through a first dedicated network. The communication terminal 4 and the abnormality specifying device 6 can perform radio communication through a second dedicated network. The communicable distance of the second dedicated network is longer than that of the first dedicated network.SELECTED DRAWING: Figure 1

Description

Technical Field

[0005] ,

[0001] The present disclosure relates to an equipment abnormality detection system.

Background Art

[0002] As equipment in a steel mill, for example, as a heating device for an annealing furnace, radiant tubes (hereinafter also referred to as RTs) are generally used. Due to aging deterioration caused by thermal expansion, abnormalities such as cracks in the tubes and bending such that the tubes themselves sag occur in the RTs. Therefore, when an abnormality is found in the RT, it is necessary to replace it appropriately. Conventional inspection of RTs has been carried out by an operator climbing between rows by hanging on the RTs, visually inspecting the RTs to be inspected, and filling in a checklist when there is an abnormality. This has been a factor in risks such as falling and increased man-hours.

Summary of the Invention

Problems to be Solved by the Invention

[0003] In the above-described conventional inspection method, it is necessary to fill in the checklist for the abnormal location, and there is a possibility of human errors such as incorrect entry in the checklist and overlooking abnormalities in the RTs. In recent years, inspection of various equipment using unmanned imaging means such as drones has been widely carried out. However, a suitable system configuration for ensuring the safety of imaging by the unmanned imaging device, ensuring the confidentiality of information, and efficiently and accurately inspecting equipment abnormalities has not been particularly considered. That is, there has been room for improvement in conventional abnormality detection techniques.

[0004] An object of the present disclosure made in view of such circumstances is to improve the equipment abnormality detection technology.

Means for Solving the Problems

[0005] (1) An anomaly detection system according to one embodiment of the present disclosure is an anomaly detection system comprising: an unmanned camera that takes images of equipment to be inspected; a communication terminal that acquires the images from the unmanned camera; and an anomaly identification device that acquires the images from the communication terminal and identifies an anomaly in the equipment to be inspected from the images, The unmanned camera and the communication terminal are wirelessly connected via a first dedicated network, and the communication terminal and the anomaly identification device are wirelessly connected via a second dedicated network, characterized in that the communication range of the second dedicated network is longer than the communication range of the first dedicated network.

[0006] (2) An anomaly detection system according to one embodiment of the present disclosure is the anomaly detection system described in (1), The abnormality detection device is capable of identifying abnormalities in the radiant tube, including cracks in the radiant tube that heats the steel plate, using an abnormality detection program that can identify abnormalities in the radiant tube. The anomaly identification program is machine-trained based on first training data relating to cracks in the radiant tube, and the first training data is characterized in that it includes images processed for the purpose of increasing information on the width, length, and clarity of cracks based on captured images of the cracks.

[0007] (3) An anomaly detection system according to one embodiment of the present disclosure is an anomaly detection system according to (1) or (2), The abnormality detection device is capable of identifying abnormalities in the radiant tube, including bending of the radiant tube that heats the steel plate, using an abnormality detection program that can identify abnormalities in the radiant tube. The anomaly detection program is machine-trained based on second training data relating to the bending of the radiant tube, and the second training data is characterized in that it includes images of the same bending taken at multiple angles.

[0008] (4) An anomaly detection system according to one embodiment of the present disclosure is an anomaly detection system according to (2) or (3), When the abnormality detection device detects an abnormality in the radiant tube, it transmits result information indicating the presence of the identified abnormality to the communication terminal. The aforementioned result information is characterized by including a risk indicator showing the degree of risk of an anomaly.

[0009] (5) An anomaly detection system according to one embodiment of the present disclosure is an anomaly detection system according to any one of (2) to (4), The abnormality detection device acquires the operating conditions related to the radiant tubes, predicts whether or not an abnormality has occurred in each radiant tube and the degree of risk, sets a priority for each radiant tube based on the predicted degree of risk, and the result information includes a priority display indicating the priority. [Effects of the Invention]

[0010] According to an equipment anomaly detection system according to one embodiment of this disclosure, the risk of accidents can be reduced by eliminating the need for inspectors to climb over equipment by photographing the equipment with an unmanned camera. Furthermore, since communication in this anomaly detection system is carried out using a first dedicated network or a second dedicated network, the risk of information leakage can be reduced. In other words, according to an equipment anomaly detection system according to one embodiment of this disclosure, equipment anomaly detection technology can be improved. [Brief explanation of the drawing]

[0011] [Figure 1] This figure shows an example configuration of an anomaly detection system according to one embodiment of the present disclosure. [Figure 2] This diagram shows an example of a flight path for an unmanned camera. [Figure 3] This diagram shows the overall structure of a radiant tube. [Figure 4] This is a schematic diagram showing the configuration of a radiant tube. [Figure 5] This is an example of result information displayed by a communication terminal. [Figure 6] This figure shows the hardware configuration of the unmanned camera 1 according to one embodiment of the present disclosure. [Figure 7] This figure shows the hardware configuration of a communication terminal 2 according to one embodiment of the present disclosure. [Figure 8] This figure shows the hardware configuration of a communication terminal 4 according to one embodiment of the present disclosure. [Figure 9] This figure shows the hardware configuration of an abnormality detection device 6 according to one embodiment of the present disclosure. [Modes for carrying out the invention]

[0012] The anomaly detection system according to the embodiments of this disclosure will be described below with reference to the drawings. In the following description, the RT used as a heating device for an annealing furnace will be used as an example of the equipment to which the anomaly detection system of the present invention is applied, but the equipment to be inspected is not limited to the RT. Examples of equipment other than the RT include the girder of a crane and cracks inside a chimney.

[0013] In each figure, identical or corresponding parts are denoted by the same reference numerals. In the description of this embodiment, the description of identical or corresponding parts will be omitted or simplified as appropriate.

[0014] Figure 1 shows an example configuration of the anomaly detection system 100 according to this embodiment. The anomaly detection system 100 includes an unmanned camera 1, a communication terminal 2, a communication terminal 4, and an anomaly identification device 6.

[0015] The unmanned camera 1 has an imaging unit such as a camera. For example, the unmanned camera 1 can be any device that can take pictures without being attached to a person's body (such as being held in the hand or attached to a helmet) when taking pictures with the imaging unit, and may be an unmanned aerial vehicle, for example. An unmanned aerial vehicle includes a drone. The captured image 3 taken by the imaging unit is transmitted from the unmanned camera 1 to the communication terminal 2. The unmanned camera 1 and the communication terminal 2 communicate using a short-range wireless communication standard (the first dedicated network described later). In the following embodiment, the case in which the unmanned camera 1 is a drone will be described, but it is not limited to this.

[0016] The communication terminal 2 and the communication terminal 4 are communication terminals equipped with functions such as the operation and monitoring of an unmanned aerial vehicle possessed by an operator such as a monitor of the unmanned imaging device 1 or other related persons (hereinafter, also simply referred to as an operator). In this embodiment, the communication terminal 2 has the function of operating the unmanned aerial vehicle. Also, the communication terminal 2 transmits the captured image 3 received from the unmanned imaging device 1 to the communication terminal 4. In other words, the communication terminal 4 acquires the captured image from the unmanned imaging device 1. For example, the communication terminal 2 is a control controller of the unmanned imaging device 1. The communication terminal 4 has the function of monitoring the unmanned aerial vehicle. Also, the communication terminal 4 includes a display unit that displays the captured image 3 transmitted from the communication terminal 2. Also, the display unit can display the abnormality diagnosis result of RT described later for browsing. The communication terminal 4 is, for example, a tablet terminal. The communication terminal 2 and the communication terminal 4 can communicate wirelessly via a first dedicated network. Note that the unmanned imaging device 1 and the communication terminal 4 may communicate directly. For example, the communication terminal 4 may directly receive the captured image from the unmanned imaging device 1. In this case, the unmanned imaging device 1 and the communication terminal 4 communicate via the first dedicated network.R Note that the functions of the communication terminal 2 and the communication terminal 4 may be configured by one communication terminal. For example, the communication terminal 4 may have the function of operating and monitoring the unmanned aerial vehicle. In this case, the unmanned imaging device 1 and the communication terminal 4 communicate via the first dedicated network.

[0017] The abnormality identification device 6 is a server device or the like having an abnormality identification program that detects the presence or absence of an abnormality based on the captured image 5 of the inspection target. The captured image 5 is transmitted from the communication terminal 4 to the abnormality identification device 6. In other words, the abnormality identification device 6 acquires the captured image from the communication terminal 4 and identifies the abnormality of the inspection target from the captured image. Although FIG. 1 shows an example in which there is one abnormality identification device 6 included in the abnormality detection system 100, it is not limited to this. The abnormality detection system 100 may include two or more abnormality identification devices 6.

[0018] The abnormality identification program is constructed so that abnormalities occurring in the equipment to be inspected can be identified by machine learning. In the present embodiment, it is an abnormality identification program constructed by learning a large amount of teacher data (hereinafter also referred to as first teacher data) including images of abnormalities related to cracks as abnormalities of RT, and teacher data (hereinafter also referred to as second teacher data) including images of abnormalities related to bending.

[0019] The first teacher data includes images pixel-adjusted for the purpose of increasing information on the width, length, and clarity of cracks based on the photographed images of cracks. In other words, the first teacher data includes images processed for the purpose of increasing information on the width, length, and clarity of cracks based on the photographed images of cracks. The second teacher data includes images of the same bend photographed from a plurality of angles, for example, from the front, back, left, and right, as bend data. That is, the second teacher data includes images of the same bend photographed from a plurality of angles. In this way, for bending, by performing machine learning using images photographed from a plurality of angles, the accuracy of abnormality detection related to bending abnormalities can be improved.

[0020] The abnormality identification device 6 can determine whether an abnormality has occurred in the RT by inputting the photographed image photographed by the unmanned photographing device 1 such as a drone into the abnormality identification program. Further, when an abnormality has occurred, the abnormality identification device 6 can specify whether either or both of cracks and bending have occurred. Note that the abnormalities to be learned may be appropriately set according to the equipment.

[0021] In the present embodiment, the unmanned photographing device 1, the communication terminal 2, and the communication terminal 4, and the communication terminal 4 and the abnormality identification device 6 can perform wireless communication according to different communication standards. Hereinafter, the communication standard between the unmanned photographing device 1, the communication terminal 2, and 4 is also referred to as the first dedicated network, and the communication standard between the communication terminal 4 and the abnormality identification device 6 is also referred to as the second dedicated network. Here, the "dedicated network" refers to a network accessible by devices granted access rights within a limited range.

[0022] The first dedicated network is a short-range wireless communication standard, such as NFC communication, Bluetooth®, or WiFi®. The first dedicated network is a private, dedicated network, and only communication devices authenticated during the initial connection, etc., can communicate. In this embodiment, the unmanned camera 1, communication terminal 2, and communication terminal 4 are assumed to be pre-authenticated. This embodiment will be explained using WiFi® as an example.

[0023] The second dedicated network is a communication standard with a longer communication range than the first dedicated network, and wireless communication is performed via the communication network. For example, the second dedicated network consists of wireless communication networks such as local 5G and private LTE, and base stations. The second dedicated network is a private, dedicated network, and only communication devices authenticated during the initial connection, etc., can communicate. In this embodiment, the communication terminal 4 and the abnormality detection device 6 are assumed to be authenticated in advance. This embodiment will be explained using the case of private LTE as an example.

[0024] Figure 2 shows an example of the flight route of the unmanned imaging device 1 when inspecting RT8. Arrow 7 indicates the flight route of the unmanned imaging device 1. As shown in Figure 2, the take-off and landing point for the unmanned imaging device 1 is provided at the bottom of the furnace directly below the row of RT8. The unmanned imaging device 1 is set up at this take-off and landing point. With the unmanned imaging device 1 set up at the take-off and landing point, a control signal to start the inspection is transmitted from communication terminal 4 via communication terminal 2, and the inspection starts when the unmanned imaging device 1 receives this control signal. The overall structure and schematic diagram of RT8 are shown in Figures 3 and 4. As shown in Figure 3, multiple rows of RT8 are arranged in the annealing furnace, and the steel plates are heated by the RT8. Also, as shown in Figure 4, the air inside the RT8 tubes is heated by the burner 81.

[0025] The flight path of the unmanned camera 1 is predetermined as described above. In this embodiment, the RT1 row is divided vertically into two sections, with one section flying upwards and the other flying downwards. For example, in the flight path indicated by arrow 7a, the unmanned camera 1 flies upwards. On the other hand, for example, in the flight path indicated by arrow 7b, the unmanned camera 1 flies downwards.

[0026] Waypoints are pre-set for the flight route, and the route returns to the takeoff and landing point while taking RT8 images at each waypoint. As described above, the unmanned camera 1 takes images at the set waypoints and transmits the captured images to the communication terminal 4 via the first dedicated network through the communication terminal 2. These captured images include the time the drone took the image and location information indicating which waypoint on the flight route the image was taken at. The communication terminal 4 transmits the received captured image 5 to the anomaly detection device 6 via the second dedicated network, and the anomaly detection program is executed by the anomaly detection device 6 upon receiving the captured image 5 to diagnose whether there is an anomaly in the RT8. The diagnosis result is transmitted to the communication terminal 4 via the second dedicated network, and the communication terminal 4 displays the diagnosis result. The operator can check the diagnosis result on the communication terminal 4.

[0027] In this embodiment, communication between the unmanned camera 1 and communication terminals 2 and 4 is conducted via a first dedicated network, which is short-range wireless communication, because the flight status / inspection progress of the unmanned camera 1 should be monitored at a distance visible to the operator, and to ensure the image transmission speed from the unmanned camera 1. On the other hand, the communication standard between communication terminal 4 and the anomaly identification device 6 is a second dedicated network because executing the anomaly identification program places a load on the system, and therefore it is necessary to transmit the captured images to the anomaly identification device 6, which is installed in a remote location different from the inspection site (measurement site).

[0028] In this embodiment, the unmanned camera 1 and the anomaly detection device 6 do not communicate directly. That is, the images captured by the unmanned camera 1 are always transmitted to the anomaly detection device 6 via communication terminals 2 and 4. With this configuration, for example, if a failure occurs in the second dedicated network, the operator can check the captured images themselves using communication terminal 4 to confirm whether or not there is an anomaly. Furthermore, by adding equipment information (information indicating which of the multiple existing RTs the image is for) when transmitting the captured images to the anomaly detection device 6, it is possible to transmit diagnostic result information (hereinafter also referred to as result information), including past diagnostic results for a specific RT stored in the anomaly detection device 6, to communication terminal 4 all at once, and the result information can be viewed on communication terminal 4.

[0029] Figure 5 shows an example of result information displayed by the communication terminal 4. The result information displayed by the communication terminal 4 includes a rectangular frame object 9 indicating whether or not an abnormality has occurred in the RT being inspected, a display object 10 ("crack" display) indicating the type of abnormality, and an abnormality judgment display 11. The rectangular frame object 9 allows the operator to easily identify the location of the abnormality. The display object 10 also allows the operator to easily identify the type of abnormality. The abnormality judgment display 11 is an object that indicates that an abnormality is present in the image. This allows the operator to easily identify result information that contains an abnormality. Note that the display method of the diagnostic results is not limited to this, and for example, the presence and type of abnormality may be indicated by a single display method, such as changing the color of the frame of the rectangular frame object 9 according to the type of abnormality.

[0030] Furthermore, the degree of danger may also be displayed according to the extent of the abnormality, such as the size of the crack or the degree of bending. In other words, the result information may include a danger level indicator showing the degree of danger of the abnormality. The text object 12 in Figure 5 is an example of a danger level indicator. For example, the danger level indicator may be in three stages: high, medium, and low.

[0031] The abnormality identification device 6 may acquire operating conditions related to the radiant tubes, predict whether or not an abnormality has occurred in each radiant tube and the degree of risk, and set a priority for each radiant tube based on the predicted degree of risk. In this case, the result information may include a priority display indicating such priority. By displaying the priority, for example, if an abnormality occurs in multiple RTs (RTs located in different locations), maintenance workers can easily determine which RT to start maintenance work on. Alternatively, it is possible to prioritize the RTs from highest priority and then send the result information to the communication terminal 4 to encourage maintenance work in that priority order. The text object 13 in Figure 5 is an example of a priority display. For example, the priority display may be in three stages: high, medium, and low. Note that Figure 5 shows an example where only the priority of one location is displayed, but it is not limited to this. The communication terminal 4 may display the priority of result information for multiple locations side by side. In this case, the priority may be represented by the color of each rectangular frame 14 related to each image. For example, when the priority is represented in three stages: high, medium, and low, the color of the rectangular frame 14 is red if the priority is high. Furthermore, if the priority is moderate, the color of the rectangular frame 14 will be yellow. On the other hand, if the priority is low, the color of the rectangular frame 14 will be green. This allows the operator to easily recognize high-priority images.

[0032] In the above description, the unmanned camera 1 performs autonomous flight along a predetermined flight route, but this invention can also be applied to manual drone operation by an operator. Furthermore, while the present invention can be applied to videos captured by the unmanned camera 1, application to images is preferable from the viewpoint of reducing the data size for data transmission and reception. By using images, data can be transferred continuously during the flight of the unmanned camera 1, and AI analysis (anomaly detection) can be performed in real time. Moreover, the unmanned shooting means is not limited to the unmanned camera 1 such as a drone; any method that allows for unmanned shooting in a manner that does not require workers to climb onto equipment while carrying a camera can be adopted. For example, an omnidirectional camera inspection unit equipped with an imaging unit such as a camera may be used.

[0033] (Examples) Table 1 shows a comparison of the anomaly detection rate and identification time with the conventional method after introducing the anomaly detection system 100 according to this embodiment. The anomaly detection rate for cracks and bending has improved dramatically, and the identification time has also been significantly reduced.

[0034] [Table 1]

[0035] (Hardware configuration) Figure 6 shows an example of the hardware configuration of an unmanned imaging device 1 according to one embodiment of the present disclosure. As shown in Figure 6, the unmanned imaging device 1 comprises a control unit 101, a storage unit 102, a communication unit 103, a positioning unit 104, and an imaging unit 105.

[0036] The control unit 101 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). The control unit 101 controls each part of the unmanned imaging device 1 and executes processes related to the operation of the unmanned imaging device 1.

[0037] The storage unit 102 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM (random access memory) or ROM (read-only memory). The RAM is, for example, SRAM (static random access memory) or DRAM (dynamic random access memory). The ROM is, for example, EEPROM (electrically erasable programmable read-only memory). The storage unit 102 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 102 stores data used for the operation of the unmanned camera 1 and data obtained by the operation of the unmanned camera 1.

[0038] The communication unit 103 includes at least one wireless communication interface. The wireless communication interface is an interface that corresponds to communication via the first dedicated network described above. The communication unit 103 receives data used for the operation of the unmanned camera 1 and transmits data obtained by the operation of the unmanned camera 1.

[0039] The positioning unit 104 includes a receiver compatible with a satellite positioning system. The receiver is compatible with, for example, GPS (Global Positioning System), but is not limited to this, and may be compatible with any satellite positioning system. The positioning unit 104 also includes, for example, a gyro sensor, a geomagnetic sensor, and a barometric pressure sensor. In this embodiment, the unmanned camera 1 can acquire the camera's shooting position information, the direction the camera is facing, and the camera's tilt using the positioning unit 104. The position information may include two-dimensional coordinate data including latitude and longitude, or it may include three-dimensional coordinate data including altitude in addition to latitude and longitude.

[0040] The imaging unit 105 includes an imaging device such as a camera for photographing an object. The imaging device may consist of, for example, a CMOS (Complementary Metal Oxide Semiconductor) image sensor or a CCD (Charge Coupled Device).

[0041] Figure 7 shows an example of the hardware configuration of a communication terminal 2 according to one embodiment of the present disclosure. As shown in Figure 7, the communication terminal 2 comprises a control unit 201, a storage unit 202, a communication unit 203, and an input unit 204.

[0042] The control unit 201 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). The control unit 201 controls each part of the communication terminal 2 and executes processes related to the operation of the communication terminal 2.

[0043] The storage unit 202 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM (random access memory) or ROM (read-only memory). The RAM is, for example, SRAM (static random access memory) or DRAM (dynamic random access memory). The ROM is, for example, EEPROM (electrically erasable programmable read-only memory). The storage unit 202 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 202 stores data used for the operation of the communication terminal 2 and data obtained by the operation of the communication terminal 2.

[0044] The communication unit 203 includes at least one wireless communication interface. The wireless communication interface is an interface that corresponds to communication via the first dedicated network described above. The communication unit 203 receives data used for the operation of the communication terminal 2 and transmits data obtained through the operation of the communication terminal 2.

[0045] The input unit 204 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touchscreen integrated with a display. The input unit 204 accepts operations to input data used for the operation of the communication terminal 2.

[0046] Figure 8 shows an example of the hardware configuration of a communication terminal 4 according to one embodiment of the present disclosure. As shown in Figure 8, the communication terminal 4 comprises a control unit 401, a storage unit 402, a communication unit 403, an input unit 404, and a display unit 405.

[0047] The control unit 401 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (central processing unit) or GPU (graphics processing unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (field-programmable gate array) or an ASIC (application-specific integrated circuit). The control unit 401 controls each part of the communication terminal 4 and executes processes related to the operation of the communication terminal 4.

[0048] The storage unit 402 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM (random access memory) or ROM (read-only memory). The RAM is, for example, SRAM (static random access memory) or DRAM (dynamic random access memory). The ROM is, for example, EEPROM (electrically erasable programmable read-only memory). The storage unit 402 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 402 stores data used for the operation of the communication terminal 4 and data obtained by the operation of the communication terminal 4.

[0049] The communication unit 403 includes at least two wireless communication interfaces. Specifically, the wireless communication interfaces include an interface corresponding to communication via the first dedicated network described above, and an interface corresponding to communication via the second dedicated network. The communication unit 403 receives data used for the operation of the communication terminal 4 and transmits data obtained through the operation of the communication terminal 4.

[0050] The input unit 404 includes at least one input interface. The input interface may be, for example, a physical key, a capacitive key, a pointing device, or a touchscreen integrated with a display. Alternatively, the input interface may be, for example, a microphone that accepts voice input or a camera that accepts gesture input. The input unit 404 accepts operations to input data used for the operation of the communication terminal 4. Instead of being provided in the communication terminal 4, the input unit 404 may be connected to the communication terminal 4 as an external input device. Any connection method can be used, for example, USB (Universal Serial Bus), HDMI (registered trademark) (High-Definition Multimedia Interface), or Bluetooth (registered trademark).

[0051] The display unit 405 includes at least one display output interface. The display output interface is, for example, a display that outputs information as video. The display is, for example, an LCD (liquid crystal display) or an organic EL (electroluminescence) display. The display unit 405 displays and outputs data obtained by the operation of the communication terminal 4. Instead of being provided in the communication terminal 4, the display unit 405 may be connected to the communication terminal 4 as an external output device. Any connection method can be used, for example, USB, HDMI (registered trademark), or Bluetooth (registered trademark).

[0052] The functions of the communication terminal 4 are realized by executing the program according to this embodiment on a processor corresponding to the communication terminal 4. In other words, the functions of the communication terminal 4 are realized by software. The program causes the computer to perform the operations of the communication terminal 4, thereby causing the computer to function as the communication terminal 4. That is, the computer functions as the communication terminal 4 by performing the operations of the communication terminal 4 according to the program.

[0053] Figure 9 shows an example of the hardware configuration of an anomaly detection device 6 according to one embodiment of the present disclosure. As shown in Figure 9, the anomaly detection device 6 comprises a control unit 601, a storage unit 602, and a communication unit 603.

[0054] The control unit 601 includes at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU or GPU, or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA or ASIC. The control unit 601 controls each part of the abnormality detection device 6 and executes processes related to the operation of the abnormality detection device 6.

[0055] The storage unit 602 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or at least two combinations thereof. The semiconductor memory is, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 602 functions, for example, as a main memory, auxiliary memory, or cache memory. The storage unit 602 stores data used for the operation of the abnormality identification device 6 and data obtained by the operation of the abnormality identification device 6.

[0056] The communication unit 603 includes at least one wireless communication interface. Specifically, the wireless communication interface includes an interface that corresponds to communication via the second dedicated network described above. The communication unit 603 receives data used for the operation of the anomaly identification device 6 and transmits data obtained by the operation of the anomaly identification device 6.

[0057] The function of the anomaly detection device 6 is realized by executing the program according to this embodiment on a processor corresponding to the anomaly detection device 6. In other words, the function of the anomaly detection device 6 is realized by software. The program causes the computer to perform the operations of the anomaly detection device 6, thereby causing the computer to function as the anomaly detection device 6. That is, the computer functions as the anomaly detection device 6 by performing the operations of the anomaly detection device 6 according to the program.

[0058] In this embodiment, the program can be recorded on a computer-readable recording medium. The computer-readable recording medium includes non-temporary computer-readable media, such as magnetic recording devices, optical discs, magneto-optical recording media, or semiconductor memory. The program can be distributed, for example, by selling, transferring, or lending portable recording media such as DVDs (digital versatile discs) or CD-ROMs (compact disc read-only memory) on which the program is recorded. Alternatively, the program may be distributed by storing it on the storage of an external server and transmitting it from the external server to other computers. The program may also be provided as a program product.

[0059] While this disclosure has been described based on the drawings and embodiments, it should be noted that those skilled in the art will find it easy to make various modifications and alterations based on this disclosure. Therefore, it should be noted that these modifications and alterations are within the scope of this disclosure. For example, the functions, etc., included in each means or each step, etc., can be rearranged in a logically consistent manner, and multiple means or steps, etc., can be combined into one or divided. [Explanation of symbols]

[0060] 100 Anomaly Detection Systems 1. Unmanned camera 2. Communication terminals 3. Captured images 4. Communication terminals 5. Captured images 6 Abnormality identification device 7, 7a, 7b arrows 8 RT 81 burners 9. Rectangular Frame Object 10 Display Objects 11 Abnormality judgment display 12, 13 Text objects 14 Rectangular frame 101, 201, 401, 601 Control Units 102, 202, 402, 602 Storage section 103, 203, 403, 603 Communications Department 104 Positioning Unit 105 Imaging Unit 204, 404 Input Section 405 Display section

Claims

1. An anomaly detection system comprising: an unmanned camera that takes images of equipment to be inspected; a communication terminal that acquires the images from the unmanned camera; and an anomaly identification device that acquires the images from the communication terminal and identifies an anomaly in the equipment to be inspected from the images, An anomaly detection system characterized in that the unmanned camera and the communication terminal can communicate wirelessly via a private first dedicated network to which only devices authenticated at the time of initial connection can connect, the communication terminal and the anomaly identification device can communicate wirelessly via a private second dedicated network to which only devices authenticated at the time of initial connection can connect, and the communication range of the second dedicated network is longer than the communication range of the first dedicated network.

2. An anomaly detection system comprising: an unmanned camera for taking images of equipment to be inspected; a communication terminal for acquiring images from the unmanned camera; and an anomaly identification device for acquiring the images from the communication terminal and identifying an anomaly in the equipment to be inspected from the images, The unmanned camera and the communication terminal are wirelessly connected via a first dedicated network, the communication terminal and the anomaly identification device are wirelessly connected via a second dedicated network, and the communication range of the second dedicated network is longer than that of the first dedicated network. The abnormality detection device is capable of identifying abnormalities in the radiant tube, including cracks in the radiant tube that heats the steel plate, using an abnormality detection program that can identify abnormalities in the radiant tube. An anomaly detection system characterized in that the anomaly identification program is machine-learned based on first training data relating to cracks in the radiant tube, and the first training data includes images processed for the purpose of increasing information on the width, length, and clarity of cracks based on captured images of the cracks.

3. The abnormality detection device is capable of identifying abnormalities in the radiant tube, including cracks in the radiant tube that heats the steel plate, using an abnormality detection program that can identify abnormalities in the radiant tube. The anomaly detection system according to claim 1, characterized in that the anomaly identification program is machine-trained based on first training data relating to cracks in the radiant tube, and the first training data includes images processed for the purpose of increasing information on the width, length, and clarity of cracks based on captured images of the cracks.

4. The abnormality detection device is capable of identifying abnormalities in the radiant tube, including bending of the radiant tube that heats the steel plate, using an abnormality detection program that can identify abnormalities in the radiant tube. The anomaly detection system according to any one of claims 1 to 3, characterized in that the anomaly identification program is machine-trained based on second training data relating to the bending of the radiant tube, and the second training data includes images of the same bending taken at multiple angles.

5. When the abnormality detection device detects an abnormality in the radiant tube, it transmits result information indicating the presence of the identified abnormality to the communication terminal. The anomaly detection system according to claim 4, characterized in that the result information includes a risk indicator showing the degree of anomaly.

6. The abnormality detection system according to claim 5, characterized in that the abnormality identification device acquires operating conditions relating to the radiant tubes, predicts whether or not an abnormality has occurred in each radiant tube and the degree of risk, sets a priority for each radiant tube based on the predicted degree of risk, and the result information includes a priority display indicating the priority.

Images