Anomaly Detection System

The system addresses the limitations of fixed sensor installations by integrating a camera and vibration/thermal sensors to detect abnormalities across the entire transport route, reducing costs and enhancing detection accuracy through continuous monitoring.

JP7579030B2Active Publication Date: 2024-11-07LOPAS CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2024018448
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2019-03-04
Filing Date
2024-02-09
Publication Date
2024-11-07
Estimated Expiration
2039-06-04

AI Technical Summary

Technical Problem

Existing conveyor systems face limitations in detection range due to the need for numerous sensors installed at specific locations, which increases costs and complexity.

Method used

A system utilizing a current position detection unit, state detection unit, and storage unit that integrates a vibration sensor, camera, and thermal sensor to detect abnormalities on a transport device without fixed installations, enabling continuous detection across the entire transport route.

Benefits of technology

Minimizes sensor installation, reduces costs, and allows for continuous detection of abnormalities throughout the transport path, improving detection accuracy through deep learning and sensor integration.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007579030000001
    Figure 0007579030000001
  • Figure 0007579030000002
    Figure 0007579030000002
  • Figure 0007579030000003
    Figure 0007579030000003
Patent Text Reader

Abstract

To provide an abnormality detection system that can detect abnormality of an entire transport route at a low cost.SOLUTION: A container 1 that is an abnormality detection system includes: a camera 2 that detects the current position on a conveyor device 50; sensor modules 4L, 4R that detect the condition of the conveyer device 50; a memory part 3b that associates the current position detected by the camera 2 and the detection results detected by the sensor modules 4L, 4R at the current position and accumulates it as accumulated information; and a processing part 3a that detects abnormality at the position based on the detection results detected by the sensor modules 4L, 4R and a learning model generated from the accumulated information accumulated in the memory part 3b that correspond to the position. The container 1 is transported as a delivery item by the conveyor device 50 on the conveyor device.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an abnormality detection system that detects an abnormality in a conveying device installed in, for example, a warehouse. [Background technology]

[0002] Conventionally, conveyor systems are often used as transport devices for storing and retrieving goods in warehouses, etc. In this type of conveyor system, detection units such as sensors are fixedly installed on components constituting the conveyor system or around the conveyor system to detect failures.

[0003] For example, in Patent Document 1, a conveyor 1 is provided with a bearing unit 10 for a transport device, and a power generating element 14 provided in the bearing unit 10 for a transport device functions as a sensor to detect a temperature rise due to an abnormality in the bearing.

[0004] In addition, in Patent Document 2, optical sensors 31 and 32 are attached near the belt 22 of the belt conveyor 20 to detect the transported object 23, and the transport speed of the transported object is calculated based on the detection results of the optical sensors 31 and 32. The transport speed based on the rotation speed of the motor 1 is compared with the transport speed based on the optical sensors 31 and 32 to detect abnormalities. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2013-32211 A [Patent Document 2] JP 2007-112565 A Summary of the Invention [Problem to be solved by the invention]

[0006] When a detection unit such as a sensor is fixedly installed as described in Patent Documents 1 and 2, there is a problem that the detection range is limited. For example, in the case of the conveyor bearing unit 10 of Patent Document 1, the number of units to be installed may become enormous if they are installed at all locations where there are bearings. Also, in the case of Patent Document 2, if a conveyor route is formed by multiple belt conveyors or multiple conveyor routes are formed, an optical sensor needs to be installed on each belt conveyor.

[0007] The present invention is intended to solve the above problems, and has an object to detect abnormalities in the entire conveying route at low cost. [Means for solving the problem]

[0008] The invention described in claim 1, which has been made to solve the above problem, is an abnormality detection system comprising a current position detection unit that detects a current position on a conveying device, a status detection unit that detects the status of the conveying device, a storage unit that associates the current position detected by the current position detection unit with the detection result detected by the status detection unit at the current position and stores them as accumulated information, and an abnormality detection unit that detects an abnormality at the position based on the detection result detected by the status detection unit and the accumulated information accumulated in the storage unit at the position where the detection result was detected, wherein at least the current position detection unit and the status detection unit are transported on the conveying device by the conveying device as a transported item, and the status detection unit includes a vibration sensor that measures vibrations on the conveying device, and the vibration sensor is arranged so as to be in direct contact with the conveying device at the bottom of the transported item and at the longitudinal center of the transported item.

[0009] The invention described in claim 2 is characterized in that, in the invention described in claim 1, the current position detection unit includes a camera that captures images of the outside and a map information storage unit that stores three-dimensional map information of the transport route of the transport device, and the current position detection unit detects the current position based on an image captured by the camera and the three-dimensional map information, and the three-dimensional map information is generated by extracting feature points from each of a plurality of images captured by the camera and connecting them together.

[0010] Furthermore, the invention described in claim 3 is characterized in that, in the invention described in claim 1 or 2, the status detection unit includes a thermal sensor that measures heat generation of the conveying device, and the thermal sensor is composed of a thermal camera.

[0011] The invention described in claim 4 is the invention described in any one of claims 1 to 3, further comprising a transmitting unit that transmits the detection result detected by the status detection unit, and a receiving unit that receives the current position and the detection result transmitted by the transmitting unit, wherein the current position and the detection result received by the receiving unit are associated with each other and stored in the storage unit, and the abnormality detection unit performs the abnormality detection based on the detection result received by the receiving unit and the accumulated information stored in the storage unit at the position where the detection result was detected.

[0012] Moreover, the invention described in claim 5 is characterized in that, in the invention described in any one of claims 1 to 4, it further comprises a learning unit that learns the normal range using multiple pieces of accumulated information at the same position, and the abnormality detection unit detects the abnormality based on the learning results in the learning unit. Effect of the Invention

[0013] As described above, according to the present invention, the status detection unit and the current position detection unit can detect the status of the conveying device while being conveyed on the conveying device as a conveyed object, so there is no need to install sensors on the conveying device, and the number of sensors can be minimized to reduce costs. Furthermore, the status detection unit can detect the status at detection intervals according to the resolution of the status detection unit, making it possible to perform substantially continuous detection. Furthermore, since the status detection unit and the current position detection unit are conveyed on the conveying device as a conveyed object, abnormalities in the entire conveying path can be detected. [Brief description of the drawings]

[0014] [Figure 1] 1 is a top view of a container having an anomaly detection system according to a first embodiment of the present invention. [Diagram 2] FIG. 2 is a cross-sectional view of the container shown in FIG. 1 taken along line AA. [Diagram 3] FIG. 2 is a block diagram of the anomaly detection system shown in FIG. [Figure 4] 2 is a flowchart of a map information generating operation of the anomaly detection system shown in FIG. 1. [Diagram 5] 2 is a flowchart of a trained model generation operation of the anomaly detection system shown in Figure 1. [Figure 6] 2 is a flowchart of an anomaly detection operation of the anomaly detection system shown in FIG. 1. [Figure 7] FIG. 4 is a block diagram of an anomaly detection system according to a modified example of the first embodiment. [Figure 8] FIG. 11 is a top view of a container having an anomaly detection system according to a second embodiment of the present invention. [Figure 9] FIG. 9 is a cross-sectional view of the container shown in FIG. 8 taken along line AA. [Figure 10] FIG. 2 is a block diagram of the anomaly detection system shown in FIG. [Figure 11] FIG. 2 is an explanatory diagram of a self-location estimation method according to the present embodiment. [Figure 12] 3 is a flowchart of a self-location estimation method according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] (First embodiment) An information processing device according to a first embodiment of the present invention will be described with reference to Fig. 1 to Fig. 7. Fig. 1 is a top view of a container having an anomaly detection system according to the first embodiment of the present invention. Fig. 2 is a cross-sectional view taken along line AA of the container shown in Fig. 1.

[0016] The container 1 is placed on a conveyor device 50 as a transport device and transported by the conveyor device 50. In Fig. 1, the container is transported in the direction of the arrow. Although Figs. 1 and 2 show a roller conveyor as the transport device, other transport devices such as a belt conveyor may also be used. Furthermore, although Figs. 1 and 2 show only a part of the conveyor device 50, the conveyor device 50 is installed, for example, in a warehouse and has a transport path consisting of straight lines, curves, a ramp, etc. Therefore, the conveyor device 50 may be composed of multiple conveyor devices.

[0017] 1 and 2 is formed in a substantially rectangular box shape and constitutes a storage section 11. The storage section 11 has an opening at the top to allow items to be put in and taken out. The storage section 11 is also composed of four side sections 11a, 11b, 11c, and 11d and a bottom section 11e.

[0018] 1 and 2, the side portions 11a and 11b are the short side portions of the rectangular parallelepiped, and the side portions 11c and 11d are the long side portions of the rectangular parallelepiped. In this embodiment, the side portion 11a is the front side, that is, the conveying direction (travel direction) side. Therefore, the side portion 11b is the rear side, the side portion 11c is the left side in the travel direction, and the side portion 11d is the right side in the travel direction.

[0019] The container 1 includes a camera 2, a control unit 3, sensor modules 4L and 4R, and a battery 5.

[0020] The camera 2 is a camera module having an imaging element such as a charge coupled device (CCD) image sensor or a complementary metal oxide semiconductor (CMOS) image sensor. The camera 2 is installed at the upper center of the side surface 11b of the container 1 and captures an image obliquely upward in the direction of the side surface 11a opposite to the side surface 11b. In other words, the camera 2 captures an image obliquely upward in the traveling direction of the container 1. In this embodiment, the camera 2 is installed on the rear side surface 11b, but it may be installed on the front side surface 11a to capture an image in the traveling direction.

[0021] The control unit 3 is provided further below the bottom surface portion 11e. In other words, the container 1 has a double bottom. The control unit 3 is directly or indirectly installed on a vibration absorbing member 8, such as a vibration absorbing mat. The vibration absorbing member 8 can make the control unit 3 and the like less susceptible to the effects of vibrations generated during transportation.

[0022] The control unit 3 estimates the current position (self-position) of the container 1 based on the image captured by the camera 2. The control unit 3 also learns the results detected by the sensor modules 4L, 4R by deep learning, and determines whether the results detected by the sensor modules 4L, 4R are within a normal range based on the learning results, thereby determining whether there is an abnormality. Details will be described later.

[0023] The sensor module 4L includes a sound sensor 4a, a heat sensor 4b, and a vibration sensor 4c. The sensor module 4L is provided close to the side surface portion 11c. The sound sensor 4a and the heat sensor 4b are directly or indirectly installed on a vibration absorbing member 8, and the vibration sensor 4c is directly installed on the bottom surface of the container 1 below the vibration absorbing member 8.

[0024] The sensor module 4R is basically similar in configuration to the sensor module 4L. The sensor module 4R is different from the sensor module 4L in that it is provided closer to the side surface portion 11d. In other words, the sensor module 4L detects the state of the left side of the container 1 in the traveling direction, and the sensor module 4R detects the state of the right side of the container 1 in the traveling direction.

[0025] The sound sensor 4a collects external sounds and detects sounds emitted by a predetermined conveyor device 50. The sound sensor 4a can be configured, for example, with a unidirectional microphone and a frequency filter. The heat sensor 4b detects the temperature of a predetermined part of the conveyor device. The heat sensor 4b can be configured, for example, with a thermo camera. The vibration sensor 4c detects vibrations applied to the container 1. The vibration sensor 4c can be configured with an acceleration sensor. In this embodiment, the sensor modules 4L and 4R are configured with three types of sensors, but other sensors such as optical sensors and magnetic sensors may also be used. That is, the sensor modules 4L and 4R function as a state detection unit that detects the state of the conveyor device 50.

[0026] The battery 5 is directly or indirectly mounted on a vibration absorbing member 8. The battery 5 supplies power to the camera 2, the control unit 3, and the sensor modules 4L and 4R. The container 1 also has a terminal (not shown) for charging the battery 5. Alternatively, the battery 5 may be detachable for charging.

[0027] A block diagram of the container (anomaly detection system) 1 according to this embodiment is shown in Fig. 3. As shown in Fig. 3, the control unit 3 includes a processing unit 3a and a storage unit 3b.

[0028] The processing unit 3a is composed of, for example, a microprocessor, and performs the above-mentioned self-position estimation, deep learning, and determination of the presence or absence of an abnormality. That is, the processing unit 3a functions as a current position detection unit together with the camera 2. The processing unit 3a also functions as a learning unit and an abnormality detection unit.

[0029] The storage unit 3b is composed of a storage device such as an SSD (Solid State Drive), and the detection results of the sensor modules 4L and 4R are stored in association with self-location-estimated position information. That is, the storage unit 3b functions as a storage unit. The storage unit 3b also stores map information for self-location estimation.

[0030] Next, the operation of the anomaly detection system having the above-mentioned configuration will be described with reference to the flowcharts of Figures 4 to 6. Figure 4 is a flowchart showing the generation of three-dimensional map information for self-location estimation from an image captured by camera 2.

[0031] First, captured images are collected from the camera 2 (step S11), and the processing unit 3a extracts feature points from the collected captured images (step S12). Then, the processing unit 3a generates a 3D map (map information) of the transport route formed by the conveyor device 50 based on the extracted feature points (step S13). This 3D map is created by extracting and stitching together feature points from a plurality of images captured by the camera 2 while it is being transported by the conveyor device 50, and contains information about the feature points on the transport route.

[0032] Figure 5 is a flowchart for generating a trained model by deep learning based on the detection results detected by the sensor modules 4L and 4R.

[0033] First, the detection results detected by the sensor modules 4L and 4R are collected (step S21), and the processing unit 3a learns the normal detection results of each sensor by well-known deep learning (step S22). That is, the detection results of the sensors when the conveyor device 50 is operating normally are learned. At this time, the normal state may have a certain range of values. Also, in this step, the normal state (detection result) is learned for each position of the conveyor device 50. This is because the range of normal sounds, temperatures, and vibrations often differ depending on the position of the conveyor device 50. That is, learning is performed in association with the position by referring to the three-dimensional map information. Then, the processing unit 3a generates a learned model that has learned a predetermined amount of detection results (step S23).

[0034] FIG. 6 is a flowchart for detecting anomalies using the map information generated in the flowchart of FIG. 4 and the trained model generated in the flowchart of FIG. 5.

[0035] First, the detection results detected by the sensor modules 4L and 4R are collected (step S31), and the processing unit 3a estimates the self-position of the container 1 based on the image captured by the camera 2 and the map information stored in the storage unit 3b (step S32). Then, the processing unit 3a judges whether the detection results collected in step S31 are within a normal range based on the trained model for the self-position estimated in step S32 (step S33), and if they are not within the normal range (step S33: NO), it reports the abnormality detection by, for example, an alarm device (not shown), and stores the position information of the abnormality detected in the storage unit 3b (step S34). On the other hand, if they are within the normal range (step S33: YES), the process returns to step S31.

[0036] Here, step S33 is judged for each sensor. That is, it is judged whether the detection result for each sensor is within the normal range, and it is determined that the detection results of all sensors are normal if they are within the normal range. Therefore, if the detection result of one sensor is outside the normal range, it is determined that there is an abnormality.

[0037] In this way, for example, the following signs of failure can be detected. However, it is not necessary for the abnormality detection system 1 to identify the following details of the failure, as long as it detects that there is some abnormality at the position. Then, the details of the failure can be identified by another measuring device, by an operator, or the like.

[0038] For example, the detection result of the sound sensor 4a can detect damage to the rollers or shafts of the conveyor device 50, non-transmission of driving force to the carrier rollers, free rotation of the rollers, etc. The detection result of the vibration sensor 4c can detect damage to the rollers or shafts of the conveyor device 50, tilt of the roller surface, non-transmission of driving force to the carrier rollers, free rotation of the rollers, etc. The detection result of the heat sensor 4b can detect abnormal heat generation in the power supply of the conveyor device 50.

[0039] Furthermore, by combining the detection results of the sound sensor 4a and the determination results of the vibration sensor 4c, it is possible to detect a failure in the power supply of the conveyor device 50. Furthermore, by combining the detection results of the sound sensor 4a, the detection results of the heat sensor 4b, and the determination results of the vibration sensor 4c, it is possible to detect a failure in the motor of the conveyor device 50.

[0040] For example, the detection results of the sound sensor 4a alone can detect the occurrence of any of the following: damage to the rollers or shafts of the conveyor device 50, failure to transmit driving force to the carrier rollers, or rollers spinning freely. By correlating this with the position information based on the self-position estimation results, it is possible to identify where such a failure symptom occurred.

[0041] According to the present embodiment described above, the container 1, which is an anomaly detection system, includes the camera 2 that detects the current position on the conveyor device 50, and the sensor modules 4L and 4R that detect the state of the conveyor device 50. The container 1 includes a memory unit 3b that associates the current position detected by the camera 2 with the detection results detected by the sensor modules 4L and 4R at the current position and stores them as accumulated information, and a processing unit 3a that detects an anomaly at the position based on the detection results detected by the sensor modules 4L and 4R and a learning model generated from the accumulated information stored in the memory unit 3b at the position where the detection results were detected. The container 1 is transported on the conveyor device 50 by the conveyor device as a transported article.

[0042] In this way, the state of the conveyor device 50 can be detected while the container 1 is being transported on the conveyor device 50 as a transported article, so there is no need to install sensors on the conveyor device 50 side, and the number of sensors can be minimized to reduce costs. Furthermore, the sensor modules 4L and 4R can detect the state at detection intervals according to the resolution of the sensors, making approximately continuous detection possible. Furthermore, since the container 1 is transported on the conveyor device 50 as a transported article, abnormalities in the entire transport path formed by the conveyor device 50 can be detected.

[0043] Furthermore, the processing unit 3a learns the normal range by deep learning using multiple pieces of accumulated information at the same position, and detects anomalies based on a learning model generated by the learning. In this way, the container 1 is transported on the conveyor device 50 many times to collect many detection results of the sensor modules 4L and 4R, thereby making it possible to successively update the learning model and improve the judgment accuracy.

[0044] Moreover, since the processing unit 3 estimates its own position based on the image captured by the camera 2 that captures the outside and map information in the conveyor device 50, it is possible to estimate its own position without installing markers or the like. Also, it is possible to estimate its own position even if radio waves from a GPS (Global Positioning System) or the like cannot be received.

[0045] Furthermore, since the sensor modules 4L and 4R detect the state in the left and right directions with respect to the traveling direction of the conveyor device 50, it is possible to specify at least whether the location where the abnormality is detected is on the right side or the left side.

[0046] In the above-described embodiment, deep learning and determination of the presence or absence of abnormality are performed in the container 1, but the image captured by the camera 2 and the detection results of the sensor modules 4L, 4R may be transmitted to an external computer or the like, and the self-position estimation, deep learning, and determination of the presence or absence of abnormality may be performed by the computer. The configuration in this case is shown in Fig. 7. In Fig. 7, a communication unit 6 and a computer (PC) 60 are added to the configuration in Fig. 3.

[0047] The communication unit 6 performs wireless communication by a communication method such as Wi-Fi (registered trademark). The communication unit 6 transmits the detection results of the sensor modules 4L, 4R along with the captured image of the camera 2 to the computer 60. That is, the communication unit 6 functions as a transmission unit. The computer 60 performs self-location estimation, deep learning, and determination of the presence or absence of an abnormality based on the received captured image and detection results. The methods of self-location estimation, deep learning, and determination of the presence or absence of an abnormality are the same as those in Figs. 4 to 6. That is, the computer 60 functions as a receiving unit, a current location detection unit, an abnormality detection unit, a storage unit, and a learning unit. In the case of the configuration of Fig. 7, the container 1 and the computer 60 constitute an anomaly detection system.

[0048] 7, the self-location estimation, deep learning, and determination of the presence or absence of anomalies can be performed by the computer 60, which reduces the processing load on the processing unit 3a of the container 1. Therefore, by employing a CPU or the like with low power consumption in the processing unit 3a, consumption of the battery 5 can be suppressed.

[0049] 7, the container 1 may perform operations up to self-location estimation. In this case, the communication unit 6 transmits the detection results of the sensor modules 4L and 4R to the computer 60 together with the location information.

[0050] Second embodiment Next, a second embodiment of the present invention will be described with reference to Figures 8 to 12. Note that the same parts as those in the first embodiment are given the same reference numerals and the description thereof will be omitted.

[0051] This embodiment differs from the first embodiment in the means for self-location estimation and the means for state detection. Fig. 8 shows a top view of a container 1A having an anomaly detection system according to this embodiment, and Fig. 9 shows a cross-sectional view of the container 1A shown in Fig. 8 taken along line AA.

[0052] As shown in FIG. 8, in this embodiment, the camera 2 and the sensor module 4 are eliminated, and cameras 20 (20a, 20b, 20c, 20d, 20e) are provided. The cameras 20a to 20c are provided on the side surface portion 11a and photograph the front of the container 1A. The cameras 20a to 20c are provided so as to photograph the lower front side of the container 1A as a center (see FIG. 9). The camera 20d is provided on the side surface portion 11c. The camera 20e is provided on the side surface portion 11d.

[0053] Camera 20a photographs the left front in the transport direction of container 1A. Camera 20b photographs the center front in the transport direction of container 1A. Camera 20c photographs the right front in the transport direction of container 1A. Camera 20d photographs the left side in the transport direction of container 1A. Camera 20e photographs the right side in the transport direction of container 1A. Cameras 20a and 20c are thermal cameras. Cameras 20b, 20d, and 20e are wide-angle cameras.

[0054] In this embodiment, the cameras 20a and 20c can detect the temperature of the conveyor device 50A in the conveying direction. That is, the cameras 20a and 20c function as a state detection unit that detects the state in the forward direction with respect to the traveling direction of the conveyor device. The camera 20b can detect the vibration of the conveyor device 50A. The camera 20b is also used for self-position estimation, which will be described later.

[0055] Fig. 10 shows a block diagram of a container (anomaly detection system) 1A according to this embodiment. It is basically the same as Fig. 3, except that the camera 2 and the sensor module 4 are omitted and cameras 20a to 20e are provided.

[0056] Next, the self-position estimation method in this embodiment will be described with reference to Fig. 11. The self-position estimation method in this embodiment is targeted at a roller conveyor. The conveyor device 50A (roller conveyor) includes a first frame 51 and a second frame 52 serving as support members arranged parallel to each other, and a transport roller 53 supported by the first frame 51 and the second frame 52.

[0057] Furthermore, the conveyor device 50A according to this embodiment is provided with guide poles 54. A plurality of guide poles 54 are erected at predetermined intervals on the first frame 51 and the second frame 52. That is, the guide poles 54 function as guide sections installed at predetermined intervals on the conveying path.

[0058] The guide poles 54 are installed at predetermined intervals at predetermined positions on the conveyor device 50A (transport path). Therefore, the self-position can be estimated by detecting the guide poles 54 from images captured by the cameras 20d, 20e using image recognition or the like. For example, if the position serving as the origin, such as the start position, can be recognized, the installation intervals of the guide poles 54 are known in advance, and the self-position can be estimated by identifying which guide pole 54 is located from the origin. Alternatively, a display indicating the current position may be added to the guide pole 54.

[0059] However, since the guide poles 54 are installed at a predetermined interval, the accuracy of estimating the position between the guide poles 54 decreases if only the guide poles 54 are used. Therefore, in this embodiment, the position between the guide poles 54 is estimated by detecting the conveying rollers 53 by image recognition or the like from an image captured by the camera 20b. Since the installation interval of the guide poles 54 is known in advance, the number of conveying rollers 53 between the guide poles 54 can also be obtained in advance. Therefore, after detecting the guide poles 54, the position between the guide poles 54 can be estimated by counting how many conveying rollers 53 have been detected. That is, the processing unit 3a functions as a counting unit that detects the number of rollers of the roller conveyor and a detection unit that detects the current position based on the coefficient results of the guide unit and the counting unit.

[0060] Next, a flowchart of the above-mentioned self-position estimation operation is shown in Fig. 12. First, the processing unit 3a detects the guide pole 54 from the collected captured images by image recognition, and if it is detected (step S41: YES), the processing unit 3a estimates the self-position based on the detected guide pole 54 (step S42).

[0061] On the other hand, if the guide pole 54 is not detected from the collected captured images (step S41: NO), the conveying roller 53 is detected from the collected captured images by image recognition, and if it is detected (step S43: YES), the processing unit 3a estimates its own position based on the detected conveying roller and guide pole 54 (step S42).

[0062] In this embodiment, the guide pole 54 is described as the guide portion, but any projection, marking, or the like can be provided at a predetermined interval on the conveying path and can be image-recognized as the guide portion. The guide portion is not limited to being provided upright on the first frame 51 or the second frame 52, and may be provided within the range photographed by the cameras 20d and 20e. Furthermore, the guide portion may be provided on only one side of the traveling direction, rather than both the left and right, in which case one of the cameras 20d and 20e may be omitted.

[0063] In addition, in this embodiment, the camera 20 is used as the state detection unit, but the sensor module 4 described in the first embodiment may be used. In other words, the combination of the current position detection unit and the state detection unit is not limited to the combination in the first and second embodiments, but is arbitrary.

[0064] According to this embodiment, the conveyor device 50A is composed of a roller conveyor, and the processing unit 3a detects its own position based on the counting results of the guide poles 54 installed at a predetermined interval on the conveying path and the conveying rollers 53 of the roller conveyor, so that it is possible to detect its own position without complex processing or map information.

[0065] Furthermore, since the self-position is detected based on the counting result (number) of the transport rollers 53 in addition to the guide poles 54, the installation intervals of the guide poles 54 can be increased, and the number of additional guide poles 54 can be reduced.

[0066] Furthermore, since the cameras 20a and 20c detect the temperature in the forward direction relative to the traveling direction of the transport device, it is possible to detect abnormalities in the forward direction of the transport.

[0067] Furthermore, the present invention is not limited to the above-described embodiment. In other words, a person skilled in the art can implement the present invention by modifying it in various ways in accordance with conventionally known knowledge without departing from the gist of the present invention. As long as the configuration of the anomaly detection system of the present invention is still included in the scope of the present invention even after such modification, it is of course included in the scope of the present invention. [Explanation of symbols]

[0068] 1 Container (anomaly detection system) 2 Camera (current location detection section) 3. Control Unit 3a Processing section (current position detection section, abnormality detection section, learning section, counting section, detection section) 3b Storage unit (storage unit) 4L Sensor module (status detection section) 4R Sensor module (status detection section) 6 Communication unit (transmission unit) 20 Camera (current location detection section) 50 Transport device 50A Roller Conveyor (Transportation Equipment) 54 Guide pole (guide part) 60 Computer (receiving unit, abnormality detection unit, storage unit, learning unit)

Claims

1. a current position detection unit that detects a current position on the conveying device; A state detection unit that detects a state of the transport device; a storage unit that stores the current position detected by the current position detection unit and the detection result detected by the state detection unit at the current position as stored information in association with each other; an abnormality detection unit that detects an abnormality at a position where the detection result is detected based on a detection result detected by the state detection unit and accumulated information accumulated in the accumulation unit at the position where the detection result is detected, At least the current position detection unit and the state detection unit are transported as transported objects by the transport device on the transport device, the state detection unit includes a vibration sensor that measures vibrations on the conveying device, The vibration sensor is provided at a bottom of the transported object and at a central portion of the transported object in a longitudinal direction thereof so as to directly contact the transport device. An anomaly detection system comprising:

2. the current position detection unit includes a camera for capturing an image of the outside and a map information storage unit for storing three-dimensional map information of a transport route of the transport device, the current position detection unit detects a current position based on an image captured by the camera and the three-dimensional map information; 2. The anomaly detection system according to claim 1, wherein the three-dimensional map information is generated by extracting feature points from a plurality of images captured by the camera and connecting the extracted feature points.

3. the state detection unit includes a heat sensor for measuring heat generated by the conveying device, The thermal sensor is a thermal camera.

3. The anomaly detection system according to claim 1 or 2.

4. a transmission unit that transmits a detection result detected by the state detection unit; a receiving unit that receives the current position and the detection result transmitted by the transmitting unit, The anomaly detection system according to any one of claims 1 to 3, characterized in that the current location and the detection result received by the receiving unit are associated with each other and stored in the storage unit, and the anomaly detection unit performs the anomaly detection based on the detection result received by the receiving unit and accumulated information stored in the storage unit at the location where the detection result was detected.

5. a learning unit that learns a normal range based on a plurality of pieces of accumulated information at the same position; 5. The anomaly detection system according to claim 1, wherein the anomaly detection unit detects the anomaly based on a learning result in the learning unit.

Citation Information

Patent Citations

  • Load handling detecting and recording device

    JP1988263419A

  • Check system for built-in timer

    JP1989046116A

  • Drive system diagnostic device

    JP2007112565A

  • Beverage container type oscillation measuring device and method for measuring oscillation of beverage container

    JP2010269920A

  • Bearing unit for conveying device with abnormality detection function, and conveyor facility

    JP2013032211A