Abnormality detection system for material handling equipment

Abstract

To provide an abnormality detection system of a material handling device capable of accurately detecting sudden abnormality with a simple configuration.SOLUTION: This abnormality detection system 2 for material handling equipment includes: a plurality of acceleration sensors 6 attached to a carrier machine 4; a state determination unit 24 which receives measurement results from the plurality of acceleration sensors 6 and determines whether the carrier machine 4 is in a state of loading and unloading cargo, running, or stopping; an abnormality determination unit 26 which determines whether the carrier 4 is abnormal from the measurement results when the carrier 4 is determined to be loading and unloading cargo or running; and a notification unit 28 which receives signals from the abnormality determination unit 26 and notifies an administrator of the occurrence of abnormality. The abnormality determination unit 26 determines that an abnormality has occurred by comparing at least two of the measurement results with different reference values.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to an anomaly detection system for material handling equipment. [Background technology]

[0002] Material handling equipment is used at logistics and manufacturing sites to automatically carry in, carry out, and move cargo. In material handling equipment, under the control of a control device, transport machines such as shuttles and stacker cranes automatically collect cargo placed in a designated location, travel on a track such as a rail to move to the destination, and carry the cargo out to the designated location.

[0003] Breakdowns of material handling equipment and abnormal operation during loading, unloading, and movement can cause logistics to stagnate and result in significant losses. JP 2020-76750 A discloses a method for predicting part replacement for material handling equipment to reduce such risks. This method uses artificial intelligence technology to learn the relationship between the amount of vibration fluctuation due to changes over time and the degree of abnormality of the parts, thereby predicting the time to replace parts. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2020-76750 Summary of the Invention [Problem to be solved by the invention]

[0005] In material handling equipment, sudden abnormalities can occur, such as foreign objects adhering to the wheels of a conveyor causing it to derail from the running path, or failure to grip cargo when loading it, etc. Methods using artificial intelligence technology require learning from a large amount of data, and the system is complex, so it takes time and money to build the system, and this method is not effective for detecting sudden abnormalities.

[0006] As a method for easily detecting sudden abnormalities, for example, an acceleration sensor is attached to the conveyor, and when the acceleration of the conveyor exceeds a predetermined value, it is determined that an abnormality has occurred. However, since the weight and shape of the cargo being conveyed differ depending on the cargo, the acceleration generated in the conveyor differs even when the conveyor is traveling normally. With this method, there is a high possibility that an abnormal state will be overlooked, or a normal state will be mistaken for an abnormal state. There is a demand for an abnormality detection system that has a simple configuration and can accurately detect sudden abnormalities.

[0007] The present inventors intend to provide an anomaly detection system that has a simple configuration and is capable of detecting sudden anomalies with high accuracy. [Means for solving the problem]

[0008] An anomaly detection system for material handling equipment according to one embodiment includes a plurality of acceleration sensors attached to a conveyor of the material handling equipment, a state determiner that receives measurement results from the plurality of acceleration sensors and determines whether the conveyor is unloading cargo, traveling, or stopped, an anomaly determiner that determines whether the conveyor is abnormal from the measurement results when it is determined that the conveyor is unloading cargo or traveling, and a notifier that receives a signal from the anomaly determiner and notifies the occurrence of an abnormality. The anomaly determiner determines that an abnormality has occurred by comparing at least two of the measurement results with different reference values. Effect of the Invention

[0009] The inventors attached multiple acceleration sensors to different locations on a conveyor and analyzed the difference in acceleration between the normal state and the abnormal state of the material handling equipment. As a result, they found that, for example, even if a sensor that detects a large acceleration exists, the change in acceleration of other sensors is relatively small in the normal state, whereas in the abnormal state, there is a strong tendency for other sensors to detect a larger acceleration than in the normal state. This is thought to be because in the case of a sudden abnormality, a large acceleration occurs over a wide range of the conveyor compared to the normal state. They also found that the detection accuracy of a sudden abnormality can be improved by attaching multiple sensors to the conveyor and comparing the measurement results of the sensors with different appropriate reference values.

[0010] In this anomaly detection system for material handling equipment, a detector for detecting anomalies in a conveying machine detects the occurrence of an anomaly by comparing at least two of the measurement results of a plurality of acceleration sensors attached to the conveying machine with different reference values. In this anomaly detection system, improved accuracy in detecting sudden anomalies is achieved. Furthermore, this system detects anomalies by comparing the measurement results with reference values. The configuration of this system is simple. In this system, the simple configuration improves accuracy in detecting sudden anomalies. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic diagram showing an anomaly detection system for material handling equipment according to one embodiment, together with a conveying machine. [Diagram 2] 2(a) and (b) are plan views showing the conveyor and acceleration sensor of FIG. [Diagram 3] FIG. 3 is a flowchart showing the flow of anomaly detection processing executed in the system of FIG. [Figure 4] FIG. 4 is a flowchart showing the flow of the state determination process of FIG. [Diagram 5] FIG. 5 is a flowchart showing the flow of the unloading abnormality determination process of FIG. [Figure 6]FIG. 6 is a flowchart showing the flow of the process of determining driving abnormality in FIG. [Figure 7] FIG. 7(a) is a graph showing a part of the detection result of the acceleration sensor in a normal state, and FIG. 7(b) is a graph showing a part of the detection result of the acceleration sensor in an abnormal state. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, the present invention will be described in detail based on preferred embodiments with reference to the drawings as appropriate.

[0013] 1 is a schematic diagram showing an anomaly detection system 2 for material handling equipment according to one embodiment, together with a conveyor 4 of the material handling equipment. The anomaly detection system 2 includes a plurality of acceleration sensors 6, a signal processing computer 14, and a notifier 28. As shown in FIG. 1, the acceleration sensor 6 is attached to the conveyor 4.

[0014] 2(a) and (b) are plan views showing the conveyor 4 and the acceleration sensor 6 in FIG. 1. The conveyor 4 is a shuttle. In these figures, the arrow Y indicates the front of the conveyor 4 (the traveling direction of the conveyor 4), and the opposite is the rear. The arrow X indicates the right direction of the conveyor 4, and the opposite is the left direction. The arrow Z in FIG. 1 indicates the upward direction of the conveyor 4, and the opposite is the downward direction. Although not shown, in addition to the conveyor 4, this material handling equipment includes a travel path (e.g., a rail) and a control device installed in a facility such as a warehouse or a factory. Under the control of the control device, the conveyor 4 travels on the travel path to the position of the cargo, loads the cargo, travels on the travel path to the destination, and unloads the cargo, all automatically.

[0015] 1 and 2(a) show a state in which the conveying machine 4 is traveling with cargo 8 loaded. FIG. 2(b) shows a state in which the conveying machine 4 is in the middle of loading the cargo 8. As shown in these figures, the conveying machine 4 has a body 10 and a pair of arms 12. As shown in FIG. 2(a), these arms 12 are retracted when the conveying machine 4 is traveling. As shown in FIG. 2(b), when loading the cargo 8, the conveying machine 4 extends the arms 12 toward the cargo 8. The conveying machine 4 grasps the cargo 8 with the arms 12 and then retracts the arms 12. As a result, the cargo 8 is loaded onto the body 10. Similarly, when unloading the cargo 8, the conveying machine 4 extends and retracts the arms 12.

[0016] As shown in Figs. 2(a) and (b), in this embodiment, three acceleration sensors 6 are attached to the conveyor 4. In this embodiment, the first acceleration sensor 6a and the second acceleration sensor 6b are attached to each of the pair of arms 12, and the third acceleration sensor 6c is attached to the body 10. The first acceleration sensor 6a and the second acceleration sensor 6b are located at the base side of the corresponding arm 12. When the arm 12 expands and contracts, the first acceleration sensor 6a and the second acceleration sensor 6b do not move in accordance with the expansion and contraction of the arm 12. The third acceleration sensor 6c is located in front of the pair of arms 12. The third acceleration sensor 6c may be located behind the pair of arms 12. The number of acceleration sensors 6 may be two or four or more. Each acceleration sensor 6 is a three-axis acceleration sensor. That is, each of these acceleration sensors 6 measures acceleration in the X-axis direction, the Y-axis direction, and the Z-axis direction. Each acceleration sensor 6 sends the measurement result to the signal processing computer 14. In this embodiment, the acceleration sensors 6 and the signal processing computer 14 communicate wirelessly.

[0017] The signal processing computer 14 detects an abnormality in the conveyor 4 based on the measurement results from the acceleration sensor 6. As shown in FIG.

[0018] In this embodiment, the input interface 16 has a receiver for receiving a radio signal and a converter for converting the received signal into a digital signal. The controller 18 processes the signal from the input interface 16. A typical controller 18 is a CPU. The signal processing computer 14 may have a plurality of CPUs as the controller 18. The storage device 20 stores a program for operating the controller 18. The storage device 20 is typically a semiconductor memory or a hard disk. A plurality of semiconductor memories or hard disks may exist as the storage device 20. The communication interface 22 transmits and receives data via the network 30. The signal processing computer 14 may be realized by a gateway device or a personal computer.

[0019] The signal processing computer 14 determines whether the conveyor 4 is unloading cargo, traveling, or stopped, based on the measurement results from the acceleration sensor 6. Furthermore, when it is determined that the conveyor 4 is unloading cargo or traveling, the signal processing computer 14 determines whether the conveyor 4 is abnormal, based on the measurement results. In other words, in this embodiment, a state determiner 24 that determines the state of the conveyor 4 and an abnormality determiner 26 that determines whether the conveyor 4 is abnormal are realized by the signal processing computer 14. The state determiner 24 and the abnormality determiner 26 may be realized by separate circuits.

[0020] The notifier 28 notifies the administrator when the signal processing computer 14 determines that an abnormality has occurred. In this embodiment, the personal computer 32 receives the abnormality determination signal from the signal processing computer 14 via the network 30 and notifies the administrator. The network 30 may be the Internet or an intranet. The server 34 may receive the abnormality determination signal from the signal processing computer 14 via the network 30, and the personal computer 32 connected to the server 34 may notify the administrator. In this embodiment, the personal computer 32 and the server 34 constitute the notifier 28. The personal computer 32 directly connected to the signal processing computer 14 may be used as the notifier 28. A speaker connected to the signal processing computer 14 or built into the signal processing computer 14 for notifying of an abnormality may be used as the notifier 28.

[0021] Fig. 3 is a flowchart showing the flow of an abnormality detection process performed by the signal processing computer 14. In this embodiment, these processes are executed by operating the controller 18 by a program. As shown in Fig. 3, this process includes steps S1 to S5.

[0022] In step S1, the measurement results continuously sent from the acceleration sensor 6 are framed for each predetermined period. For example, the measurement results from the acceleration sensor 6 are set as one frame every 10 seconds. The subsequent steps S2 to S5 are executed for each frame.

[0023] In step S2, it is determined based on the measurement result whether the conveyor 4 is unloading, traveling, or stopped. If it is determined to be in the unloading state, the process proceeds to step S3, and if it is determined to be in the traveling state, the process proceeds to step S4. If it is determined to be in the stopped state, the process returns to step S1, and the next period is framed.

[0024] In step S3, it is determined whether the conveyor 4 is abnormal or normal when unloading the cargo 8. If it is determined to be abnormal, the process proceeds to step S5, and if it is determined to be normal, the process returns to step S1.

[0025] In step S4, it is determined whether the conveyor 4 is normal or abnormal during travel. If it is determined to be abnormal, the process proceeds to step S5, and if it is determined to be normal, the process returns to step S1.

[0026] In step S5, a signal indicating an abnormality determination is output. As described above, this abnormality determination output is notified to the administrator by the notifier 28. After the signal indicating the abnormality determination is output, the process returns to step S1.

[0027] Fig. 4 is a detailed flowchart of the state determination process of step S2 in Fig. 3. In step S2, state determination is performed based on the rate of change of the Y-direction component (the component in the traveling direction of the conveyor 4) of the measurement results of each acceleration sensor 6. The process of step S2 includes the processes of steps S2-1 to S2-4.

[0028] In step S2-1, the rate of change dy of the Y-direction component is calculated for each of the measurement results of the multiple acceleration sensors 6. In this embodiment, the rate of change dy1 is calculated from the measurement results of the first acceleration sensor 6a, the rate of change dy2 is calculated from the measurement results of the second acceleration sensor 6b, and the rate of change dy3 is calculated from the measurement results of the third acceleration sensor 6c. This rate of change can be calculated, for example, by dividing the measurement results in a frame into units of very short time (for example, 1 second) and taking the difference between the Y-direction components of acceleration between adjacent units. By connecting these differences, a graph showing the change rate in the frame can be created for each of the rate of change dy1, the rate of change dy2, and the rate of change dy3. Note that in this step, data that can be used to create a graph showing the change rate is prepared, and it is not necessary to actually create a graph. However, for ease of understanding, the following description will be given assuming that this "graph" exists.

[0029] In step S2-2, it is determined whether or not there is a portion in the graphs of the change rates dy1, dy2, and dy3 where the change rates are equal to or greater than a predetermined threshold T1. The "change rate" compared with the threshold T1 here is the "absolute value of the change rate" without a sign. This is the same in the subsequent steps. In this embodiment, for example, the threshold T1 is set to 2 G / sec (G is the gravitational acceleration). If there is a portion in any of the graphs of the change rates where the value of the change rate is equal to or greater than the predetermined threshold T1, the conveyor 4 is determined to be "unloading". If there is no portion in any of the graphs of the change rates where the value of the change rate is equal to or greater than the predetermined threshold T1, the process proceeds to step S2-3.

[0030] In step S2-3, it is determined whether or not there are two or more portions in the graph of the rate of change dy1, the rate of change dy2, and the rate of change dy3 where the rate of change is equal to or greater than a predetermined threshold value T2. In other words, it is determined whether or not there is a graph in which the rate of change exceeds the threshold value T2, then drops below the threshold value T2 once, and then returns to above the threshold value T2. If there is such a graph, the conveyor 4 is determined to be "unloading." If there is not, the process proceeds to step S2-4. Note that the threshold value T2 is a value smaller than the threshold value T1, and is set to, for example, 1.5 G / sec (G is the acceleration of gravity).

[0031] In step S2-4, it is determined whether or not there is a portion in the graph of the rate of change dy1, the rate of change dy2, and the rate of change dy3 where the rate of change is equal to or greater than a predetermined threshold value T3. The threshold value T3 is a value smaller than the threshold value T2, and in this embodiment, it is set to, for example, 0.1 G / sec. If there is such a portion, the conveyor 4 is determined to be "running". If there is not, the conveyor 4 is determined to be "stopped". This ends the processing of step S2.

[0032] Fig. 5 is a flowchart illustrating in detail the process of determining whether there is a loading / unloading abnormality in step S3 in Fig. 3. The process in step S2 includes the processes in steps S3-1 to S3-4.

[0033] In step S3-1, a maximum component a1 is identified from the three-axis measurement results of the multiple acceleration sensors 6. In this embodiment, the maximum value of the acceleration sensor 6 that detects the maximum component among the X-direction component, Y-direction component, and Z-direction component measured by the first acceleration sensor 6a, the second acceleration sensor 6b, and the third acceleration sensor 6c is the maximum component a1. Furthermore, a component a2 that is the same magnitude as a1 or the second largest after a1 and is detected by an acceleration sensor 6 other than the acceleration sensor 6 that detected the maximum component a1 at the same time as the detection of the maximum component a1 is identified. This is called the second component a2. When the maximum component is detected by multiple acceleration sensors 6 at the same time, the maximum component a1 and the second component a2 have the same value.

[0034] In step S3-2, the following determination is made: a1>T4 a2>a1 / 2 Here, T4 is a predetermined threshold value, and is set to, for example, 5G. The threshold value T4 is a reference value for comparison with the maximum component a1. The reference value for comparison with the second component a2 is a1 / 2. The maximum component a1 and the second component a2 are compared with different reference values. When both of these inequalities are satisfied, the process proceeds to step S3-3. When any one of these inequalities is not satisfied, it is determined to be normal.

[0035] In step S3-3, the maximum acceleration A1 is identified from the measurement results of the multiple acceleration sensors 6. The magnitude of the acceleration in this step is the magnitude of the total acceleration obtained by combining the X-direction component, the Y-direction component, and the Z-direction component, and is an "absolute value" without a sign. The maximum value of the acceleration sensor 6 that detected the maximum acceleration is the maximum acceleration A1. Furthermore, in this step, the acceleration A2 (second acceleration A2) of the acceleration sensor 6 that detected the acceleration equal to or next to the maximum acceleration A1 at the same time as the maximum acceleration A1 was detected, and the acceleration A3 (minimum acceleration A3) of the acceleration sensor 6 that detected the minimum acceleration are identified. When the maximum acceleration is detected by multiple acceleration sensors 6 at the same time, the maximum acceleration A1 and the second acceleration A2 have the same value. When the number of acceleration sensors 6 is two, the second acceleration A2 and the minimum acceleration A3 have the same value.

[0036] In step S3-4, the following determination is made: A2>A1 / 2 A3>T5 Here, T5 is a predetermined threshold smaller than the threshold T4, and is set to, for example, 1G. The threshold T5 is a reference value for comparison with the minimum acceleration A3. The reference value for comparison with the second acceleration A2 is A1 / 2. The minimum acceleration A3 and the second acceleration A2 are compared with different reference values. When both of these inequalities are satisfied, it is determined that there is an abnormality in loading / unloading. When either of these inequalities is not satisfied, it is determined that there is a normality. With the above, the processing of step S3 is completed.

[0037] Fig. 6 is a flowchart illustrating in detail the process of determining whether or not the vehicle is traveling abnormally in step S4 in Fig. 3. The process of step S4 includes the processes of steps S4-1 and S4-2.

[0038] In step S4-1, a maximum acceleration B1 is identified from the measurement results of the multiple acceleration sensors 6. The magnitude of acceleration here is the magnitude of the total acceleration obtained by combining the X-direction component, the Y-direction component, and the Z-direction component. The maximum value of the acceleration sensor 6 that detected the maximum acceleration is the maximum acceleration B1. Furthermore, in this step, an acceleration B2 (minimum acceleration B2) of the acceleration sensor 6 that detected the minimum acceleration at the same time that the maximum acceleration B1 was detected is identified.

[0039] In step S4-2, the following determination is made: B1>T6 B2>T7 Here, T6 is a predetermined threshold value, and is set to, for example, 2G. T7 is a predetermined threshold value smaller than T6, and is set to, for example, 1.5G. Threshold value T6 is a reference value for comparison with maximum acceleration B1, and threshold value T7 is a reference value for comparison with minimum acceleration B2. When both of these inequalities are satisfied, it is determined that the driving is abnormal. When either of these inequalities is not satisfied, it is determined that the driving is normal. With the above, the processing of step S4 is completed.

[0040] The effects of this embodiment will be described below.

[0041] In the material handling equipment anomaly detection system 2 of this embodiment, multiple acceleration sensors 6 are attached to the conveyor 4. The anomaly detector of this anomaly detection system 2 detects the occurrence of an anomaly by comparing at least two of the detection results of the multiple acceleration sensors 6 with different reference values. This can improve the accuracy of detecting sudden anomalies in which large acceleration occurs over a wide range of the conveyor 4. In this anomaly detection system 2, improved accuracy of detecting sudden anomalies is achieved.

[0042] The anomaly detection system 2 of this embodiment detects anomalies by comparing the measurement results with a reference value. The configuration of this system 2 is simple. With this system 2, the detection accuracy of sudden anomalies is improved with a simple configuration.

[0043] The abnormality detection system 2 of this embodiment is composed of a plurality of acceleration sensors 6 attached to the conveyor 4, a state determiner 24 and an abnormality determiner 26 which can be realized by a signal processing computer 14, and a notifier 28 which can be realized by a personal computer 32. The configuration of this system 2 is simple. Furthermore, when applying this system 2, there is no need to make any changes to the material handling equipment itself. This system 2 can be easily applied to various material handling equipment.

[0044] In this embodiment, the state determiner 24 determines whether the state is cargo unloading, traveling, or stopped, based on the rate of change in the Y-direction component of the measurement results of each acceleration sensor 6. When gripping cargo 8 during cargo unloading, the arm 12 extends in the X direction and then moves in the Y direction. At the moment when the cargo 8 is gripped, there is an acceleration sensor 6 where the Y-direction component of acceleration changes suddenly. On the other hand, the Y-direction component during traveling changes more slowly in comparison, and there is almost no change in the Y-direction component when stopped. The difference in acceleration during loading / unloading, traveling, and stopped is easily detected from the rate of change in the Y-direction component. By basing the state determination on the rate of change of the Y-direction component, highly accurate state determination is realized.

[0045] In this embodiment, the determination of the loading / unloading abnormality is performed based on the maximum acceleration and the second acceleration. This can improve the accuracy of detection of a sudden abnormality in which a large acceleration occurs over a wide range of the conveyor 4 compared to the normal state. In this abnormality detection system 2, the improvement of the detection accuracy of a sudden abnormality is realized.

[0046] It is preferable that at least one acceleration sensor 6 is attached to the arm 12, and at least one sensor is attached to the body 10. In this case, it is preferable that the position of the acceleration sensor 6 attached to the body 10 is located forward or rearward of either of the pair of arms 12. In this way, highly accurate abnormality detection can be achieved.

[0047] From the viewpoint of improving the accuracy of anomaly detection, the number of acceleration sensors 6 is preferably three or more. From the viewpoint of easily configuring the anomaly detection system 2, the number of acceleration sensors 6 is preferably five or less. EXAMPLES

[0048] The effects of the present anomaly detection system will be clarified below through examples, but the scope of the disclosure of this specification should not be construed as being limited based on the description of these examples.

[0049] [Flow of the Example] The detection system shown in Figure 1 was prepared, and three acceleration sensors were attached to each of the pair of arms of the shuttle and to the body as shown in Figure 2. Anomaly detection was performed according to the flow in Figures 3-6. Thresholds T1-T7 were set as follows through experiments. T1=2G / sec, T2=1.5G / sec, T3=0.1G / sec, T4=5G, T5=1G, T6=2G, T7=1.5G

[0050] [Flow of Comparative Example] The detection system shown in Fig. 1 was prepared, and three acceleration sensors were attached to each of a pair of arms of the shuttle and to the body as shown in Fig. 2. Anomaly detection was performed according to the flow in Fig. 3. However, unlike the embodiment, the state determination process, loading / unloading anomaly determination process, and running anomaly determination process are simplified as follows. A single reference value is used in each anomaly determination process. Status determination process: If the rate of change of all acceleration components in the Y direction is less than 0.1 G / sec, the vehicle is deemed to be stopped. If the result from only one acceleration sensor exceeds 0.1 G / sec, the vehicle is deemed to be in a moving state. In all other cases, the vehicle is deemed to be in an unloading state. Processing for determining loading / unloading abnormalities: If the maximum acceleration exceeds 5G, it is determined that there is a loading / unloading abnormality; otherwise, it is determined to be normal. Processing for determining abnormal driving: If the maximum acceleration exceeds 2G, it is determined that the driving is abnormal; otherwise, it is determined that the driving is normal.

[0051] [Example 1 and Comparative Example 1] The shuttle was repeatedly run "normally" on a given route for 80 seconds. In Table 1, this is recorded as "normal running" in the "Shuttle status" column and "80" in the "Operation time" column. Status and abnormality determinations were performed in the flow of the example and the flow of the comparative example.

[0052] [Example 2 and Comparative Example 2] A foreign object was attached to the wheels of a shuttle, and the shuttle was repeatedly run in an "abnormal" state for 120 seconds on a specified running path. In Table 1, this is recorded as "abnormal running" in the "Shuttle state" column and "120" in the "Operation time" column. State judgment and abnormality judgment were performed in the flow of the example and the flow of the comparative example.

[0053] [Example 3 and Comparative Example 3] The shuttle arm was operated, and normal loading and unloading of cargo was repeated for 90 seconds. In Table 2, this is recorded as "Normal loading and unloading" in the "Shuttle status" column and "90" in the "Operation time" column. Status determination and abnormality determination were performed in the flow of the example and the flow of the comparative example.

[0054] [Example 4 and Comparative Example 4] The cargo that could not be loaded was placed, the shuttle's arms were operated, and the abnormal cargo loading and unloading operation was repeated for 90 seconds. In Table 2, this is recorded as "Abnormal loading and unloading" in the "Shuttle status" column and "90" in the operation time column. Status judgment and abnormality judgment were performed in the flow of the example and the flow of the comparative example.

[0055] [Status and abnormality judgment results] In the status judgment of each example and comparative example, the most frequent judgment result during execution time is recorded in "Status Judgment Result" in Table 1. In the abnormality judgment, if an "abnormal" judgment is made even once during execution time, "abnormal" is recorded in "Status Judgment Result" in Table 1. As can be seen from the results of "Example 1-4" in Tables 1 and 2, the abnormality detection system of this embodiment can correctly judge normal and abnormal states both during loading / unloading and while traveling. On the other hand, as can be seen from the results of "Comparative Example 1-4", the flow of the comparative example contains erroneous judgments.

[0056] [Table 1]

[0057] [Table 2]

[0058] FIG. 7(a) is a graph showing a part of the detection results of the acceleration sensors in a normal driving state in this embodiment, and FIG. 7(b) is a graph showing a part of the detection results of the acceleration sensors in an abnormal driving state. Since each of the three acceleration sensors measures the acceleration in the three axial directions of XYZ, nine broken lines are present in both FIG. 7(a) and (b). As shown in region R1 of FIG. 7(a), large acceleration may be measured even in normal operation, but this is detected by one acceleration sensor (there are two broken lines showing large acceleration in region R1, but both are detection results from the same acceleration sensor). On the other hand, in an abnormal state, large acceleration is measured by multiple acceleration sensors, as shown in region R2 of FIG. 7(b). It can be seen from this graph that the accuracy of abnormality detection is improved by comparing the maximum acceleration and the second acceleration with different reference values.

[0059] As described above, in this embodiment, an anomaly detection system that can accurately detect sudden anomalies with a simple configuration is realized. This clearly shows the superiority of this anomaly detection system.

[0060] [Disclosure items] The following section discloses preferred embodiments.

[0061] [Item 1] A plurality of acceleration sensors are attached to a conveyor of the material handling equipment; a state determiner that receives measurement results from the plurality of acceleration sensors and determines whether the conveyor is unloading cargo, traveling, or stopped; an abnormality determiner that determines whether the conveying machine is abnormal based on the measurement results when it is determined that the conveying machine is unloading cargo or traveling; a notification device that receives a signal from the abnormality determination device and notifies the occurrence of an abnormality; Equipped with The abnormality determination device determines that an abnormality has occurred by comparing at least two of the measurement results with different reference values.

[0062] [Item 2] The acceleration sensor is a three-axis acceleration sensor, When it is determined that the conveyor is unloading cargo, 2. The abnormality detection system for material handling equipment described in Item 1, wherein the abnormality determiner determines whether the conveying machine is in a normal state based on a maximum component a1 of an acceleration sensor that detected the maximum component among the acceleration components in three directions detected by the multiple acceleration sensors, and a component a2 of the same magnitude as a1 or the second largest after a1, which is detected by an acceleration sensor 6 other than the acceleration sensor 6 that detected the maximum component a1 at the same time that a1 was detected.

[0063] [Item 3] 3. The abnormality detection system for material handling equipment described in item 2, which determines whether the conveying machine is in an abnormal state based further on a maximum value A1 of the acceleration sensor that detected the maximum acceleration, a value A2 of the acceleration sensor that detected the same acceleration as A1 or the next largest acceleration at the same time that A1 was detected, and a minimum value A3 of the acceleration sensor that detected the minimum acceleration at the same time that A1 was detected.

[0064] [Item 4] When it is determined that the conveyor is traveling, 2. The anomaly detection system for material handling equipment according to claim 1, which determines whether an abnormal state exists based on a maximum value B1 of the acceleration sensor that detects a maximum acceleration and a minimum value B2 of the acceleration sensor that detects a minimum acceleration at the same time that B1 is detected.

[0065] [Item 5] 5. An abnormality detection system for material handling equipment according to any one of items 1 to 4, wherein the state determiner determines the state of the conveying machine based on the rate of change of the traveling direction component of the acceleration of the conveying machine from the measurement results of each acceleration sensor.

[0066] [Item 6] 6. The anomaly detection system for material handling equipment described in item 5, wherein when a measurement result exists in which the rate of change is equal to or greater than T1 in a graph showing the transition of the rate of change within a predetermined period, or when a measurement result exists in which the rate of change is equal to or greater than T2 in two or more portions, the conveyor is determined to be unloading cargo. Here, T1 and T2 are predetermined thresholds that satisfy T1>T2.

[0067] [Item 7] If it is not determined that the conveyor is unloading cargo, 7. The anomaly detection system for material handling equipment according to item 6, wherein when there is a measurement result in which a portion in which the rate of change is equal to or greater than T3 exists, it is determined that the conveying machine is traveling, and when such a portion does not exist, it is determined that the conveying machine is stopped. Here, T3 is a predetermined threshold value that satisfies T2>T3.

[0068] [Item 8] 8. The anomaly detection system for material handling equipment according to any one of items 1 to 7, wherein the number of the acceleration sensors is three or more.

[0069] [Item 9] 9. The anomaly detection system for material handling equipment according to any one of items 1 to 8, wherein at least one of the acceleration sensors is attached to an arm of the conveying machine, and at least one of the acceleration sensors is attached to a body of the conveying machine. [Industrial Applicability]

[0070] The anomaly detection system described above can be applied to various material handling equipment. [Explanation of symbols]

[0071] 2. Anomaly detection system 4. Conveyor 6. Acceleration sensor 8...Freight 10. Body 12 Arm 14 Signal Processing Computer 16 Input interface 18. Controller 20...Memory 22 Communication interface 24. State judgement device 26... Abnormality detector 28...Notifier 30. Network 32. Computer 34 Server

Claims

1. A plurality of acceleration sensors are attached to a conveyor of the material handling equipment; a state determiner that receives measurement results from the plurality of acceleration sensors and determines whether the conveyor is unloading cargo, traveling, or stopped; an abnormality determiner that determines whether the conveying machine is abnormal based on the measurement results when it is determined that the conveying machine is unloading cargo or traveling; a notification device that receives a signal from the abnormality determination device and notifies the occurrence of an abnormality; Equipped with The abnormality determination device determines that an abnormality has occurred by comparing at least two of the measurement results with different reference values.

2. The acceleration sensor is a three-axis acceleration sensor, When it is determined that the conveyor is unloading cargo, 2. The abnormality detection system for material handling equipment as described in claim 1, wherein the abnormality determiner determines whether the conveying machine is in a normal state based on a maximum component a1 of an acceleration sensor that detected the maximum component among the acceleration components in three directions detected by the multiple acceleration sensors, and a component a2 of the same magnitude as a1 or the second largest after a1, which is detected by an acceleration sensor 6 other than the acceleration sensor 6 that detected the maximum component a1 at the same time that a1 was detected.

3. 3. The abnormality detection system for material handling equipment according to claim 2, further determining whether the conveying machine is in an abnormal state based on a maximum value A1 of the acceleration sensor that detected a maximum acceleration, a value A2 of the acceleration sensor that detected the same acceleration as A1 or the next largest acceleration at the same time that A1 was detected, and a minimum value A3 of the acceleration sensor that detected the minimum acceleration at the same time that A1 was detected.

4. When it is determined that the conveyor is traveling, 2. The anomaly detection system for material handling equipment according to claim 1, wherein an abnormality is determined based on a maximum value B1 of the acceleration sensor that detects a maximum acceleration and a minimum value B2 of the acceleration sensor that detects a minimum acceleration at the same time that B1 is detected.

5. An abnormality detection system for material handling equipment as described in any one of claims 1 to 4, wherein the state determiner determines the state of the conveying machine based on the rate of change of the traveling direction component of the acceleration of the conveying machine from the measurement results of each acceleration sensor.

6. 6. The anomaly detection system for material handling equipment according to claim 5, wherein when a measurement result exists in which the rate of change is equal to or greater than T1 in a graph showing the progress of the rate of change within a predetermined period of time, or when a measurement result exists in which there are two or more portions in which the rate of change is equal to or greater than T2, it is determined that the conveying machine is unloading cargo. Here, T1 and T2 are predetermined thresholds that satisfy T1>T2.

7. When it is not determined that the conveyor is unloading cargo, The abnormality detection system for material handling equipment as described in claim 6, wherein when there is a measurement result in which a portion in which the rate of change is equal to or greater than T3 exists, it is determined that the conveying machine is running, and when such a portion does not exist, it is determined that the conveying machine is stopped. Here, T3 is a predetermined threshold value that satisfies T2>T3.

8. 5. The anomaly detection system for material handling equipment according to claim 1, wherein the number of the acceleration sensors is three or more.

9. 5. The abnormality detection system for material handling equipment according to claim 1, wherein at least one of the acceleration sensors is attached to an arm of the conveying machine, and at least one of the acceleration sensors is attached to a body of the conveying machine.

Images