Waste classification device operating system

Abstract

A waste classification device operating system according to an embodiment of the present invention comprises: a processing amount calculation unit for recognizing a blank area in which waste has not been placed on a conveyor belt passing through a waste classification device which automatically classifies waste and calculating a waste processing amount of the waste processed by the waste classification device; and a device monitoring unit for detecting whether the waste classification device is operating abnormally and the type of abnormal operation on the basis of a change in the waste processing amount.

Description

Waste sorting device operating system

[0001] The present invention relates to a waste sorting device operating system, and more specifically, to a waste sorting device operating system that detects abnormalities in a waste sorting device and adjusts its operation based on the amount of waste processed.

[0002] This patent application claims priority to Korean Patent Application No. 10-2024-0140381 filed with the Korean Intellectual Property Office on October 15, 2024, and the disclosures of said patent application are incorporated herein by reference.

[0003] The amount of waste generated from households, factories, and other sources is rapidly increasing. To create a sustainable society, technologies are being researched and developed to recover reusable resources from this waste.

[0004] A waste sorting process is necessary to recover reusable resources. While human labor has traditionally been involved in manually sorting waste, waste sorting devices that eliminate the need for human intervention are being introduced recently.

[0005] The waste sorting device can identify waste using artificial intelligence and sort waste using various sorting means, such as robotic arms.

[0006] Recently, attempts are being made to construct large-scale resource recovery centers by connecting multiple waste sorting devices.

[0007] In order to efficiently operate a resource recovery center composed of multiple such waste sorting devices, there is a need for an operating system capable of monitoring whether the waste sorting devices are functioning normally and supporting their management.

[0008] To solve the aforementioned problems, the present invention aims to provide a waste sorting device operating system that calculates the amount of waste processed by the waste sorting device and adjusts the operation of the waste sorting device in consideration of the calculated amount of waste processed.

[0009] The waste sorting device operating system of the present invention may include: a throughput calculation unit that analyzes distribution characteristics regarding the arrangement of waste on a conveyor belt passing through a waste sorting device that sorts waste according to preset criteria and calculates the amount of waste processed by the waste sorting device; a device monitoring unit that detects whether the waste sorting device is operating abnormally and the type of abnormal operation based on fluctuations in the amount of waste processed; and an operation management unit that adjusts the operation of the waste sorting device based on the amount of waste processed.

[0010] The above distribution characteristics may include at least one of an empty area where waste is not placed on the conveyor belt and the number of wastes.

[0011] The above throughput calculation unit may include a vision sensor that acquires at least one of a first image, which is an image of waste at the point where waste is fed into the waste sorting device, and a second image, which is an image of waste at the point where waste is discharged from the waste sorting device.

[0012] The above throughput calculation unit may include a first artificial intelligence model that has learned data including the area of ​​the blank region within the first image and the second image, the number of wastes, and the waste throughput; and a second artificial intelligence model that has learned data including the area of ​​the blank region within the first image, the number of wastes, and the waste throughput.

[0013] The above throughput calculation unit can compare the area of ​​the blank region included in the first image and the second image using the above first artificial intelligence model, and calculate the amount of waste processed by the waste classification device based on the difference in the area of ​​the blank region.

[0014] The above throughput calculation unit can compare the number of waste items included in the first image and the second image using the above first artificial intelligence model, and calculate the amount of waste processed by the waste classification device based on the difference in the number of waste items.

[0015] The above throughput calculation unit can predict the waste processing volume of the waste sorting device based on the area of ​​the blank region included in the first image through the above second artificial intelligence model.

[0016] The above throughput calculation unit can predict the waste processing volume of the waste classification device based on the number of waste items included in the first image through the above second artificial intelligence model.

[0017] The above device monitoring unit may include a third artificial intelligence model that has learned data including the type of abnormal operation of the waste classification device and the amount of waste processed when an abnormality occurs in the waste classification device.

[0018] If the calculated waste processing volume increases or decreases compared to the waste processing volume predicted by the throughput calculation unit, the device monitoring unit can output the expected type of abnormal operation of the waste classification device using the third artificial intelligence model.

[0019] The above-mentioned operation management unit receives the predicted waste processing volume from the above-mentioned throughput calculation unit and can determine the waste sorting device to be operated by considering the predicted waste processing volume together with the preset waste processing volume criteria.

[0020] The above-mentioned operation management unit can accumulate the amount of waste processed by the waste sorting device during a preset period and determine the waste sorting device to be operated by taking into account the accumulated amount of waste processed.

[0021] The above-mentioned operation management department can determine the operating conditions of the waste sorting device to be operated.

[0022] The waste classification device operating system of the present invention may include at least one of the waste classification devices.

[0023] According to the present invention as described above, the following effects are achieved.

[0024] The present invention can easily calculate the amount of waste processed by a waste classification device through waste images.

[0025] The present invention allows for easy prediction of the amount of waste that a waste classification device can process through waste images.

[0026] The present invention can efficiently support the maintenance of a waste sorting device by automatically detecting whether the waste sorting device is operating abnormally and the type of abnormal operation.

[0027] The present invention enables the efficient operation of a waste sorting device by determining whether to operate and the operating conditions of the waste sorting device based on the waste processing volume.

[0028] In addition, other features and advantages of the present invention may be newly identified through the embodiments of the present invention.

[0029] FIG. 1 is a drawing showing a waste classification device according to an embodiment of the present invention.

[0030] FIG. 2 is a drawing showing a resource recovery center composed of a waste sorting device according to an embodiment of the present invention.

[0031] FIG. 3 is a diagram showing the schematic configuration of a waste classification device operating system according to an embodiment of the present invention.

[0032] FIG. 4 is a diagram showing the detailed configuration of a throughput calculation unit according to an embodiment of the present invention.

[0033] FIG. 5 is a diagram to help understand the process of a throughput calculation unit calculating a waste throughput according to an embodiment of the present invention.

[0034] FIG. 6 is a diagram showing the detailed configuration of a device monitoring unit according to an embodiment of the present invention.

[0035] It should be noted that in assigning reference numbers to the components of each drawing in this specification, identical components are given the same number as much as possible, even if they are shown in different drawings.

[0036] Meanwhile, the meaning of the terms described in this specification should be understood as follows.

[0037] A singular expression should be understood to include a plural expression unless the context clearly defines otherwise, and terms such as "first," "second," etc., are intended to distinguish one component from another, and the scope of rights shall not be limited by these terms.

[0038] Terms such as "include" or "have" should be understood as not excluding in advance the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0039] Hereinafter, preferred embodiments of the present invention designed to solve the above problems will be described in detail with reference to the attached drawings.

[0040] FIG. 1 is a drawing showing a waste classification device according to an embodiment of the present invention.

[0041] Referring to FIG. 1, the waste sorting device (1400) may be a device comprising a conveyor, a robotic arm, and an imaging device. The conveyor may transport waste (10) into the waste sorting device. The imaging device may acquire an image or spectral spectrum of the waste (10). The waste sorting device (1400) may analyze the image or spectral spectrum of the waste through artificial intelligence and determine whether the waste (10) is a subject for classification according to preset criteria. If the waste (10) is a subject for classification, the waste sorting device (1400) may use the robotic arm to pick the waste (10) and move it to a collection bin.

[0042] FIG. 2 is a drawing showing a resource recovery center composed of a waste sorting device according to an embodiment of the present invention.

[0043] Referring to FIG. 2, the resource recovery center may be composed of a plurality of waste sorting devices (1400). As shown in FIG. 2, a plurality of waste sorting devices (1400) may be connected in series. For example, a first waste sorting device (1400a), a second waste sorting device (1400b), a third waste sorting device (1400c), ..., an nth waste sorting device (1400n) may be connected in series. A plurality of waste sorting devices (1400) connected in series can rapidly sort waste in large quantities.

[0044] A resource recovery center can be constructed by arranging multiple lines of waste sorting devices (1400) connected in series. Each line can be configured in parallel, and depending on the conditions of the resource recovery center, the lines may be branched or merged.

[0045] The resource recovery center may include a number of waste sorting devices (1400). Therefore, if each waste sorting device (1400) is not properly managed, the overall efficiency of the resource recovery center may be significantly reduced.

[0046] According to an embodiment of the present invention, a waste sorting device operating system (1000) can support the efficient operation of a resource recovery center composed of waste sorting devices (1400) by monitoring the waste sorting device (1400) based on the amount of waste processed and adjusting the operation.

[0047] FIG. 3 is a diagram showing the schematic configuration of a waste classification device operating system according to an embodiment of the present invention.

[0048] Referring to FIG. 3, an automatic waste sorting device according to an embodiment of the present invention may include a throughput calculation unit (1100), a device monitoring unit (1200), an operation management unit (1300), and a waste sorting device (1400).

[0049] A throughput calculation unit (1100) according to an embodiment of the present invention can analyze distribution characteristics regarding the arrangement of waste on a conveyor belt passing through a waste sorting device (1400). The distribution characteristics may include at least one of an empty area where waste is not placed on the conveyor belt and the number of waste items.

[0050] Waste fed into the waste sorting device can be placed on a conveyor belt. If the amount of waste is small, empty areas on the conveyor belt where waste is not placed may occur, and if the amount of waste is large, the empty areas on the conveyor belt where waste is not placed can be reduced.

[0051] The amount of waste can be expressed in terms of the number of waste items. The number of waste items can be expressed as the total number, the number by type, or the number by category, and the criteria for counting the number of waste items can be appropriately selected.

[0052] The throughput calculation unit (1100) can calculate the waste throughput by recognizing an empty area on the conveyor belt where waste is not placed. For example, the throughput calculation unit (1100) can calculate that the waste throughput is 3 kg / min when the area of ​​the empty area on the conveyor belt that has passed through the waste sorting device (1400) where waste is not placed is 30%.

[0053] The throughput calculation unit (1100) can calculate the amount of waste to be processed by counting the number of waste placed on the conveyor belt. For example, the throughput calculation unit (1100) can calculate that the amount of waste to be processed is 5 kg / min when the number of waste placed on the conveyor belt that has passed through the waste sorting device (1400) is 30.

[0054] The waste processing capacity may vary depending on the specifications and operating conditions of the input waste sorting device, the type and condition of the waste, and the scale and characteristics of the resource recovery center.

[0055] The device monitoring unit (1200) according to an embodiment of the present invention can detect whether the waste sorting device (1400) is operating abnormally and the type of abnormal operation based on fluctuations in the waste processing volume. When the waste sorting device (1400) is operating normally, the waste processing volume may be constant. However, if an abnormality occurs in the waste sorting device (1400), the waste processing volume may fluctuate. For example, if a malfunction occurs in the robot arm (1420), the robot arm (1420) may not be able to properly pick up waste. In such cases, a tendency for the waste processing volume to decrease may appear. The device monitoring unit (1200) can recognize fluctuations in the waste processing volume and detect abnormal operation of the waste sorting device (1400).

[0056] When abnormal operation of the waste sorting device (1400) is detected, the device monitoring unit (1200) can detect the type of abnormal operation of the waste sorting device (1400) based on the waste processing volume. For example, if the amount of waste input exceeds the average input amount and the waste processing volume shows a decreasing trend, the device monitoring unit (1200) can detect that a phenomenon of interference between the waste and the robot arm has occurred.

[0057] An operation management unit (1300) according to an embodiment of the present invention can adjust the operation of waste sorting devices (1400) based on the amount of waste processed. For example, as shown in FIG. 2, waste sorting devices (1400) can be connected in series. If the amount of waste processed by a waste sorting device (1400a) located at the front is greater than or equal to a preset standard, the operation management unit (1300) can stop the operation of the remaining waste sorting devices located at the rear.

[0058] A waste sorting device operating system (1000) according to an embodiment of the present invention may include at least one waste sorting device (1400). For example, the waste sorting device operating system (1000) may control the operation of one waste sorting device (1400) installed in a small-scale resource recovery center. Alternatively, the waste sorting device operating system (1400) may control the operation of multiple waste sorting devices (1400) installed in a large-scale resource recovery center. The number of waste sorting devices (1400) is not limited and may be appropriately selected depending on the situation.

[0059] FIG. 4 is a diagram showing the detailed configuration of a throughput calculation unit according to an embodiment of the present invention.

[0060] Referring to FIG. 4, a throughput calculation unit (1100) according to an embodiment of the present invention may include a vision sensor (1110), a first artificial intelligence model (1120), and a second artificial intelligence model (1130).

[0061] The vision sensor (1110) can acquire at least one of a first image, which is an image of waste at the point where waste is fed into the waste sorting device (1400), and a second image, which is an image of waste at the point where waste is discharged from the waste sorting device.

[0062] A vision sensor (1110) can be installed to acquire a first image of waste at the point where waste is fed into the waste sorting device (1400).

[0063] A vision sensor (1110) may be installed to acquire a second image, which is an image of waste at the point where waste is discharged into the waste sorting device (1400). The location of the vision sensor (1110) is not limited, and an appropriate location capable of acquiring the first image or the second image may be selected.

[0064] Accordingly, there may be at least one vision sensor (1110). For example, one vision sensor (1110) may be installed at the front end of the waste sorting device (1400), and another vision sensor (1110) may be installed at the rear end.

[0065] A vision sensor (1110) can acquire at least one of a first image or a second image, and a single vision sensor (1110) can acquire both the first image and the second image.

[0066] For example, a plurality of waste sorting devices (1400) may be arranged in series. In this case, a vision sensor (1110) may be installed between the first waste sorting device (1400a) and the second waste sorting device (1400b). This vision sensor (1110) can acquire a second image of the first waste sorting device (1400a) and a first image of the second waste sorting device (1400b). According to this example, the second image of the first waste sorting device (1400a) and the first image of the second waste sorting device (1400b) may be the same image.

[0067] As another example, a vision sensor (1110) may be rotatably installed in the center of the waste sorting device (1400). When waste is fed into the waste sorting device (1400), the rotatably installed vision sensor (1110) can acquire a first image. When the robot arm (1420) completes the sorting operation, the vision sensor (1110) rotates in the opposite direction to acquire a second image of the discharged waste.

[0068] FIG. 5 is a diagram to help understand the process of a throughput calculation unit calculating a waste throughput according to an embodiment of the present invention.

[0069] Referring to FIG. 5, the throughput calculation unit (1100) can compare the area of ​​the blank region included in the first image and the second image using a learned first artificial intelligence model (1120), and calculate the amount of waste processed by the waste classification device (1400) based on the difference in the area of ​​the blank region.

[0070] Specifically, the first artificial intelligence model (1120) can recognize the empty area of ​​the conveyor belt where waste is not placed in the first image and the second image and calculate the area of ​​the empty area. For example, as shown in FIG. 5 (a), the first artificial intelligence model (1120) can calculate that the area of ​​the empty area where waste is not placed in the first image is 2% of the total area of ​​the first image. As shown in FIG. 5 (b), the first artificial intelligence model (1120) can calculate that the area of ​​the empty area where waste is not placed in the second image is 75% of the total area of ​​the second image.

[0071] The first artificial intelligence model (1120) can calculate the amount of waste processed by the waste sorting device (1400) based on the difference in the area of ​​the blank region. For example, as shown in FIG. 5 (c), the first artificial intelligence model can calculate that the area of ​​the blank region included in the first image is 25% of the area of ​​the first image. As shown in FIG. 5 (d), the first artificial intelligence model (1120) can calculate that the area of ​​the blank region included in the second image is 70% of the area of ​​the second image. The first artificial intelligence model (1120) can calculate that 4.5 kg of waste has been processed, which corresponds to 45% of the difference between the area of ​​the blank region of the first image and the area of ​​the blank region of the second image.

[0072] According to another embodiment of the present invention, the throughput calculation unit (1100) can compare the number of waste items included in the first image and the second image using a learned first artificial intelligence model (1120), and calculate the amount of waste processed by the waste classification device (1400) based on the difference in the number of waste items.

[0073] Specifically, the first artificial intelligence model (1120) can recognize waste in the first image and the second image and count the number of waste items. For example, as shown in FIG. 5 (a), the first artificial intelligence model (1120) can count the number of waste items in the first image as 30. As shown in FIG. 5 (b), the first artificial intelligence model (1120) can count the number of waste items in the second image as 8.

[0074] The first artificial intelligence model (1120) can calculate the amount of waste processed by the waste sorting device (1400) based on the difference in the number of waste items. For example, as shown in FIG. 5 (c), the first artificial intelligence model can calculate that the number of waste items included in the first image is 25. As shown in FIG. 5 (d), the first artificial intelligence model (1120) can calculate that the number of waste items included in the second image is 15. The first artificial intelligence model (1120) can calculate that 2 kg of waste, corresponding to the difference of 10 between the number of waste items in the first image and the number of waste items in the second image, has been processed.

[0075] According to an embodiment of the present invention, the first artificial intelligence model (1120) may be a model that has been pre-trained with data including the area of ​​the blank region included in the first image and the second image, the number of wastes, and the amount of waste processed.

[0076] Specifically, the first artificial intelligence model (1120) can learn input data including the area of ​​the blank area and the number of waste, and output data including the waste processing volume. For example, in addition to the area of ​​the blank area and the number of waste, the input data may include the weight of each type of waste, information on resource recovery centers, information on waste sorting devices, etc. The output data may include the processing volume of each type of waste, etc. The input data and output data may include other data, and the types of data are not limited.

[0077] According to an embodiment of the present invention, the second artificial intelligence model (1130) may be a model that has been pre-trained with data including the area of ​​the blank region included in the first image, the number of wastes, and the amount of waste processed.

[0078] Specifically, the second artificial intelligence model (1130) can learn input data including the area of ​​the blank area and the number of waste, and output data including the waste processing volume. For example, in addition to the area of ​​the blank area and the number of waste, the input data may include the weight of each type of waste, information on resource recovery centers, information on waste sorting devices, waste processing volume, etc. The output data may include the processing volume of each type of waste, etc. The input data and output data may include other data, and the types of data are not limited.

[0079] The throughput calculation unit (1100) can predict the waste processing volume of the waste sorting device (1400) based on the area of ​​the blank region included in the first image through the learned second artificial intelligence model (1130).

[0080] Specifically, the second artificial intelligence model (1130) can recognize the empty area of ​​the conveyor belt where waste is not placed in the first image and calculate the area of ​​the empty area. The second artificial intelligence model (1130) can calculate the amount of waste input based on the area of ​​the empty area included in the first image and predict the amount of waste that the waste sorting device (1400) can process.

[0081] For example, the second artificial intelligence model (1130) can calculate that the area of ​​the blank region included in the first image is 5% of the area of ​​the first image. The second artificial intelligence model (1130) can calculate that 9.5 kg of waste corresponding to 5% of the area of ​​the blank region of the first image has been input. The second artificial intelligence model (1130) can predict that the waste sorting device (1400) can process 4 kg of the 9.5 kg of waste that has been input.

[0082] According to another embodiment of the present invention, the throughput calculation unit (1100) can predict the waste throughput of the waste classification device (1400) based on the number of waste items included in the first image through a learned second artificial intelligence model (1130).

[0083] Specifically, the second artificial intelligence model (1130) can recognize waste in the first image and count the number of waste items. The second artificial intelligence model (1130) can calculate the amount of waste to be processed based on the number of waste items included in the first image and predict the amount of waste to be processed by the waste sorting device (1400).

[0084] For example, the second artificial intelligence model (1130) can calculate that the number of waste items included in the first image is 50. The second artificial intelligence model (1130) can calculate that 9.5 kg of waste corresponding to the number of waste items in the first image, which is 50, has been input. The second artificial intelligence model (1130) can predict that the waste sorting device (1400) can process 4 kg of the input 9.5 kg of waste.

[0085] FIG. 6 is a diagram showing the detailed configuration of a device monitoring unit according to an embodiment of the present invention.

[0086] Referring to FIG. 6, the device monitoring unit (1200) may include a third artificial intelligence model (1210).

[0087] According to an embodiment of the present invention, a third artificial intelligence model (1210) can be pre-trained with data including the type of abnormal operation of the waste classification device (1400) and the amount of waste processed when an abnormality occurs in the waste classification device (1400).

[0088] Specifically, the third artificial intelligence model (1210) can be pre-trained with data including the amount of waste processed when the waste sorting device (1400) is operating normally and the amount of waste processed when it is operating abnormally. For example, the third artificial intelligence model (1210) can learn data that when the waste sorting device (1400) is operating normally, it processes 3 kg (kg / min) of PET bottles and 2 kg (kg / min) of plastic containers every minute. The third artificial intelligence model (1210) can learn data that when the waste sorting device (1400) is operating abnormally, it processes 2 kg (kg / min) of PET bottles and 1 kg (kg / min) of plastic containers every minute.

[0089] The third artificial intelligence model (1210) can be pre-trained with data including abnormal operation types of the waste sorting device (1400) and variations in waste processing volume for each abnormal operation type. For example, the third artificial intelligence model (1210) can be trained with data that when the gripper of the robot arm (1420) collides with the conveyor, the waste processing volume of the waste sorting device (1400) decreases from 5 kg / min to 1 kg / min.

[0090] As another example, the third artificial intelligence model (1210) can be trained with data that when the gripper of the robot arm (1420) is damaged, the waste processing capacity of the waste sorting device (1400) decreases from 5 kg / min to 0 kg / min.

[0091] When the device monitoring unit (1200) increases or decreases the calculated waste processing amount compared to the waste processing amount predicted by the processing amount calculation unit (1100), it can output the expected type of abnormal operation of the waste classification device using the third artificial intelligence model (1210).

[0092] Specifically, when waste is fed into the waste sorting device (1400), the processing volume calculation unit (1100) can predict the waste processing volume of the waste sorting device (1400). The device monitoring unit (1200) can receive the predicted waste processing volume information from the processing volume calculation unit (1100).

[0093] When the waste sorting device (1400) performs a sorting operation, the throughput calculation unit (1100) can calculate the amount of waste processed by the waste sorting device (1400) and transmit it to the device monitoring unit (1200).

[0094] The device monitoring unit (1200) can detect abnormal operation of the waste classification device (1400) and output the expected type of abnormal operation when the calculated waste processing amount increases or decreases compared to the predicted waste processing amount.

[0095] For example, the throughput calculation unit (1100) can predict the waste throughput to be 8 kg / min and transmit the predicted waste throughput information to the device monitoring unit (1200). After the waste sorting device (1400) performs the sorting operation, the throughput calculation unit (1100) can calculate the waste throughput to be 1 kg / min. Since the calculated waste throughput is less than the predicted waste throughput of 8 kg / min, the device monitoring unit (1200) can detect abnormal operation of the waste sorting device (1400). Along with this, the device monitoring unit (1200) can output an abnormal type such as the gripper of the robot arm (1420) colliding with the conveyor.

[0096] The first artificial intelligence model (1120), the second artificial intelligence model (1130), and the third artificial intelligence model (1210) according to an embodiment of the present invention may be models based on a neural network. The artificial intelligence learning model may be designed to simulate the structure of the human brain on a computer and may include a plurality of network nodes having weights that simulate neurons of a human neural network. The plurality of network nodes may each form a connection relationship to simulate the synaptic activity of neurons that transmit and receive signals through synapses.

[0097] According to an embodiment of the present invention, the first artificial intelligence model (1120), the second artificial intelligence model (1130), and the third artificial intelligence model (1210) may include a neural network model or a deep learning model developed from a neural network model. In the deep learning model, a plurality of network nodes may be located at different depths (or layers) and may exchange data according to convolutional connection relationships.

[0098] For example, the first artificial intelligence model (1120), the second artificial intelligence model (1130), and the third artificial intelligence model (1210) may be a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), a Bidirectional Recurrent Deep Neural Network (BRDNN), etc., but are not limited thereto and other appropriate models may be selected.

[0099] According to another embodiment of the present invention, the first artificial intelligence model (1120), the second artificial intelligence model (1130), and the third artificial intelligence model (1210) may be the same single artificial intelligence model. For example, a single artificial intelligence model may learn all the data to be learned by the first artificial intelligence model (1120), the second artificial intelligence model (1130), and the third artificial intelligence model (1210), and perform the calculation of waste throughput, prediction of waste throughput, detection of abnormal operation, and detection of abnormal operation types. According to such an embodiment, an appropriate artificial intelligence model may be selected and learned.

[0100] The operation management unit (1300) according to an embodiment of the present invention receives the predicted waste processing amount from the processing amount calculation unit (1100) and can determine the waste classification device (1400) to be operated by considering the predicted waste processing amount and the preset processing speed standard together.

[0101] In order to efficiently operate a resource recovery center composed of multiple waste sorting devices (1400), it may be necessary to operate all waste sorting devices (1400) or only a portion of the waste sorting devices (1400) depending on the situation. In such cases, the operation management department (1300) can decide whether to operate all waste sorting devices (1400) or only a portion of the waste sorting devices (1400) based on the predicted waste processing volume and the pre-set waste processing volume standards.

[0102] For example, the throughput calculation unit (1100) can predict the waste processing amount of each waste sorting device (1400) to be 7 kg / min. The preset waste processing amount standard may be 5 kg / min. In this case, the operation management unit (1300) can operate 5 of the total 10 waste sorting devices in the resource recovery center.

[0103] The operation management department (1300) can accumulate the amount of waste processed by the waste sorting device (1400) during a preset period and determine the waste sorting device to be operated by taking into account the accumulated amount of waste processed.

[0104] In a resource recovery center composed of multiple waste sorting devices (1400), if only some of the waste sorting devices (1400) are operated according to the amount of waste processed, the level of aging may vary for each waste sorting device (1400). According to an embodiment of the present invention, by varying the waste sorting devices (1400) to be operated according to the accumulated amount of waste processed, it is possible to prevent only some of the waste sorting devices (1400) from becoming aging.

[0105] For example, the preset period may be one month. During the past month, the amount of waste processed by the first waste sorting device (1400a) may be 5,000 kg, the amount of waste processed by the second waste sorting device (1400b) may be 3,000 kg, and the amount of waste processed by the third waste sorting device (1400c) may be 2,500 kg. If the operation management department (1300) needs to operate some of the waste sorting devices (1400), it may stop the operation of the first waste sorting device (1400a), which has the largest accumulated amount of waste processed, and operate the remaining waste sorting devices.

[0106] The operation management department (1300) can determine the operating conditions of the waste sorting device (1400) to be operated. Specifically, the operation management department (1300) can increase or decrease the operating conditions of the waste sorting device (1400) if the predicted waste processing amount differs from the preset waste processing amount standard.

[0107] For example, the predicted waste processing volume may be 3 kg / min and the preset waste processing volume standard may be 5 kg / min. The operation management department (1300) may decide to operate all waste sorting devices (1400) within the resource recovery center and, at the same time, increase the operating speed of the conveyor by 20% compared to the existing speed.

[0108] The use of all examples or exemplary terms (e.g., etc.) in the present invention is merely for the purpose of describing the invention in detail, and the scope of the invention is not limited by such examples or exemplary terms unless limited by the claims. Furthermore, a person skilled in the art will understand that various modifications, combinations, and changes may be made according to design conditions and factors within the scope of the claims or equivalents to which they are added.

[0109] It will be obvious to those skilled in the art that the present invention described above is not limited to the aforementioned embodiments and attached drawings, and that various substitutions, modifications, and changes are possible within the scope of the technical concept of the present invention.

[0110] A waste sorting device operating system according to an embodiment of the present invention includes a throughput calculation unit that recognizes an empty area where waste is not placed on a conveyor belt passing through a waste sorting device that automatically sorts waste, and calculates the amount of waste processed by the waste sorting device; and a device monitoring unit that detects whether the waste sorting device is operating abnormally and the type of abnormal operation based on fluctuations in the amount of waste processed, and can efficiently operate the waste sorting device by determining whether the waste sorting device is operating and the operating conditions based on the amount of waste processed.

Claims

1. A throughput calculation unit that analyzes distribution characteristics regarding the arrangement of waste on a conveyor belt passing through a waste sorting device that classifies waste according to preset standards, and calculates the amount of waste processed by the waste sorting device; A waste classification device operating system comprising a device monitoring unit that detects whether the waste classification device is operating abnormally and the type of abnormal operation based on fluctuations in the waste processing volume.

2. In Paragraph 1, A waste sorting device operating system comprising an operation management unit that adjusts the operation of the waste sorting device based on the waste processing volume.

3. In Paragraph 1, A waste sorting device operating system, wherein the above distribution characteristics include at least one of a blank area where waste is not placed on the conveyor belt and the number of waste.

4. In Paragraph 1, A waste sorting device operating system comprising a vision sensor that acquires at least one of a first image, which is a waste image at a point where waste is fed into the waste sorting device, and a second image, which is a waste image at a point where waste is discharged from the waste sorting device.

5. In Paragraph 4, The above throughput calculation unit A first artificial intelligence model trained on data including the area of ​​blank regions within the first and second images, the number of wastes, and the waste processing volume; and A waste classification device operating system comprising a second artificial intelligence model that has learned data including the area of ​​the blank region within the first image, the number of wastes, and the waste processing volume.

6. In Paragraph 5, A waste sorting device operating system in which the above throughput calculation unit compares the area of ​​a blank region included in the first image and the second image using the above first artificial intelligence model, and calculates the amount of waste processed by the waste sorting device based on the difference in the area of ​​the blank region.

7. In Paragraph 5, A waste classification device operating system in which the above throughput calculation unit compares the number of waste items included in the first image and the second image using the above first artificial intelligence model, and calculates the amount of waste processed by the waste classification device based on the difference in the number of waste items.

8. In Paragraph 5, A waste sorting device operating system in which the above throughput calculation unit predicts the waste throughput of the waste sorting device based on the area of ​​the blank region included in the first image through the above second artificial intelligence model.

9. In Paragraph 5, A waste sorting device operating system in which the above throughput calculation unit predicts the waste processing volume of the waste sorting device based on the number of wastes included in the first image through the above second artificial intelligence model.

10. In Paragraph 1, A waste sorting device operating system comprising a third artificial intelligence model that has learned data including the type of abnormal operation of the waste sorting device and the amount of waste processed when an abnormality occurs in the waste sorting device.

11. In Paragraph 10, A waste classification device operating system in which the above-mentioned device monitoring unit outputs the expected type of abnormal operation of the waste classification device using the above-mentioned third artificial intelligence model when the calculated waste processing amount increases or decreases compared to the waste processing amount predicted by the above-mentioned throughput calculation unit.

12. In Paragraph 2, A waste sorting device operating system in which the above-mentioned operation management unit receives the predicted waste processing volume from the above-mentioned throughput calculation unit and determines the waste sorting device to be operated by considering the predicted waste processing volume together with a preset waste processing volume standard.

13. In Paragraph 12, A waste sorting device operating system in which the above-mentioned operation management unit accumulates the amount of waste processed by the above-mentioned waste sorting device during a preset period and determines the waste sorting device to be operated in consideration of the accumulated amount of waste processed.

14. In Paragraph 12, A waste sorting device operating system in which the above-mentioned operation management department determines the operating conditions of the waste sorting device to be operated.

15. In Paragraph 1, A waste sorting device operating system comprising at least one of the above-mentioned waste sorting devices.

Images