Method for measuring remaining amount of feed in feed bin and management server thereof

Abstract

The present invention relates to a method for measuring a remaining amount of feed in a feed bin and a management server thereof. According to an embodiment of the present invention, the method for measuring the remaining amount of feed in a feed bin comprises: a distance information acquisition step of acquiring distance information by measuring a distance to a reference point in a state in which the reference point is displayed by outputting a laser onto feed in the feed bin from a measurement device installed in the feed bin; an image information acquisition step of acquiring image information on the feed from the measurement device in a state in which the reference point is displayed; and a feed remaining amount prediction step of predicting the remaining amount of the feed by using the distance information to the reference point in the feed bin and the image information.

Description

Method for measuring remaining feed in feed bins and management server

[0001] The present invention relates to a method for measuring the remaining feed amount in a feed bin and a management server, and discloses a technology for predicting the remaining feed amount by improving the measurement accuracy of the remaining feed amount in the feed bin.

[0002] Technologies for managing livestock feed include load cell methods for measuring the weight of feed bins and laser methods for measuring the height inside feed bins. The load cell method is problematic due to frequent breakdowns caused by the excessive application of load to the feed bins. The laser method requires various equipment and periodic leveling checks, and there were issues with inaccurate information when the laser beam scattered. Therefore, there was a need for a technology that is easier to manage and allows for accurate measurement to control the amount of feed in feed bins for general livestock farms.

[0003] Among the prior art, Korean Registered Patent Publication No. 10-2381730 (April 1, 2022) relates to a silo-mounted low-power wireless measuring device and wireless measuring system, and discloses a technology for measuring the height of an object contained inside a silo by outputting a laser signal from the upper center of the inner side of the silo.

[0004] However, the aforementioned conventional technology had a limitation in that it could not accurately determine the position information measured when a laser signal was emitted inside the silo. Consequently, more measurement data is required to improve the accuracy of the estimated feed remaining amount, which increases the overall workload.

[0005] The technical problem to be solved by the present invention is to provide a method for measuring the remaining amount of feed in a feed bin and a management server that can more accurately predict the remaining amount of feed by establishing a reference point for the feed inside the feed bin, acquiring distance information and image information, and learning from them.

[0006] In addition, the purpose is to provide a method for measuring the remaining feed quantity in a feed bin and a management server capable of analyzing internal environmental information to determine the degree of feed spoilage and warning the manager.

[0007] In addition, the purpose is to provide a method for measuring the remaining feed in a feed bin and a management server capable of predicting the remaining feed more accurately by comparing a remaining feed model trained based on distance information and image information from the feed inside the bin with a remaining feed model trained based on weight information.

[0008] A method for measuring the remaining amount of feed in a feed bin according to an embodiment of the present invention comprises: a distance information acquisition step of acquiring distance information by measuring the distance to a reference point while a laser is output from a measuring device installed in the feed bin to the feed in the feed bin to mark a reference point; an image information acquisition step of acquiring image information about the feed from the measuring device while the reference point is marked; and a feed remaining amount prediction step of predicting the remaining amount of feed using the distance information to the reference point in the feed bin and the image information.

[0009] In addition, it may further include an environmental information acquisition step of acquiring at least one of the temperature, humidity, and gas concentration inside the feed bin detected through the measuring device.

[0010] In addition, the method may further include a spoilage management step of generating a spoilage prediction model for the feed using the remaining amount information of the feed and the environmental information, and transmitting a warning signal to an administrator if the degree of spoilage of the feed exceeds a preset value through the spoilage prediction model.

[0011] In addition, the feed remaining amount prediction step may modify the first feed remaining amount model by comparing the first feed remaining amount model generated by learning the distance information and the image information with the second feed remaining amount model generated by learning the weight information of the feed inside the feed bin.

[0012] In addition, the method may further include a spoilage management step of generating a spoilage prediction model for the feed using the above remaining amount information and the above environmental information, and analyzing the above environmental information to open the cover of the feed bin using a drive motor when the contamination level exceeds a preset level.

[0013] Meanwhile, a management server according to another embodiment of the present invention includes a communication unit, a processor, a database, and an input / output unit, wherein the processor predicts the remaining amount of feed using distance information obtained by measuring the distance from a measuring device to a reference point while the measuring device outputs a laser to the feed in the feed bin to mark a reference point, and image information regarding the feed while the reference point is marked from the measuring device.

[0014] Accordingly, by establishing a reference point for the feed inside the feed bin and acquiring and learning distance and image information, the remaining amount of feed can be predicted more accurately.

[0015] In addition, by analyzing environmental information inside the feed bin, the degree of feed spoilage can be determined and a warning can be issued to the manager.

[0016] In addition, a more accurate remaining feed amount can be predicted by comparing a remaining feed model trained based on distance information and image information from the feed inside the feed bin with a remaining feed model trained based on weight information.

[0017] Figure 1 is a configuration diagram of a feed residue measurement system in a feed bin.

[0018] FIG. 2 is a configuration diagram of a management server according to an embodiment of the present invention.

[0019] Figure 3 is a flowchart of a method for measuring the remaining amount of feed in a feed bin of a management server according to Figure 2.

[0020] Figure 4 is an example diagram illustrating the method of measuring the remaining amount of feed in the feed bin of the management server according to Figure 2, specifically the output of a reference point on the feed.

[0021] Figure 5 is an example diagram illustrating the method of measuring the remaining amount of feed in a feed bin of a management server according to Figure 2, which involves learning image information captured at multiple reference points.

[0022] Figure 6 is an example diagram illustrating the prediction of the shape of the feed among the methods for measuring the remaining amount of feed in the feed bin of the management server according to Figure 2.

[0023] Figures 7 and 8 are example diagrams of the loading type of feed among the methods for measuring the remaining amount of feed in the feed bin of the management server according to Figure 2.

[0024] Figure 9 is an example diagram illustrating the opening of the cover of the feed bin for spoilage control among the methods for measuring the remaining amount of feed in the feed bin of the management server according to Figure 2.

[0025] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. The terms used are selected considering their functions in the embodiments, and their meanings may vary depending on the intent of the user or operator, or case law. Therefore, the meaning of the terms used in the embodiments described below shall follow the definitions specifically defined in this specification if such definitions exist, and shall be interpreted according to the meaning generally recognized by those skilled in the art if no specific definitions exist.

[0026]

[0027] Figure 1 is a configuration diagram of a feed residue measurement system in a feed bin.

[0028] Referring to FIG. 1, the feed remaining quantity measuring system includes a feed bin (10), a measuring device (20), and a feed remaining quantity management server (100).

[0029] The feed bin (10) accommodates feed (1). The feed bin (10) may be designed so that feed (1) is injected through an upper cover. A certain amount of feed (1) is discharged through an outlet at the bottom of the feed bin (10). A measuring device (20) is installed inside the feed bin (10). In this case, it is preferable that the measuring device (20) be installed in the inner direction of the cover of the feed bin (10). The shape and size of the feed bin (10) can be formed in various types according to the user's design.

[0030] A measuring device (20) is installed inside a feed bin (10) to measure distance information or image information regarding the feed (1). For example, the measuring device (20) sets the position of the center of the feed (1) by emitting a laser through a light-emitting unit (21). The measuring device (20) measures distance information using a LiDAR sensor (22). The measuring device (20) can acquire image information regarding the feed (1) using a camera (23). The measuring device (20) can remove foreign substances adhering to the surfaces of the light-emitting unit (21), the LiDAR sensor (22), and the camera (24) using a wiper (24). In this case, the measuring device (20) communicates with the feed remaining amount management server (100) to transmit distance information or image information in real time.

[0031] Additionally, the measuring device (20) emits a laser beam into the feed (1) inside the feed bin (10) to indicate a reference point. Here, the measuring device (20) may be formed on the cover, etc., inside the feed bin (10), but is not necessarily limited thereto. For example, a laser emitting part (21) may be installed in the measuring device (20). The measuring device (20) emits a laser beam into the feed (1) inside the feed bin (10) so that the reference point is indicated in the form of a point. In this case, the shape of the reference point may be formed as a '+' mark according to the user's settings.

[0032] Additionally, the measuring device (20) may output multiple reference points to the feed (1). This is to allow for more precise measurement of the distance to the feed (1) using multiple reference points. The color of the reference points may vary according to the user's settings. These reference points enable precise measurement of the distance between the measuring device (20) and the feed (1). The measuring device (20) may display reference points until the distance is measured or image information is acquired. Accordingly, errors in the distance information or image information can be minimized.

[0033] The feed remaining quantity management server (100) communicates with the measuring device (20) and predicts the feed remaining quantity. The feed remaining quantity management server (100) obtains distance information from the feed in the feed bin and image information of the top of the feed from the measuring device (20) to predict the current feed remaining quantity. The feed remaining quantity management server (100) may generate a graph of the feed remaining quantity and display it in a time series. Below, the feed remaining quantity management server (100) will be described in detail.

[0034]

[0035] FIG. 2 is a configuration diagram of a management server according to an embodiment of the present invention.

[0036] Referring to FIG. 2, a management server (100) according to an embodiment of the present invention includes a communication unit (110), a processor (120), a database (130), and an input / output unit (140).

[0037] The communication unit (110) communicates with other devices or communication networks and can be implemented with various communication technologies. That is, Wi-Fi, WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), HSPA (High Speed ​​Packet Access), Mobile WiMAX, WiBro, LTE (Long Term Evolution), Bluetooth, infrared communication (IrDA, infrared data association), NFC (Near Field Communication), Zigbee, wireless LAN technology, etc. can be applied.

[0038] For example, the communication unit (110) enables the processor (120) to communicate with the user terminal and transmit and receive various data. In addition, when providing services connected to the Internet, it may follow TCP / IP (Transmission Control Protocol / Internet Protocol), which is a standard protocol for information transmission on the Internet.

[0039] The processor (120) may be a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application-Specific Integrated Circuit), or one or more integrated circuits for controlling program execution in the solution of the present application. The processor (120) generally controls the communication unit (110), the database (120), and the input / output unit (140). Here, the processor (120) may be connected to the communication unit (110), the database (120), and the input / output unit (140) using a communication bus such as a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, etc.

[0040] The database (130) stores and collects various data used to provide a method for measuring the amount of feed remaining in a feed bin according to an embodiment of the present invention. This database (130) may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (ReadOnly Memory), EEPROM (Electrically Erasable Programmable ReadOnly Memory), PROM (Programmable ReadOnly Memory), magnetic memory, magnetic disk, and optical disk, but is not limited thereto and may include any medium capable of storing data.

[0041] The input / output unit (140) specifically includes an output device and an input device, and the output device communicates with the processor (120) and can display information or output voice in a plurality of ways. For example, the output device may be an LCD (Liquid Crystal Display), an LED (Light Emitting Diode) display, an OLED (Organic Light Emitting Diode) display, a speaker, etc. The input device communicates with the processor (120) and can receive user input in a plurality of ways. For example, the input device may be a mouse, a keyboard, a touch screen, or a sensing device.

[0042]

[0043] Figure 3 is a flowchart of a method for measuring the remaining amount of feed in a feed bin of a management server according to Figure 2.

[0044] Referring to FIG. 3, the method for measuring the remaining feed quantity in a feed bin includes a distance information acquisition step (S110), an image information acquisition step (S120), and a feed quantity prediction step (S130). The method for measuring the remaining feed quantity in a feed bin of FIG. 3 is performed by a processor (120) in a feed quantity management server (100).

[0045] The distance information acquisition step (S110) measures the distance from the measuring device (20) to the reference point. For example, the measuring device (20) may be equipped with a LiDAR sensor to measure the distance. This is to ensure that the measuring device (20) more accurately acquires distance information from the location of the reference point on the feed (1). This distance information can be stored and managed together with image information regarding the feed (1). The distance information acquisition step (S110) may re-measure if the distance information to the reference point deviates from a preset reference range. This is to eliminate errors where the distance information to the feed (1) becomes excessively short or long due to the unstable position of the measuring device (20).

[0046] Here, the measuring device (20) is formed with both a LiDAR sensor and a laser emitter so that the position for the LiDAR sensor to measure distance can be aligned with a reference point. This is to prevent the reference point from changing with each measurement, thereby minimizing the error. In other words, the position of the reference point on the feed (1) aligns with the reference position where the distance information is measured. Therefore, even when acquiring image information, if the position of the reference point is identified, the distance information at that reference point can be accurately verified.

[0047]

[0048] The image information acquisition step (S120) acquires image information regarding the feed (1) from the measuring device (20) while the reference point is displayed. The image information acquisition step (S120) can acquire image information at a preset time interval, and this time interval can be varied according to the user's settings. The image information acquisition step (S120) can determine that if the reference point is not included in the image information acquired from the measuring device (20), this is an error. This is to accurately measure the distance information to the feed (1) through the reference point and accurately predict the amount of remaining feed inside the feed bin (10).

[0049] Additionally, the image information acquisition step (S120) may also learn previously acquired image information regarding the feed (1) within the feed bin (10). The image information acquisition step (S120) may also learn image information acquired at a predetermined time interval. This is intended to be used as data for analyzing the shape of the feed (1) inside the feed bin (10) at different times. Learning of such image information may utilize a neural network type CNN (Convolutional Neural Networks) model, but is not necessarily limited thereto. Accordingly, the accuracy of the feed remaining amount prediction can be improved by periodically learning image information regarding the feed (1) within the feed bin (10).

[0050]

[0051] The feed remaining amount prediction step (S130) predicts the remaining amount of feed (1) using distance information to a reference point within the feed bin (10) and image information. The feed remaining amount prediction step (S130) can estimate the average depth using shape information of the feed (1) analyzed through the distance information and image information. In this case, the shape information of the feed (1) can be pre-set based on pre-learned image data. Accordingly, the position of the reference point is fixed on the image information, and the error can be minimized while learning a large amount of image information.

[0052] Specifically, the feed remaining amount prediction step (S130) analyzes image information to determine the loading type of the feed (1). In this case, the feed remaining amount prediction step (S130) can distinguish the loading type by analyzing the occurrence of holes, slope, etc., through data mining of the image information of the feed (1). In the case of (a) of FIG. 6, it can be confirmed that no holes have occurred in the feed (1), and in (b), it can be confirmed that no holes have occurred in the feed (1). The feed remaining amount prediction step (S130) can determine the loading type of the feed (1) by identifying a bending pattern from the image information of the upper surface of the feed (1).

[0053] For example, the feed remaining amount prediction step (S130) can be classified into the loading types of feed (1), such as (a) inclined type, (b) inverted cone type, (c) dome type in FIG. 7, (d) cave type, (e) funnel type, (f) bridge type in FIG. 8, but is not necessarily limited thereto. These loading types of feed (1) are shapes that are naturally formed during the process of loading and discharging feed (1) within the feed bin (10), and may vary depending on the type of feed (1), internal temperature, humidity, etc.

[0054] Additionally, the feed remaining amount prediction step (S130) predicts the amount of feed using distance information based on the loading type of the feed (1). The feed remaining amount prediction step (S130) predicts the amount of feed using image information input from the measuring device (20) and distance information input from the measuring device (20). For example, if the loading type of the feed (1) is sloped, the distance information is determined to be the highest point of the feed (1), and the total amount of feed is calculated. If the loading type of the feed (1) is inverted cone, the distance information is determined to be the lowest point of the feed (1), and the total amount of feed is calculated. In this case, the feed remaining amount prediction step (S130) predicts the amount of feed using a learning algorithm that uses big data for the loading type of the feed (1) and distance information.

[0055] Additionally, the feed remaining amount prediction step (S130) can calculate the volume of the feed (1) and calculate the weight information of the entire feed (1). The feed remaining amount prediction step (S130) calculates the volume of the entire feed (1) according to the loading type and distance information of the feed (1), and calculates the total weight of the feed using the density value of the feed (1). The feed remaining amount prediction step (S130) determines whether to replenish the feed (1) using the calculated feed amount. In this case, it is preferable that a standard feed amount is set according to the feed bin (10). The feed remaining amount prediction step (S130) outputs a warning signal when the feed amount is less than the standard feed amount. The warning signal may be output using a speaker or a flashing light, but is not necessarily limited to this.

[0056] Additionally, the feed remaining amount prediction step (S130) can calculate the amount of feed that can be replenished by calculating the distance between the upper surface of the feed (1) and the injection port of the feed bin (10) when the amount of feed predicted through distance information according to the loading type of the feed (1) is insufficient. This is to determine the amount of replenishment in the case where the feed (1) is solidified after loading, so that when the feed (1) is discharged from the feed bin (10), only the feed (1) at the bottom is discharged and the loading height of the feed (1) at the top is maintained. This is to prevent the feed (1) from leaking out of the feed bin (10) while replenishing the feed (1) when the amount of feed to be replenished is greater than the amount of feed that can be replenished.

[0057] For example, if the height of the upper part of the feed (1) in the feed bin (10) does not change but the lower cross-section is discharged in a '∧' shape, the total amount of feed may be insufficient. The feed remaining amount prediction step (S130) may output a warning signal if the amount of feed available for replenishment is less than the preset value. This is to allow the manager to crush the solidified feed (1) and fill the empty space at the bottom of the feed bin (10). Through this, the abnormal type of feed (1) being loaded in the feed bin (10) can be detected early and addressed, thereby ensuring the supply of normal feed (1).

[0058] Additionally, the feed remaining amount prediction step (S130) may generate a first feed remaining amount model by learning distance information and image information obtained from the measuring device (20), and generate a second feed remaining amount model by learning weight information of the feed (1) inside the feed bin (10) obtained from the measuring device (20). The first feed remaining amount model and the second feed remaining amount model may be learned independently of each other. For example, in the case of a feed bin (10) where weight information inside the feed bin (10) is not obtained, the first feed remaining amount model may be learned. In the case of a feed bin (10) where weight information of the feed bin (10) is obtained, the second feed remaining amount model may be learned.

[0059] In this case, the feed remaining amount prediction step (S130) can modify the first feed remaining amount model by comparing the first feed remaining amount model with the second feed remaining amount model. This allows for the correction of errors by comparing the first feed remaining amount model, which was learned using only distance information and image information inside the feed bin (10), with the second feed remaining amount model, which was learned using only weight information. This is intended to improve accuracy by comparing the first feed remaining amount model, which was learned without weight information, with the second feed remaining amount model, which was learned based on weight information.

[0060]

[0061] Meanwhile, the method for measuring the remaining amount of feed in a feed bin according to an embodiment of the present invention may further include an environmental information acquisition step.

[0062] The environmental information acquisition step acquires at least one environmental information among the temperature, humidity, and gas concentration inside the feed bin (10) detected through the measuring device (20). Here, the measuring device (20) generates environmental information by detecting at least one of the temperature, humidity, and gas concentration inside the feed bin (10). For example, the measuring device (20) may be implemented by including a temperature and humidity sensor and a gas detection sensor. This environmental information is intended to predict the loading type of feed (1) or to determine the spoilage state of the feed (1) according to environmental changes inside the feed bin (10). The loading type or spoilage information for each environmental information can be set in advance. Accordingly, the amount of feed can be calculated more accurately by confirming the loading type or spoilage information of the feed (1) that occurs frequently at a specific temperature or humidity.

[0063]

[0064] Meanwhile, the method for measuring the remaining feed amount in a feed bin according to an embodiment of the present invention may further include a spoilage management step.

[0065] The spoilage management stage generates a spoilage prediction model for the feed (1) using the remaining amount information of the feed (1) and environmental information. The spoilage prediction model refers to a model that predicts the state of spoilage over time based on environmental information such as temperature and humidity of the feed (1) stored inside the feed bin (10). This spoilage prediction model can be learned by analyzing the amount of gas generated according to environmental conditions for various feeds (1). For example, at least one gas among methane (CH4), carbon dioxide (CO2), hydrogen sulfide (H2S), and ammonia (NH3) can be used in the spoilage prediction model.

[0066] In addition, the spoilage management stage may also transmit a warning signal to the manager if the degree of spoilage of the feed (1) exceeds a preset value through a spoilage prediction model. Here, the degree of spoilage refers to an indicator predicted through the spoilage prediction model. The spoilage management stage may also transmit a warning signal to the manager by dividing the degree of spoilage into multiple stages. For example, the degree of spoilage can be classified into stages such as minor, moderate, and severe, but is not necessarily limited to these. Accordingly, the manager can more specifically identify the degree of spoilage of the feed (1) in the feed bin (10).

[0067] In addition, the spoilage management stage may modify the spoilage prediction model by comparing the degree of spoilage in the spoilage prediction model with the degree of spoilage of the actual feed (1). In this case, the spoilage prediction model may receive the inspection results after providing a sample of the feed (1) to a pre-set inspection agency at a pre-set time interval. This allows the spoilage prediction model to be modified by comparing the degree of spoilage of the actual feed (1) sample with the degree of spoilage in the spoilage prediction model. This is intended to improve the accuracy of the spoilage prediction model.

[0068] Additionally, the spoilage management stage may also open and close the cover of the feed bin (10). The spoilage management stage may open the cover of the feed bin (10) if the environmental information inside the feed bin (10) is analyzed and the contamination level exceeds a preset level. In this case, the cover of the feed bin (10) may be connected to a drive motor (not shown) and opened or closed from the feed bin (10). In this case, it is also possible to discharge the internal air to the outside through a fan formed in the measuring device (20). This is to reduce the spoilage rate of the feed (1) when the temperature, humidity, and gas concentration inside the feed bin (10) exceed a preset level of contamination. Accordingly, the spoilage of the feed (1) may be delayed by analyzing the contamination level caused by the feed (1) inside the feed bin (10).

[0069]

[0070] Although the present invention has been described above with reference to preferred embodiments described with reference to the drawings, it is not limited thereto. Accordingly, the present invention should be interpreted by the description of the claims, which is intended to encompass obvious variations derivable from the described embodiments.

Claims

1. A distance information acquisition step of acquiring distance information by measuring the distance to a reference point while the laser is output from a measuring device installed in the feed bin to the feed in the feed bin to mark a reference point; Image information acquisition step of acquiring image information for the feed from the above measuring device while the above reference point is displayed; and A method for measuring the remaining amount of feed in a feed bin, comprising a feed remaining amount prediction step that predicts the remaining amount of feed using distance information to the reference point in the feed bin and image information.

2. In Paragraph 1, A method for measuring the remaining amount of feed in a feed bin, further comprising an environmental information acquisition step of acquiring at least one of the temperature, humidity, and gas concentration inside the feed bin detected through the measuring device.

3. In Paragraph 2, A method for measuring the remaining amount of feed in a feed bin, further comprising a spoilage management step of generating a spoilage prediction model for the feed using the remaining amount information of the feed and the environmental information, and transmitting a warning signal to an administrator if the degree of spoilage of the feed exceeds a preset value through the spoilage prediction model.

4. In any one of paragraphs 1 through 3, The above feed remaining amount prediction step is, A method for measuring the remaining feed in a feed bin by comparing a first remaining feed model generated by learning the distance information and the image information with a second remaining feed model generated by learning the weight information of the feed inside the feed bin, and modifying the first remaining feed model.

5. In any one of paragraphs 1 through 3, A method for measuring the remaining amount of feed in a feed bin, further comprising a spoilage management step of generating a spoilage prediction model for the feed using the above remaining amount information and the above environmental information, and opening the cover of the feed bin using a drive motor when the environmental information is analyzed and the contamination level exceeds a preset level.

6. Includes a communication unit, a processor, a database, and an input / output unit, The above processor is, A management server that predicts the remaining amount of feed using distance information obtained by measuring the distance from a measuring device to a reference point while the measuring device is installed in the feed bin and a laser is emitted from the measuring device to the feed in the feed bin to mark a reference point, and image information regarding the feed while the reference point is marked from the measuring device.

Images