Optical sorter, sorting simulation device, and simulation method related to sorting of objects sorted using an optical sorter
By simulating the sorting results using the light source, sensors, and controller of the optical sorting machine, the problem of insufficient quality control in the existing technology is solved. It enables accurate prediction of yield and quality before sorting, ensuring that the products meet the target quality conditions while improving the yield.
Patent Information
- Application Number
- CN202280038928.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2021-06-02
- Filing Date
- 2022-03-30
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2042-03-30
AI Technical Summary
Existing optical sorting machines have shortcomings in quality control. Users find it difficult to determine the appropriate removal ratio before sorting, resulting in a tradeoff between product quality and yield. This can lead to reduced profits, especially when the rate of defective products mixed in is high.
An optical sorting machine is provided, equipped with a light source, optical sensors and a controller, which predicts the yield and qualified product quantity under target quality conditions by simulating sorting results, allows users to set the final target quality conditions, and adjusts the sorting device and air jet range through the controller to achieve precise control.
It enables accurate prediction of yield and quality before sorting, and can adjust sorting parameters according to the actual mixing situation to ensure that the product meets the target quality conditions, while improving the yield and controlling the removal accuracy of defective products.
Smart Images

Figure CN117460949B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to sorting technology for optical sorting machines. Background Technology
[0002] When operators purchase rice from producers, the rice grading is based on visual inspection and sample testing using grain sorting devices. Regarding grading, as an agricultural product inspection standard, grades one, two, and three are defined in descending order of quality, based on the rate of contamination with substandard products. The higher the grade of rice, the higher the purchase price; therefore, producers aim to ship grade one rice. Furthermore, a higher yield rate results in higher profits; therefore, producers aim for a high yield rate.
[0003] Because of this, optical sorting machines have been used to remove defective rice from the rice before shipment, thereby improving the quality of the rice as a product. Furthermore, Japanese Patent Nos. 5035696 and 5071712 disclose technologies that improve the yield of the product by removing only a portion of the cracked rice, rather than completely removing it. Specifically, Japanese Patent No. 5035696 discloses a sorting machine that removes only a predetermined proportion of rice from the rice determined to be cracked. Japanese Patent No. 5071712 discloses a sorting machine that removes only cracked rice with a crack length exceeding a predetermined threshold.
[0004] However, the optical sorting machines described in Japanese Patent No. 5035696 and Japanese Patent No. 5071712 still have room for improvement in quality control. For example, users must pre-set the degree of cracked rice to be removed from rice that has been determined to be cracked, but users cannot know the quality and yield of the product that can be obtained through sorting before the sorting process, so there is a concern that an appropriate removal ratio cannot be set.
[0005] Furthermore, product quality and yield are generally in a trade-off relationship, so it cannot be said that maximizing quality will necessarily lead to higher profits. For example, if the harvested rice is of poor quality (i.e., the rate of defective products is very high), removing a large number of defective products to improve the grade will significantly reduce the yield, and as a result, it may actually lead to lower profits.
[0006] Because of this situation, there is a need to improve the quality control of optical sorting machines. The above-mentioned problems are not limited to rice, but are common to any kind of granular material (e.g., any grain other than rice, resin, etc.). Summary of the Invention
[0007] This disclosure was made to solve at least a part of the above-mentioned problems, for example, it can be implemented in the following manner.
[0008] According to a first aspect of this disclosure, an optical sorting machine is provided. The optical sorting machine includes: a light source configured to illuminate a transported object to be sorted; an optical sensor configured to detect light illuminating the object from the light source and establishing a correlation with it; a sorting device configured to sort at least a portion of the object to be sorted that is determined to be defective based on a signal acquired by the optical sensor; and a controller configured to control the operation of the optical sorting machine. The controller is configured to: accept candidate inputs of target quality conditions related to the allowable rate of contamination of nonconforming products among the sorted items discharged as qualified products from the optical sorting machine; accept inputs of quality information representing the contamination rate of nonconforming products related to at least a portion of the sorted items; simulate sorting results related to the quantity and / or yield of sorted items discharged as qualified products when sorting is performed by the sorting device in a candidate manner that can achieve the target quality conditions based on the quality information, and output the simulation results; accept inputs of the final target quality conditions to be adopted when sorting is performed by the sorting device; and perform sorting based on sorting control parameters that can achieve the final target quality conditions.
[0009] "Light associated with the sorted item" can be light reflected by the sorted item, i.e., reflected light, or light transmitted through the sorted item, i.e., transmitted light, or both reflected and transmitted light. Alternatively, instead of reflected and / or transmitted light, or based on reflected and / or transmitted light, "light associated with the sorted item" can include light generated by fluorescence when light is irradiated onto the sorted item containing fluorescent material. "Sorted items discharged as qualified items" is not limited to qualified items, but can also include unqualified items that are determined not to require sorting (removal).
[0010] According to this optical sorting machine, users can confirm simulation results related to the quantity and / or yield of sorted items discharged as qualified products under candidate conditions using target quality conditions before starting sorting operation. Therefore, users can determine the final target quality conditions to be adopted based on the simulation results, considering the quantity and / or yield of sorted items discharged as qualified products. Thus, sorted items of the desired quality and yield can be obtained.
[0011] According to the second aspect of this disclosure, based on the first aspect, the controller is configured to control the sorting device in a manner that sorts only a portion of the sorted items determined to be non-conforming. The sorting control parameters include a setpoint related to the sorting rate, which is the proportion of sorted items that should be sorted among the sorted items determined to be non-conforming. According to this approach, the contamination rate of non-conforming items can be directly controlled, thus easily controlling quality and yield in a manner that meets the final target quality conditions.
[0012] According to the third method of this disclosure, based on the first or second method, the sorting control parameters include a threshold for determining non-conforming items. According to this method, the number of sorted items determined to be non-conforming can be controlled, thus enabling control over quality and yield.
[0013] According to the fourth aspect of this disclosure, based on any of the first to third aspects, the sorting device includes a plurality of nozzles capable of selectively injecting air, arranged in a direction orthogonal to the conveying direction of the items to be sorted. The sorting device is configured to selectively inject air from the plurality of nozzles onto the items to be sorted to sort at least a portion of the items determined to be non-conforming. The controller is configured to variably set the air injection range onto the items to be sorted. The sorting control parameters include settings related to the air injection range.
[0014] The "spray range" of air onto the sorted object is not limited to the area of air sprayed at a single instant, but refers to the range within a coordinate system that moves along with the sorted object during transport. For example, the relative positional relationship between the sorted object and the area where air is sprayed changes constantly as the sorted object is transported, but within the coordinate system moving along with the sorted object, the entire coordinate area that the air contacts even at a single instant can be considered the "spray range" of air onto the sorted object. This air spray range can be changed, for example, by changing the spray period. Alternatively, the air spray range can be changed by the number of nozzles among multiple nozzles that should spray air. Specifically, the spray range can be changed by spraying air from one nozzle among multiple nozzles, or by spraying air from one nozzle and the nozzle adjacent to that one nozzle. That is, the "setting related to the air spray range" can be a setting for the spray period, a setting for the allocation of the spray responsibility area related to the detection position of the sorted object in the arrangement direction of the multiple nozzles, or both.
[0015] According to the fourth method, the removal precision of defective products or the frequency of entanglement removal (when air is sprayed on the sorted product to be removed, the sorted product adjacent to the sorted product to be removed is also removed) can be suppressed, thereby controlling the quality and yield.
[0016] According to the fifth aspect of this disclosure, based on any of the first to fourth aspects, the optical sorting machine includes a primary sorting system and a secondary sorting system. Each of the primary and secondary sorting systems is configured to perform optical sorting via a light source, an optical sensor, and a sorting device. The optical sorting mechanism sorts the items fed into the primary sorting system into a first group of items and a second group of items. The first group of items is discharged from the primary sorting system as qualified products. The second group of items is fed into the secondary sorting system, where it is sorted into a third group of items and a fourth group of items. Furthermore, the optical sorting machine is configured to be able to switch the discharge destination of the third group of items between re-feeding into the primary sorting system and discharge as qualified products, and to switch the discharge destination of the fourth group of items between discharge as qualified products and discharge as unqualified products. The sorting control parameters include settings related to the discharge destination of the third group of items and / or the fourth group of items. According to this method, quality and yield can be controlled by changing the discharge destination of the third and / or fourth sorted groups.
[0017] According to the sixth aspect of this disclosure, based on any of the first to fifth aspects, the controller is configured to detect, during sorting operation, the level of contamination of non-conforming products in the sorted materials within a specified period based on signals acquired by an optical sensor, and to adjust sorting control parameters based on the contamination level. The actual contamination level of non-conforming products may not be consistent with quality information, but according to this aspect, the sorting control parameters can be adjusted based on the actual contamination level of non-conforming products. Therefore, the target quality conditions can be achieved more reliably.
[0018] According to the seventh aspect of this disclosure, based on the sixth aspect, the controller is configured to calculate the sorting results related to the target quality conditions within a specified period based on the contamination status during sorting operation, and to change the sorting control parameters based on the calculated sorting results. According to this approach, the quality of the sorted items discharged as qualified items from the optical sorting machine can be calculated based on the actual contamination status of non-conforming items and the setting of the sorting control parameters. Furthermore, during sorting operation, the sorting control parameters can be changed based on the achievement status of the final target quality conditions obtained from the calculation results. Therefore, feedback control can be performed to make the actual sorting process result approximate the final target quality conditions.
[0019] According to the eighth method of this disclosure, based on the seventh method referencing the fifth method, the controller is configured to calculate the sorting results related to the target quality conditions within a specified period during sorting operation, based on signals acquired in each of the primary and secondary sorting systems. The sorted material discharged as qualified from the primary sorting system is obtained by subtracting the sorted material input into the secondary sorting system from the sorted material input into the primary sorting system. According to this method, the quality of the sorted material discharged as qualified from the primary sorting system can be more accurately determined based on the actual quality of the sorted material input into both the primary and secondary sorting systems.
[0020] According to the ninth method of this disclosure, based on the seventh or eighth method, the controller is configured to change the sorting control parameters in a direction that moves the quality represented by the calculated sorting result closer to the final target quality condition when the quality indicated by the calculated sorting result is lower than the final target quality condition by a specified degree. According to this method, the final target quality condition can be reliably achieved.
[0021] According to the tenth embodiment of this disclosure, based on any of the seventh to ninth embodiments, the controller is configured to change the sorting control parameters in a direction that increases the yield of sorted items discharged as qualified products when the quality indicated by the calculated sorting result is higher than the final target quality condition by a specified degree. According to this embodiment, the yield can be increased while achieving the final target quality condition.
[0022] According to the eleventh aspect of this disclosure, a sorting simulation apparatus is provided. This sorting simulation apparatus includes a controller. The controller is configured to: when sorting the items using an optical sorting machine, accept inputs of candidate target quality conditions related to the allowable rate of contamination of non-conforming items among the sorted items discharged as qualified items from the optical sorting machine; accept inputs of quality information representing the contamination rate of non-conforming items related to at least a portion of the sorted items; simulate, based on the quality information, sorting results related to the quantity and / or yield of sorted items discharged as qualified items when sorting is performed by the optical sorting machine in a manner that can achieve the candidate target quality conditions; and output simulation results. According to this sorting simulation apparatus, the same effect as in the first aspect can be obtained.
[0023] According to the twelfth aspect of this disclosure, a simulation method related to the sorting of items using an optical sorting machine is provided. The method includes the following steps: a user determining candidates for target quality conditions related to the allowable rate of contamination of non-conforming items among the sorted items discharged as qualified items from the optical sorting machine; acquiring quality information representing the contamination rate of non-conforming items related to at least a portion of the sorted items; simulating sorting results related to the quantity and / or yield of sorted items discharged as qualified items when sorting is performed by the optical sorting machine in a manner capable of achieving the target quality conditions based on the quality information, and presenting this result to the user; a user determining the final target quality conditions to be adopted when sorting by the optical sorting machine; and a step of having the optical sorting machine perform sorting based on sorting control parameters capable of achieving the final target quality conditions. According to this method, the same effects as the first aspect can be obtained.
[0024] According to the thirteenth aspect of this disclosure, an optical sorting machine is provided. The optical sorting machine includes: a light source configured to illuminate a transported object to be sorted; an optical sensor configured to detect light illuminating the object from the light source and establishing a correlation with the object to be sorted; a sorting device configured to sort at least a portion of the object to be sorted that is determined to be defective based on a signal acquired by the optical sensor; and a controller configured to control the operation of the optical sorting machine. The controller is configured to: accept input of quality information representing the contamination rate of nonconforming products related to at least a portion of the sorted items; for each of multiple candidates of target quality conditions related to the allowable contamination rate of nonconforming products in the sorted items discharged as qualified products from the optical sorter; simulate, based on the quality information, the sorting results related to the quantity and / or yield of sorted items discharged as qualified products when sorted by the optical sorter in a candidate manner that can achieve the target quality conditions; determine the final target quality conditions to be adopted when sorted by the sorting device based on the simulation results; and perform sorting based on sorting control parameters that can achieve the final target quality conditions.
[0025] Multiple candidate target quality conditions can be pre-determined and stored in the optical sorting machine's memory, or they can be input by the user and processed by the controller. The controller can either determine the candidate with the highest yield as the final target quality condition, or it can calculate the projected sales revenue by multiplying the quantity of sorted items discharged as qualified products by a pre-determined unit price, and then determine the candidate with the highest projected sales revenue as the final target quality condition. The controller can either automatically execute the sorting after determining the final target quality condition, or it can output the simulation results and / or the projected sales revenue to an image display device and prompt the user, executing the sorting after the user's instruction.
[0026] Based on this optical sorting machine, the controller can set optimal sorting control parameters to achieve the highest possible yield or product sales forecast. It can also add any of the second to tenth methods to the thirteenth method.
[0027] According to the fourteenth aspect of this disclosure, an optical sorting machine is provided. This optical sorting machine includes: a light source configured to illuminate a transported object to be sorted; an optical sensor configured to detect light illuminating the object from the light source and establishing a correlation with it; a sorting device for sorting at least a portion of the object to be sorted that is determined to be defective based on a signal acquired by the optical sensor; and a controller configured to control the operation of the optical sorting machine. The controller is configured to receive inputs related to a target quality condition concerning the allowable rate of defective products in the object to be sorted and discharged as qualified products from the optical sorting machine. During sorting operation, the controller detects the degree of defective product contamination in the object to be sorted within a specified period based on the signal acquired by the optical sensor, and can change the sorting control parameters based on the contamination degree and the target quality condition. According to this optical sorting machine, sorting control parameters capable of achieving the target quality condition can be set according to the actual degree of defective product contamination. Therefore, the target quality condition can be reliably achieved. Any of the seventh to tenth aspects can also be added to the fourteenth aspect. Attached Figure Description
[0028] Figure 1 This is a block diagram illustrating the process of sorting items in an optical sorting machine according to one embodiment of this disclosure.
[0029] Figure 2 This is a schematic diagram showing the simplified structure of a primary sorting system and a secondary sorting system.
[0030] Figure 3 It is a flowchart illustrating the sorting process involved in one implementation method.
[0031] Figure 4 It is a flowchart illustrating the process of parameter change handling involved in one implementation method.
[0032] Figure 5 This is a diagram representing an example of a user interface used to accept target quality conditions and output simulation results.
[0033] Figure 6 This is a schematic diagram illustrating an example of setting the spray range of each nozzle.
[0034] Figure 7 This is a diagram illustrating an example of a method that calculates sorting results based on signals acquired by optical sensors. Detailed Implementation
[0035] Figure 1 This is a schematic diagram showing a simplified structure of an optical sorting machine (hereinafter referred to as the sorting machine) 20 as one embodiment of the present disclosure. In this embodiment, the sorting machine 20 is used to sort out defective products (meaning not whole grains, such as immature grains, colored grains, foreign objects (e.g., small stones, mud, glass fragments, etc.)) from rice grains (more specifically, brown rice), which is an example of the sorted material 90.
[0036] like Figure 1 As shown, the sorting machine 20 is configured to receive the material to be sorted 90 from the conveyor line 11. The conveyor line 11 transports the brown rice (the material to be sorted 90) that has been dehulled by a dehuller (not shown) from the dehuller to the sorting machine 20.
[0037] A measuring device 12 is disposed midway along the conveyor line 11. The measuring device 12 includes a sample collection mechanism, a camera, and a judgment unit. The sample collection mechanism automatically collects a portion of the sorted items 90 conveyed via the conveyor line 11 as a sample. The sample collection mechanism can use any known mechanism. For example, the sample collection mechanism can be a chute having an opener / closer that is connected to the conveyor line 11. In this case, when the opener / closer is opened, a portion of the sorted items 90 on the conveyor line 11 can fall onto the chute and be supplied to the measuring device 12. Alternatively, the sample collection mechanism can also be a robotic arm.
[0038] The camera of the measuring device 12 captures image data of the collected sample. The judgment unit of the measuring device 12 measures the quality information of the sorted item 90 based on the image data. Here, quality information refers to the contamination rate of non-conforming items in the sample (in this embodiment, by weight). In this embodiment, non-conforming items are defined according to the agricultural product inspection standards stipulated by the Agricultural Product Inspection Law. Specifically, non-conforming items refer to damaged grains, dead rice, discolored grains, foreign grains, and foreign objects. Damaged grains refer to damaged grains, such as broken grains and fragments. Foreign grains refer to grains other than brown rice. Foreign objects refer to anything other than grains.
[0039] Specifically, the determination unit determines for each grain of rice whether it is a whole grain or a defective product (more specifically, what type of defective product). This determination is performed, as is known, for example, by comparing the grayscale value of image data with a preset threshold. The function of the determination unit is implemented, for example, by the CPU executing a predetermined program stored in memory. In this embodiment, the sample measured by the measuring device 12 is returned to the conveyor line 11.
[0040] A grain detector can also be used as such a camera and determination unit. Grain detectors are well known, for example, those described in Japanese Patent Application Publication No. 2016-125867, Japanese Patent Application Publication No. 2016-118455, or U.S. Patent Application Publication No. 2017 / 350825. These applications are incorporated herein by reference in their entirety.
[0041] In this embodiment, the measuring device 12 is electrically connected to the controller 25 of the sorting machine 20, and the quality information acquired by the measuring device 12 is output to the controller 25. The controller 25 controls the overall operation of the sorting machine 20. The functions of the controller 25 can be implemented by a CPU executing a prescribed program, by a dedicated circuit, or by a combination thereof. Each function of the controller 25 can also be implemented by a single integrated device. For example, each function of the controller 25 can be implemented by a single CPU. Alternatively, each function of the controller 25 can be distributed across at least two devices. For example, the controller 25 can also include a dedicated controller for the primary sorting system 20a, a dedicated controller for the secondary sorting system 20b, and a controller that encompasses them.
[0042] Alternatively, the sorting machine 20 may have a measuring device 12 instead of having the measuring device 12 installed on the conveyor line 11. In this case, the measuring device 12 is positioned upstream of the flow of the sorted material 90 in the sorting machine 20 compared to the primary sorting system 20a.
[0043] like Figure 1 As shown, the sorting machine 20 includes a primary sorting system 20a and a secondary sorting system 20b. In this embodiment, the primary sorting system 20a and the secondary sorting system 20b have the same device structure. Therefore, the primary sorting system 20a and the secondary sorting system 20b will be used as examples below. Figure 2 A brief description of the structure of the primary sorting system 20a is provided. For example... Figure 2 As shown, the primary sorting system 20a includes light sources 31 and 32, optical sensors 41 and 42, sorting device 50, storage tank 71, feeder 72, chute 73, qualified product discharge trough 74 and unqualified product discharge trough 75.
[0044] Storage tank 71 temporarily stores the sorted items 90. Feeder 72 supplies the sorted items 90 stored in storage tank 71 onto a chute 73, which is an example of a sorted item transfer unit. The sorted items 90 supplied onto the chute 73 slide downwards on the chute 73 and fall from the lower end of the chute 73. The chute 73 has a predetermined width that allows a number of sorted items 90 to fall simultaneously. In the following description, the direction in which the sorted items 90 are transferred after falling from the chute 73 (in other words, the falling direction of the sorted items 90) is also referred to as the transfer direction D1. Furthermore, the direction orthogonal to the transfer direction D1 (in other words, the width direction of the chute 73) is also referred to as the orthogonal direction D2.
[0045] Light source 31 is disposed on one side (also called the front side) of the transfer path 95 of the sorted item 90 (in other words, the falling trajectory of the sorted item 90), and light source 32 is disposed on the other side (also called the rear side) of the transfer path 95 of the sorted item 90. Light sources 31 and 32 respectively irradiate light 33 and 34 onto the sorted item 90 (i.e., the sorted item 90 that has slid down from the slide 73) being transferred on the transfer path 95. In this embodiment, light sources 31 and 32 each include: a plurality of LEDs emitting red light; a plurality of LEDs emitting green light; a plurality of LEDs emitting blue light; and a plurality of LEDs emitting near-infrared light. However, the specifications of light sources 31 and 32 (e.g., number, light emission form, wavelength range of light 33 and 34, etc.) are not particularly limited. For example, only LEDs emitting visible light or LEDs emitting near-infrared light may be used as light sources 31 and 32. Alternatively, LEDs emitting near-infrared light may be disposed only on one side of the front and rear sides. Alternatively, one of the light sources, 31 or 32, can be omitted.
[0046] Optical sensor 41 is disposed on the front side, and optical sensor 42 is disposed on the rear side. Optical sensors 41 and 42 detect light that is irradiated by light sources 31 and 32 and associated with the sorted item 90. Specifically, the front optical sensor 41 can detect light 33 irradiated by the front light source 31 and reflected by the sorted item 90, and light 34 irradiated by the rear light source 32 and transmitted through the sorted item 90. The rear optical sensor 42 can detect light 34 irradiated by the rear light source 32 and reflected by the sorted item 90, and light 33 irradiated by the front light source 31 and transmitted through the sorted item 90.
[0047] In this embodiment, optical sensors 41 and 42 are a color CCD sensor and a near-infrared sensor, respectively, and each has multiple light-receiving elements arranged in a straight line. These light-receiving elements are arranged along an orthogonal direction D2 (i.e., the width direction of the slide 73). Therefore, optical sensors 41 and 42 can simultaneously capture images of a plurality of sorted items 90 transported across a predetermined width of the slide 73. The specifications of optical sensors 41 and 42 are not particularly limited and can be arbitrarily determined based on the specifications of light sources 31 and 32. Alternatively, one of the optical sensors 41 or 42 may be omitted.
[0048] The analog signals from the outputs of optical sensors 41 and 42, representing the intensity of the detected light, are amplified by an AC / DC converter (not shown) at a specified gain and converted into digital signals. These digital signals (i.e., the grayscale values corresponding to the analog signals) are then input to the controller 25 (see reference 25). Figure 1 The controller 25 identifies defective items in the sorted items 90 based on the detection results (i.e., images) of the input light. Specifically, it compares the grayscale value (i.e., image density) of the image corresponding to a color (wavelength) predetermined for each type of defective item with a threshold predetermined for each type of defective item (hereinafter also referred to as the density threshold), and determines whether the sorted item 90 is a whole grain or a defective item based on their magnitude relationship. Alternatively, by the same comparison, it determines whether each pixel of the image representing the sorted item 90 represents a defective portion. This determination can use at least one image based on reflected light 33, transmitted light 34, light synthesized from reflected light 33 and transmitted light 34 detected by the optical sensor 41, and light synthesized from reflected light 34, transmitted light 33, light synthesized from reflected light 33 and transmitted light 34 detected by the optical sensor 42. In addition, for a specific type of defective item, a threshold related to the size of the defective portion (pixels representing defects) (hereinafter referred to as the size threshold) can also be set. For example, for broken grains, a size threshold related to the crack length can be set, and only sorted items 90 with crack lengths exceeding the size threshold can be identified as broken grains. Similarly, for fragments, a size threshold related to grain size (e.g., area or length) can be set, and sorted items 90 with grain sizes below the size threshold can be identified as fragments. Furthermore, for any type of nonconforming product other than fragments, a size threshold can be set, and only sorted items 90 with defective portions exceeding the size threshold can be identified as nonconforming products.
[0049] The sorting device 50 sprays air toward at least a portion of the sorted items 90 that have been determined to be defective, thereby sorting the sorted items 90. Specifically, the sorting device 50 includes a plurality of nozzles 51 and a number of valves 52 corresponding to the number of nozzles 51 (in this embodiment, the same number as the number of nozzles 51, but it may also be different from the number of nozzles 51). The plurality of nozzles 51 are arranged along an orthogonal direction D2 (i.e., the width direction of the slide 73). As the valves 52, for example, piezoelectric valves, solenoid valves, etc., can be used.
[0050] Multiple nozzles 51 are connected to a compressor (not shown) via multiple valves 52. The valves 52 are selectively opened according to a control signal from the controller 25, thereby selectively injecting air 53 towards the sorted item 90 from the multiple nozzles 51. More specifically, each of the multiple nozzles 51 is associated with a spraying responsibility area related to a detection position of the sorted item 90 in the orthogonal direction D2. Furthermore, each of the multiple nozzles 51 injects air 53 when a defective item (or a defective portion of a defective item) is located within its corresponding spraying responsibility area, or when a predetermined position (e.g., the center) of a defective item (or a defective portion of a defective item) is located within its corresponding spraying responsibility area. Thus, each of the multiple nozzles 51 is assigned a range of air 53 to be sprayed in relation to a detection position of the sorted item 90 in the orthogonal direction D2. In practice, the spraying responsibility area is defined by the position of the orthogonal direction D2 on the image input to the controller 25.
[0051] Air 53 is sprayed onto all or part of the sorted items 90 that are determined to be non-conforming (the specific part to which air 53 is sprayed will be described later). The sorted items 90 that have been sprayed with air 53 are blown away by the air 53, detached from the drop track (i.e., the transfer path 95) from the chute 73, and guided to the non-conforming item discharge tank 75. Figure 2 The sample 90 is designated as the sorted item 91. On the other hand, air 53 is not injected into the sorted item 90 that is determined to be a whole particle. Therefore, the whole particle does not change its falling trajectory and is guided as a qualified product to the qualified product discharge trough 74. Figure 2 The "qualified product" (represented as sorted product 92) is shown in the diagram. As explained above, the "qualified product" guided to the qualified product discharge tank 74 may include not only whole particles but also loose particles that were not sprayed by air 53. Furthermore, if the spraying of air 53 causes the surrounding sorted product 90 to be removed to be removed along with other sorted products (the aforementioned entanglement removal), then the sorted product 90 that should be discharged as qualified products (i.e., whole particles) will be discharged as unqualified products. Therefore, the "unqualified product" guided to the unqualified product discharge tank 75 may also include whole particles.
[0052] Alternatively, the transport path of the sorted items 90 can be altered by injecting air 53 towards the sorted items 90 sliding on the slide 73, instead of injecting air 53 towards the sorted items 90 after they fall from the slide 73. Furthermore, a belt conveyor can be used instead of the slide 73 as the sorted item transport unit. In this case, air can be injected towards the sorted items falling from one end of the belt conveyor. Alternatively, air can be injected towards the sorted items being transported on the belt conveyor.
[0053] This section will explain how to return to... Figure 1 The sorted material 90 discharged as qualified products from the primary sorting system 20a (more specifically, the qualified product discharge tank 74) is stored in the qualified product hopper 21. The sorted material 90 in the qualified product hopper 21 is supplied to equipment installed in its subsequent process (e.g., a metering and packaging device). On the other hand, the sorted material 90 discharged as unqualified products from the primary sorting system 20a (more specifically, the unqualified product discharge tank 75) is fed into the secondary sorting system 20b. The sorted material 90 fed into the secondary sorting system 20b is sorted in the same way as in the primary sorting system 20a.
[0054] In this embodiment, the sorting machine 20 is configured to switch the discharge destination of the sorted material 90 discharged as qualified product from the secondary sorting system 20b via the switching valve 23. Specifically, this discharge destination can be adjusted for re-feeding into the primary sorting system 20a. Figure 1 (indicated by solid arrows) and discharge as qualified products ( Figure 1 (Indicated by a dashed arrow), the discharge destination can be switched between the discharge point and the qualified product hopper 21. Users can perform this switching operation using the user interface. Normally, this discharge destination is set to re-feeding into the primary sorting system 20a. According to this setting, the sorted material 90 that has been removed in the primary sorting system 20a can be re-feeded into the primary sorting system 20a and ultimately recycled as qualified product. Therefore, the yield of the sorted material 90 recycled as qualified product can be improved.
[0055] Furthermore, the sorting machine 20 is configured to switch the discharge destination of the sorted material 90 discharged as defective products from the secondary sorting system 20b via the switching valve 24. Specifically, this discharge destination can be switched from the discharge destination of qualified products (…). Figure 1 (Indicated by dashed arrows), namely, discharge into hopper 21 for qualified products and discharge as unqualified products. Figure 1 (Indicated by a solid arrow in the image), this allows switching between discharge to container 22 and discharge to non-conforming products. Users can perform this discharge destination switching operation using the user interface. Normally, the discharge destination is set to discharge to container 22.
[0056] In this embodiment, the sorting accuracy of the secondary sorting system 20b is set to be lower than that of the primary sorting system 20a. That is, the contamination rate of unqualified products discharged from the secondary sorting system 20b as qualified products is higher than that of the sorted product 90 discharged as qualified products from the primary sorting system 20a. This setting can be achieved, for example, by setting the sensitivity of the secondary sorting system 20b to that of the unqualified products to be lower than that of the primary sorting system 20a (i.e., by adjusting the concentration threshold and / or size threshold). With this setting, the yield can be further improved. However, the sorting accuracy of the secondary sorting system 20b can also be set to be equal to that of the primary sorting system 20a.
[0057] The sorting machine 20 described above has the function of performing sorting in a manner that the quality of the sorted items 90 that are recovered as qualified products (specifically, the mixing rate of each type of non-qualified product) meets the quality required by the user. Details of this function will be explained below. Figure 3 This is a flowchart illustrating an example of the sorting process performed by the sorting machine 20. In this process, the controller 25 first receives input of the quality information of the raw material, i.e., the material 90 to be sorted, which is fed into the primary sorting system 20a (step S110). In this embodiment, this quality information is input from the measuring device 12 to the controller 25. That is, the controller 25 receives input of the contamination rate of the sample measured in the measuring device 12. In this embodiment, the controller 25 receives input of the contamination rate (by weight) of damaged grains, dead rice, discolored grains, different types of grains (more specifically, rice, wheat, and other different types of grains each), and foreign matter.
[0058] In an alternative embodiment, quality information can also be input by the user through a user interface. In this case, the user can also use a grain detector to measure the quality of the sample and input the measurement result. Alternatively, the user can visually confirm the quality of the sample and input the confirmation result. Furthermore, when the mixing rate input from the measuring device 12 to the controller 25 is given as a grain number ratio, the controller 25 can also calculate the weight ratio using the specific gravity set according to the type of each nonconforming item.
[0059] Next, the controller 25 receives basic information about the raw materials input by the user through the user interface (not shown) of the sorting machine 20 (step S120). This basic information may include input amount, variety, properties (moisture, etc.).
[0060] Next, the controller 25 accepts the candidate target quality conditions input by the user (step S130). The target quality conditions refer to the conditions related to the allowable amount of non-conforming products mixed in with the sorted material 90 that is discharged from the sorting machine 20 as qualified products. In other words, it is the quality condition that the user expects for the sorted material 90 that is discharged from the sorting machine 20 as qualified products. In the above-mentioned agricultural product inspection standards, grades are specified as first grade, second grade, and third grade. The higher the grade (i.e., the smaller the grade number), the higher the quality of the product (sorted material 90), and the higher the price it is traded. Each grade specifies the upper limit value of the individual mixing rate of dead rice, colored grains, foreign grains, and foreign objects, as well as the upper limit value of the total mixing rate of damaged grains, dead rice, colored grains, foreign grains, and foreign objects (i.e., non-whole grains).
[0061] Figure 5 This diagram illustrates an example of a user interface used to accept target quality conditions. The illustrated user interface 60 is a touch panel-type graphical user interface. The raw material quality display area 61 of the user interface 60 displays the quality information received by the controller 25 in step S110. In this embodiment, in addition to displaying quality information, the basic information received in step S120 is also displayed in the raw material quality display area 61. Figure 5 In the example, the input quantity of 300 kg received in step S120 is displayed in the raw material quality display area 61. In step S130, the user can input candidates for the target quality conditions through the target quality input area 62. The target quality input area 62 has a selectable grade input area 63 and a blending rate input area 64.
[0062] In the grade input area 63, users can enter the grade number according to the agricultural product inspection standards. Specifically, users can select first-grade, second-grade, third-grade, and intermediate grades as candidates for the target quality condition by pressing the "+" or "-" button a certain number of times. Figure 5 The text shows the selection of the level input area 63, and the selection of the first level.
[0063] When the mixing rate input area 64 is selected from the grade input area 63 and the mixing rate input area 64, the user can enter any upper limit value for the mixing rate for each type of nonconforming product as a candidate for the target quality condition in the mixing rate input area 64. Specifically, the user can increase or decrease the value of the upper limit value for the mixing rate by pressing the "+" or "-" button. The currently set upper limit value for the mixing rate is displayed between the "+" and "-" buttons.
[0064] In this embodiment, the grade input area 63 and the contamination rate input area 64 are configured to be interconnected. Specifically, if any grade is selected in the grade input area 63, the contamination rate upper limit value for each type of nonconforming product corresponding to the selected grade is displayed in the contamination rate input area 64. Figure 5 In the mixing rate input area 64, the upper limit value of the mixing rate for each type of nonconforming product corresponding to Grade 1 selected in the grade input area 63 is displayed. Furthermore, if any upper limit value of the mixing rate is entered in the mixing rate input area 64 for each type of nonconforming product, the grade corresponding to that input is displayed in the grade input area 63. For example, if the input includes an upper limit value of the mixing rate corresponding to Grade 1 and an upper limit value of the mixing rate corresponding to Grade 2 based on the type of nonconforming product, the overall number of conforming products is equivalent to Grade 2; therefore, the same display is performed in the grade input area 63 as when Grade 2 is selected.
[0065] Next, the controller 25 simulates the sorting results related to the amount of sorted items 90 discharged from the sorting machine 20 as qualified products and the yield rate when the sorting machine 20 sorts the items in a manner that can achieve the target quality conditions accepted in step S130, and outputs the simulation results (step S140).
[0066] Specifically, the controller 25 first sets a control target value for each type of nonconforming product based on the candidates for the target quality condition. This control target value is set below the upper limit of the mixing rate corresponding to the candidate for the target quality condition. For example, when selecting grade one, the upper limit of the mixing rate of dead rice equivalent to grade one is 7%. Therefore, the control target value is set to a value below 7%. In this embodiment, the control target value is set to the same value as the upper limit of the mixing rate corresponding to the candidate for the target quality condition. In an alternative embodiment, the control target value is set by multiplying the upper limit of the mixing rate corresponding to the candidate for the target quality condition by a safety factor. The safety factor is a coefficient used to provide a margin for reliably achieving the candidate for the target quality condition, and is a positive number less than 1. The safety factor can be any value greater than 0.7 and less than 1. By preventing the safety factor from becoming too small, the decrease in yield can be suppressed.
[0067] Next, the controller 25 calculates the quantity and yield of sorted items 90 discharged as qualified products from the sorting machine 20 when sorting is performed in a manner that exactly achieves the control target value for each type of nonconforming product (i.e., in a manner that makes the sorting result consistent with the control target value). For example, if the proportion of dead rice in the quality information is 10% and the control target value for dead rice is 7%, the controller calculates the quantity and yield of sorted items 90 discharged as qualified products from the sorting machine 20 when only a portion of all dead rice input into the sorting machine 20 is sorted (removed) so that the proportion of dead rice in the sorted items 90 discharged as qualified products from the sorting machine 20 is 7%. That is, the calculation is performed without over-sorting that exceeds the control target value. For types of nonconforming products where the control target value can be achieved without sorting at all, the calculation is performed as if no sorting (removal) is performed.
[0068] Next, the controller 25 outputs the calculation results, i.e., the simulation results, to the user interface 60. Figure 5 In the inference value display area 65 used to display simulation results, the amount of sorted material 90 discharged from the sorter 20 as qualified products is displayed as "product quantity", and the yield rate is also displayed. The product quantity is calculated based on the input quantity received in step S120.
[0069] In step S140, by displaying the simulation results in this way, the user can know what sorting results (i.e., product quantity and yield) will be obtained if the candidate target quality conditions entered in step S130 are used for sorting before starting the sorting process. If the product quantity and yield displayed in step S140 are not within the user's desired range, the user can also enter other candidates for the target quality conditions. In this case, the controller 25 executes steps S130 and S140 again, displaying the product quantity and yield when sorting was performed using other candidates for the target quality conditions. Through this operation, the user can confirm multiple combinations of target quality conditions with product quantity and yield, and determine the target quality conditions corresponding to the desired combination of target quality conditions with product quantity and yield as the final target quality conditions to be used when sorted by the sorting machine 20.
[0070] In an alternative embodiment, the controller 25 may also display the simulation results for each of the multiple candidates for the target quality condition, simultaneously displaying the simulation results associated with each of the multiple candidates. In this case, the multiple candidates may be predetermined (e.g., they may be determined as first-class, second-class, and third-class), or the sorting machine 20 may have a user interface that allows the user to input multiple candidates on a single screen. In a further alternative embodiment, only the product quantity and yield may be displayed.
[0071] Next, the controller 25 receives the final target quality condition input by the user (step S150). Then, the controller 25 sets the sorting control parameters that can achieve the final target quality condition (step S160).
[0072] The sorting control parameters include a set value (hereinafter referred to as the sorting rate) related to the proportion of sorted items 90 that should be sorted (i.e. should be removed by air jet) among the sorted items 90 that are determined to be non-conforming.
[0073] Based on the quality information and the control target value corresponding to the final target quality conditions, the sorting rate setting value is set for each type of nonconforming product. Specifically, the sorting rate that exactly achieves the control target value corresponding to the final target quality conditions (i.e., the sorting rate when the sorting result is consistent with the control target value) is calculated based on the quality information and the control target value. For example, if the contamination rate of dead rice is 10% based on the quality information, the control target value related to dead rice is 7%, the input amount is 300 kg, and the simulated product quantity is 285 kg, the contamination amount of dead rice in the input amount becomes 300 kg × 10% = 30 kg, and the allowable contamination amount of dead rice in the product becomes 285 kg × 7% = 19.95 kg. Therefore, the amount of dead rice to be removed is 30 kg - 19.95 kg = 10.05 kg, and the sorting rate that exactly achieves the control target value becomes 10.05 kg ÷ 30 kg = 33.5%. Regarding the primary sorting system 20a, the sorting rate setpoint is set to the same value as the sorting rate that exactly achieves the control target value, or to a value obtained by multiplying the sorting rate by a safety factor (a value greater than 1). In this embodiment, the sorting rate setpoint of the secondary sorting system 20b is set such that the mixing rate of each type of non-conforming item among the sorted items 90 discharged as qualified items from the secondary sorting system 20b is consistent with the raw material quality (i.e., the mixing rate based on the quality information received in step S110).
[0074] Furthermore, the sorting control parameters include a threshold for determining nonconforming items, namely, the aforementioned threshold (concentration threshold, or concentration threshold and size threshold) predetermined according to the type of each nonconforming item. The threshold for determining nonconforming items specifies the sensitivity for nonconforming items. In this embodiment, regardless of the quality information and the control target value corresponding to the final target quality condition, the threshold for determining nonconforming items is set to an initial value. The initial value is predetermined through experiments, etc.
[0075] Furthermore, the sorting control parameters include settings related to the spray range of the air 53 used to remove defective items. Here, the air spray range refers to the range in the coordinate system that moves along with the sorted items 90 during transport. Settings related to the spray range may include the setting of the air 53 spray period (i.e., the duration of continuous spraying). A longer spray period results in a larger spray range of air 53 onto the sorted items 90 in the transport direction D1, thus enabling more reliable removal of defective items; however, on the other hand, the probability of entanglement removal increases.
[0076] Furthermore, the settings related to the spray range can include the allocation of the spray responsibility range for the detection position of the sorted item 90 in the arrangement direction (orthogonal direction D2) of the plurality of nozzles 51. Hereinafter, the setting of the spray responsibility range allocation will be specifically explained by assuming that the center of the defective part in the defective item is located at the specified detection position, and air 53 is sprayed from the nozzle 51 that includes the detection position within the spray responsibility range.
[0077] Figure 6 This is a schematic diagram illustrating an example of how the spray coverage area is allocated. Figure 6 For ease of explanation, only three nozzles 51 arranged in the middle of the orthogonal direction D2 will be designated as nozzles 51a to 51c. Valves 52a to 52c are connected to nozzles 51a to 51c respectively. Figure 6 In this context, each grid represents a pixel that constitutes the image 80 input to the controller 25. For example... Figure 6 As shown, nozzles 51a to 51c are respectively associated with spray control ranges 83a to 83c. Figure 6 In the diagram, the correspondence between nozzles 51a and 51c and their associated spray ranges 83a and 83c is represented by a dashed line, while the correspondence between nozzle 51b and its associated spray range 83b is represented by a dashed line. For example... Figure 6 As shown, the two spray coverage areas 83a and 83b corresponding to the two adjacent nozzles 51a and 51b overlap in the overlapping region 84a. Similarly, the two spray coverage areas 83b and 83c corresponding to the two adjacent nozzles 51b and 51c overlap in the overlapping region 84b.
[0078] When the center of the defective portion is located at pixel 82, pixel 82 belongs only to the spraying area 83b, so air 53 is sprayed only from the nozzle 51b corresponding to the spraying area 83b. On the other hand, when the center of the defective portion is located at pixel 81, pixel 81 belongs to the overlapping area 84a (i.e., it belongs to both spraying areas 83a and 83b), so air 53 is sprayed from the two nozzles 51a and 51b corresponding to the spraying areas 83a and 83b. In this way, depending on the allocation of the spraying areas, it is determined whether air 53 is sprayed from one of the multiple nozzles 51, or from that one nozzle 51 and the nozzle 51 adjacent to that one nozzle 51. The overlapping area can be variably set with any number of pixels greater than zero. If air 53 is sprayed from the two adjacent nozzles 51, the spraying range of air 53 on the sorted item 90 in the orthogonal direction D2 becomes larger, so the defective items can be removed more reliably, but on the other hand, the probability of entanglement removal increases.
[0079] In this embodiment, regardless of the quality information and the control target value corresponding to the final target quality condition, the settings related to the spray range are all set to initial values. The initial values are predetermined through experiments or the like.
[0080] Furthermore, the sorting control parameters include settings related to the discharge destinations of the sorted items 90 discharged as qualified products from the secondary sorting system 20b and the sorted items 90 discharged as unqualified products from the secondary sorting system 20b (i.e., settings of switching valves 23 and 24). In this embodiment, regardless of the quality information and the control target value corresponding to the final target quality condition, the settings related to the discharge destination are set to the initial state (re-input of the sorted items 90 discharged as qualified products into the primary sorting system 20a, and discharge of the sorted items 90 discharged as unqualified products into the unqualified product container 22). In addition, switching valves 23 and 24 can be omitted. When only switching valve 23 is omitted, the settings related to the discharge destination become the settings related to the discharge destination of the sorted items 90 discharged as unqualified products. When only switching valve 24 is omitted, the settings related to the discharge destination become the settings related to the discharge destination of the sorted items 90 discharged as qualified products.
[0081] Furthermore, the sorting control parameters include flow rate (the amount supplied from the feeder 72 to the chute 73). In this embodiment, regardless of the quality information and the control target value corresponding to the final target quality condition, the setting related to this flow rate is set to an initial value. The initial value is determined in advance through experiments, etc. The larger the flow rate, the greater the processing capacity of the sorter 20, but on the other hand, the gap between the sorted items 90 falling from the chute 73 becomes smaller, thus increasing the probability of entanglement removal.
[0082] As explained above, in this embodiment, when setting sorting control parameters that achieve the final target quality conditions, the adjustment for achieving the final target quality conditions is performed solely by adjusting the sorting rate setpoint. However, at least one of the other sorting control parameters mentioned above can be adjusted in addition to adjusting the sorting rate setpoint. Specifically, at least one of the following can be changed based on the quality information and the control target value corresponding to the final target quality conditions: a threshold (concentration threshold, or concentration threshold and size threshold), the size of the spraying period and / or the overlapping area, the discharge destination, and the flow rate. Furthermore, the controller 25 can also change the initial value or initial state related to at least a portion of the sorting control parameters other than the sorting rate setpoint based on the variety and / or characteristics received in step S120.
[0083] If the sorting control parameters are set in this way, the controller 25 will perform sorting based on the primary sorting system 20a and the secondary sorting system 20b based on the sorting control parameters set in step S160 (step S170).
[0084] In step S170, sorting is performed based on the sorting rate setting value set in step S160. For example, if the sorting rate setting value for dead rice is set to 50% and the sorting rate setting value for colored grains is set to 25%, air 53 is sprayed only on 50% of the sorted items 90 that are determined to be dead rice, and only on 25% of the sorted items 90 that are determined to be colored grains.
[0085] This selective removal of defective products is performed as follows in this embodiment. First, the controller 25 counts the defective products in the images acquired within a specified period. Furthermore, the controller 25 only sprays air 53 onto defective products with numbers corresponding to the sorting rate setting. For example, when the sorting rate setting for dead rice is 50%, air 53 is only sprayed onto dead rice with even-numbered numbers. Similarly, when the sorting rate setting for colored grains is 25%, air 53 is only sprayed onto colored grains with numbers that are multiples of 4. Through this control, the number of identified defective parts is considered equal to the number of defective products, and thus the defective products are counted.
[0086] In an alternative embodiment, selective removal of defective products can also be performed according to a priority ranking corresponding to the concentration of the defective portion. Specifically, defective portions with higher concentrations (defective portions with grayscale values that differ relatively greatly from the concentration threshold) are given higher priority for removal. This structure can be implemented, for example, by sorting defective products in images acquired within a specified period according to the concentration of the defective portion, and only spraying air 53 onto defective products with defective portions that reach a ranking corresponding to the sorting rate setting. According to this structure, product quality can be improved by preferentially removing defective products with more severe defects (specifically, more concentrated defects). For example, if the type of defective product is colored grains, colored grains with relatively high color concentrations can be preferentially removed. In addition, if the type of defective product is white dead rice, white dead rice with relatively high white concentrations can be preferentially removed.
[0087] In a further alternative embodiment, selective removal of defective products can also be performed according to a priority order corresponding to the size of the defective portion. For example, for defective products other than small particles, the larger the defective portion (e.g., a large defective portion in area, a large defective portion in length, etc.), the higher the priority for removal. According to this structure, product quality can be improved by prioritizing the removal of defective products with more severe defects (specifically, larger defective portions). For example, in the case where defective products include fully colored particles and partially colored particles, fully colored particles can be removed first compared to partially colored particles. Alternatively, regarding small particles, the larger the particles, the higher the priority for removal. Since the target quality condition is set by weight ratio, when prioritizing the removal of large particles (i.e., relatively heavy particles), the weight of defective products that can be removed with one air jet increases. Therefore, the target quality condition can be achieved efficiently with fewer air jets. If the number of air jets is reduced, the number of incident removals also decreases, thus, according to this structure, the yield can be improved.
[0088] In a further alternative embodiment, a priority order related to the decision of whether to remove (hereinafter also referred to as removal decision) can be set among the types of nonconforming products. Specifically, nonconforming products of types with strict control target values (low mixing rate as the target) can be preferentially subject to removal decision. In this case, for example, if there are nonconforming products with a first type of defect and a second type of defect with a lower priority order for removal decision than the first type of defect, if the first type of defect is determined not to require removal, the second type of defect is not subject to removal decision, and the nonconforming product is treated as a conforming product. According to this structure, in the case of nonconforming products that repeatedly have multiple types of defects, it is possible to suppress the excessive removal of nonconforming products relative to the control target value. In a further alternative embodiment, nonconforming products of types with a large difference between quality information and control target value can be preferentially subject to removal decision.
[0089] In this embodiment, in step S170, the controller 25 is configured to perform parameter change processing in order to perform feedback control so that the actual sorting process result (i.e., the mixing rate of various types of non-conforming products) is close to the final target quality condition. Parameter change processing refers to the process of changing the sorting control parameters according to the processing status during sorting operation. The parameter change processing will be explained below.
[0090] Figure 4 This is a flowchart illustrating the parameter change processing procedure. During the sorting operation of the sorting machine 20, this process is repeated periodically (e.g., every few seconds or every few minutes). If the parameter change processing begins, the controller 25 first calculates the sorting results related to the target quality conditions over a specified period based on the signals (more specifically, images) acquired by the optical sensors 41, 42 (step S210). In other words, the controller 25 detects the contamination status of each type of nonconforming item from the images of the sorted items 90 actually being processed, and calculates the contamination rate (i.e., the sorting result) of each type of nonconforming item among the sorted items 90 that are discharged from the sorting machine 20 as qualified items based on its detection results.
[0091] Specifically, based on the images acquired by the optical sensors 41 and 42 of the primary sorting system 20a, the total quantity of the sorted items 90 input into the primary sorting system 20a and the quantity of each type of defective item can be determined. Similarly, based on the images acquired by the optical sensors 41 and 42 of the secondary sorting system 20b, the total quantity of the sorted items 90 input into the secondary sorting system 20b and the quantity of each type of defective item can be determined. Since the sorted items 90 discharged as defective items from the primary sorting system 20a are input into the secondary sorting system 20b, the total quantity of the sorted items 90 discharged as qualified items (products) from the primary sorting system 20a and the quantity of each type of defective item can be calculated based on the differences between the total quantity of the sorted items 90 input into the primary sorting system 20a and the quantity of each type of defective item input into the secondary sorting system 20b.
[0092] Figure 7This is a diagram illustrating an example of the calculation method in step S170. In this example, for simplicity, the re-feeding of the sorted material 90 discharged as qualified products from the secondary sorting system 20b to the primary sorting system 20a is not considered. The amount "A (kg)" fed into the primary sorting system 20a can be calculated, for example, as follows: First, the number of particles or pixels representing the sorted material 90 is counted using images acquired by the optical sensors 41 and 42 of the primary sorting system 20a. Then, the amount "A (kg)" is calculated by multiplying the obtained number of particles or pixels by an assumed value for the weight of each particle or the weight of each pixel. Sometimes the specific gravity of the particles differs between whole particles and unqualified products, or between different types of unqualified products. Therefore, in an alternative embodiment, the number of particles or pixels representing the sorted item 90 can be counted according to the whole particles and the type of each defective item, and the resulting number of particles or pixels can be multiplied by a pre-defined weight for each particle or pixel set according to the whole particles and the type of each defective item to calculate the weight of the whole particles and the type of each defective item. In this case, the input quantity "A (kg)" is calculated by adding the weights of the whole particles and the type of each defective item. The input quantity "I (kg)" to the secondary sorting system 20b can also be calculated using the same method using images acquired by the optical sensors 41 and 42 of the secondary sorting system 20b.
[0093] Furthermore, the weight ratio "B (%)" of whole particles in the sorted items 90 fed into the primary sorting system 20a can be calculated, for example, as follows. First, the number of particles or pixels representing whole particles is counted using images acquired by the optical sensors 41 and 42 of the primary sorting system 20a. Then, the weight of the whole particle is calculated by multiplying the obtained number of particles or pixels by an assumed value for the weight of each whole particle or the weight of each whole particle pixel. Finally, the weight of the whole particle is calculated by dividing the weight of the whole particle by the input amount "A (kg)". The weight ratios C to H of each non-conforming item can also be calculated using a similar method. Specifically, for example, first, the number of particles representing a specific type of non-conforming item is counted, assuming that the number of defective parts is equal to the number of non-conforming items. Then, the weight ratios C to H of each non-conforming item are calculated by multiplying the obtained number of particles or pixels by an assumed value for the weight of each non-conforming item of that type. Alternatively, assuming the number of defective parts is equal to the number of non-conforming products, the number of defective parts of a specific type is multiplied by an assumed value for the number of pixels per particle of that type of non-conforming product, and then multiplied by an assumed value for the weight of each pixel of that type of non-conforming product to calculate the weight ratio C to H of each non-conforming product. Furthermore, the weight ratio J to P of whole particles and each non-conforming product in the sorted items 90 fed into the secondary sorting system 20b can also be calculated using images acquired by the optical sensors 41 and 42 of the secondary sorting system 20b in the same way as the primary sorting system 20a.
[0094] The weight ratio T of the sorted material 90 (i.e., the product) discharged as qualified products from the primary sorting system 20a can be calculated by subtracting the result of multiplying the amount of sorted material 90 (Ikg) input into the primary sorting system 20a and the proportion of whole particles therein (B%) from the result of multiplying the amount of sorted material 90 input into the secondary sorting system 20b (Ikg) and the proportion of whole particles therein (J%), and then dividing the result by the product quantity (Skg). The proportions U to Z of each non-conforming product in the product (i.e., the contamination rate) are also calculated as follows: Figure 7 As shown, the same calculation method can be used.
[0095] This section will explain how to return to... Figure 4The acquisition period of the image that forms the basis of the calculation in step S210 (the specified period mentioned above) can, for example, be from the last execution of parameter change processing up to the present. Alternatively, it can be from the start of the sorting operation of the sorting machine 20 up to the present. Furthermore, the timing of image acquisition, which forms the basis of the calculation in step S210, can be the same for both the images acquired by the optical sensors 41 and 42 of the primary sorting system 20a (hereinafter also referred to as primary sorting images) and the images acquired by the optical sensors 41 and 42 of the secondary sorting system 20b (hereinafter also referred to as secondary sorting images). This allows for simple calculation of the sorting results. Alternatively, the secondary sorting images can be acquired at a time delayed compared to the primary sorting images. This delay time corresponds to the envisioned time from when the sorted items 90 captured in the primary sorting system 20a are discharged as defective items and placed into the secondary sorting system 20b until they are captured. This allows for more accurate calculation of the sorting results.
[0096] If the sorting results are calculated as described above, the controller 25 then determines whether the calculated sorting results are higher or lower than the final target quality conditions (step S220). This determination is made for each type of nonconforming product.
[0097] If the calculated sorting result is lower than the final target quality condition (step S220: low), then the controller 25 changes the sorting control parameters in a direction that improves the product quality (i.e., the quality represented by the calculated sorting result is close to the final target quality condition) (step S230). Specifically, in this embodiment, the controller 25 changes the sorting rate setting value related to the type of non-conforming product whose quality is judged to be lower than the target quality condition to a value greater than the current setting value. The new sorting rate setting value is determined based on the calculated sorting result (…). Figure 7 The difference between the U~Z values and the target quality conditions is calculated in order to achieve the final target quality conditions. According to this structure, the spray frequency of air 53 on the sorted items 90 that are judged to be non-conforming increases (i.e., the number of non-conforming items that are intentionally not removed decreases), thus enabling the product quality to approach the final target quality conditions.
[0098] In an alternative embodiment, the controller 25 changes the concentration threshold related to the type of nonconforming product judged to be below the target quality condition to a value lower than the currently set value. That is, the concentration threshold is changed in a way that increases the sensitivity relative to nonconforming products. In a further alternative embodiment, when the sorting result related to the combined contamination rate of damaged grains (including broken grains), dead rice, colored grains, different types of grains, and foreign matter is judged to be below the target quality condition, the controller 25 changes the size threshold related to broken grains to a value greater than the currently set value. In a further alternative embodiment, when any type of nonconforming product other than broken grains is judged to be below the target quality condition, the controller 25 changes the size threshold related to that type of nonconforming product to a value lower than the currently set value. By changing the concentration threshold or size threshold in this way, the number of sorted items 90 judged to be nonconforming products increases, and therefore the spray frequency of air 53 on the sorted items 90 judged to be nonconforming products also increases, enabling the product quality to approach the final target quality condition.
[0099] In a further alternative embodiment, the controller 25 changes the setting of the spray range related to the type of defective product judged to be below the target quality condition by increasing the spray range. Specifically, the controller 25 may also change the spray period to a longer value than the current setting. Alternatively, the controller 25 may change the setting of the spray range allocation instead of changing the spray period, or on this basis, by increasing the overlap area (i.e., by making it easier to spray air 53 from both nozzles 51). If the spray range is changed in this way, defective products can be removed more reliably when air 53 is sprayed, thus bringing the product quality closer to the final target quality condition.
[0100] In a further alternative embodiment, if the sorting results calculated for all or some types of nonconforming products are lower than the final target quality condition, the controller 25 changes the flow rate to a value smaller than the current setting. This increases the gap between the sorted items 90 falling from the chute 73, allowing for more accurate detection of nonconforming products. Therefore, the product quality can be brought closer to the final target quality condition. Furthermore, the increased gap between the sorted items 90 falling from the chute 73 suppresses entrainment and improves the yield.
[0101] In a further alternative embodiment, two or more of the aforementioned changes to sorting parameters can be combined arbitrarily. This allows the product quality to more reliably approach the final target quality conditions. According to step S230, even if the quality information received in step S110 differs from the actual non-conforming product mix-in rate, the final target quality conditions can still be reliably achieved.
[0102] On the other hand, if the calculated sorting result is higher than the final target quality condition (step S220: high), the controller 25 changes the sorting control parameters in the direction of increasing the product yield. This is intended to increase the yield while reducing the product quality to a level that can achieve the final target quality condition. Specifically, in this embodiment, the controller 25 changes the sorting rate setting value related to the types of non-conforming products whose quality is determined to be higher than the target quality condition to a value lower than the current setting value. The new sorting rate setting value is calculated based on the difference between the calculated sorting result and the target quality condition, such that the quality of the changed product is lower than the final target quality condition. According to this structure, the product yield can be increased while achieving the final target quality condition.
[0103] In an alternative embodiment, the controller 25 changes the concentration threshold related to the types of nonconforming items judged to be of higher quality than the target quality condition to a value greater than the currently set value. This reduces the sensitivity to nonconforming items (i.e., reduces the number of sorted items 90 judged to be nonconforming), thus reducing the number of nonconforming items removed and improving the yield. In a further alternative embodiment, when the sorting result related to the combined contamination rate of damaged grains (including broken grains), dead rice, colored grains, different types of grains, and foreign matter is judged to be of higher quality than the target quality condition, the controller 25 changes the size threshold related to broken grains to a value less than the currently set value. This also improves the yield. Furthermore, by removing larger (i.e., heavier) broken grains from the removal target while leaving smaller (i.e., lighter) broken grains in the removal target, the yield calculated based on weight can be efficiently improved. In a further alternative embodiment, if any type of defective product other than fragments is determined to be of higher quality than the target quality condition, the controller 25 changes the size threshold associated with that type of defective product to a value greater than the currently set value. This reduces the sensitivity to defective products, thereby improving the yield.
[0104] In a further alternative embodiment, the controller 25 changes the setting of the spray range related to the type of non-conforming product judged to be above the target quality condition by reducing the spray range. Specifically, the controller 25 may also change the spray period to a shorter value than the current setting. Alternatively, the controller 25 may change the setting of the spray range allocation instead of changing the spray period, or on this basis, by reducing the overlap area (i.e., making it less likely for air 53 to be sprayed from the two nozzles 51). If the spray range is changed in this way, the generation of entanglement removal is suppressed, and the yield can be improved.
[0105] In a further alternative embodiment, if the sorting results calculated for all types of nonconforming products are higher than the final target quality condition, the settings related to the discharge destination of the sorted items 90 discharged from the secondary sorting system 20b as either conforming or nonconforming products are changed. Specifically, the switching valve 23 can be switched so that the discharge destination of the sorted items 90 discharged from the secondary sorting system 20b as conforming products is changed from refeeding to the primary sorting system 20a to the conforming product 21 hopper. Alternatively, or based on this, the switching valve 24 can be switched so that the discharge destination of the sorted items 90 discharged from the secondary sorting system 20b as nonconforming products is changed from the nonconforming product container 22 to the conforming product 21 hopper.
[0106] Whether to switch from the initial state to the discharge destination, and whether to switch one or both of the control valves 23 and 24, can also be determined based on the calculated difference between the sorting result and the final target quality condition. Specifically, these judgments are based on whether the final target quality condition can be achieved. Within the range where the final target quality condition can be achieved, the switching valves 23 and 24 are controlled in a way that guides as much of the sorted material 90 as possible to the qualified product hopper 21. Such judgments can be based on the calculated sorting result (e.g., Figure 7 The judgment is made based on the weight ratios J to P and the sorting control parameters of the secondary sorting system 20b. In order to make this judgment, the mixing rate of various non-conforming products discharged from the secondary sorting system 20b as qualified products can also be inferred based on the weight ratios J to P and the sorting control parameters of the secondary sorting system 20b.
[0107] In a further alternative embodiment, two or more of the aforementioned changes to sorting parameters can be combined arbitrarily. This can further improve the yield. According to step S240, the yield can be increased while achieving the final target quality conditions.
[0108] Thus, if step S230 or step S240 is executed, the parameter change process ends. Furthermore, although the illustration is omitted, in step S220, if the calculated sorting result is equal to the final target quality condition, the parameter change process ends, and the process does not proceed to steps S230 or S240. In an alternative embodiment, in step S220, the calculated sorting result may also be compared with the control target value. Alternatively, if in step S220 it is determined that the calculated sorting result is lower than the final target quality condition or control target value by a specified degree, the controller 25 may allow the process to proceed to step S230; if it is determined that the calculated sorting result is higher than the final target quality condition or control target value by a specified degree, the controller 25 may allow the process to proceed to step S240. Alternatively, a control lag may be set in the determination of step S220. That is, the determination criteria for allowing the process to proceed from step S220 to step S230 and the determination criteria for allowing the process to proceed from step S220 to step S240 may also be different.
[0109] Based on the sorting machine 20 described above, the user can confirm simulation results related to the quantity of sorted material 90 discharged as qualified products and the yield rate under candidate conditions using the target quality conditions before starting the sorting operation. Therefore, the user can determine the final target quality conditions to be adopted based on the simulation results (i.e., considering the quantity of sorted material 90 discharged as qualified products and / or the yield rate). Thus, sorted material 90 with the desired quality and yield rate can be obtained as the product.
[0110] The embodiments of this disclosure have been described above, but these embodiments are for ease of understanding of the teachings and do not limit the invention. The invention can be modified and improved without departing from its spirit, and the invention includes its equivalents. Furthermore, within the scope of solving at least a portion of the above-described problems, or within the scope of achieving at least a portion of the effects, any combination or arbitrary omission of the constituent elements described in the specification and the scope of protection claimed in this application is possible.
[0111] For example, the flowchart above is merely an example. Without departing from the spirit of the present invention, the processing order of each process constituting the flowchart can be changed or transformed into an equivalent process.
[0112] For example, in step S140, the controller 25 may display the simulation results of quality conditions on the user interface 60 in addition to product quantity and / or yield. Furthermore, the input of various information by the user and the display of simulation results are not limited to the user interface of the sorting machine 20; they can also be performed using other information processing devices communicatively connected to the sorting machine 20.
[0113] Furthermore, if the sorting machine 20 does not have a secondary sorting system 20b, in step S210, the controller 25 can calculate the sorting result based solely on the images acquired by the optical sensors 41 and 42 of the primary sorting system 20a. In this case, for example, it can also be based on... Figure 7 The information A through H shown, along with the sorting rate settings, are used to calculate the mixing rate of various non-conforming products in the product.
[0114] Furthermore, steps S110 and S140 can be omitted. In this case, during sorting operation, the controller 25 can set sorting control parameters that achieve the target quality conditions based on the target quality conditions received in step S130 and the contamination rate of non-conforming products calculated based on images acquired in the primary sorting system 20a, or the primary sorting system 20a and the secondary sorting system 20b, instead of [presumably a separate process]. Figure 4 The parameter change process is shown below.
[0115] Alternatively, the controller 25 may calculate the contamination rate (i.e., the contamination rate of each type of nonconforming item) of the sorted items 90 fed into the primary sorting system 20a based on images acquired in the primary sorting system 20a, instead of... Figure 4 The parameter change processing is shown. In this case, the controller 25 can also change the sorting control parameters based on the difference between the quality information received in step S110 and the calculated mixing rate for each type of nonconforming product. Specifically, the controller 25 can also perform the processing of step S230 if the quality information indicates a mixing rate lower than the calculated mixing rate by a specified degree, and perform the processing of step S240 if the quality information indicates a mixing rate higher than the calculated mixing rate by a specified degree. This control is performed on a per-type nonconforming product basis.
[0116] In this way, the controller 25 can also detect the contamination status of non-conforming products in the sorted material 90 within a specified period based on signals acquired by the optical sensors 41, 42 of the primary sorting system 20a, or the primary sorting system 20a and the secondary sorting system 20b, and change the sorting control parameters based on the contamination status. With this structure, appropriate sorting control parameters for achieving the target quality conditions can be set based on the actual contamination rate of non-conforming products.
[0117] Furthermore, in at least one of the primary sorting system 20a and the secondary sorting system 20b, if the contamination rate of defective products is high, defective products and whole particles can be separated by spraying air 53 towards the sorted product 90 that is determined to be whole particles instead of the sorted product 90 that is determined to be defective (so-called reverse removal). In this case, as long as air 53 is also sprayed on a portion of the sorted product 90 that is determined to be defective to intentionally mix a portion of the defective product into the whole particles, the sorting rate can be controlled as described in the above embodiment.
[0118] Furthermore, any sorting device can be used instead of the air-jet sorting device 50. For example, the sorting device may include multiple components (e.g., louvers) configured to be adjacent to the transport path of the items to be sorted 90 and selectively displaced by actuators. In this case, the component corresponding to the location where a defective item is detected is displaced to collide with the defective item, thereby changing the transport path of the defective item to sort it. Alternatively, the sorting device may include multiple air suction devices configured to be adjacent to the transport path of the items to be sorted 90 and selectively driven. In this case, the air suction device corresponding to the location where a defective item is detected can be driven to suction the defective item, thereby changing the transport path of the defective item to sort it.
[0119] Furthermore, the controller 25 may accept multiple candidate inputs of the target quality condition in step S130. Alternatively, the controller 25 may read multiple candidate target quality conditions pre-stored in the memory of the sorting machine 20 in step S130, thereby accepting their input. Besides these structures, the output of the simulation result may be omitted in step S140, and step S150 may also be omitted. In this case, the controller 25 may determine the final target quality condition based on the simulation result in step S130. In this case, the controller 25 may either determine the candidate target quality condition with the highest yield as the final target quality condition, or it may calculate the product sales forecast by multiplying the quantity of sorted items discharged as qualified products by a predetermined product unit price, and determine the candidate target quality condition with the highest product sales forecast as the final target quality condition. Furthermore, in this case, the controller 25 may automatically perform sorting after determining the final target quality condition. Alternatively, controller 25 can display simulation results (i.e., product quantity and / or yield) and / or product sales forecasts on user interface 60, and perform sorting after receiving sorting execution instructions from the user via user interface 60. This structure reduces the user's workload, thus improving convenience.
[0120] In addition to the sorting machine exemplified above, this invention can be implemented in various ways, such as as a simulation device, a simulation method, a sorting method, a simulation program, or a storage medium storing the program in a computer-readable manner. When this invention is implemented as a simulation device, the simulation device can be mounted on the aforementioned grain detector, or the simulation results can be output to the graphical user interface of the grain detector. In this way, the user can obtain quality information through the grain detector while also confirming the simulation results. Alternatively, when this invention is implemented as a simulation device, the simulation device can also be an information processing device (e.g., a personal computer) with a pre-defined program installed.
[0121] Furthermore, the sorted material 90 is not limited to brown rice; it can be any granular material. For example, the sorted material 90 can also be polished white rice, wheat grains, legumes (soybeans, chickpeas, edamame, etc.), resin (granules, etc.), etc. In this case, the contents of the non-conforming product can be appropriately defined according to the required sorting performance.
[0122] Explanation of reference numerals in the attached figures
[0123] 11...Conveyor line; 12...Measuring device; 20...Sorter; 20a...Primary sorting system; 20b...Secondary sorting system; 21...Qualified product hopper; 22...Unqualified product container; 23, 24...Switching valve; 25...Controller; 31, 32...Light source; 33, 34...Light; 41, 42...Optical sensor; 50...Sorting device; 51, 51a, 51b, 51c...Nozzle; 52, 52a, 52b, 52c...Valve; 53...Air; 60...User interface; 61...Raw material quality Display area; 62...Target quality input area; 63...Grade input area; 64...Mix-input rate input area; 65...Inferred value display area; 71...Storage tank; 72...Feeder; 73...Cutter; 74...Qualified product discharge chute; 75...Unqualified product discharge chute; 80...Image; 81, 82...Pixels; 83a, 83b, 83c...Spraying coverage area; 84a, 84b...Overlapping area; 90, 91, 92...Sorted items; 95...Transfer path; D1...Transfer direction; D2...Orthogonal direction.
Claims
1. An optical sorting machine, characterized in that, have: The light source is configured to illuminate the sorted items during transport. An optical sensor is configured to detect light illuminating the light source and associated with the sorted object; The sorting device is configured to sort all or part of the items to be sorted that are determined to be defective based on signals acquired by the optical sensor; and The controller is configured to control the operation of the optical sorting machine. The controller is configured as follows: Accepts candidate inputs related to the allowable rate of contamination of non-conforming items in the sorted products discharged as qualified items from the optical sorting machine. The system accepts input of quality information relating to at least a portion of the items to be sorted, which is fed into the optical sorting machine, and this quality information indicates the contamination rate of the non-conforming items. Based on the quality information, the simulation results are generated, relating to the amount and / or yield of the sorted items discharged as qualified products, assuming that the sorting device has sorted the items in a manner that can achieve the target quality conditions. The simulation results are then output. The system accepts inputs specifying the final target quality conditions to be applied during sorting by the sorting device. Sorting is performed based on sorting control parameters that enable the achievement of the final target quality conditions.
2. The optical sorting machine according to claim 1, characterized in that, The controller is configured to control the sorting device in a manner that sorts only a portion of the sorted items that are determined to be defective. The sorting control parameters include setpoints related to the sorting rate, which is the proportion of the sorted items that should be sorted out among those judged as non-conforming products. The portion of the sorted items that is determined to be non-conforming is determined based on the sorting rate.
3. The optical sorting machine according to claim 1 or 2, characterized in that, The sorting control parameters include thresholds for determining the non-conforming products.
4. The optical sorting machine according to claim 1 or 2, characterized in that, The sorting device includes: Multiple nozzles, capable of selectively spraying air, are arranged in a direction orthogonal to the transport direction of the sorted material. The sorting device is configured to selectively spray air from the plurality of nozzles into the items to be sorted in order to sort all or a portion of the items that are determined to be defective. The controller is configured to variably set the air jet range on the sorted material. The sorting control parameters include settings related to the air injection range.
5. The optical sorting machine according to claim 1 or 2, characterized in that, The optical sorting machine has a primary sorting system and a secondary sorting system. Each of the primary sorting system and the secondary sorting system is configured to perform optical sorting using the light source, the optical sensor, and the sorting device. The optical sorting mechanism sorts the items fed into the primary sorting system into a first sorted group and a second sorted group. The first sorted group is discharged from the primary sorting system as qualified products. The second sorted group is then fed into the secondary sorting system, where it is further sorted into a third sorted group and a fourth sorted group. Furthermore, the optical sorting mechanism is capable of switching the discharge destination of the third sorted group between re-into the primary sorting system and discharge as qualified products, and / or is configured to switch the discharge destination of the fourth sorted group between discharge as qualified products and discharge as unqualified products. The sorting control parameters include settings related to the discharge destination of the third sorted group and / or the fourth sorted group.
6. The optical sorting machine according to claim 1 or 2, characterized in that, The controller is configured to detect the contamination status of the non-conforming products in the sorted items within a specified period based on the signal acquired by the optical sensor during sorting operation, and to change the sorting control parameters based on the contamination status.
7. The optical sorting machine according to claim 6, characterized in that, The controller is configured to calculate sorting results related to the target quality conditions within the specified period based on the mixing status during the sorting operation, and to change the sorting control parameters based on the calculated sorting results.
8. The optical sorting machine according to claim 5, characterized in that, The controller is configured to, during the sorting operation, detect the contamination status of the non-conforming products in the sorted materials within a specified period based on the signal acquired by the optical sensor, calculate the sorting results related to the target quality conditions within the specified period based on the contamination status, and be able to change the sorting control parameters based on the calculated sorting results. The controller is configured to calculate the sorting results related to the target quality conditions within the specified period based on the signals acquired in each of the primary and secondary sorting systems during the sorting operation.
9. The optical sorting machine according to claim 7, characterized in that, The controller is configured to change the sorting control parameters in a direction that moves the quality represented by the calculated sorting result closer to the final target quality condition when the quality represented by the calculated sorting result is lower than the final target quality condition by a specified degree.
10. The optical sorting machine according to claim 7, characterized in that, The controller is configured to change the sorting control parameters in a direction that increases the yield of the sorted items that are discharged as qualified products when the quality represented by the calculated sorting result is higher than the final target quality condition by a specified degree.
11. A sorting simulation device, characterized in that, Equipped with a controller The controller is configured as follows: When sorting items using an optical sorting machine, candidate inputs related to the allowable rate of contamination of non-conforming items among the sorted items discharged as qualified items from the optical sorting machine are accepted. The system accepts input of quality information relating to at least a portion of the items to be sorted, which is fed into the optical sorting machine, and this quality information indicates the contamination rate of the non-conforming items. Based on the quality information, the simulation results are generated, which are related to the amount and / or yield of the sorted items discharged as qualified products when the optical sorting machine sorts the items in a manner that can achieve the target quality conditions. The simulation results are then output.
12. A simulation method relating to the sorting of items using an optical sorting machine, characterized in that, It includes the following processes: The user determines candidate processes for target quality conditions related to the allowable rate of contamination of non-conforming items in the sorted goods that are discharged as qualified items from the optical sorting machine. The process of acquiring quality information related to at least a portion of the items to be sorted, fed into the optical sorting machine, the quality information representing the contamination rate of the non-conforming items; and Based on the quality information, the process simulates the sorting results related to the amount and / or yield of the sorted items discharged as qualified products when the optical sorting machine sorts the items in a candidate manner that can achieve the target quality conditions, and provides this information to the user.
13. An optical sorting machine, characterized in that, have: The light source is configured to illuminate the sorted items during transport. An optical sensor is configured to detect light illuminating the light source and associated with the sorted object; The sorting device is configured to sort all or part of the items to be sorted that are determined to be defective based on signals acquired by the optical sensor; and The controller is configured to control the operation of the optical sorting machine. The controller is configured as follows: The system accepts input of quality information relating to at least a portion of the items to be sorted, which is fed into the optical sorting machine, and this quality information indicates the contamination rate of the non-conforming items. For each of a plurality of candidate target quality conditions related to the allowable rate of contamination of non-conforming items among the sorted items discharged as qualified items from the optical sorting machine, based on the quality information, the sorting results related to the quantity and / or yield of the sorted items discharged as qualified items are simulated, assuming that the optical sorting machine has performed sorting in a candidate manner that can achieve the target quality condition. The final target quality conditions to be adopted when the sorting device performs sorting are determined based on the simulation results. Sorting is performed based on sorting control parameters that enable the achievement of the final target quality conditions.
Citation Information
Patent Citations
JP1975035696A
JP1975071712A
Grain quality discriminating apparatus
JP2016118455A
Grain quality discriminating device
JP2016125867A
Grain quality level discrimination device
US20170350825A1
