Sorting device and method

Abstract

A sorting device according to the present invention is used for selecting a desired crushed piece from a plurality of crushed pieces obtained by crushing a vehicle body structure, said sorting device comprising a detection means for detecting the doses of infrared light radiated from the crushed pieces to be sorted, an acquisition means for acquiring the emissivity of the crushed pieces on the basis of the detection result, and a classification means for classifying the crushed pieces on the basis of the acquisition result.

Description

Sorting device and method

[0001] The present invention is primarily directed to a method for separating desired fragments from a plurality of fragments.

[0002] In recent years, efforts to significantly reduce waste generation have been intensified through the prevention, reduction, recycling, and reuse of waste. To achieve this, research and development has been conducted on the recycling of metal materials that make up car bodies, such as iron and aluminum (see Patent Document 1).

[0003] Patent No. 6726753

[0004] In the above-mentioned recycling process, relatively expensive sorting techniques such as LIBS (Laser-Induced Breakdown Spectroscopy) can be used to sort the fragments obtained by shredding the vehicle body structure, but there is generally a demand for cheaper and simpler techniques.

[0005] An exemplary object of the present invention is to enable the realization of a relatively inexpensive and simple sorting technique, and ultimately to contribute to the reduction of waste.

[0006] A first aspect of the present invention relates to a method for selecting desired fragments from a plurality of fragments obtained by crushing a vehicle body structure, characterized in that the method comprises the steps of: detecting the dose of infrared radiation emitted from the fragments to be selected; acquiring the emissivity of the fragments based on the results of the detection; and classifying the fragments based on the results of the acquisition.

[0007] According to the present invention, the separation of crushed pieces can be achieved relatively inexpensively and easily.

[0008] Fig. 1 is a diagram showing an example of the configuration of a sorting device according to an embodiment. Fig. 2 is a diagram showing an example of the configuration of a sorting device according to an embodiment. Fig. 3 is a diagram showing a captured image of an example of crushed pieces. Fig. 4 is a diagram showing a captured image of an example of crushed pieces. Fig. 5 is a diagram showing a captured image of another example of crushed pieces. Fig. 6 is a flowchart showing an example of a method for sorting crushed pieces.

[0009] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the claimed invention, and not all combinations of features described in the embodiments are necessarily essential to the invention. Two or more of the features described in the embodiments may be arbitrarily combined. Furthermore, the same reference numerals are used for the same or similar components, and redundant explanations will be omitted.

[0010] 1A is a perspective view showing an example of the configuration of a sorting device 1 according to a first embodiment, and Fig. 1B is a schematic side view of the sorting device 1. The sorting device 1 includes a conveying mechanism 11, a camera group 12, a transfer destination switching mechanism 13, and a controller 14, and sorts desired fragments OB from a plurality of crushed fragments OB obtained by shredding a vehicle body structure with a shredder (not shown).

[0011] The transport mechanism 11 may be configured to transport multiple fragments OB, and typically, a belt conveyor is used. In this embodiment, the transport mechanism 11 includes a transport belt 111 and a power source 112. The transport belt 111 forms a transport path for transporting each fragment OB, and transports each fragment OB received from a shredder that shreds the vehicle body structure or a subsequent processing device in a predetermined direction based on the power of the power source 112. In the figure, the transport direction of the fragments OB is defined as the X direction, the direction perpendicular to the X direction and forming a horizontal plane is defined as the Y direction, and the up-down direction perpendicular to the horizontal plane is defined as the Z direction.

[0012] The camera group 12 includes multiple cameras for capturing images of individual fragments OB on the conveyor belt 111, and in this embodiment, includes a visible light camera 12a and a thermal camera 12b. While the cameras 12a and 12b are shown here arranged together for ease of viewing, they may be individually positioned according to their intended purpose. The visible light camera 12a is capable of capturing images of fragments OB on the conveyor belt 111 in the visible light range. A camera equipped with a CCD / CMOS image sensor may typically be used as the visible light camera 12a. The thermal camera 12b is capable of capturing images of fragments OB on the conveyor belt 111 in the infrared range. As will be described in more detail below, the thermal camera 12b is used to detect the amount of infrared radiation emitted from the fragments OB.

[0013] The destination switching mechanism 13 is used to switch the destination of the crushed fragments OB on the conveyor belt 111 between the collection unit 19a and 19b. In this embodiment, the destination switching mechanism 13 includes a switching plate 131 and a power source 132, and switches the destination of the crushed fragments OB between the collection units 19a and 19b by changing the orientation of the switching plate 131 based on the power of the power source 132. The configuration of the destination switching mechanism 13 is not limited to this example, and other mechanisms capable of achieving equivalent functions may be used. For example, a robot arm or the like may be used instead of the destination switching mechanism 13. Boxes, trays, etc. are typically used for the collection units 19a and 19b. Although the number of collection units is two here, three or more may be used.

[0014] The controller 14 controls the drive of each of the above-mentioned elements, thereby transferring each of the multiple fragments OB on the conveyor belt 111 to the collection unit 19a or 19b for sorting. For example, the controller 14 uses the visible light camera 12a to capture an image of the fragments OB to be sorted and acquire image data, and then acquires position data of the fragments OB on the conveyor belt 111 based on the image data. The controller 14 also evaluates the fragments OB using the thermal camera 12b, as will be described in detail later. Then, the controller 14 controls the destination switching mechanism 13 based on the evaluation results and selects one of the collection units 19a or 19b as the destination for the fragments OB. The drive control of the destination switching mechanism 13 may be performed at a timing corresponding to the position data of the fragments OB.

[0015] Now, since a vehicle body structure may contain multiple metal materials such as iron and aluminum, the crushed fragments OB obtained by crushing the vehicle body structure may contain multiple metal materials, but the differences between them are generally difficult to discern visually. Furthermore, vehicle body structures generally contain a mixture of painted and unpainted areas, and the crushed fragments OB may also contain a mixture of painted and unpainted areas. However, depending on the paint color, the painted and unpainted areas may be visually similar, making the differences between them also difficult to discern visually. In other words, sorting crushed fragments OB is generally relatively difficult, and a technology that can sort crushed fragments OB relatively inexpensively and easily is needed.

[0016] As a specific example, an image (visible light image) captured by the visible light camera 12a and an image (thermography) captured by the thermal camera 12b are shown with reference to two fragments OB.

[0017] Figure 2A shows a visible light image of a first sample, fragment OB (illustrated as fragment OB1), and Figure 2B shows a thermography of fragment OB1. Figure 3A shows a visible light image of a second sample, fragment OB (illustrated as fragment OB2), and Figure 3B shows a thermography of fragment OB2.

[0018] The fragments OB1 and OB2 are exemplified as samples that mainly contain a mixture of top-coated areas P1 and non-top-coated areas P2, and contain a mixture of multiple materials. As can be seen from the comparison of the visible light image and the thermography, the presence or absence of top coating on the fragments OB1 and OB2 can be difficult to see in the visible light image, but is visible in the thermography. Furthermore, the constituent materials are also visible in the thermography.

[0019] In the following description, when no distinction is required, the fragments OB1 and OB2 will be simply referred to as fragments OB.

[0020] As described above, differences between multiple metal materials in crushed fragments OB are generally difficult to see, and differences between metal materials with similar paint colors are also difficult to see. However, by referring to thermography, the differences become more easily visible, making it possible to properly sort the crushed fragments OB.

[0021] 4 is a flowchart showing an example of a method for sorting crushed debris OB. This flowchart corresponds to a control method for the sorting device 1, and the functions of each step can be mainly realized by the controller 14. For example, the controller 14 includes a CPU and memory, and the functions of each step can be realized by the CPU executing a predetermined program while expanding it into the memory. Note that the functions of each step may also be realized by a semiconductor device such as an ASIC (application-specific integrated circuit); that is, this flowchart may be realized by either hardware or software.

[0022] In step S4010 (hereinafter simply referred to as "S4010"; the same applies to other steps described below), the presence or absence of broken fragments OB on the conveyor belt 111 is detected. If broken fragments OB to be evaluated are present, the process proceeds to S4020; if not, the process returns to S4010. In this embodiment, the detection of broken fragments OB is performed by the visible light camera 12a, but in other embodiments, the detection may be performed by the thermal camera 12b or by another known sensor.

[0023] In S4020, image data of the visible light image of the fragments OB (visible light image data) is acquired using the visible light camera 12a, and position data of the fragments OB on the conveyor belt 111 is acquired based on the visible light image data. The position data includes the distance from a reference position on the conveyor belt 111 (position in the X direction) and may additionally include the position in the belt width direction (position in the Y direction). The visible light image data is associated with the position data and stored in a predetermined memory (e.g., RAM).

[0024] In S4030, thermographic image data (thermography data) of the broken pieces OB is acquired using the thermal camera 12b. The thermographic data is associated with the position data and stored in a predetermined memory (e.g., RAM). That is, the visible light image data and the thermographic data can be linked to each other by the position data.

[0025] In S4040, the thermographic data is analyzed to obtain the brightness distribution of each pixel in the thermographic data, and the constituent material of the fragments OB and whether or not they are painted are evaluated based on the brightness distribution, as will be described in detail below.

[0026] As described above, the thermal camera 12b can detect the amount of infrared radiation emitted from the fragments OB. This allows a brightness distribution corresponding to the detected infrared radiation dose to be obtained. An object in a given temperature environment emits infrared energy, which is generally given by: Im = ε × Ib, where Im is the object's thermal radiation intensity, Ib is the blackbody's thermal radiation intensity, and ε is the emissivity. Even for fragments OB with a uniform temperature distribution, Im will vary from part to part depending on the constituent material and whether or not the object is painted. Furthermore, Im corresponds to the amount of infrared radiation detectable by the thermal camera 12b, i.e., corresponds to the brightness in the thermography data (e.g., the greater the infrared radiation dose, the higher the brightness). Therefore, the emissivity ε of the target part can be obtained based on the brightness of each pixel in the thermography data, and is calculated as ε = Im / Ib. Note that Ib can be set as a fixed value in advance.

[0027] Generally, the shredded pieces OB from a shredder or a subsequent processing device have a uniform temperature distribution, but the ease of heat dissipation from the surface can vary depending on the constituent material and whether or not the shredded pieces OB are painted. Therefore, to ensure a uniform temperature distribution in the shredded pieces OB, a step of uniformly heating the shredded pieces OB may be added at least before S4030. The heating means may be a known heating unit, such as a hot air fan that blows hot air.

[0028] In S4050, the transfer destination switching mechanism 13 is controlled based on the evaluation result of S4040 at a timing corresponding to the position data of the broken pieces OB, and one of the recovery units 19a and 19b is selected as the transfer destination for the broken pieces OB. By sorting the broken pieces OB in this way, the sorting is completed and the broken pieces OB can be appropriately reused.

[0029] Here, the variation in emissivity between different metal materials is generally greater than the variation in emissivity between painted and unpainted metals. Therefore, a step of sorting the fragments OB by their primary material may be added at least before step S4010. The sorting means may be a known sorting unit, such as a magnetic separator that sorts by magnetism. In this case, steps S4010 to S4050 described above may be performed for each of the classified materials. For example, in the case of aluminum, it is possible to identify the type of alloy the fragments OB are (e.g., either an Al-Mg alloy (a so-called 5000-series aluminum alloy) or an Al-Mg-Si alloy (a so-called 6000-series aluminum alloy)). Furthermore, in the case of iron, it is possible to identify, for example, whether the fragments are high-tensile steel or interstitial-free steel (IF steel).

[0030] If the configuration of the original vehicle body structure is identified, it may be easy to identify which part of the original vehicle body structure each of the fragments OB belongs to (for example, whether it is part of an outer panel having a top-coated painted area P1 or an inner panel not having a top-coated painted area P1). For example, each of the fragments OB can be relatively easily classified based on the proportion of areas with different emissivity.

[0031] Generally, a top coat is often applied to the exterior panels of a vehicle body structure. Therefore, in the analysis of the thermography data in S4040, for example, the presence or absence of a top coat is determined by first obtaining the emissivity of the debris OB based on the brightness of each pixel in the thermography data. If it is determined that a top coat is present on the debris OB, it can be determined that the debris OB is part of the exterior panel of the vehicle body structure based on whether the area satisfies a criterion.

[0032] The above-described analysis can be realized, for example, by referring to a database in which each component of the original vehicle body structure is registered. The database may be registered in a memory within the controller 14, or may be registered in an external memory outside the controller 14 or in a server with which the controller 14 can communicate.

[0033] Furthermore, since vehicle body structures may be identical but have different paint colors, a database may be prepared for each paint color. In this case, the above-described analysis can be realized by determining, based on visible light image data, whether the color of the topcoat-coated area P1 matches a color registered in the database. Determining the color based on visible light image data also makes it possible to identify differences in the paint type (e.g., topcoat paint or electrodeposition paint), and referencing the database may enable this identification to be performed with increased precision.

[0034] Furthermore, some vehicle body structures contain materials with significantly different emissivities. Therefore, if the debris OB contains a region with a predetermined emissivity, the debris OB can be identified as a desired material. An example of such a material is a contaminant (a material containing a predetermined impurity).

[0035] As described above, the broken pieces OB may contain multiple metal materials. Furthermore, the broken pieces OB may contain a mixture of top-coated and uncoated areas P1 and P2, making sorting them relatively difficult. However, the emissivity of such broken pieces OB varies depending on their constituent materials or whether or not they have a top coat. Therefore, even if the broken pieces OB have a uniform temperature distribution, the amount of infrared radiation emitted from the broken pieces OB varies. Therefore, in this embodiment, the amount of infrared radiation emitted from the broken pieces OB is detected, and the emissivity of the broken pieces OB is obtained based on the detected infrared radiation. This makes it possible to appropriately identify which metal material the broken pieces OB are primarily composed of or which part of the vehicle structure they were obtained from. Therefore, according to this embodiment, the broken pieces OB can be sorted relatively inexpensively and easily based on the emissivity of the broken pieces OB, enabling the broken pieces OB to be appropriately reused.

[0036] The sorting of the debris OB may be performed by AI (Artificial Intelligence). In this case, the controller 14 may include, as a part thereof, a learning device having, for example, an input layer, an intermediate layer, and an output layer as a neural network. As an example, the learning device includes a Convolutional Neural Network (CNN), thereby enabling machine learning, which may also be referred to as deep learning. As another example, an autoencoder may be employed instead of or in addition to the CNN.

[0037] In the above explanation, for ease of understanding, each element is shown with a name related to its function, but each element is not limited to having the content described in the embodiment as its main function, and may have that function as an auxiliary function.

[0038] (Summary of Embodiments) [1] A method for sorting desired fragments from a plurality of fragments obtained by shredding a vehicle body structure, comprising: a step of detecting an amount of infrared radiation emitted from the fragments to be sorted; a step of acquiring the emissivity of the fragments based on the result of the detection; and a step of classifying the fragments based on the result of the acquisition. According to the above [1], it is possible to sort the fragments based on their emissivity relatively cheaply and easily, and the fragments can be appropriately reused, i.e., it is possible to reduce waste.

[0039] [2] The method according to [1], further comprising a step of uniformly heating the fragments before the detecting step. According to the above [2], the emissivity of the fragments can be properly evaluated, thereby enabling the fragments to be more properly sorted.

[0040] [3] The method according to [1] or [2], characterized in that in the detecting step, a distribution of infrared radiation doses emitted from the fragments is detected, and in the acquiring step, a distribution of emissivity of the fragments is acquired. According to the above [3], by referring to the distribution of emissivity, it is possible to more appropriately sort the fragments.

[0041] [4] The method according to [3], wherein the detecting step includes a step of capturing an image of the fragments using a thermal camera to obtain image data. According to the above [4], the fragment sorting can be achieved with a relatively inexpensive configuration.

[0042] [5] The method according to [3] or [4], wherein in the classifying step, the fragments are classified based on the proportion of regions of the fragments with different emissivity. According to the above [5], the fragments can be more appropriately sorted.

[0043] [6] The method according to [5], wherein the classification step includes a first step of determining whether the fragments are painted or not based on the emissivity of the fragments, and a second step of determining that the fragments are part of the outer panel of the vehicle body structure if the area determined to be painted satisfies a criterion. According to the above [6], the fragments can be more appropriately sorted.

[0044] [7] The method according to [6], further comprising a step of registering the vehicle body structure parts in a database, wherein in the second step, the broken pieces are determined to be part of the outer panel of the vehicle body structure by referring to the database. According to the above [7], broken pieces can be more appropriately sorted.

[0045] [8] The method according to [7], further comprising a step of capturing an image of the fragments in the visible light region, wherein the second step includes a step of determining whether the color of the region where the fragments are determined to be painted matches a color registered in the database. According to the above [8], the fragments can be more appropriately sorted.

[0046] [9] The method according to [7] or [8], characterized in that in the classification step, the crushed fragments are identified as the desired material if they contain a region of a predetermined emissivity. According to the above [9], the crushed fragments can be more appropriately sorted.

[0047]

[10] The method according to any one of [1] to [9], further comprising the steps of: transporting the plurality of crushed pieces on a transport path; and acquiring positional information of each crushed piece on the transport path, wherein in the sorting step, the destination of the crushed pieces to be sorted is switched based on the positional information. According to the above

[10] , it is possible to appropriately classify the crushed pieces.

[0048]

[11] A sorting device for sorting desired fragments from a plurality of fragments obtained by crushing a vehicle body structure, comprising: a detection means for detecting an amount of infrared radiation emitted from the fragments to be sorted, an acquisition means for acquiring the emissivity of the fragments based on the detection result, and a classification means for classifying the fragments based on the acquisition result. According to the above

[11] , the same effect as the above [1] can be obtained.

[0049]

[12] Each step in [1] above and / or each means in

[11] above may be realized by a program or by one or more processor circuits with a memory executing instructions stored in the memory. Such a program or instructions may be stored in a computer-readable non-volatile memory.

[0050] The invention is not limited to the above-described embodiment, and various modifications and variations are possible within the scope of the gist of the invention.

Claims

1. A method for selecting desired fragments from multiple fragments obtained by crushing a vehicle body structure, comprising the steps of: detecting the amount of infrared radiation emitted from the fragments to be selected; acquiring the emissivity of the fragments based on the results of said detection; and classifying the fragments based on the results of said acquisition.

2. The method of claim 1, further comprising the step of uniformly heating the fragments prior to the detecting step.

3. The method according to claim 1, characterized in that the detecting step detects the distribution of infrared radiation doses emitted from the fragments, and the acquiring step acquires the distribution of emissivity of the fragments.

4. The method according to claim 3, wherein said detecting step includes a step of capturing an image of said debris using a thermal camera to obtain image data.

5. The method of claim 3, wherein said classifying step classifies said fragments based on the proportion of areas of said fragments that have different emissivities.

6. The method of claim 5, wherein the classification step includes a first step of determining whether the debris is painted or not based on the emissivity of the debris, and a second step of determining that the debris is part of an outer panel of the vehicle body structure if the area determined to be painted satisfies a criterion.

7. The method according to claim 6, further comprising a step of registering the parts of the vehicle body structure in a database, wherein the second step determines that the fragment is part of an outer panel of the vehicle body structure by referring to the database.

8. The method according to claim 7, further comprising a step of capturing an image of the debris in the visible light region, wherein the second step includes a step of determining whether the color of the area where the debris is determined to be painted matches a color registered in the database.

9. The method of claim 7, wherein said classifying step identifies said fragment as said desired material if said fragment contains a region of a predetermined emissivity.

10. The method according to claim 1, further comprising the steps of: transporting the plurality of fragments on a transport path; and acquiring positional information of each fragment on the transport path; wherein in the classification step, the destination of the fragments to be sorted is switched based on the positional information.

11. A sorting device for selecting desired fragments from multiple fragments obtained by crushing a vehicle body structure, comprising: a detection means for detecting the amount of infrared radiation emitted from the fragments to be selected; an acquisition means for acquiring the emissivity of the fragments based on the detection results; and a classification means for classifying the fragments based on the acquisition results.

Images