Disassembly procedure selection device, disassembly procedure selection method, and disassembly device

Abstract

To provide a dismantling procedure selection device and method and a dismantling device which can perform dismantling even when a dismantling procedure is not stored or when the states of a dismantling object like breakage or deformation are different.SOLUTION: A dismantling procedure selection device comprises: a dismantling information storage part 4 which stores a plurality of pieces of dismantling information including a predetermined dismantling procedure of a dismantling item 10S being the dismantling reference of a dismantling object 10; an entire detection part 2 which images the entire dismantling object with a camera; a detail detection part 3 which images at least a portion of the dismantling object with the camera; and a dismantling procedure derivation part 5 which extracts a portion being the feature of the dismantling object on the basis of the data obtained by imaging by at least one of the entire detection part and the detail detection part, obtains the matching degree between the extracted feature and the feature for each dismantling information stored in the dismantling information storage part and selects the dismantling procedure of the dismantling information with the highest matching degree, and can perform dismantling in the selected dismantling procedure.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a dismantling procedure selection device, a dismantling procedure selection method, and a dismantling device for dismantling objects in which the dismantling procedures differ depending on the model. [Background technology]

[0002] Economic activities involving mass consumption and mass waste have given rise to environmental problems on a global scale, such as global warming and resource depletion.

[0003] In this situation, the Home Appliance Recycling Law came into force in Japan in April 2001, with the aim of building a resource-circulating society. The Home Appliance Recycling Law requires the recycling of used home appliances (such as air conditioners, televisions, refrigerators, freezers, washing machines, clothes dryers, etc.). As a result, used home appliances are disassembled by hand at home appliance recycling plants and collected into individual materials. Alternatively, used home appliances are crushed into small pieces by a crusher, and then sorted and collected by material type using magnetism, wind power, vibration, etc., and recycled as recyclable materials.

[0004] In manual disassembly, since the housings or circuit boards of many home appliances are fixed with multiple fixing members, these fixing members must be removed in an orderly manner and separated during dismantling. Since the sizes of used home appliances to be dismantled and the fixing locations or fixing methods of each component vary from product to product, there are many steps that require complex dismantling operations or depend on the intuition or experience of the worker, making automation very difficult.

[0005] In light of this situation, technology has been proposed to automate part of the dismantling process, such as that disclosed in Patent Document 1.

[0006] FIG. 10 is a diagram showing a conventional dismantling device described in Patent Document 1.

[0007] In FIG. 10, display panel 101 is transported by transport unit 102, first fixing member detection unit 103 and second fixing member detection unit 104 detect the fixing points of the fixing members of the housing, and fixing member dismantling unit 105 enables the fixing of the fixing members to be released, which is effective in automating the dismantling process of flat-screen televisions and the like in which fixing members are fastened in one direction. [Prior art documents] [Patent documents]

[0008] [Patent Document 1] Patent No. 6051501 Summary of the Invention [Problem to be solved by the invention]

[0009] However, in the conventional configuration, in the case of a home appliance in which the fixing members are fastened from multiple directions and there are multiple fastening methods, such as an outdoor unit of an air conditioner, it is possible to deal with the case if there is a dismantling procedure, but it is difficult to deal with the case if there is no dismantling procedure. Also, in the case of a product that has been used outdoors, there is a problem that it is difficult to dismantle the dismantling unit by detection using normal image recognition, etc., because the product is different from the existing condition, particularly in terms of rust, deformation, or damage.

[0010] The present invention is devised to solve the above-mentioned problems in the conventional art, and aims to provide a dismantling procedure selection device and method, and a dismantling device that enable dismantling even when a dismantling procedure is not stored or when the condition of the object to be dismantled is different, such as being damaged or deformed. [Means for solving the problem]

[0011] In order to achieve the above object, a disassembly procedure selection device according to one aspect of the present invention comprises: a dismantling information storage unit configured to store a plurality of pieces of dismantling information including a dismantling procedure for separating or disassembling a dismantled object, which is a predetermined dismantling criterion for the dismantling object, for each of the components; a disassembly procedure derivation unit that calculates a degree of agreement between a first feature that is a feature of the disassembly object extracted from data captured by at least one of an entire detection unit that captures an image of the entire disassembly object and a detail detection unit that captures an image of at least a part of the disassembly object, and a second feature that is a feature of the disassembly information stored in the disassembly information storage unit and associated with a disassembly procedure of the component parts, and selects a disassembly procedure associated with the second feature of the disassembly information storage unit that has the highest degree of agreement; Preparation, The disassembly information includes: A disassembly procedure for the components; the second characteristic being associated with a disassembly procedure of the component parts; As the first feature, A boundary line of a boundary of a component part of the dismantling object; A structure of a fastening portion between components constituting a housing of the object to be disassembled; Position information of fastening members between parts constituting the dismantling object; The material of the component parts of the dismantling object is at least one of the following: As the second feature, A boundary line of a boundary of a component part of the disassembled object; A structure of a fastening portion between components constituting the housing of the disassembled object; Position information of fixing members between parts constituting the disassembled object; and the material of the component parts of the disassembled object.

[0012] Further, a disassembly procedure selection method according to another aspect of the present invention includes the steps of: The whole or part of the object to be dismantled is photographed with a camera, a dismantling procedure derivation unit determines a degree of agreement between a first feature, which is a feature of the dismantling object extracted from the captured data, and a second feature, which is a feature associated with the dismantling procedure of the component parts, and which is predetermined and stored in a dismantling information storage unit that stores a plurality of pieces of dismantling information including dismantling procedures of the component parts for separating or disassembling dismantled objects that are dismantling criteria for the dismantling objects, for each of the component parts; The disassembly procedure deriving unit selects a disassembly procedure associated with the second feature in the disassembly information storage unit that has the highest degree of match, and The disassembly information includes: A disassembly procedure for the components; the second characteristic being associated with a disassembly procedure of the component parts; As the first feature, A boundary line of a boundary of a component part of the dismantling object; A structure of a fastening portion between components constituting a housing of the object to be disassembled; Position information of fastening members between parts constituting the dismantling object; The material of the component parts of the dismantling object is at least one of the following: As the second feature, A boundary line of a boundary of a component part of the disassembled object; A structure of a fastening portion between components constituting the housing of the disassembled object; Position information of fixing members between parts constituting the disassembled object; and the material of the component parts of the disassembled object.

[0013] Further, a disassembly apparatus according to another aspect of the present invention includes the disassembly procedure selection device, a robot arm that dismantles the dismantling object in accordance with the dismantling procedure selected by the dismantling procedure selection device. Effect of the Invention

[0014] As described above, the dismantling procedure selection device, dismantling procedure selection method, and dismantling device according to the above aspects of the present invention include a dismantling procedure derivation unit that extracts characteristic parts of the dismantling object based on the captured data, calculates the degree of agreement between the extracted features and the features stored in the dismantling information storage unit, and selects the dismantling procedure associated with the feature in the dismantling information storage unit that has the highest degree of agreement, and dismantles the object using the dismantling procedure derived by the dismantling procedure derivation unit. This makes it possible to dismantle the object even if no dismantling procedure is stored or if the state of the object is different, such as damaged or deformed. As a result, dismantling without relying on human labor is possible even for used home appliances whose dismantling methods differ depending on the manufacturer or model number, and the labor required for dismantling the object can be reduced. [Brief description of the drawings]

[0015] [Figure 1] A configuration block diagram of a dismantling device according to a first embodiment of the present invention. [Diagram 2] 1 is a schematic diagram of a dismantling device according to a first embodiment of the present invention; [Diagram 3] Flowchart of disassembly in the first embodiment of the present invention [Figure 4A] FIG. 1 is a diagram for explaining extraction of characteristic parts of a dismantling device according to a first embodiment of the present invention. [Figure 4B] FIG. 1 is a diagram for explaining an example of features stored in a dismantling information storage unit of the dismantling device according to the first embodiment of the present invention. [Diagram 5] FIG. 2 is a diagram for explaining derivation of a disassembly procedure based on the degree of agreement of the disassembly device in the first embodiment of the present invention. [Figure 6] FIG. 1 is a diagram illustrating a disassembly procedure A of the disassembly device in the first embodiment of the present invention. [Figure 7] Flowchart of disassembly decision in the first embodiment of the present invention [Figure 8] Schematic diagram of a dismantling device according to a second embodiment of the present invention. [Figure 9] 1 is a schematic diagram of a dismantling device according to a third embodiment of the present invention; [Figure 10] FIG. 1 shows a conventional dismantling device described in Patent Document 1. [Figure 11] FIG. 1 is an explanatory diagram illustrating a fixing method of a fixed holder of a dismantling device according to the first embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings.

[0017] (Embodiment 1) Fig. 1 is a block diagram showing the configuration of a dismantling device 1 according to a first embodiment of the present invention. As shown in Fig. 1, the dismantling device 1 according to the first embodiment includes at least a dismantling procedure selection device 1A having at least an overall detection unit 2, a detail detection unit 3, a dismantling information storage unit 4, and a dismantling procedure derivation unit 5. In the dismantling procedure selection device 1A, the dismantling information storage unit 4 and the dismantling procedure derivation unit 5 function as a control unit 9 and comprehensively control the overall detection unit 2 and the detail detection unit 3.

[0018] As an example, dismantling apparatus 1 further includes fixing / transporting unit 6, robot arm 7, and dismantling hand 8. In this case, dismantling information storage unit 4 and dismantling procedure derivation unit 5 function as control unit 9 to comprehensively control overall detection unit 2, detail detection unit 3, fixing / transporting unit 6, robot arm 7, and dismantling hand 8.

[0019] As shown in FIG. 2, the dismantling device 1 in the present embodiment 1 fixes a dismantling target 10 to a fixed holder 11 and transports the same by a transport unit 12.

[0020] The fixed holder 11 is, for example, a plate-like member having a fixed holding surface capable of fixing the dismantling object 10. There are several fixing methods using the fixed holder 11. For example, as shown in FIG. 11(1), the fixed holder 11 is composed of a magnetic plate member 11c, and the dismantling object is fixed by magnetic force. As shown in FIG. 11(2), the dismantling object is adsorbed and fixed from the bottom by air suction using an adsorption pad 11f. As shown in FIG. 11(3), there is a method of mechanically clamping and fixing a certain part of the dismantling object 10E. More specifically, in FIG. 11(3), the bottom part of the dismantling object 10E on the support base 11d is mechanically clamped and fixed by, for example, a pair of plate members 11e.

[0021] The transport unit 12 is, for example, a belt conveyor capable of transporting the fixed holders 11 one after another in the transport direction.

[0022] The overall detection unit 2 is, for example, a camera, and is positioned upstream of the robot arm 7 of the conveying unit 12. It captures an image of the entire object 10 to be dismantled on the fixed holding unit 11 placed on the belt of the conveying unit 12, and transmits the captured image data to the control unit 9.

[0023] The detail detection unit 3 is, for example, a camera, and is disposed near the dismantling hand 8 at the tip of the robot arm 7 of the transport unit 12. The detail detection unit 3, for example, points the dismantling hand 8 toward the dismantling object 10, captures an image of a part of the dismantling object 10 near the dismantling hand 8 of the robot arm 7, and transmits the captured image data to the control unit 9. When capturing an image of a part of the dismantling object 10, for example, by capturing an image while moving along the boundary of the joint or along the outer shape or side, it is possible to easily capture and extract features related to the boundary or outer shape. As another example, it is also possible to capture an image of a fastening part between parts constituting the housing of the dismantling object 10, a fixing member 10a such as a screw between parts constituting the dismantling object 10, or a component of the dismantling object 10, and to extract features such as the structure of the fastening part, position information of the fixing member 10a, or the material of the component.

[0024] The dismantling procedure derivation unit 5 extracts a part that is a feature (i.e., a first feature) of the dismantling object 10 based on imaging data obtained from at least one of the overall detection unit 2 and the detailed detection unit 3 during the transportation of the dismantling object 10 or at a timing when the transportation is temporarily stopped, and compares the extracted feature with the feature (i.e., the second feature) of the dismantling object 10S that is the dismantling criterion for the dismantling object 10 in the dismantling information stored in the dismantling information storage unit 4, and derives a dismantling procedure associated with the feature of the dismantling object 10 that is closest to the extracted feature from the dismantling information. The dismantling criterion here means an object that has the same dismantling procedure when dismantling the dismantling object 10 and is of the same type or a similar type as the dismantling object 10.

[0025] The dismantling information storage unit 4 stores at least dismantling information including a dismantling procedure associated with a characteristic (ie, a second characteristic) of the dismantling object 10S that is the dismantling criterion of the dismantling target 10.

[0026] Specifically, the disassembly information includes at least a disassembly procedure for dismantling, i.e., separating or disassembling, an object identical or similar to the object to be disassembled 10, i.e., a disassembly object 10S, into its component parts, and characteristics of the disassembly object 10S associated with the disassembly procedure.

[0027] The features include at least one of boundary lines 10Sb (e.g., position information of boundary lines 10Sb) of, for example, joints of components of the dismantled object 10S, structures of fastening parts between components constituting the casing of the dismantled object 10S, position information of fastening members such as screws between components constituting the dismantled object 10S, and materials of the components of the dismantled object 10S. When features are compared between the object to be dismantled 10 and the dismantled object 10S, boundary lines (e.g., position information of boundary lines), structures of fastening parts, position information of fastening members, or materials are compared.

[0028] Under the control of disassembly procedure deriving unit 5, disassembly target object 10 is successively disassembled by robot arm 7 and disassembly hand 8 in accordance with the disassembly procedure derived by disassembly procedure deriving unit 5.

[0029] Below, a more detailed description will be given using an outdoor unit of an air conditioner, which is a home appliance, as an example of the object 10 to be dismantled.

[0030] First, as shown in Fig. 2, the dismantling target 10 is fixed to the fixed holder 11 and transported by the transport unit 12. Next, after imaging by at least one of the overall detection unit 2 and the detailed detection unit 3, dismantling starts when the dismantling target 10 passes a certain position during transport (for example, a position where the overall detection unit 2 can capture an image of the dismantling target 10) or when the transport temporarily stops. From now on, the dismantling flow will be explained based on the dismantling flowchart shown in Fig. 3.

[0031] First, in step S1, the control unit 9 acquires air conditioner outdoor unit image data 14 of the air conditioner outdoor unit 13 as shown in Fig. 4A from at least one of the overall detection unit 2 and the detail detection unit 3. The air conditioner outdoor unit image data 14 is image data of the entire air conditioner outdoor unit 13 when imaged by the overall detection unit 2, and is image data of only a portion of the air conditioner outdoor unit 13 when imaged by the detail detection unit 3.

[0032] Next, in step S2, the dismantling procedure derivation unit 5 extracts characteristic parts of the dismantling object 10 from the air conditioner outdoor unit image data 14 acquired in step S1. When extracting the characteristic parts, the dismantling procedure derivation unit 5 extracts them using a learning model that has been trained in advance on image data of a plurality of outdoor units by machine learning, for example, using a method such as template matching. Specifically, when shape characteristics are extracted from the front, back, right side, and left side of the air conditioner outdoor unit 13 in FIG. 4A as an example of the dismantling object 10, the dismantling procedure derivation unit 5 extracts features related to the joints of each side from the air conditioner outdoor unit 13, such as a front feature 15, a back feature 16, a right side feature 17, and a left side feature 18 (for example, features of thin black bands showing the boundaries of the joints as boundary lines 10b).

[0033] On the other hand, in this example, the features of the dismantling object 10S that serves as the dismantling standard for the dismantling target 10 are stored in the dismantling information storage unit 4 as the dismantling standard air conditioner outdoor unit image data 14S, which is composed of features related to the joints of each side from the air conditioner outdoor unit 13S (for example, features of the thin black band portions indicating the boundaries of the joints as boundary lines 10Sb), such as a front feature 15S, a back feature 16S, a right side feature 17S, and a left side feature 18S, as shown in FIG. 4B.

[0034] Next, in step S3, based on the features extracted in step S2 and the features in the disassembly information stored in the disassembly information storage unit 4, the disassembly procedure derivation unit 5 compares the features as shown in FIG. 5 to calculate a degree of agreement.

[0035] For example, comparing the extracted feature in FIG. 4A with the stored feature in FIG. 4B corresponds to a comparison with the top feature in the table in FIG. 5. The degree of match is 98.5%, which corresponds to disassembly procedure A. As another example, comparing the second feature in the table in FIG. 5 with the feature in FIG. 4B, the degree of match is 1.0%, which corresponds to disassembly procedure B. Comparing the bottom feature in the table in FIG. 5 with the feature in FIG. 4B, the degree of match is 0.5%, which corresponds to disassembly procedure C. Here, it is shown that the disassembly procedures differ depending on the degree of match between the features.

[0036] Next, in step S4, the disassembly procedure associated with the feature having the highest degree of match among those found in step S3 is determined to be the disassembly procedure with the highest priority, and is derived as the disassembly procedure by the disassembly procedure derivation unit 5. In the previous example, the disassembly procedure associated with the feature having the highest degree of match is A, and the disassembly procedure derivation unit 5 derives disassembly procedure A. This makes it possible for the disassembly procedure derivation unit 5 to derive and select a disassembly procedure associated with a feature that is closest to the extracted feature among the features stored in the disassembly information storage unit 4, even if there is no feature that matches 100%.

[0037] Next, in step S5, under the control of disassembly procedure deriving unit 5, robot arm 7 and disassembly hand 8 disassemble disassembly object 10 in accordance with the disassembly procedure derived by disassembly procedure deriving unit 5. In the case of the result shown in Fig. 5, disassembly procedure A with the highest degree of agreement is set as the disassembly procedure, and disassembly object 10 is disassembled in order of (1) to (4) shown in Fig. 6, such as top cover 19, front cover 20, left side cover 21, right side cover 22, and internal organs 23.

[0038] In the first embodiment, the method of extracting the characteristic parts in step S2 can be appropriately selected according to the disassembly target 10. In the above embodiment, a learning model trained by machine learning is used, but if the features are clear, they may be extracted using a simple image processing method such as contour extraction from the image data. In addition, in the case of a complex characteristic part, they may be extracted by combining a learning model trained by machine learning with a simple image processing method such as contour extraction.

[0039] As described above, according to the first embodiment, the disassembly procedure deriving unit 5 is provided, which extracts a characteristic part of the disassembly object 10 based on the captured data, calculates the degree of agreement between the extracted characteristic and the characteristic stored in the disassembly information storage unit 4, and selects a disassembly procedure associated with the characteristic of the disassembly information storage unit 4 that has the highest degree of agreement, and disassembly is possible according to the disassembly procedure derived by the disassembly procedure deriving unit 5. This makes it possible to disassemble the disassembly object 10 even if the disassembly procedure is not stored or if the state of the disassembly object 10 is different, such as damaged or deformed. As a result, disassembly without relying on manpower is possible even for used home appliances whose disassembly method differs depending on the manufacturer or model number, and the labor required for disassembly of the disassembly object 10 can be reduced.

[0040] (Modification of the first embodiment) As a modified example of the present embodiment 1, depending on the used home appliance as shown in the present embodiment 1, there is a possibility that the dismantling target 10 may be damaged or deformed depending on the usage condition of the owner or the storage condition of the stockyard of the discarded home appliance. Therefore, in addition to the dismantling flow up to step S5 in Fig. 3, step S6 of whether separation is possible and step S7 of whether dismantling is completed may be further provided in the dismantling procedure derivation unit 5 as shown in Fig. 7.

[0041] In step S6, the dismantling procedure derivation unit 5 determines whether or not a dismantling part has been dismantled, for example separated, from the dismantling object 10 based on a difference between image data of the dismantling object 10 before dismantling, which has been imaged in advance by the overall detection unit 2 or the detailed detection unit 3, and image data of the dismantling object 10 after dismantling, which has been imaged by the overall detection unit 2 or the detailed detection unit 3. By carrying out this step S6, it is possible to detect parts of the dismantling object 10 that cannot be dismantled due to damage or deformation, etc.

[0042] If disassembly is completed in step S6, the disassembly procedure deriving unit 5 determines in step S7 whether all disassembly is complete, and if not, the next cover in the disassembly order is disassembled in step S5.

[0043] If disassembly is not possible in step S6, in step S4, a disassembly procedure with the second highest degree of matching among the degrees of matching found in step S3, which is the degree of matching found immediately before, is derived, and steps S4 to S6 are repeated until all disassembly is completed.

[0044] By repeating steps S5 to S7 described above until all dismantling is completed in step S7, dismantling can be performed in any condition, including the occurrence of damage or deformation of the object 10 to be dismantled.

[0045] In addition, the dismantling procedure derivation unit 5 associates the dismantling procedure that was successfully dismantled in step S6 with the features of the dismantling object 10 extracted in step S2 and stores the associated dismantling procedure in the dismantling information storage unit 4, thereby significantly shortening the processing time required to dismantle a similar dismantling object 10 from the next time onwards.

[0046] (Embodiment 2) Fig. 8 is a schematic diagram of a dismantling device 1 according to a second embodiment of the present invention. In Fig. 8, the same components as those in Fig. 2 are given the same reference numerals, and the description thereof will be omitted.

[0047] In the second embodiment of the present invention shown in FIG. 8, a plurality of overall detection units 2 are provided to surround the dismantling object 10, and imaging data is acquired. As an example, a pair of cameras may be arranged in a direction opposite to the conveying direction. Specifically, for example, a camera of the first overall detection unit 2 that images the dismantling object 10 from the upstream side of the conveying direction and a camera of the second overall detection unit 2 that images the dismantling object 10 from the downstream side of the conveying direction may be arranged. Alternatively, differently from this, a camera of the third overall detection unit 2 that images the dismantling object 10 from one side in the width direction intersecting with the conveying direction and a camera of the fourth overall detection unit 2 that images the dismantling object 10 from the other side in the width direction may be arranged.

[0048] In this way, the object 10 to be disassembled on the fixed holder can be imaged without blind spots, and the features can be extracted more accurately and easily. In other words, since detection can be performed from multiple directions, the accuracy of feature extraction is improved. In addition, since the number of detections can be reduced compared to the first embodiment, the detection time (and therefore the time required for disassembly) can be shortened.

[0049] (Embodiment 3) Fig. 9 is a schematic diagram of a dismantling device 1 according to a third embodiment of the present invention. In Fig. 9, the same components as those in Figs. 2 and 8 are designated by the same reference numerals, and the description thereof will be omitted.

[0050] 9, a fixed rotation unit 24 is provided to rotate the disassembly target 10 to acquire image data. Instead of transportation by the transport unit 12, the fixed rotation unit 24 is configured to rotate the disassembly target 10 on a turntable by a motor or the like.

[0051] According to such a configuration, detection can be performed without moving the overall detection unit 2 or the detail detection unit 3 to detect from multiple directions, thereby reducing the time required to move the overall detection unit 2 or the detail detection unit 3. Also, compared to the second embodiment, there is no need to provide multiple detection units, making it possible to achieve this at low cost.

[0052] In addition, by appropriately combining any of the various embodiments or modifications described above, it is possible to achieve the effects of each of them. In addition, combinations of embodiments, combinations of examples, or combinations of embodiments and examples are possible, and combinations of features of different embodiments or examples are also possible. [Industrial Applicability]

[0053] By using the dismantling procedure selection device, the dismantling procedure selection method, and the dismantling device according to the above aspects of the present invention, it is possible to break away from the dismantling process that has relied on human labor. Conventionally, automation was difficult because the positions of fixing members or the dismantling method differed for each model. By solving this problem, it is possible to reduce the number of people and further promote the utilization of resources from used home appliances. [Explanation of symbols]

[0054] 1 Demolition equipment 1A Dismantling procedure selection device 2. Overall detection section 3. Detailed detection section 4. Dismantling information storage section 5. Disassembly procedure derivation section 6 Fixing and transport section 7. Robot Arm 8 Dismantling Hand 9. Control Unit 10 Objects to be dismantled 10a Fixing member 10b Border 10S Demolition 10Sb border 11 Fixed holding part 12 Conveyor section 13. Air conditioner outdoor unit 13S Dismantling standard air conditioner outdoor unit 14 Air conditioner outdoor unit image data 14S Dismantling standard air conditioner outdoor unit image data 15 Front Features 15S Dismantling Standards Front Features 16 Back Features 16S Disassembly Standard Rear Features 17 Right side features 17S Right side features of dismantling standard 18 Left side features 18S Disassembly Standard Left Side Features 19 Top cover 20 Front cover 21 Left side cover 22 Right side cover 23 Offal 24 Fixed rotating part 101 Display Panel 102 Transport unit 103 First fixing member detection unit 104 Second fixing member detection unit 105 Fixed component dismantling unit

Claims

1. A dismantling information storage unit that stores a plurality of dismantling information including a dismantling procedure for separating or disassembling a dismantled object, which is a predetermined dismantling criterion for the dismantling object, for each of the dismantling parts; a disassembly procedure derivation unit that calculates a degree of agreement between a first feature that is a feature of the disassembly object extracted from data captured by at least one of an entire detection unit that captures an image of the entire disassembly object and a detail detection unit that captures an image of at least a part of the disassembly object, and a second feature that is a feature of the disassembly information stored in the disassembly information storage unit and associated with a disassembly procedure of the component parts, and selects a disassembly procedure associated with the second feature of the disassembly information storage unit that has the highest degree of agreement; Preparation, The disassembly information includes: A disassembly procedure for the components; the second characteristic being associated with a disassembly procedure of the component parts; As the first feature, A boundary line of a boundary of a component part of the dismantling object; A structure of a fastening portion between components constituting a housing of the object to be disassembled; Position information of fastening members between parts constituting the dismantling object; The material of the component parts of the dismantling object is at least one of the following: As the second feature, A boundary line of a boundary of a component part of the disassembled object; A structure of a fastening portion between components constituting the housing of the disassembled object; Position information of fixing members between parts constituting the disassembled object; and the material of the component parts of the dismantled object.

2. The dismantling procedure derivation unit determines whether or not a dismantling part has been dismantled from the dismantling object based on a difference between data of the dismantling object before dismantling, which has been imaged in advance by the overall detection unit or the detail detection unit, and data of the dismantling object after dismantling in which the dismantling procedure has been performed, which has been imaged by the overall detection unit or the detail detection unit. The disassembly procedure selection device according to claim 1.

3. the disassembly procedure deriving unit, when disassembly of the disassembly parts from the disassembly target object fails, selects a disassembly procedure having a second highest degree of agreement after the disassembly procedure having the highest degree of agreement. The disassembly procedure selection device according to claim 2.

4. When disassembly of the disassembly target object has failed, the disassembly procedure deriving unit selects a disassembly procedure having a second highest degree of agreement after the disassembly procedure having the highest degree of agreement, dismantling the object using a dismantling procedure that has the second highest degree of agreement after the most highly consistent dismantling procedure, and if dismantling is still not possible, dismantling the object using a dismantling procedure that has the second highest degree of agreement after the second most highly consistent dismantling procedure, and repeating the change of the dismantling procedure until dismantling is possible; a disassembly procedure for the last disassembly is associated with features of the disassembly object and stored in the disassembly information storage unit; The disassembly procedure selection device according to claim 3.

5. The whole or part of the object to be dismantled is photographed with a camera, a dismantling procedure derivation unit determines a degree of agreement between a first feature, which is a feature of the dismantling object extracted from the captured data, and a second feature, which is a feature associated with the dismantling procedure of the component parts, and which is predetermined and stored in a dismantling information storage unit that stores a plurality of pieces of dismantling information including a dismantling procedure of the component parts for separating or disassembling dismantled objects that are dismantling criteria for the dismantling object, The disassembly procedure deriving unit selects a disassembly procedure associated with the second feature in the disassembly information storage unit that has the highest degree of agreement, and The disassembly information includes: A disassembly procedure for the components; the second characteristic being associated with a disassembly procedure of the component parts; As the first feature, A boundary line of a boundary of a component part of the dismantling object; A structure of a fastening portion between components constituting a housing of the object to be disassembled; Position information of fastening members between parts constituting the dismantling object; The material of the component parts of the dismantling object is at least one of the following: As the second feature, A boundary line of a boundary of a component part of the disassembled object; A structure of a fastening portion between components constituting the housing of the disassembled object; Position information of fixing members between parts constituting the disassembled object; and the material of the components of the dismantled object.

6. After selecting the disassembly procedure, when executing the selected disassembly procedure, the dismantling procedure deriving unit determines whether or not a dismantling portion has been dismantled from the dismantling object based on a difference between data of the dismantling object before dismantling that has been previously imaged and data of the dismantling object that has been imaged after dismantling; The disassembly procedure selection method according to claim 5 .

7. After selecting the disassembly procedure, when executing the selected disassembly procedure, selecting a disassembly procedure having a second highest degree of agreement after the disassembly procedure having the highest degree of agreement when disassembly of the disassembly part from the disassembly target object has failed; The disassembly procedure selection method according to claim 6.

8. In the disassembly procedure derivation unit, When disassembly of the disassembly part from the disassembly target object has failed, a disassembly procedure having a second highest degree of agreement after the disassembly procedure having the highest degree of agreement is selected, dismantling the object using a dismantling procedure that has the second highest degree of agreement after the most highly consistent dismantling procedure, and if dismantling is still not possible, dismantling the object using a dismantling procedure that has the second highest degree of agreement after the second most highly consistent dismantling procedure, and repeating the change of the dismantling procedure until dismantling is possible; a disassembly procedure for the last disassembly is associated with features of the disassembly object and stored in the disassembly information storage unit; The disassembly procedure selection method according to claim 7.

9. A disassembly procedure selection device according to any one of claims 1 to 3, a robot arm that dismantles the object to be dismantled according to the dismantling procedure selected by the dismantling procedure selection device,

Images