Apparatus for determining defect in saggar for use in secondary battery cathode material production process, method for determining defect by the same, and machine-readable medium

Abstract

According to the present invention, a defect determination device (700) for a secondary battery cathode material production process comprises: a photographic device (750 or 760) installed in a sintering device for a secondary battery cathode material production process; The control unit (730) includes a processor (710) and a memory (720), wherein the control unit (730) acquires an image of the saga (10) by the imaging device (750 or 760) (310), detects defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image (320), calculates a first probability for the first defect to an Nth probability for the Nth defect (330), compares the first probability to the Nth probability (510), sets the largest probability as the first probability and the next largest probability as the second probability (520), compares the first probability with a predetermined first reference value (530), and if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability is the Determining as a defect of the saga (10) (540), and if, as a result of the comparison (530), the first probability is not greater than the first reference value, the second probability is compared with a predetermined second reference value (550), and if, as a result of the comparison (550), the second probability is greater than the second reference value, the defect corresponding to the second probability is determined as a defect of the saga (10) (560), and if, as a result of the comparison (550), the second probability is not greater than the second reference value, the saga (10) is determined to be defect-free (570).

Description

Technology Field

[0001] The present invention relates to a device for determining defects in saggar for a secondary battery cathode material production process, a method for determining defects in saggar by the device, and a machine-readable medium. More specifically, the invention relates to a device for determining defects in saggar for a secondary battery cathode material production process, a method for determining defects in saggar by the device, and a machine-readable medium capable of determining defects in saggar with high accuracy without omission. Background Technology

[0003] Generally, a saga used in the secondary battery cathode material production process is a box-shaped container with an open top, which is transported into a high-temperature kiln containing cathode materials by a conveyor system. After the firing process, it is inverted to empty the processed cathode materials inside, clean the interior, and then transported back into the kiln after receiving cathode materials to be processed. As the saga undergoes this secondary battery cathode material production process repeatedly, fatigue accumulates in the material due to high-temperature environments, mechanical shock, chemical reactions, etc., and the saga may eventually be damaged.

[0004] Damage or defects occurring in the saga can be classified into cracks, breakage, inversion failure, surface peeling (or abrasion), etc. For example, if the calcination process of a secondary battery cathode material is carried out using a saga with surface peeling, the peeled material from the surface may be mixed into the cathode product, thereby degrading its quality. If a damaged saga is used, the cathode material may leak out of the saga, causing loss and leading to reduced productivity, or the process may be halted as the saga cannot be transported. Additionally, when the saga is inverted, poor gripping due to the damaged area may cause the saga to fall onto the cathode product, leading to quality degradation or process interruption. If a saga with an inversion failure is used, the cathode material is fed into the calcination furnace one more time, which may degrade the quality of the product.

[0005] To prevent such quality degradation and productivity loss, a large quantity of saga can be replaced in bulk after a certain period of use, but replacement costs may be wasted because even good saga is replaced.

[0006] On the other hand, a worker can determine whether to replace the saga by visually inspecting its condition based on a limit sample, but this may have a negative impact on the secondary battery cathode material production process.

[0007] There is a growing need in the relevant industry to detect, classify, and accurately determine defects in saga without omission, and to respond appropriately, before defective or damaged saga negatively affect the quality and productivity of secondary battery cathode materials. Prior art literature

[0009] Republic of Korea Published Patent 10-2022-0071031 The problem to be solved

[0010] The present invention, devised to solve the aforementioned problems, provides a defect determination device for a secondary battery cathode material production process capable of determining defects in a saga with high accuracy without omission, a method for determining defects in a saga by the device, and a machine-readable medium.

[0012] The objects of the present invention are not limited to those mentioned above, and other unmentioned objects and advantages of the present invention may be understood from the following description and will be more clearly understood by the embodiments of the present invention. Furthermore, it will be readily apparent that the objects and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims. means of solving the problem

[0014] To solve the above-mentioned problem, the present invention provides a defect determination device (700) for a secondary battery cathode material production process, comprising: a photographic device (750 or 760) installed in a sintering device for a secondary battery cathode material production process; and includes a control unit (730) comprising a processor (710) and a memory (720), wherein the control unit (730) acquires an image of the saga (10) by the imaging device (750 or 760) (310), detects defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image (320), calculates a first probability for the first defect to an Nth probability for the Nth defect (330), compares the first probability to the Nth probability (510), sets the largest probability as the first probability and the next largest probability as the second probability (520), compares the first probability with a predetermined first reference value (530), and if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability is the Determining (540) that the first probability is not greater than the first reference value as a result of the comparison (530), comparing the second probability with a predetermined second reference value (550), determining (560) that the defect corresponding to the second probability is greater than the second reference value as a result of the comparison (550), determining (570) that the second probability is not greater than the second reference value as a result of the comparison (550), determining (570) that the first probability is not greater than the second reference value, and after the determination (570), comparing (610) that the sum of the first probability and the second probability is greater than the third reference value,A defect determination device for a saga is provided, which determines a defect corresponding to the first probability as a defect of the saga (620), and determines the saga (10) as defect-free (630) if the sum of the first probability and the second probability is not greater than the third reference value.

[0015] In one embodiment of the present invention, the items of the defect may include at least cracks and breakage.

[0016] In one embodiment of the present invention, the defect item may further include a surface signifying defect-free.

[0017] In one embodiment of the present invention, the defect may further include inversion defects, foreign matter, and peeling.

[0018] In one embodiment of the present invention, the imaging device (750 or 760) can photograph the saga (10) from above toward the interior (15) of the saga (10).

[0019] The present invention relates to a method for determining defects in a saga by a defect determination device (700) for a secondary battery cathode material production process, comprising: a step (310) of acquiring an image of a saga (10) by a shooting device (750 or 760); a step (320) of detecting defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image; a step (330) of calculating a first probability for the first defect to an Nth probability for the Nth defect; a step (510) of comparing the first probability to the Nth probability; a step (520) of setting the largest probability resulting from the comparison (510) as the first probability and the next largest probability as the second probability; and a step (530) of comparing the first probability with a predetermined first reference value. A step (540) of determining the defect corresponding to the first probability as a defect of the saga (10) if, as a result of the comparison (530), the first probability is greater than the first reference value; a step (550) of comparing the second probability with a predetermined second reference value if, as a result of the comparison (530), the first probability is not greater than the first reference value; a step (560) of determining the defect corresponding to the second probability as a defect of the saga (10) if, as a result of the comparison (550), the second probability is greater than the second reference value; a step (570) of determining the saga (10) as defect-free if, as a result of the comparison (550), the second probability is not greater than the second reference value; and a step (610) of comparing the sum of the first probability and the second probability with a predetermined third reference value after the determination (570). As a result of the above comparison (610), if the sum of the first probability and the second probability is greater than the third reference value, a step (620) of determining the defect corresponding to the first probability as the defect of the saga;A method for determining a defect in a saga, comprising the step (630) of determining the saga (10) as defect-free when the sum of the first probability and the second probability is not greater than the third reference value.

[0020] In one embodiment of the present invention, the items of the defect may include at least cracks and breakage.

[0021] In one embodiment of the present invention, the defect item may further include a surface signifying defect-free.

[0022] In one embodiment of the present invention, the defect may further include inversion defects, foreign matter, and peeling.

[0023] In one embodiment of the present invention, the imaging device (750 or 760) can photograph the saga (10) from above toward the interior (15) of the saga (10).

[0024] The present invention stores code executable by a processor of a control unit as a machine-readable medium, wherein when the code is executed by the processor, the processor acquires an image of a saga (10) by a shooting device (750 or 760) (310), detects defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image (320), calculates a first probability for the first defect to an Nth probability for the Nth defect (330), compares the first probability to the Nth probability (510), sets the largest probability as the first probability and the next largest probability as the second probability (520), compares the first probability with a predetermined first reference value (530), and if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability is the Determining as a defect of the saga (10) (540), and if, as a result of the comparison (530), the first probability is not greater than the first reference value, comparing the second probability with a predetermined second reference value (550), and if, as a result of the comparison (550), the second probability is greater than the second reference value, determining the defect corresponding to the second probability as a defect of the saga (10) (560), and if, as a result of the comparison (550), the second probability is not greater than the second reference value, determining the saga (10) as defect-free (570), and after the determination (570), comparing the sum of the first probability and the second probability with a predetermined third reference value (610), and if, as a result of the comparison (610), the sum of the first probability and the second probability is greater than the third reference value, determining the defect corresponding to the first probability as a defect of the saga (620), and the first If the sum of the probability and the second probability is not greater than the third reference value,Provides a machine-readable medium that determines (630) the above saga (10) as defect-free.

[0025] In one embodiment of the present invention, the items of the defect may include at least cracks and breakage.

[0026] In one embodiment of the present invention, the defect item may further include a surface signifying defect-free.

[0027] In one embodiment of the present invention, the defect may further include inversion defects, foreign matter, and peeling.

[0028] In one embodiment of the present invention, the imaging device (750 or 760) can photograph the saga (10) from above toward the interior (15) of the saga (10). Effects of the invention

[0030] According to various embodiments of the present invention, in classifying and determining defects in saga, the omission of defects can be reduced and the accuracy of defect determination can be improved. Furthermore, when various embodiments of the present invention are applied, improvement in the quality of secondary battery cathode materials, reduction in downtime of the production process, and improvement in production yield can be expected. Brief explanation of the drawing

[0032] Figure 1 is a conceptual diagram of a calcination apparatus and a defect determination apparatus for a secondary battery cathode material production process. Figure 2 is a perspective view of Saga. Figure 3 illustrates an example of a defect that occurred in a saga. FIG. 4 illustrates a defect determination process for a saga used in a secondary battery cathode material production process according to an embodiment of the present invention. Figure 5 illustrates the decision process executed in post-processing 1 of Figure 4. Figure 6 illustrates the decision process executed in post-processing 2 of Figure 4. Specific details for implementing the invention

[0033] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0034] Although terms such as "first," "second," etc., are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are used merely to distinguish one component from another, and unless specifically stated otherwise, the first component may also be the second component.

[0035] Throughout the specification, unless specifically stated otherwise, each component may be singular or plural.

[0036] In the following, the statement that any configuration is placed on the "upper (or lower)" of a component or on the "upper (or lower)" of a component may mean not only that any configuration is placed in contact with the upper (or lower) surface of said component, but also that another configuration may be interposed between said component and any configuration placed on (or below) said component.

[0037] In addition, where it is stated that one component is "connected," "combined," or "contacted" with another component, it should be understood that while the components may be directly connected or joined to each other, another component may be "interposed" between each component, or each component may be "connected," "combined," or "contacted" through another component.

[0038] Singular expressions used in this specification include plural expressions unless the context clearly indicates otherwise. In this application, terms such as "composed of" or "comprising" should not be interpreted as necessarily including all of the various components or steps described in the specification, and should be interpreted as meaning that some of the components or steps may be omitted or additional components or steps may be included.

[0039] Throughout the specification, "A and / or B" means A, B, or A and B unless specifically stated otherwise, and "C to D" means C or more and D or less unless specifically stated otherwise.

[0041] Hereinafter, various embodiments will be described with reference to the attached drawings.

[0042] Referring to FIG. 1, a conceptual diagram of a calcination device (100) and a defect determination device (700) for a secondary battery cathode material production process is disclosed. As illustrated, the firing apparatus (100) comprises a saga conveyor system (170) for transporting a saga (10) (see FIG. 2), a firing furnace (180) for firing an anode material contained in the interior (15) of the saga (10), a crusher (110) for crushing the anode material contained in the interior (15) of the saga (10) processed in the firing furnace (180), a detector (120) for detecting defects in the saga (10), an inverter (130) for turning the saga (10) over to empty the saga (10), a cleaner (150) for removing the anode material remaining in the interior (15) of the saga (10), a replacement robot (160) for removing the corresponding saga (10) from the saga conveyor system (170) according to a classification result received from a defect determination device (700) described later, and a defect determination device for classifying and determining defects in the saga (10). It may include a device (700).

[0043] As described, the defect determination device (700) of the saga includes a shooting device, such as a camera (750, 760), for acquiring an image of the saga (10) being used in the firing device (100), and a control unit (730) that receives the image acquired from the shooting device (750, 760) and classifies and determines defects therefrom.

[0044] The first camera (750) is installed in the defect detector (120) and can photograph the saga (10), for example, from the upper side. The second camera (760) is installed in the peeling (or abrasion) detector (140) and can photograph the interior (15) of the empty saga (10), for example, from the upper side. The installation location or number of the imaging devices are not limited to those shown and can be determined according to the type of defect to be classified, etc. For example, the camera can be installed in the inverter (130) to photograph the lower surface of the saga (10). Or it can be installed in the crusher (110) to photograph foreign matter (see FIG. 3 (e)) on the anode material contained in the saga (10). The image obtained from the imaging device is provided to the defect determination device (700). The method of provision may be wired or wireless.

[0045] The control unit (730) of the defect determination device (700) includes a processor (710) and a memory (720) in which a program is stored. When this program is read and executed by the processor (710), the processor (710) can perform the defect determination process (300) of the saga (see FIG. 4 to 6) described later, thereby classifying and determining defects (see FIG. 3) of the saga (10) from images received from the imaging device. The defect determination device (700) can transmit the defect determination result to the replacement robot (160), and the replacement robot (160) can retrieve the corresponding saga from the saga conveyor system (170). For example, if peeling (or abrasion) occurs on the saga (10), the saga can be retrieved after a certain usage time depending on the peeling condition.

[0046] The processor (710) may be composed of, for example, a PLC (programmable logic controller), a DDC (direct digital controller), or a DCS (distributed control system).

[0047] In the calcination device (100) for the secondary battery cathode material production process illustrated in FIG. 1, the position or number of each component (110, 120, 130, 140, 150, 160, 170) is not limited to what is illustrated and can be changed as needed. For example, the order of the peeling detector (140) and the cleaner (150) may be reversed, or a separate cleaner may be additionally installed in front of the peeling detector (140).

[0048] Referring to FIG. 2, a perspective view of a saga (10) is shown. As shown, the saga (10) may have a rectangular shape with an open top and an exposed interior (15). A concave cutout is formed in each side wall (11) so that even if a plurality of sagas (10) are stacked, gas can be supplied to the interior (15) through the concave cutout and can flow out from the interior (15). The saga may be formed of a ceramic material capable of withstanding high temperatures.

[0049] Referring to FIG. 3, examples of defects occurring in the saga (10) are illustrated. FIG. 3 (a) shows a fine crack occurring in the saga (10). If the saga (10) is used continuously, the crack may progress to breakage. FIG. 3 (b) shows breakage occurring in the saga (10). If the saga (10) breaks, the cathode material leaks out, resulting in product loss. Furthermore, the saga cannot be transported, causing the secondary battery cathode material production process to stop, which may lead to reduced productivity. Additionally, when the saga (10) is inverted, the damaged part causes poor gripping, and the saga (10) may fall onto the collected cathode material product, leading to product quality degradation and production failures due to post-processing. FIG. 3 (c) shows a failure in inversion. When inverted, the cathode material inside (15) is not completely removed and remains, and since it is fed back into the kiln (180), it may lead to product defects. FIG. 3(d) shows peeling that has occurred on the surface of the saga (10). If the surface peels off, it may be incorporated into the product and lead to a decrease in product quality. FIG. 3(e) shows foreign matter on the anode material contained in the interior (15) of the saga (10). The foreign matter may have fallen from the kiln and may lead to a decrease in product quality.

[0050] Referring to FIG. 4, a defect determination process (300) for a secondary battery cathode material production process according to an embodiment of the present invention is illustrated. This defect determination process (300) of the saga can be carried out by a defect determination device (700) of the saga as described above. As illustrated in FIG. 4, the defect determination process (300) of the saga may include: a step (310) of capturing an image of the saga (10) with a camera (750, 760) and acquiring an image; a step (320) of detecting defects from the acquired image; a step (330) of classifying defects and calculating a probability (or defect classification probability) for each defect; a post-processing step 1 (340) of determining a first defect classification probability and a second defect classification probability; and a post-processing step 2 (350) of re-determining a first defect classification probability and a second defect classification probability.

[0051] In step 310, a shooting device as illustrated in FIG. 1, i.e., a camera (750, 760), can acquire an image of the saga (10) at a defect detector (120) and / or a peeling detector (140), etc. Alternatively, an image of the lower surface of the saga (10) can be acquired at another location where an image of the saga (10) can be acquired, e.g., at an inverter (130), and an image of the surface of the side wall (11) of the saga (10) can be acquired. Alternatively, an image of the interior (15) of the cleaned saga (10) can be acquired at a cleaner (150). The camera (750, 760) may be composed of one or more of, for example, a high-resolution camera, an infrared camera, a depth camera, a thermal imaging camera, and a visible light camera. The image acquired by the shooting device can be transmitted to a control unit (730).

[0052] In step 320, defects occurring in the saga (10) are detected from the image obtained in step 310. The types of defects may include cracks, breakage, inversion defects, peeling, foreign matter, etc., as illustrated in FIG. 3. The types of defects may be used as items for classification and judgment. Additionally, as items for classification and judgment to which AI is applied, surfaces indicating that they are not defects may be further included.

[0053] The detection of such defects can be performed using AI-based image analysis models. For example, various algorithms can be considered, ranging from machine learning techniques such as Sobel or Cannay algorithms, HDC (Harris Corner Detection) algorithm, SIFT (Scale-Invariant Feature Transform), SURF (Speeded Up Robust Features) algorithm, LBP (Local Binary Patterns), GLCM (Gray Level Co-occurrence Matrix), SVM (Support Vector Machine), and Random Forest, to deep learning techniques such as CNN (Convolutional Neural Networks), R-CNN (Region-based CNN), and YOLO (You Only Look Once).

[0054] In step 330, the defects detected in step 320 are classified, and the probability (or defect classification probability) for each defect is calculated. As in step 320, this can be performed using an AI-based image analysis model.

[0055] In post-processing 1 (340), defects are determined based on the defect classification probability of the classified defects.

[0056] First, in step 510, the defect classification probabilities for each defect obtained in step 330 are compared.

[0057] In step 520, the largest probability resulting from the comparison in step 510 is set as the first probability, and the next largest probability is set as the second probability.

[0058] In step 530, the first probability is compared with a predetermined first reference value. The first reference value can be input by an operator through an input unit (not shown) provided in the control unit (730).

[0059] If the first probability resulting from the comparison in Step 530 is greater than the first reference value, Step 540 is performed. In Step 540, the defect corresponding to the first probability is determined as the defect of the company.

[0060] If the first probability is not greater than the first reference value as a result of the comparison in step 530, step 550 is performed. Step 550 compares the second probability with a predetermined second reference value. The second reference value can be input by an operator through an input unit (not shown) provided in the control unit (730).

[0061] If, as a result of the comparison in Step 550, the second probability is greater than a predetermined second threshold value, Step 560 is performed. In Step 560, the defect corresponding to the second probability is determined as a defect of the company.

[0062] If, as a result of the comparison in step 550, the second probability is not greater than the predetermined second threshold value, step 570 is performed. In step 570, the price is determined to be No Defect. Then, it proceeds to post-processing 2 (350).

[0063] Post-processing 2 (350) re-evaluates the defects based on the defect classification probability of the classified defects.

[0064] First, in step 610, the sum of the first probability and the second probability is compared with a predetermined third reference value. The third reference value can be input by an operator through an input unit (not shown) provided in the control unit (730).

[0065] If, as a result of the comparison in Step 610, the sum of the first probability and the second probability is greater than the third threshold value, Step 620 is performed. In Step 620, the defect corresponding to the first probability is determined as the defect of the company.

[0066] If the process proceeds from step 570 to step 620, what was determined to be defect-free in step 570 is modified to determine the defect corresponding to the first probability as the defect of the saga.

[0067] If, as a result of the comparison in Step 610, the sum of the first and second probabilities is not greater than the third threshold value, Step 630 is performed. Here, Saga is determined to be free of defects.

[0068] If the process proceeds from Step 570 to Step 630, the result is that the determination of no defects in Step 570 is maintained.

[0069] This judgment process can be determined by the first reference value, the second reference value, and the third reference value. That is, for a specific first probability and a second probability, depending on the first reference value, the second reference value, and the third reference value, the step 540, the step 560, and the step 570 may be passed, and the step 620 and the step 630 may be passed.

[0070] The above-described judgment process is explained below by providing examples of specific defect items and defect classification probabilities.

[0071] Referring to FIG. 5, a judgment process executed in post-processing 1 (340) is illustrated. First, in step 510, the probability for each defect obtained in step 330 is compared. For example, the defects may include cracks and breakage, which are critical defects that must not be omitted among the defects shown in FIG. 3. And for the AI's comparison judgment, defect-free status may be included as a single item called 'surface'. Accordingly, the first probability for the first defect, the second probability for the second defect, and the third probability for the third defect are compared. The defects are exemplified as being based on images obtained by capturing with a first camera (750) installed in the defect detector (120).

[0072] In step 520, the largest probability among the first to third probabilities resulting from the comparison in step 510 becomes the first probability, and the next largest probability becomes the second probability (see Table 1).

[0074] turn Defect Name First probability Defect Name Second probability Final decision note 1 crack 95.0 break 3.0 crack Case 1 2 crack 55.0 break 45.0 break Case 2 3 crack 60.0 surface 25.0 Integrity Case3 4 break 55.0 crack 39.0 Flawless ▷ Damage Case 4 5 surface 90.0 crack 10.0 Case 5

[0075] Table 1 shows the first probability and the corresponding defect name, and the second probability and the corresponding defect name for each case (Case 1 to 4).

[0076] In step 530, the first probability is compared with a predetermined first reference value.

[0077] If the first probability is greater than the first threshold value as a result of the comparison in Step 530, the process proceeds to Step 540, where the first defect corresponding to the first probability, the second defect corresponding to the first probability, or the third defect corresponding to the first probability is determined as a defect of the company. Cases 1 and 5 in Table 1 may correspond to this.

[0078] If the result of the comparison in step 530 is that the first probability is not greater than the first reference value, the process proceeds to step 550, where the second probability is compared with a predetermined second reference value.

[0079] If, as a result of the comparison in Step 550, the second probability is greater than the predetermined second threshold value, the process proceeds to Step 560, where the first defect corresponding to the first probability with the second probability, the second defect corresponding to the second probability with the second probability, or the third probability corresponding to the third probability with the second probability is determined as the defect of the saga. Case 2 in Table 1 may correspond to this.

[0080] If, as a result of the comparison in Step 550, the second probability is not greater than the predetermined second threshold value, the process proceeds to Step 570, where the value is determined to be No Defect. Cases 3 and 4 in Table 1 may correspond to this.

[0081] Referring to FIG. 6, a decision process executed in post-processing 2 (350) is illustrated. Post-processing 2 (350) may proceed following post-processing 1 (340). First, in step 610, the sum of the first probability and the second probability is compared with a predetermined third reference value.

[0082] If, as a result of the comparison in Step 610, the sum of the first probability and the second probability is greater than the third threshold value, the process proceeds to Step 620, where the first defect corresponding to the first probability, the second defect corresponding to the second probability, or the third defect corresponding to the third probability is determined as a defect of the company. Cases 1, 2, 4, and 5 in Table 1 may correspond to this.

[0083] If the sum of the first and second probabilities in step 610 is not greater than the third threshold value, the process proceeds to step 630, where the saga is determined to be defect-free. Case 3 in Table 1 may correspond to this.

[0085] The process described above may be implemented in the form of program code that can be executed by various control means or processors and may be recorded or stored on a machine-readable medium. The machine-readable medium may include program code, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software. Examples of machine-readable recording media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program code, such as ROM, RAM, and flash memory. Examples of program code may include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc.

[0087] As described above, according to an embodiment of the present invention, defect determination of saga for a secondary battery cathode material production process can be carried out with high accuracy without omission. Therefore, furthermore, appropriate countermeasures against defects in saga in the secondary battery cathode material production process can be taken more effectively, thereby improving the quality and productivity of the cathode material.

[0089] Although the present invention has been described above with reference to the illustrated drawings, the present invention is not limited by the embodiments and drawings disclosed in this specification, and it is obvious that various modifications can be made by a person skilled in the art within the scope of the technical concept of the present invention. Furthermore, even if the effects of the configuration of the present invention were not explicitly described while explaining the embodiments of the present invention above, it is natural to acknowledge that the effects predictable by said configuration should also be recognized. Explanation of the symbols

[0091] 10: Saga 11: Sidewall 15: Inside 100: Firing apparatus 110: Shredder 120: Fault Detector 130: Inverter 140: Peel-off detector 150: Cleaner 160: Replacement Robot 170: Saga Conveyor System 700: Saga's Fault Determination Device 710: Processor 720: Memory 730: Control unit 750, 760: Camera

Claims

Claim 1 As a defect determination device (700) for a secondary battery cathode material production process, a shooting device (750 or 760) installed in a firing device for a secondary battery cathode material production process;The control unit (730) includes a processor (710) and a memory (720), and the control unit (730) acquires an image of the saga (10) by the imaging device (750 or 760) (310), detects defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image (320), calculates a first probability for the first defect to an Nth probability for the Nth defect (330), compares the first probability to the Nth probability (510), sets the largest probability as the first probability and the next largest probability as the second probability (520), compares the first probability with a predetermined first reference value (530), and if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability is the Determining as a defect of the saga (10) (540), and if, as a result of the comparison (530), the first probability is not greater than the first reference value, comparing the second probability with a predetermined second reference value (550), and if, as a result of the comparison (550), the second probability is greater than the second reference value, determining the defect corresponding to the second probability as a defect of the saga (10) (560), and if, as a result of the comparison (550), the second probability is not greater than the second reference value, determining the saga (10) as defect-free (570), and after the determination (570), comparing the sum of the first probability and the second probability with a predetermined third reference value (610), and if, as a result of the comparison (610), the sum of the first probability and the second probability is greater than the third reference value, determining the defect corresponding to the first probability as a defect of the saga (620), and the first A defect determination device for a saga (10) that determines the saga as defect-free (630) when the sum of the probability and the second probability is not greater than the third reference value.; Claim 2 A defect determining device of a saga, wherein the defect items of claim 1 include at least cracks and breakage. Claim 3 A defect determination device of a saga, wherein the defect item of claim 2 further includes a surface signifying defect-free. Claim 4 A defect determining device of a saga according to claim 3, wherein the defect further includes inversion failure, foreign matter, and peeling. Claim 5 A defect determination device for a saga, wherein the imaging device (750 or 760) images the saga (10) from above toward the interior (15) of the saga (10). Claim 6 A method for determining defects in a saga by a defect determination device (700) for a secondary battery cathode material production process, comprising: a step (310) of acquiring an image of a saga (10) by a shooting device (750 or 760); a step (320) of detecting defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image; a step (330) of calculating a first probability for the first defect to an Nth probability for the Nth defect; a step (510) of comparing the first probability to the Nth probability; a step (520) of setting the largest probability resulting from the comparison (510) as the first probability and the next largest probability as the second probability; a step (530) of comparing the first probability with a predetermined first reference value; and, if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability is the A step (540) of determining as a defect of the saga (10); a step (550) of comparing the second probability with a predetermined second reference value if, as a result of the comparison (530), the first probability is not greater than the first reference value; a step (560) of determining the defect corresponding to the second probability as a defect of the saga (10) if, as a result of the comparison (550), the second probability is greater than the second reference value; a step (570) of determining the saga (10) as defect-free if, as a result of the comparison (550), the second probability is not greater than the second reference value; a step (610) of comparing the sum of the first probability and the second probability with a predetermined third reference value after the determination (570); a step (620) of determining the defect corresponding to the first probability as a defect of the saga if, as a result of the comparison (610), the sum of the first probability and the second probability is greater than the third reference value.A method for determining a defect in a saga, comprising the step (630) of determining the saga (10) as defect-free if the sum of the first probability and the second probability is not greater than the third reference value.; Claim 7 A method for determining defects in a saga according to claim 6, wherein the defect items include at least cracks and breakage. Claim 8 A method for determining a defect in a saga according to claim 7, wherein the defect item further includes a surface meaning defect-free. Claim 9 A method for determining defects in a saga according to claim 8, wherein the defects further include inversion failure, foreign matter, and peeling. Claim 10 A method for determining a defect in a saga, wherein the imaging device (750 or 760) images the saga (10) from above toward the interior (15) of the saga (10). Claim 11 As a machine-readable medium, code executable by a processor of a control unit is stored, and when the code is executed by the processor, the processor acquires an image of the saga (10) by a shooting device (750 or 760) (310), detects defects including at least a first defect to an Nth defect (where N is a natural number greater than or equal to 2) of the saga (10) from the acquired image (320), calculates a first probability for the first defect to an Nth probability for the Nth defect (330), compares the first probability to the Nth probability (510), sets the largest probability as the first probability and the next largest probability as the second probability (520), compares the first probability with a predetermined first reference value (530), and if the first probability is greater than the first reference value as a result of the comparison (530), the defect corresponding to the first probability of the saga (10) Determining as a defect (540), and if, as a result of the comparison (530), the first probability is not greater than the first reference value, comparing the second probability with a predetermined second reference value (550), and if, as a result of the comparison (550), the second probability is greater than the second reference value, determining the defect corresponding to the second probability as a defect of the saga (10) (560), and if, as a result of the comparison (550), the second probability is not greater than the second reference value, determining the saga (10) as defect-free (570), and after the determination (570), comparing the sum of the first probability and the second probability with a predetermined third reference value (610), and if, as a result of the comparison (610), the sum of the first probability and the second probability is greater than the third reference value, determining the defect corresponding to the first probability as a defect of the saga (620), and the first probability and the second probability If the sum is not greater than the third reference value mentioned above,A machine-readable medium that determines the above saga (10) as defect-free (630). Claim 12 In claim 10, the defect item comprises at least cracks and breakage, a machine-readable medium. Claim 13 In claim 12, the item of the defect further comprises a surface signifying defect-free, a machine-readable medium. Claim 14 A machine-readable medium according to claim 13, wherein the defect further comprises inversion failure, foreign matter, and peeling. Claim 15 In claim 11, the imaging device (750 or 760) is a machine-readable medium that images the saga (10) from above toward the interior (15) of the saga (10).

Images