Electrolytic tank pole plate fault detection method and device, electronic equipment and storage medium

Abstract

The invention relates to an electrolytic bath pole plate fault detection method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining to-be-detected infrared image data of a target electrolytic bath pole plate; threshold segmentation processing is carried out on the infrared image data to be detected according to a target segmentation threshold, a target binary image is obtained, and the target segmentation threshold is a threshold in a preset segmentation threshold array; according to a preset connected domain fault judgment rule, identifying a fault plate in the target binary image; and counting all fault plates to obtain a fault detection result of the target electrolytic cell pole plate. The short-circuit fault automatic inspection of the copper electrolytic cell is realized based on the infrared thermal imaging technology, the short-circuit fault inspection efficiency can be effectively improved, and the short-circuit fault of the copper electrolytic cell polar plate can be accurately identified.

Description

Technical Field

[0001] The present invention relates to the field of infrared detection technology, and in particular to a method, device, electronic equipment and storage medium for detecting faults of an electrolytic cell plate. Background Art

[0002] During the copper electrolytic refining process, if there are abnormal phenomena such as uneven plate arrangement, plate deformation, severe anode burrs, and unqualified electrolyte quality, the current density on the plate will be unevenly distributed, and the cathode copper will easily grow "nodules" during the reaction until it contacts the anode. The short-circuited electrode will stop electrolyzing, and the electrical energy will be consumed in the form of heat energy, resulting in increased production energy consumption and decreased output; the current on the short-circuited electrode will increase significantly, resulting in a decrease in the current density on other electrodes in the same tank, further reducing the cathode copper output and having a bad impact on the electrolytic operation status.

[0003] The current short circuit inspection in electrolysis workshops generally uses reed switch meters or infrared thermal imagers. These methods require operators to use handheld devices to inspect electrodes one by one and then mark short circuits. This detection method is inefficient, takes a long time for a single test, and has a low detection frequency. It consumes electricity and reduces the amount of electrolyte. In addition, there is severe acid mist on site, which has a bad impact on the health of workers who perform long-term inspections. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present application provide a method, device, electronic device and readable storage medium for detecting electrolytic cell plate faults that can accurately identify short-circuit faults in multi-layered copper electrolytic cells. The specific solutions are as follows: In a first aspect, an embodiment of the present application provides a method for detecting a fault in an electrolytic cell plate, comprising: Acquire infrared image data of the target electrolytic cell plate to be inspected; Performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; According to a preset connected domain fault judgment rule, identifying a faulty plate in the target binary image; All faulty plates are counted to obtain the fault detection result of the target electrolytic cell plate.

[0005] According to a specific implementation of the embodiment of the present application, the step of obtaining infrared image data of the target electrolytic cell plate to be detected includes: Acquire the areas to be detected corresponding to multiple points of the electrolytic cell image taken by the infrared detector; Converting the area to be detected into a regular rectangular area based on affine transformation; Divide the rectangular area into a plurality of plates; Classifying the plate into a first plate and a second plate based on a preset grayscale threshold determination rule, wherein the first plate is a non-cloth-covered plate and the second plate is a cloth-covered plate; Correction processing is performed on the first plate and the second plate respectively to obtain the infrared image data to be detected.

[0006] According to a specific implementation of the embodiment of the present application, the classifying the blocks into the first block and the second block based on a preset gray threshold determination rule includes: Label each section in a preset order; If the absolute value of the difference between the grayscale means of two consecutive blocks is greater than a preset grayscale threshold, the larger block of the two consecutive blocks is determined to be the first block; The other blocks other than the first block are determined as the second blocks.

[0007] According to a specific implementation of the embodiment of the present application, the correction processing is performed on the first plate and the second plate respectively to obtain the infrared image data to be detected, including: Correcting the first plate according to a preset grayscale correction threshold to obtain first infrared image data; Calculating the average of the grayscale values ​​of the second plate in a preset grayscale range to obtain the second infrared image data; The infrared image data to be detected is obtained by combining the first infrared image data and the second infrared image data.

[0008] According to a specific implementation of the embodiment of the present application, the identifying the faulty plate in the target binary image according to the preset connected domain fault judgment rule includes: Performing a closing operation on the target binary image according to a preset opening and closing operation core to obtain a plurality of connected domains; Performing connected domain correction processing according to relevant parameters of each connected domain to obtain multiple available connected domains, wherein the relevant parameters include area, width and height; Calculate the grayscale mean of the blocks corresponding to each available connected domain respectively; If the grayscale mean is greater than or equal to a preset fault grayscale threshold, the block is determined as a faulty block.

[0009] According to a specific implementation of the embodiment of the present application, after performing a closing operation on the target binary image according to a preset opening and closing operation core to obtain multiple connected domains, the method further includes: Determine whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width and the maximum height; If it is determined to iterate the target segmentation threshold, in the preset segmentation threshold array, the next segmentation threshold adjacent to the current segmentation threshold is selected as a new target segmentation threshold, and the target binary image is reacquired according to the new target segmentation threshold; If it is determined not to iterate the target segmentation threshold, the step of performing connected domain correction processing according to relevant parameters of each connected domain to obtain a plurality of available connected domains is continued.

[0010] According to a specific implementation of the embodiment of the present application, determining whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width, and the maximum height includes: If the number of connected domains, the maximum width, and the maximum height meet at least one of the preset iteration conditions, determining to iterate the target segmentation threshold; The preset iteration conditions include: the number of the connected domains is greater than or equal to a preset number threshold, the maximum width of the connected domain is greater than a preset width threshold, and the maximum height of the connected domain is less than a preset height threshold.

[0011] In a second aspect, an embodiment of the present application provides an electrolytic cell plate fault detection device, comprising: An acquisition module, used for acquiring infrared image data of the target electrolytic cell plate to be detected; A segmentation module, used for performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; An identification module, used to identify the faulty plate in the target binary image according to a preset connected domain fault judgment rule; The statistical module is used to count all faulty plates to obtain the fault detection result of the target electrolytic cell plate.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the electrolytic cell plate fault detection method described in the first aspect.

[0013] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the electrolytic cell plate fault detection method described in the first aspect.

[0014] In summary, the present application provides a method, device, electronic device and storage medium for detecting faults of electrolytic cell plates, including: obtaining infrared image data to be detected of a target electrolytic cell plate; performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; identifying the faulty plate in the target binary image according to a preset connected domain fault judgment rule; and counting all faulty plates to obtain the fault detection result of the target electrolytic cell plate. The present invention realizes automatic inspection of short-circuit faults of copper electrolytic cells based on infrared thermal imaging technology, which can effectively improve the efficiency of short-circuit fault inspection and accurately identify short-circuit faults of copper electrolytic cell plates. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0016] Figure 1 A schematic diagram of an application scenario of an electrolytic cell plate fault detection method provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart of a method for detecting a fault in an electrolytic cell plate provided in an embodiment of the present application; Figure 3 A schematic diagram of the steps for obtaining infrared image data to be detected provided in an embodiment of the present application; Figure 4 A schematic diagram of the area to be detected of the infrared image of the electrolytic cell provided in an embodiment of the present application; Figure 5 A schematic diagram of the steps of dividing the first block and the second block provided in an embodiment of the present application; Figure 6 A schematic diagram of a first plate and a second plate provided in an embodiment of the present application; Figure 7 A schematic diagram of the steps of respectively correcting the first plate and the second plate provided in an embodiment of the present application; Figure 8 A schematic diagram of the steps for identifying a faulty module provided in an embodiment of the present application; Fig. 9 A schematic diagram of the steps of iterating target segmentation threshold provided in an embodiment of the present application; Fig.10 A schematic diagram of obtaining a target binary image based on target segmentation threshold division provided in an embodiment of the present application; Fig.11Another schematic diagram of obtaining a target binary image based on target segmentation threshold provided in an embodiment of the present application; Fig.12 Another schematic diagram of obtaining a target binary image based on target segmentation threshold provided in an embodiment of the present application; Fig.13 A schematic diagram of a device module of an electrolytic cell plate fault detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0018] The following describes the embodiments of the present disclosure through specific examples, and those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present disclosure.

[0019] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present disclosure, it should be understood by those skilled in the art that an aspect described herein may be implemented independently of any other aspect, and two or more of these aspects may be combined in various ways. For example, any number of aspects described herein may be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein may be used to implement this device and / or practice this method.

[0020] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present disclosure. The drawings only show components related to the present disclosure rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0021] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects described may be practiced without these specific details.

[0022] As mentioned in the previous background technology section, the existing short-circuit fault detection for copper electrolytic cells often requires manual handheld equipment to detect electrodes one by one, which is inefficient, affects product quality, and also affects the health of workers. Therefore, there is an urgent need for a fault detection solution that can quickly, efficiently and accurately identify short-circuit faults in electrolytic cells.

[0023] The electrolytic cell plate fault detection method provided in the embodiment of the present application can be applied to Figure 1 The electrolytic cell plate fault detection system shown in the figure includes an infrared detector, an infrared detector driving circuit, a field programmable gate array (FPGA) processing system and an ARM processing system.

[0024] In this embodiment, the infrared lens is a shooting lens of an infrared camera, which is used to obtain infrared signals of the electrode plates of the electrolytic cell to be detected.

[0025] The infrared detector is used to convert the infrared signal into an electrical signal. The infrared detector driving circuit is used to convert the electrical signal output by the infrared detector into a parallel digital signal with a preset number of bits, wherein the preset number of bits can be 14 bits. The FPGA processing system is used to process the parallel digital signal in real time, perform infrared image preprocessing, convert the energy data of the infrared image into grayscale data through the AGC algorithm, and output a digital video stream that meets the protocol required by the USB interface chip. The ARM processing system is burned with an embedded Linux system, image and video computer vision processing service program, and can calculate infrared vision processing through opencv and output a real-time streaming protocol (RTSP) infrared video stream. After receiving the RTSP infrared video stream, the PC-side software can display the electrolytic cell fault identification results on the screen device.

[0026] In actual application, the specific structure of the electrolytic cell plate fault detection system can also be adaptively configured based on the needs of the infrared complete equipment in the actual application scenario, which is not described in detail here.

[0027] It should be known that in this embodiment, one or more infrared cameras may be arranged on the pan-tilt head to capture infrared images of the electrode plates of the electrolytic cell to be inspected from a single or multiple angles.

[0028] refer to Figure 2 The present application embodiment provides a method for detecting electrolytic cell plate faults. Figure 1 The electrolytic cell plate fault detection system shown in is taken as an example to illustrate, comprising the following steps: S201, obtaining infrared image data of the target electrolytic cell plate to be inspected.

[0029] In this embodiment, the electrolytic cell plate is a key component in the electrolytic cell, including two parts: a main plate and a pole frame. The electrolytic cell plate can be used as an electronic conductor in the electrolytic cell and effectively separate the electrolyte solution of the cathode and the anode.

[0030] The target electrolytic cell plate in this embodiment can be a copper electrolytic cell plate. Preferably, the target electrolytic cell plate in this embodiment is a copper electrolytic cell plate with a multi-layer cover cloth. It should be noted that the fault detection method proposed in this embodiment can effectively and accurately detect the short circuit fault of the copper electrolytic cell plate with a multi-layer cover cloth.

[0031] The infrared image data to be detected in this embodiment is the grayscale data obtained after image preprocessing of the infrared image taken by the infrared camera set on the pan-tilt head. It should be noted that image preprocessing includes but is not limited to processing such as area screening, plate division, grayscale correction and grayscale calculation. The specific processing steps of image preprocessing can be adaptively configured according to the needs of actual applications.

[0032] In a specific embodiment, 16-bit infrared image data can more completely retain the temperature information of the original electrolytic cell plate. Preferably, the infrared image acquired by the infrared camera in this embodiment is a 16-bit infrared image.

[0033] S202, performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array.

[0034] In this embodiment, the preset segmentation threshold array can be expressed as ,in, is the minimum segmentation threshold, is the maximum segmentation threshold. The larger the N value, the larger the segmentation threshold. In actual application scenarios, segmentation thresholds of different values ​​can effectively improve the accuracy of identifying and locating short-circuited plates under different temperature conditions. This embodiment performs threshold segmentation on the infrared image data to be detected based on the target segmentation threshold, which can effectively avoid the problems of false fault detection and missed fault detection caused by a single threshold.

[0035] In this embodiment, the target binary image is an image obtained by threshold segmentation using a target segmentation threshold that is most suitable for the current electrolytic cell plate temperature condition.

[0036] It should be noted that the target segmentation threshold can be adaptively iterated along with the subsequent recognition process of the preset connected domain fault judgment rule, and sequentially updated in the preset segmentation threshold array to obtain the segmentation threshold that best suits the current electrolytic cell plate temperature condition.

[0037] S203, identifying the faulty plate in the target binary image according to the preset connected domain fault judgment rule.

[0038] In this embodiment, the preset connected domain fault judgment rule includes a connected domain generation step, a connected domain screening step, a connected domain correction step, a segmentation threshold iteration step and a short circuit fault identification step.

[0039] The connected domain generation step is to perform connected domain processing on the target binary image to obtain a certain number of connected domains.

[0040] The connected domain screening step is to merge, remove, and other processes the connected domains that do not meet the recognition requirements based on the connected domain related parameters such as the number of connected domains, the width and height of the connected domain circumscribed rectangle, and the area of ​​the connected domain.

[0041] The connected domain correction step is to correct the grayscale of the folded area of ​​the cover cloth or the heating area of ​​the terminal to ensure the normal operation of the subsequent short-circuit fault identification step.

[0042] The segmentation threshold iteration step is a process of determining whether to iterate the target segmentation threshold according to the relevant parameters of the connected domain. This embodiment can ensure the comprehensiveness and accuracy of the fault identification of the electrolytic cell plate by iterating the target segmentation threshold.

[0043] The short-circuit fault identification step is to perform a threshold judgment on the grayscale mean of the connected domain that meets the conditions after processing according to the above steps. If the grayscale mean of the block corresponding to the connected domain that meets the conditions is greater than or equal to the preset fault grayscale threshold, the block can be identified as a short-circuit block. It should be noted that if the grayscale mean is greater than or equal to the preset fault grayscale threshold, it means that the temperature of the corresponding block area is abnormal.

[0044] This embodiment uses connected domain division to determine whether there is a faulty plate on the electrolytic cell plate, and at the same time determine the position of the faulty plate on the electrolytic cell plate based on the connected domain position corresponding to the faulty plate, thereby achieving rapid positioning of the electrolytic cell plate short-circuit fault and assisting staff in troubleshooting and repairing the fault.

[0045] S204, counting all faulty plates to obtain the fault detection result of the target electrolytic cell plate.

[0046] In this embodiment, the faulty plate can be a cover plate or a non-cover plate in the copper electrolytic cell plate. The number of faulty plates can be one or more. The number of faulty plates to be identified needs to be determined based on the fault condition of the electrolytic cell plate to be detected in the actual application scenario.

[0047] After the electrolytic cell plate fault detection system in this embodiment identifies all faulty plates, the positions of all faulty plates on the electrolytic cell plates can be summarized, and the fault detection results of the target electrolytic cell plates can be displayed in the corresponding software interface to prompt the staff to handle the problematic electrolytic cell plates.

[0048] In summary, this embodiment provides an electrolytic cell plate fault detection method, which obtains infrared image data of the electrolytic cell plate based on infrared thermal imaging technology, and then uses a dynamically updated target segmentation threshold to perform threshold segmentation on the infrared image data to obtain a target binary image. Based on a connected domain fault judgment rule including a target segmentation threshold iteration step, short-circuit faults in the target binary image are identified, and automatic and accurate identification of copper electrolytic cell plate short-circuit faults can be achieved, greatly improving the efficiency of troubleshooting copper electrolytic cell plate short-circuit faults.

[0049] According to a specific implementation of the embodiment of the present application, Figure 3 As shown, the infrared image data to be detected of the target electrolytic cell plate is obtained, including: S301, obtaining the area to be detected corresponding to multiple points of the electrolytic cell image taken by the infrared detector.

[0050] In this embodiment, compared with the electrolytic cell plates without cloth or single-layer cloth, the high-temperature contour of the infrared image of the electrolytic cell plates with multi-layer cloth is more blurred, the cloth has more wrinkles, and because the bottom cloth cannot cover the entire tank surface, the two end plates of the electrolytic cell with multi-layer cloth will produce high-temperature areas that are significantly different from the middle plate. This embodiment divides the plates into different types of first plates and second plates through a preset grayscale threshold judgment rule, and then corrects the grayscale data of the first plate and the second plate respectively, so as to facilitate the subsequent short-circuit fault identification of the first plate and the second plate at the same time.

[0051] In this embodiment, if Figure 4 As shown, after the infrared detector captures the corresponding infrared electrolytic cell image, the electrolytic cell plate fault detection system will automatically obtain the areas to be detected corresponding to multiple preset points in the electrolytic cell image, wherein the preset points can be configured in advance based on the needs of the actual application scenario. In an embodiment, the areas to be detected include area A and area B.

[0052] S302: Convert the area to be detected into a regular rectangular area based on affine transformation.

[0053] In this embodiment, affine transformation is a linear transformation from two-dimensional coordinates to two-dimensional coordinates, which specifically includes translation, rotation, scaling, and shearing of coordinates. Based on affine transformation, an irregular area to be detected can be converted into a regular rectangular area. After the area to be detected is converted into a regular rectangular area, the width and height of the rectangular area can be obtained. This facilitates the subsequent plate division and plate short circuit fault identification based on the regular rectangular area.

[0054] S303, dividing the rectangular area into a plurality of plates.

[0055] In this embodiment, the rectangular area is Equally divided, we can get Assume that the starting plate of the electrolytic cell in the rectangular area is , the termination plate is , that is, the total number of divided plates can be determined as .

[0056] In actual application scenarios, the width of the rectangular area is , the width of a single plate is , the height of the rectangular area is .

[0057] It should be noted that there is a limit threshold for the number of blocks divided in this embodiment. When a rectangular area is divided into multiple blocks, the number of blocks should be less than or equal to the preset number of blocks. .

[0058] S304, classifying the blocks into a first block and a second block based on a preset gray threshold determination rule, wherein the first block is a non-cloth-covered block and the second block is a cloth-covered block.

[0059] In this embodiment, since the two ends of the electrolytic cell may be incompletely covered with cloth, when the two ends of the electrolytic cell are incompletely covered with cloth, the two end plates of the electrolytic cell with multi-layer cloth will produce high-temperature areas that are significantly different from the middle plates. Based on the preset grayscale threshold judgment rule, the rectangular area can be divided into The plates are classified into different categories, and the special plates without cloth (first plate) and the special plates with cloth (second plate) are distinguished, so as to facilitate the subsequent grayscale correction of the first plate and the second plate. is preset.

[0060] In the actual application process, when dividing the plates that need to be corrected, only the special plates of the non-cover cloth can be divided into the first plate, and the special plates of the cover cloth can be divided into the second plate, so as to correct the special plates of the non-cover cloth and the special plates of the cover cloth respectively. Specifically, the step of identifying the special plates and the non-special plates can be to determine the plates with differences in grayscale data and temperature data as special plates, and to determine the plates with matching grayscale data and temperature data as non-special plates. In this embodiment, the step of identifying the special plates and the non-special plates can also be set according to the needs of the actual application scenario, wherein the special plates are plates that need to be corrected, and the non-special plates are plates that do not need to be corrected.

[0061] S305, performing correction processing on the first plate and the second plate respectively to obtain infrared image data to be detected.

[0062] In this embodiment, since the first plate and the second plate have different temperature conditions, the grayscale data in the first plate and the second plate will also produce differences corresponding to the temperature conditions. This embodiment corrects the grayscale data of the first plate and the second plate respectively, which can facilitate the subsequent short-circuit fault identification of the first plate and the second plate at the same time based on the preset connected domain fault judgment rules.

[0063] This embodiment identifies the first plate without a cover cloth and the second plate with a cover cloth based on a preset grayscale threshold judgment rule, and can achieve targeted identification of short-circuit faults in the electrolytic cell plates with multiple layers of cover cloth, greatly improving the identification accuracy of the electrolytic cell plate fault detection method proposed in this embodiment.

[0064] According to a specific implementation of the embodiment of the present application, Figure 5 As shown, the blocks are classified into the first block and the second block based on the preset gray threshold judgment rule, including: S501, labeling each plate according to a preset order; S502, if the absolute value of the difference between the grayscale means of two consecutive blocks is greater than a preset grayscale threshold, determining that the larger block of the two consecutive blocks is the first block; S503, determining other blocks other than the first block as the second block.

[0065] In this embodiment, the determination rule for determining the first non-covered plate can be summarized as follows: in, For the The grayscale mean of each plate, For the The grayscale mean of each plate, is the grayscale judgment threshold corresponding to the non-covered plate, It means to find the absolute value. Indicates that the number of divided plates is satisfied The serial number of the plate In actual application, it is usually set <5 or i> 5, among which, The total number of plates.

[0066] In actual application, after executing step S303, each section can be numbered in a preset order. For example, each section can be numbered in order from left to right, so as to form two consecutive sections that can be paired for section classification.

[0067] like Figure 6 As shown, the block on the left side of the dotted line is the first block to be confirmed, and the block on the right side of the dotted line is the second block. It should be noted that it is necessary to determine whether the first block is abnormal according to the aforementioned step S502.

[0068] According to a specific implementation of the embodiment of the present application, Figure 7 As shown, the first plate and the second plate are corrected and processed respectively to obtain infrared image data to be detected, including: S701, correcting the first plate according to a preset grayscale correction threshold to obtain first infrared image data; S702, calculating the average of the grayscale values ​​of the second plate in a preset grayscale interval to obtain second infrared image data; S703, combining the first infrared image data and the second infrared image data to obtain infrared image data to be detected.

[0069] In this embodiment, the grayscale correction threshold can be based on the preset grayscale correction threshold. Perform grayscale correction on the first panel, wherein the grayscale correction threshold is preset is a grayscale value configured in advance. Adaptive configuration can be performed according to the needs of actual application scenarios, and no specific limitation is given here. The corrected grayscale data of the first plate is used as the first infrared image data.

[0070] For the second plate of the cover cloth, the number of pixels of the second plate needs to be obtained After sorting the grayscale values ​​in the second block according to the numerical value, the grayscale interval between The grayscale mean . Further, using the calculated Specifically, the grayscale values ​​less than 0 are set to 0, and the other grayscale values ​​are retained to obtain the second infrared image data.

[0071] In this embodiment, the infrared image data to be detected is grayscale data that can be used for short circuit identification at the same time.

[0072] According to a specific implementation of the embodiment of the present application, Figure 8 As shown, according to the preset connected domain fault judgment rule, the faulty plate in the target binary image is identified, including: S801, performing a closing operation on the target binary image according to a preset opening and closing operation core to obtain a plurality of connected domains; S802, performing connected domain correction processing according to relevant parameters of each connected domain to obtain multiple available connected domains, wherein the relevant parameters include area, width and height; S803, respectively calculating the grayscale mean of the blocks corresponding to each available connected domain; S804: If the grayscale mean is greater than or equal to a preset fault grayscale threshold, the block is determined as a faulty block.

[0073] In this embodiment, an opening and closing operation core is configured in advance to facilitate the closing operation of the target binary image. E ,in, E Can be a Matrix. Through the opening and closing operations and the closing operations on the target binary image, the target binary image can be calculated to obtain multiple connected domains. It should be noted that the target binary image in this embodiment includes multiple plates, and the plate types include a first plate and a second plate. When the faulty plate is identified according to the preset connected domain fault judgment rule, a separate connected domain processing can be performed for each plate in the target binary image to obtain multiple connected domains corresponding to one plate.

[0074] After obtaining the connected domain, immediately remove the small connected domain with an area smaller than the preset small connected domain removal threshold C, and in the processing direction, the merge length is smaller than the preset small length merge threshold The connected domain of , and the bounding rectangles of the remaining connected domains , the bounding rectangle Width and height , and the area of ​​each connected domain .

[0075] After selecting and merging the connected domains and calculating the relevant parameters of the connected domains, the different connected domains are further modified according to the relevant parameters of each connected domain. For example, if the area of ​​the connected domain is , it means that the current connected domain may have abnormal grayscale due to terminal heating or cover cloth folding. At this time, the threshold can be corrected based on the grayscale corresponding to terminal heating. Correct the gray value in the connected domain, where is the area threshold coefficient, is the plate height, is the length of the plate.

[0076] After the correction process is performed on each connected domain, a certain number of available connected domains can be obtained. The available connected domains in this embodiment are connected domains that can directly perform the fault identification step.

[0077] Calculate the grayscale mean of available connected domains , if the gray mean , it can be determined that the temperature of the available connected domain is abnormal, and the block corresponding to the available connected domain is determined to be a short-circuit block, where It is the gray threshold of plate short circuit fault.

[0078] It should be noted that, in this embodiment, all available connected domains need to be inspected in sequence to see if there are short circuit faults according to the above-mentioned preset connected domain fault judgment rule, and after inspecting all available connected domains, it is determined that the fault identification step is completed.

[0079] In summary, this embodiment provides a preset connected domain fault judgment rule, which can determine whether there is a short circuit fault in the multi-cover copper electrolytic cell plate based on infrared imaging technology through grayscale threshold, thereby realizing automatic fault identification of the multi-cover copper electrolytic cell plate and greatly improving fault identification efficiency and fault identification accuracy.

[0080] According to a specific implementation of the embodiment of the present application, Fig. 9 As shown, after performing a closing operation on the target binary image according to the preset opening and closing operation core to obtain multiple connected domains, the method further includes: S901, determining whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width, and the maximum height; S902, if the iterative target segmentation threshold is determined, the next segmentation threshold adjacent to the current segmentation threshold is selected from the preset segmentation threshold array as a new target segmentation threshold, and the target binary image is reacquired according to the new target segmentation threshold; S903, if it is determined that the target segmentation threshold is not to be iterated, then continue to perform the step of performing connected domain correction processing according to relevant parameters of each connected domain to obtain multiple available connected domains.

[0081] In this embodiment, if only a fixed segmentation threshold is used as the target segmentation threshold, some areas in the electrolytic cell plate may be missed, or the detected short circuit fault position may have a positioning deviation, that is, a fault in the electrolytic cell plate may be misdetected.

[0082] After dividing the connected domains, this embodiment determines whether to iterate the target segmentation threshold based on the number, maximum width and maximum height of the connected domains obtained by the division, and configures an iterative mechanism to match the target segmentation threshold that is most suitable for the electrolytic cell plate to be detected.

[0083] It should be noted that the preset segmentation threshold array can be expressed as , in each iteration, the next segmentation threshold adjacent to the current segmentation threshold is selected as the new target segmentation threshold. For example, if the current segmentation threshold is , and it is determined that the target segmentation threshold needs to be iterated, then the segmentation threshold can be as the new target segmentation threshold.

[0084] After determining the new target segmentation threshold, it is necessary to jump to step S202 to reacquire the target binary image. After reacquiring the target binary image, the division of the connected domain and subsequent processing need to be rerun.

[0085] If it is determined not to iterate the target segmentation threshold, then the step S801 may be followed by the step S802.

[0086] In actual application, the initial segmentation threshold is used The target binary image obtained by threshold division is as follows Fig.10 As shown, after at least one iteration, the target binary image obtained based on the new segmentation threshold is as follows Fig.11 As shown in FIG. 1 , after iterating to the target segmentation threshold that is most suitable for the electrolytic cell plate to be detected, the target binary value obtained by dividing the target segmentation threshold that is most suitable for the electrolytic cell plate to be detected is as follows: Fig.12 shown.

[0087] from Figure 10-12 It can be seen that based on the target segmentation threshold iteration step provided in this embodiment, the accuracy of electrolytic cell plate fault identification can be effectively improved.

[0088] According to a specific implementation of the embodiment of the present application, determining whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width, and the maximum height includes: If the number of connected domains, the maximum width, and the maximum height meet at least one of the preset iteration conditions, determining the iteration target segmentation threshold; The preset iteration conditions include: the number of connected domains is greater than or equal to a preset number threshold, the maximum width of the connected domain is greater than a preset width threshold, and the maximum height of the connected domain is less than a preset height threshold.

[0089] In this embodiment, if , and If at least one of the following conditions is met, it can be determined that the preset iteration condition is met. is the total number of connected domains obtained by partitioning, is the preset threshold of the number of connected domains, is the maximum width of all connected domains, that is, , is the maximum height among all connected domains, that is .

[0090] In actual application, if , and At least one of the following situations indicates that the current segmentation threshold is too small and does not meet the temperature condition at the corresponding plate of the current electrolytic cell plate.

[0091] In summary, this embodiment provides an electrolytic cell plate fault detection method, which obtains infrared image data of the electrolytic cell plate based on infrared thermal imaging technology, and then uses a dynamically updated target segmentation threshold to perform threshold segmentation on the infrared image data. The infrared image data can be threshold segmented based on the actual temperature condition of the electrolytic cell plate to obtain a target binary image that can accurately identify short-circuit faults. Based on a connected domain fault judgment rule including a target segmentation threshold iteration step, short-circuit faults in the target binary image are identified, and automatic and accurate identification of copper electrolytic cell plate short-circuit faults can be achieved, greatly improving the efficiency of troubleshooting copper electrolytic cell plate short-circuit faults.

[0092] Based on the same inventive concept, the embodiment of the present application also provides an electrolytic cell plate fault detection device for implementing the electrolytic cell plate fault detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the electrolytic cell plate fault detection device provided below can refer to the limitations of the electrolytic cell plate fault detection method above, and will not be repeated here.

[0093] In one embodiment, reference Fig.13 This embodiment further provides an electrolytic cell plate fault detection device 1300, comprising: an acquisition module 1310, a segmentation module 1320, an identification module 1330 and a statistical module 1340, wherein: An acquisition module 1310 is used to acquire infrared image data of a target electrolytic cell plate to be detected; The segmentation module 1320 is used to perform threshold segmentation processing on the infrared image data to be detected according to the target segmentation threshold value to obtain a target binary image, wherein the target segmentation threshold value is a threshold value in a preset segmentation threshold value array; An identification module 1330 is used to identify a faulty plate in a target binary image according to a preset connected domain fault judgment rule; The statistical module 1340 is used to count all faulty plates to obtain the fault detection result of the target electrolytic cell plate.

[0094] In one embodiment, the acquisition module 1310 is specifically used to acquire the area to be detected corresponding to multiple points of the electrolytic cell image taken by the infrared detector; convert the area to be detected into a regular rectangular area based on affine transformation; divide the regular rectangular area into multiple blocks; classify the blocks into a first block and a second block based on a preset grayscale threshold judgment rule, wherein the first block is a non-cloth-covered block and the second block is a cloth-covered block; respectively correct the first block and the second block to obtain the infrared image data to be detected.

[0095] In one of the embodiments, the acquisition module 1310 is specifically used to label each block according to a preset order; if the absolute value of the difference between the grayscale means of two consecutive blocks is greater than a preset grayscale threshold, the larger block of the two consecutive blocks is determined to be the first block; and the other blocks other than the first block are determined to be the second block.

[0096] In one embodiment, the acquisition module 1310 is specifically used to correct the first plate according to a preset grayscale correction threshold to obtain first infrared image data; calculate the mean grayscale value of the second plate in a preset grayscale range to obtain the second infrared image data; and combine the first infrared image data and the second infrared image data to obtain the infrared image data to be detected.

[0097] In one embodiment, the identification module 1330 is specifically used to perform a closing operation on the target binary image according to a preset opening and closing operation to obtain multiple connected domains; perform connected domain correction processing according to relevant parameters of each connected domain to obtain multiple available connected domains, wherein the relevant parameters include area, width and height; calculate the grayscale mean of the block corresponding to each available connected domain respectively; if the grayscale mean is greater than or equal to a preset fault grayscale threshold, determine the block as a faulty block.

[0098] In one embodiment, the identification module 1330 is specifically used to determine whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width and the maximum height; if it is determined to iterate the target segmentation threshold, in the preset segmentation threshold array, the next segmentation threshold adjacent to the current segmentation threshold is selected as the new target segmentation threshold, and the target binary image is reacquired according to the new target segmentation threshold; if it is determined not to iterate the target segmentation threshold, the steps of performing connected domain correction processing according to the relevant parameters of each connected domain to obtain multiple available connected domains are continued.

[0099] In one embodiment, the identification module 1330 is specifically used to determine the iterative target segmentation threshold if the number of connected domains, the maximum width and the maximum height meet at least one of the preset iteration conditions; the preset iteration conditions include: the number of connected domains is greater than or equal to the preset number threshold, the maximum width of the connected domain is greater than the preset width threshold and the maximum height of the connected domain is less than the preset height threshold.

[0100] In summary, the present embodiment provides an electrolytic cell plate fault detection device, which obtains infrared image data of the electrolytic cell plate based on infrared thermal imaging technology, and then uses a dynamically updated target segmentation threshold to perform threshold segmentation on the infrared image data. The infrared image data can be threshold segmented based on the actual temperature condition of the electrolytic cell plate to obtain a target binary image that can accurately identify short-circuit faults. Based on a connected domain fault judgment rule including a target segmentation threshold iteration step, short-circuit faults in the target binary image are identified, and automatic and accurate identification of copper electrolytic cell plate short-circuit faults can be achieved, greatly improving the efficiency of troubleshooting copper electrolytic cell plate short-circuit faults.

[0101] Fig.13 The specific implementation of the device shown can refer to the specific implementation of the aforementioned method embodiment, which will not be repeated here.

[0102] In addition, an embodiment of the present application further provides an electronic device, the electronic device comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the electrolytic cell plate fault detection method in the aforementioned method embodiment.

[0103] It should be noted that the electronic device in this embodiment may be an electronic device equipped with the electrolytic cell plate fault detection system in the aforementioned embodiment.

[0104] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the electrolytic cell plate fault detection method in the aforementioned method embodiment.

[0105] The electronic devices in the embodiments of the present application may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0106] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Examples of computer-readable storage media may be, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0107] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0108] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0109] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: obtains infrared image data to be detected of the target electrolytic cell plate; performs threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; identifies the faulty plate in the target binary image according to a preset connected domain fault judgment rule; and counts all the faulty plates to obtain a fault detection result of the target electrolytic cell plate.

[0110] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The units involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of a unit does not, in some cases, constitute a limitation on the unit itself.

[0113] It should be understood that various parts of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof.

[0114] The above is only a specific implementation of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present disclosure should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A method for detecting electrolytic cell plate faults, characterized in that: include: Acquire infrared image data of the target electrolytic cell plate to be inspected; Performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; According to a preset connected domain fault judgment rule, identifying a faulty plate in the target binary image; All faulty plates are counted to obtain the fault detection result of the target electrolytic cell plate.

2. The method according to claim 1, characterized in that The step of obtaining infrared image data of the target electrolytic cell plate to be detected includes: Acquire the areas to be detected corresponding to multiple points of the electrolytic cell image taken by the infrared detector; Converting the area to be detected into a regular rectangular area based on affine transformation; Divide the rectangular area into a plurality of plates; Classifying the plate into a first plate and a second plate based on a preset grayscale threshold determination rule, wherein the first plate is a non-cloth-covered plate and the second plate is a cloth-covered plate; Correction processing is performed on the first plate and the second plate respectively to obtain the infrared image data to be detected.

3. The method according to claim 2, characterized in that The classifying the blocks into the first block and the second block based on a preset gray threshold determination rule comprises: Label each section in a preset order; If the absolute value of the difference between the grayscale means of two consecutive blocks is greater than a preset grayscale threshold, the larger block of the two consecutive blocks is determined to be the first block; The other blocks other than the first block are determined as the second blocks.

4. The method according to claim 2, characterized in that: The correcting process is performed on the first plate and the second plate respectively to obtain the infrared image data to be detected, including: Correcting the first plate according to a preset grayscale correction threshold to obtain first infrared image data; Calculating the average of the grayscale values ​​of the second plate in a preset grayscale range to obtain the second infrared image data; The infrared image data to be detected is obtained by combining the first infrared image data and the second infrared image data.

5. The method according to claim 1, characterized in that The step of identifying the faulty plate in the target binary image according to the preset connected domain fault judgment rule includes: Performing a closing operation on the target binary image according to a preset opening and closing operation core to obtain a plurality of connected domains; Performing connected domain correction processing according to relevant parameters of each connected domain to obtain multiple available connected domains, wherein the relevant parameters include area, width and height; Calculate the grayscale mean of the blocks corresponding to each available connected domain respectively; If the grayscale mean is greater than or equal to a preset fault grayscale threshold, the block is determined as a faulty block.

6. The method according to claim 5, characterized in that After performing a closing operation on the target binary image according to the preset opening and closing operation core to obtain a plurality of connected domains, the method further includes: Determine whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width and the maximum height; If it is determined to iterate the target segmentation threshold, in the preset segmentation threshold array, the next segmentation threshold adjacent to the current segmentation threshold is selected as a new target segmentation threshold, and the target binary image is reacquired according to the new target segmentation threshold; If it is determined not to iterate the target segmentation threshold, the step of performing connected domain correction processing according to relevant parameters of each connected domain to obtain a plurality of available connected domains is continued.

7. The method according to claim 6, characterized in that The step of determining whether to iterate the target segmentation threshold according to the number of connected domains, the maximum width, and the maximum height includes: If the number of connected domains, the maximum width, and the maximum height meet at least one of the preset iteration conditions, determining to iterate the target segmentation threshold; The preset iteration conditions include: the number of the connected domains is greater than or equal to a preset number threshold, the maximum width of the connected domain is greater than a preset width threshold, and the maximum height of the connected domain is less than a preset height threshold.

8. An electrolytic cell plate fault detection device, characterized in that: include: An acquisition module, used for acquiring infrared image data of the target electrolytic cell plate to be detected; A segmentation module, used for performing threshold segmentation processing on the infrared image data to be detected according to a target segmentation threshold to obtain a target binary image, wherein the target segmentation threshold is a threshold in a preset segmentation threshold array; An identification module, used to identify the faulty plate in the target binary image according to a preset connected domain fault judgment rule; The statistical module is used to count all faulty plates to obtain the fault detection result of the target electrolytic cell plate.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the electrolyzer plate fault detection method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the electrolytic cell plate fault detection method according to any one of claims 1 to 7.

Images