Production system and method of lithium battery pole pieces for drones

Abstract

The present invention belongs to the technical field of lithium battery production. A production system for lithium battery pole pieces for drones is provided, including: a coating mechanism for uniformly coating the prepared slurry on a metal current collector; a drying mechanism for drying the coated pole piece; a compacting mechanism for compacting the dried pole piece; a slitting mechanism for slitting the compacted pole piece into a desired size and shape; a quality inspection mechanism for taking a high-definition image of the pole piece product output by the slitting mechanism through a high-definition camera, and detecting whether it contains defects through image recognition technology to obtain a quality inspection result; an optimization control mechanism for performing abnormal analysis based on the quality inspection result and the corresponding working parameters of the coating mechanism, drying mechanism, compacting mechanism, and slitting mechanism to determine the abnormal mechanism, and optimizing the working parameters of the abnormal mechanism based on the quality inspection result. The present invention realizes the adaptive optimization adjustment of the working parameters of the production mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium battery production, and in particular to a production system and method for lithium battery pole pieces for unmanned aerial vehicles. Background Art

[0002] Lithium battery pole pieces are key components of lithium-ion batteries, including positive and negative pole pieces. Their production process requires precise control to ensure battery performance, safety and life. Lithium battery pole piece production involves several main processes such as coating, drying, compaction, and slitting. In the existing lithium battery pole piece production, the above processes are all implemented based on fixed production parameters and cannot be adjusted according to actual conditions, especially the production parameters of the corresponding processes cannot be adjusted according to defects in the production process. As a result, the existing lithium battery production system for drones cannot meet actual needs. Summary of the invention

[0003] In this regard, the present invention provides a production system, method, electronic equipment, computer storage medium and computer program product for lithium battery electrodes for drones to solve at least one of the above-mentioned technical problems.

[0004] The present invention provides a production system for lithium battery pole pieces for drones, the system comprising a coating mechanism, a drying mechanism, a compacting mechanism, a slitting mechanism, a quality inspection mechanism and an optimization control mechanism; the optimization control mechanism is electrically connected to the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection mechanism respectively;

[0005] The coating mechanism is used to evenly coat the prepared slurry on the metal current collector;

[0006] The drying mechanism is used to dry the coated electrode;

[0007] The compacting mechanism is used to compact the pole piece after drying;

[0008] The slitting mechanism is used to slit the compacted pole pieces into required sizes and shapes;

[0009] The quality inspection mechanism is used to take a high-definition image of the electrode product output by the slitting mechanism through a high-definition camera, and detect whether there are defects therein through image recognition technology to obtain a quality inspection result;

[0010] The optimization control mechanism is used to perform abnormal analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism and optimize the working parameters of the abnormal mechanism based on the quality inspection results.

[0011] The present invention also provides a method for producing a lithium battery pole piece for a drone, the method comprising the following steps:

[0012] The optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection parameters of the quality inspection mechanism according to the target production data of the lithium battery electrode sheet for drones;

[0013] The coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism respectively perform corresponding production operation items according to the received preset working parameters, and feed back the actual working parameters to the optimization control mechanism;

[0014] The quality inspection mechanism controls the high-definition camera to capture the high-definition image of the electrode product output by the slitting mechanism according to the quality inspection parameters, and detects whether there are defects therein by image recognition technology to obtain the quality inspection result, and feeds back the quality inspection result to the optimization control mechanism;

[0015] The optimization control mechanism performs an abnormality analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, wherein the working parameters include the preset working parameters and the actual working parameters; and optimizes the preset working parameters of the abnormal mechanism based on the quality inspection results to obtain optimized working parameters, and feeds back the optimized working parameters to the corresponding abnormal mechanism for execution.

[0016] Optionally, the optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism according to the target production data of the lithium battery pole piece for the drone, including:

[0017] The optimization control mechanism divides the target production data of the lithium battery pole pieces for drones into target production sub-data corresponding to each production process, and then converts each of the target production sub-data into corresponding preset working parameters according to preset conversion rules.

[0018] Optionally, the optimization control mechanism receives and generates quality inspection parameters of the quality inspection mechanism according to target production data of lithium battery pole pieces for drones, including:

[0019] The optimization control mechanism calculates the similarity value between the target production data of the lithium battery electrodes for drones and the target production data of the previous batch, and determines the quality inspection parameters according to the similarity value. The quality inspection parameters include a quality inspection interval matrix, and each quality inspection interval in the quality inspection interval matrix increases sequentially from the start time of production to the end time of production.

[0020] Optionally, the optimization control mechanism performs abnormal analysis according to the quality inspection result and corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, including:

[0021] Calling an abnormality analysis deep model, the abnormality analysis deep model performs abnormality analysis on the quality inspection results and corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism, and outputs a number of abnormal mechanisms obtained by the analysis and corresponding abnormal probabilities;

[0022] Acquire optimization record data, wherein the optimization record data includes defect type and abnormal mechanism record data, and count the number of records of production mechanisms corresponding to each defect type in the optimization record data;

[0023] The abnormal correction probability is obtained by multiplying the number of records corresponding to each abnormal mechanism by the corresponding abnormal probability, and the abnormal mechanism corresponding to the largest abnormal correction probability is determined as the target abnormal mechanism.

[0024] Optionally, the step of feeding back the optimized working parameters to a corresponding abnormal mechanism for execution includes:

[0025] Counting the equivalent number of defects involved in the quality inspection results, and determining the optimization debugging cycle according to the equivalent number;

[0026] During the optimization and debugging cycle, the optimization working parameters are fed back to the corresponding target abnormality mechanism for execution, and the quality inspection mechanism is controlled to perform quality inspection on each electrode product output by the slitting mechanism;

[0027] If the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements, the optimization control mechanism performs a new round of abnormality analysis and optimization of the preset working parameters until the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements.

[0028] Optionally, optimizing the preset working parameters of the abnormal mechanism according to the quality inspection result includes:

[0029] Constructing an optimal parameter prediction model based on the improved Transformer, and fully training the optimal parameter prediction model;

[0030] The optimal parameter prediction model performs in-depth processing on the defect type corresponding to the target abnormal mechanism in the quality inspection result, the preset working parameters and the actual working parameters to obtain optimized working parameters.

[0031] The present invention also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements any of the methods described above when executed by the processor.

[0032] The present invention also provides a computer storage medium, which stores a computer program executable by a processor, and the computer program implements any of the above methods when executed by the processor.

[0033] The present invention also provides a computer program product, which includes a computer program executable by a processor, and the computer program implements any of the above methods when executed by the processor.

[0034] The beneficial effect of the present invention is that the three-dimensional quality inspection mechanism in the present invention detects whether the produced electrode products contain defects through image recognition technology, and the optimization control mechanism can predict the abnormal mechanism that is most likely to have abnormalities based on the quality inspection results and the working parameters of each production mechanism, and then optimize the working parameters of the abnormal mechanism. Therefore, the lithium battery production system of the present invention can achieve adaptive optimization, thereby obtaining better lithium battery production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 It is a structural schematic diagram of a production system of lithium battery pole pieces for drones disclosed in an embodiment of the present invention;

[0037] Figure 2 The present invention is a flowchart of a method for producing a lithium battery electrode for a drone disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0039] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0040] like Figure 1 As shown, the embodiment of the present invention discloses a production system for lithium battery pole pieces for drones, the system comprising a coating mechanism, a drying mechanism, a compacting mechanism, a slitting mechanism, a quality inspection mechanism and an optimization control mechanism; the optimization control mechanism is electrically connected to the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection mechanism respectively;

[0041] The coating mechanism is used to evenly coat the prepared slurry on the metal current collector (aluminum foil is used for the positive electrode and copper foil is used for the negative electrode);

[0042] The drying mechanism is used to dry the coated electrode to remove the solvent and solidify the binder;

[0043] The compacting mechanism is used to compact the dried electrode to increase its density and improve its electrochemical performance;

[0044] The slitting mechanism is used to slit the compacted pole pieces into required sizes and shapes;

[0045] The quality inspection mechanism is used to take a high-definition image of the electrode product output by the slitting mechanism through a high-definition camera, and detect whether there are defects therein through image recognition technology to obtain a quality inspection result;

[0046] The optimization control mechanism is used to perform abnormal analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism and optimize the working parameters of the abnormal mechanism based on the quality inspection results.

[0047] The lithium battery pole piece production system of the present invention includes not only conventional coating mechanism, drying mechanism, compaction mechanism, and slitting mechanism, but also quality inspection mechanism and optimization control mechanism. The quality inspection mechanism detects whether the produced pole piece products contain defects through image recognition technology, and the optimization control mechanism can predict the abnormal mechanism that is most likely to cause the defect based on the quality inspection results and the working parameters of each production mechanism, and then optimize the working parameters of the abnormal mechanism.

[0048] In addition, the production system of lithium battery pole pieces for drones should also include a slurry mixing mechanism, an environmental control mechanism, etc. Since these are not the technical focus of the present invention, they are not specifically limited or analyzed.

[0049] like Figure 2As shown, the embodiment of the present invention discloses a method for producing a lithium battery electrode for a drone, the method comprising the following steps:

[0050] The optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection parameters of the quality inspection mechanism according to the target production data of the lithium battery electrode sheet for drones;

[0051] The coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism respectively perform corresponding production operation items according to the received preset working parameters, and feed back the actual working parameters to the optimization control mechanism;

[0052] The quality inspection mechanism controls the high-definition camera to capture the high-definition image of the electrode product output by the slitting mechanism according to the quality inspection parameters, and detects whether there are defects therein by image recognition technology to obtain the quality inspection result, and feeds back the quality inspection result to the optimization control mechanism;

[0053] The optimization control mechanism performs an abnormality analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, wherein the working parameters include the preset working parameters and the actual working parameters; and optimizes the preset working parameters of the abnormal mechanism based on the quality inspection results to obtain optimized working parameters, and feeds back the optimized working parameters to the corresponding abnormal mechanism for execution.

[0054] The optimization control mechanism in the present invention first generates preset working parameters of each production mechanism and quality inspection parameters of the quality inspection mechanism according to the target production data of the lithium battery pole pieces for drones of this batch received. Each production mechanism performs production operations according to the preset working parameters, and the quality inspection mechanism identifies defects of the produced pole piece products according to the quality inspection parameters. The optimization control mechanism then locks the abnormal mechanism that causes defects in the pole piece products according to the quality inspection results and the preset working parameters and actual working parameters of each production mechanism, and then optimizes the preset working parameters of the abnormal mechanism according to the quality inspection results, thereby obtaining optimized working parameters. At this time, each production control mechanism continues to produce according to the new working parameters, which can reduce the probability of defects in the pole piece products.

[0055] In addition, if the subsequent produced electrode products still have defects, further multiple iterations of optimization can be performed until the defects in the electrode products disappear. It should be noted that the defect in the present invention refers to the defect ratio of the electrode products exceeding the tolerable set ratio.

[0056] Optionally, the optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism according to the target production data of the lithium battery pole piece for the drone, including:

[0057] The optimization control mechanism divides the target production data of the lithium battery pole pieces for drones into target production sub-data corresponding to each production process, and then converts each of the target production sub-data into corresponding preset working parameters according to preset conversion rules.

[0058] In this embodiment, the designer formulates the target production data of lithium battery pole pieces in advance according to the performance indicators of lithium batteries for drones, which includes the specific process requirements of coating, drying, compaction, and slitting. After receiving the target production data, the optimization control mechanism first divides it according to the production process to obtain each target production sub-data. However, the target production sub-data is only a production process indicator, not a preset working parameter that can be specifically executed by each production mechanism. Therefore, it is still necessary to convert each of the target production sub-data into a corresponding preset working parameter according to the preset conversion rules. The preset working parameter is the parameter that can be actually executed by the corresponding production mechanism.

[0059] Optionally, the optimization control mechanism receives and generates quality inspection parameters of the quality inspection mechanism according to target production data of lithium battery pole pieces for drones, including:

[0060] The optimization control mechanism calculates the similarity value between the target production data of the lithium battery electrodes for drones and the target production data of the previous batch, and determines the quality inspection parameters according to the similarity value. The quality inspection parameters include a quality inspection interval matrix, and each quality inspection interval in the quality inspection interval matrix increases sequentially from the start time of production to the end time of production.

[0061] In this embodiment, the production system of the present invention can perform different types of production tasks for lithium battery pole pieces, and different production tasks correspond to different working parameters of the production mechanism. In the production process of the production mechanism, some components may be misaligned, resulting in quality defects in the product. The greater the gap between two adjacent production tasks, the larger the span of the production mechanism, such as the larger the span of the operation stroke, the larger the span of the temperature change, etc., will be amplified in the case of the above-mentioned misalignment, resulting in a greater probability of quality defects. Although the production equipment will perform self-calibration after completing a batch of production tasks, self-calibration cannot completely eliminate the accumulation of deviations, and thus cannot change the above-mentioned correlation between the probability of quality defects and the size of the gap between two adjacent production tasks.

[0062] In view of the above technical problems, the optimization control mechanism first calculates the similarity value between the target production data corresponding to this production task and the target production data corresponding to the previous production task, and determines the quality inspection parameters according to the similarity value. Specifically, when the similarity between this task and the previous task is higher, it means that the production process requirements of the two tasks are closer, and the probability of misalignment of the production mechanism is theoretically very close, and after self-calibration after the completion of the previous task, the probability of misalignment will be lower, so the quality inspection interval in this case is set to be larger; on the contrary, when the similarity between this task and the previous task is lower, it means that the production process requirements of the two tasks are more different, and the probability of misalignment of the production mechanism will increase, so the quality inspection interval in this case is set to be smaller. In addition, in the early stage of each new production task, the size of the quality inspection interval is determined in the above manner, and as the production task is executed, the quality inspection interval gradually increases and stabilizes at a certain value.

[0063] The quality inspection interval may be a time interval, that is, a quality inspection is performed every certain time period; or it may be a quantity interval, that is, a quality inspection is performed every certain number of electrode products (for example, 3 electrodes). The present invention does not specifically limit this.

[0064] The similarity calculation may adopt an existing similarity calculation formula, specifically, adjacent target production data are characterized respectively, and then the similarity calculation formula is used to calculate the similarity of two feature matrices.

[0065] Optionally, the optimization control mechanism performs abnormal analysis according to the quality inspection result and corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, including:

[0066] Calling an abnormality analysis deep model, the abnormality analysis deep model performs abnormality analysis on the quality inspection results and corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism, and outputs a number of abnormal mechanisms obtained by the analysis and corresponding abnormal probabilities;

[0067] Acquire optimization record data, wherein the optimization record data includes defect type and abnormal mechanism record data, and count the number of records of production mechanisms corresponding to each defect type in the optimization record data;

[0068] The abnormal correction probability is obtained by multiplying the number of records corresponding to each abnormal mechanism by the corresponding abnormal probability, and the abnormal mechanism corresponding to the largest abnormal correction probability is determined as the target abnormal mechanism.

[0069] In this embodiment, the present invention first uses an abnormal analysis deep model to conduct an in-depth analysis of the quality inspection results of the aforementioned quality inspection organization and the preset working parameters and actual working parameters of each production organization, and predicts several abnormal organizations and corresponding abnormal probabilities that may cause defect types in the quality inspection results.

[0070] At the same time, historical statistical data is further considered. Specifically, the optimization record data of the production system includes defect types and associated abnormal mechanism record data. The abnormal mechanism record data is the production mechanism finally optimized by the optimization control mechanism, that is, the recognized abnormal mechanism, and also includes artificially determined abnormal mechanisms. The number of records of the production mechanism corresponding to each defect type is obtained through statistical calculation. Obviously, the higher the number of records, the greater the correlation between the production mechanism and the defect type, and vice versa.

[0071] Finally, the record data corresponding to each abnormal mechanism predicted by the above-mentioned abnormal analysis deep model is determined from the statistical calculation results, and the number of records is multiplied by the corresponding abnormal probability predicted above to obtain the new abnormal value of each abnormal mechanism, that is, the abnormal correction probability. Each new abnormal value is sorted, and the abnormal mechanism corresponding to the largest abnormal correction probability is determined as the target abnormal mechanism.

[0072] It should be noted that the working parameters based on which the abnormal analysis deep model in the present invention performs abnormal analysis include both preset working parameters and actual working parameters. The reason for this setting is that due to the inaccuracy of the production mechanism, the input preset working parameters cannot be executed 100%. The abnormal analysis deep model analyzes which production mechanisms are most likely to have inaccuracies by analyzing the deviation between the preset working parameters and the actual working parameters, and the corresponding abnormal probability can be predicted based on the size of the deviation. By considering the above statistical calculation data later, a more accurate abnormal correction probability can be obtained.

[0073] The abnormal analysis deep model preferably uses an improved Transformer, which includes at least an encoding function, a multi-head attention function, a sum normalization function, a forward feedback function, a linearization function, and a normalization function. The present invention does not limit the specific construction and training process.

[0074] Optionally, the step of feeding back the optimized working parameters to a corresponding abnormal mechanism for execution includes:

[0075] Counting the equivalent number of defects involved in the quality inspection results, and determining the optimization debugging cycle according to the equivalent number;

[0076] During the optimization and debugging cycle, the optimization working parameters are fed back to the corresponding target abnormality mechanism for execution, and the quality inspection mechanism is controlled to perform quality inspection on each electrode product output by the slitting mechanism;

[0077] If the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements, the optimization control mechanism performs a new round of abnormality analysis and optimization of the preset working parameters until the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements.

[0078] In this embodiment, when it is found that the quality inspection results of the lithium battery electrode production system do not meet the quality inspection requirements, it is necessary to insert an optimization and debugging cycle. The electrode products produced within this cycle need to be quality inspected. If the quality of the electrode within this cycle cannot meet the quality inspection requirements, it indicates that the optimization working parameters generated by the optimization control mechanism are not accurate, or the abnormal mechanism determined above is inaccurate, for example, the abnormal mechanism is wrong, or the abnormal mechanism is omitted (that is, the defect is caused by the abnormalities of multiple production mechanisms). At this time, the optimization control mechanism needs to perform a new round of abnormal analysis and optimization of the preset working parameters until the quality inspection results of the quality inspection mechanism do not meet the quality inspection requirements.

[0079] In addition, the length of the optimization debugging cycle is determined based on the equivalent number of defects involved in the quality inspection results of the quality inspection agency. The length of the optimization debugging cycle and the equivalent number should be in a positive correlation, that is, the more equivalent numbers there are, the longer the length of the optimization debugging cycle is. The equivalent number can be a weighted average of the number of multiple defect types, such as cracks, bubbles, and uneven coatings, and the weights of the above types of defects are set to decrease in sequence.

[0080] Optionally, optimizing the preset working parameters of the abnormal mechanism according to the quality inspection result includes:

[0081] Constructing an optimal parameter prediction model based on the improved Transformer, and fully training the optimal parameter prediction model;

[0082] The optimal parameter prediction model performs in-depth processing on the defect type corresponding to the target abnormal mechanism in the quality inspection result, the preset working parameters and the actual working parameters to obtain optimized working parameters.

[0083] In this embodiment, the present invention also constructs the above-mentioned optimal parameter prediction model based on the improved Transformer. The construction and training methods of the model can be basically the same as those of the abnormal analysis deep model. The difference between the two lies mainly in the difference in training data. The training data of the optimal parameter prediction model is [working parameters, defect type, effect mark], where the effect mark refers to the degree of attenuation of the corresponding defect type after using the corresponding working parameters, such as strong, medium, and weak. The training data of the abnormal analysis deep model is [working parameters, [defect type 1, defect probability 1]…[defect type n, defect probability n]]. The working parameters in the above two types of training data include preset working parameters and actual working parameters.

[0084] The present invention also discloses an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements any of the methods described above when executed by the processor.

[0085] The present invention also discloses a computer storage medium, which stores a computer program executable by a processor, and the computer program implements any of the above methods when executed by the processor.

[0086] The present invention also discloses a computer program product, which includes a computer program executable by a processor, and the computer program implements any of the above methods when executed by the processor.

[0087] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0088] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for producing a lithium battery pole piece for a drone, the method is based on a production system for a lithium battery pole piece for a drone, and is characterized in that: The production system includes a coating mechanism, a drying mechanism, a compacting mechanism, a slitting mechanism, a quality inspection mechanism and an optimization control mechanism; the optimization control mechanism is electrically connected to the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection mechanism respectively; The coating mechanism is used to evenly coat the prepared slurry on the metal current collector; The drying mechanism is used to dry the coated electrode; The compacting mechanism is used to compact the pole piece after drying; The slitting mechanism is used to slit the compacted pole pieces into required sizes and shapes; The quality inspection mechanism is used to take a high-definition image of the electrode product output by the slitting mechanism through a high-definition camera, and detect whether there are defects therein through image recognition technology to obtain a quality inspection result; The optimization control mechanism is used to perform abnormal analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, and optimize the working parameters of the abnormal mechanism based on the quality inspection results; The method comprises the following steps: The optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, the slitting mechanism and the quality inspection parameters of the quality inspection mechanism according to the target production data of the lithium battery electrode sheet for drones; The coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism respectively perform corresponding production operation items according to the received preset working parameters, and feed back the actual working parameters to the optimization control mechanism; The quality inspection mechanism controls the high-definition camera to capture the high-definition image of the electrode product output by the slitting mechanism according to the quality inspection parameters, and detects whether there are defects therein by image recognition technology to obtain the quality inspection result, and feeds back the quality inspection result to the optimization control mechanism; The optimization control mechanism performs an abnormality analysis based on the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, wherein the working parameters include the preset working parameters and the actual working parameters; And, optimizing the preset working parameters of the abnormal mechanism according to the quality inspection result to obtain the optimized working parameters, and feeding back the optimized working parameters to the corresponding abnormal mechanism for execution; The optimization control mechanism receives and generates the quality inspection parameters of the quality inspection mechanism according to the target production data of the lithium battery electrode sheet for drones, including: The optimization control mechanism calculates the similarity value between the target production data of the lithium battery electrode for drones and the target production data of the previous batch, and determines the quality inspection parameter according to the similarity value, wherein the quality inspection parameter includes a quality inspection interval matrix, and each quality inspection interval in the quality inspection interval matrix increases sequentially from the start time of production to the end time of production; The optimization control mechanism performs abnormal analysis according to the quality inspection results and the corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism to determine the abnormal mechanism, including: Calling an abnormality analysis deep model, the abnormality analysis deep model performs abnormality analysis on the quality inspection results and corresponding working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism, and outputs a number of abnormal mechanisms obtained by the analysis and corresponding abnormal probabilities; Acquire optimization record data, wherein the optimization record data includes defect type and abnormal mechanism record data, and count the number of records of production mechanisms corresponding to each defect type in the optimization record data; According to the number of records corresponding to each abnormal institution multiplied by the corresponding abnormal probability, an abnormal correction probability is obtained, and the abnormal institution corresponding to the largest abnormal correction probability is determined as a target abnormal institution; Feeding back the optimized working parameters to the corresponding abnormal mechanism for execution includes: Counting the equivalent number of defects involved in the quality inspection results, and determining the optimization debugging cycle according to the equivalent number; During the optimization and debugging cycle, the optimization working parameters are fed back to the corresponding target abnormality mechanism for execution, and the quality inspection mechanism is controlled to perform quality inspection on each electrode product output by the slitting mechanism; If the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements, the optimization control mechanism performs a new round of abnormality analysis and optimization of the preset working parameters until the quality inspection result of the quality inspection mechanism does not meet the quality inspection requirements.

2. The method for producing a lithium battery pole piece for a drone according to claim 1, characterized in that: The optimization control mechanism receives and generates preset working parameters of the coating mechanism, the drying mechanism, the compacting mechanism, and the slitting mechanism according to the target production data of the lithium battery electrode sheet for drones, including: The optimization control mechanism divides the target production data of the lithium battery pole pieces for drones into target production sub-data corresponding to each production process, and then converts each of the target production sub-data into corresponding preset working parameters according to preset conversion rules.

3. The method for producing a lithium battery pole piece for a drone according to claim 2, characterized in that: The optimizing the preset working parameters of the abnormal mechanism according to the quality inspection result includes: Constructing an optimal parameter prediction model based on the improved Transformer, and fully training the optimal parameter prediction model; The optimal parameter prediction model performs in-depth processing on the defect type corresponding to the target abnormal mechanism in the quality inspection result, the preset working parameters and the actual working parameters to obtain optimized working parameters.

4. An electronic device, characterized in that: The electronic device comprises: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the computer program implements the method according to any one of claims 1 to 3 when executed by the processor.

5. A computer storage medium, characterized in that: The computer storage medium stores a computer program executable by a processor, and the computer program implements the method according to any one of claims 1 to 3 when executed by the processor.

6. A computer program product, characterized in that: The computer program product comprises a computer program executable by a processor, and the computer program implements the method according to any one of claims 1 to 3 when executed by the processor.

Images