Automatic dosing method for electrophoresis tank, electrophoresis system and electronic equipment

Abstract

The invention relates to the technical field of electrophoresis, and discloses an automatic dosing method for an electrophoresis tank, an electrophoresis system and electronic equipment.The method comprises the steps that tank liquid parameters of tank liquid in the electrophoresis tank and technological parameters of an electrophoresis technology are obtained; inputting the bath solution parameters and the process parameters into a pre-constructed dosage prediction model, and predicting to obtain to-be-supplemented dosage; and controlling the automatic dosing equipment to add chemicals into the electrophoresis tank based on the dosage to be supplemented. According to the automatic dosing method, the stability of the film thickness can be improved, the working efficiency and the product quality can be improved, the use cost can be reduced, and the full-flow digital intelligence capability can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrophoresis, and in particular to an automatic dosing method for an electrophoresis tank, an electrophoresis system, an electronic device, and a computer-readable storage medium. BACKGROUND

[0002] In the field of electrophoretic coating processes, the electrophoretic film thickness directly affects the corrosion resistance of the workpiece and is one of the core quality indicators. The current industry generally uses the mode of "random inspection confirmation + manual dosing" for electrophoresis tank liquid management, but this mode causes large parameter fluctuations, no predictability of dosing, uneven tank liquid composition, low efficiency, and high quality and cost problems. SUMMARY

[0003] The present application aims to at least partially solve one of the technical problems in the related art. To this end, a first object of the present application is to provide an automatic dosing method for an electrophoresis tank, which can improve the stability of the film thickness, improve work efficiency and product quality, reduce use costs, and improve the full-process digitalization capability.

[0004] A second object of the present application is to provide an electrophoresis system.

[0005] A third object of the present application is to provide an electronic device.

[0006] A fourth object of the present application is to provide a computer-readable storage medium.

[0007] To achieve the above objects, the automatic dosing method for an electrophoresis tank according to a first aspect of the present application comprises: obtaining tank liquid parameters of a tank liquid in an electrophoresis tank and process parameters of an electrophoresis process; inputting the tank liquid parameters and the process parameters into a pre-constructed dosing amount prediction model to predict a to-be-supplemented dosing amount; and controlling an automatic dosing device to dose into the electrophoresis tank based on the to-be-supplemented dosing amount.

[0008] In addition, the automatic dosing method for an electrophoresis tank according to the above embodiments of the present application can have the following additional technical features: According to some embodiments of the present application, the tank liquid parameters include tank liquid solids, tank liquid temperature, tank liquid pH value, and tank liquid conductivity.

[0009] According to some embodiments of the present application, the process parameters include target electrophoretic film thickness, electrophoretic coating time, and electrophoretic coating voltage.

[0010] According to some embodiments of the present application, the dosing amount prediction model is expressed as:

[0011] wherein, represents the to-be-supplemented dosing amount predicted by the dosing amount prediction model. representing inputted each bath liquid parameter and process parameter; representing the dosing reference value when each bath liquid parameter and process parameter has no change; representing the influence weight of bath liquid parameter and process parameter on dosing amount; representing the error term, representing the deviation caused by the secondary parameters not covered by the dosing amount prediction model.

[0012] According to some embodiments of the present application, the above method further comprises: collecting electrophoresis tank electrophoresis production data in a historical period; wherein the electrophoresis production data includes the bath liquid parameters, process parameters, historical dosing amount and electrophoretic film thickness detection results of the electrophoresis tank in the historical period; training the basic model based on the electrophoresis production data to obtain the dosing reference value, the influence weight and the error term; and constructing the dosing amount prediction model based on the dosing reference value, the influence weight and the error term.

[0013] According to some embodiments of the present application, the above method further comprises: periodically obtaining actual film thickness data of the electrophoresis system and predicted film thickness data determined based on the output of the dosing amount prediction model according to a preset period; determining whether the difference between the actual film thickness data and the predicted film thickness data reaches a preset film thickness fluctuation threshold; and in response to the difference between the actual film thickness data and the predicted film thickness data reaching the preset film thickness fluctuation threshold, triggering re-calibration of the model parameters and the error term of the dosing amount prediction model to optimize the dosing logic of the electrophoresis system.

[0014] According to some embodiments of the present application, the above method further comprises: in response to the error term of the dosing amount prediction model exceeding a preset error range, triggering re-calibration of the model parameters and the error term of the dosing amount prediction model to optimize the dosing logic of the electrophoresis system.

[0015] The automatic dosing method for the electrophoresis tank according to the embodiments of the present application comprises: obtaining the bath liquid parameters of the bath liquid in the electrophoresis tank and the process parameters of the electrophoresis process; inputting the bath liquid parameters and the process parameters into a pre-constructed dosing amount prediction model to predict the to-be-supplemented dosing amount; and controlling the automatic dosing equipment to add dosing to the electrophoresis tank based on the to-be-supplemented dosing amount. Thus, the method can improve the stability of the film thickness, improve the work efficiency and product quality, reduce the use cost, and improve the full-process digitalization capability.

[0016] The present application aims to solve at least one of the technical problems in the related art. To this end, the second object of the present application is to provide an electrophoresis system capable of improving the stability of the film thickness, improving the work efficiency and product quality, reducing the use cost, and improving the full-process digitalization capability.

[0017] To achieve the above objectives, a second aspect of the present invention provides an electrophoresis system, comprising: an acquisition module configured to acquire tank parameters of the electrolyte in the electrophoresis tank and process parameters of the electrophoresis process; a prediction module configured to input the electrolyte parameters and process parameters into a pre-constructed dosage prediction model to predict the amount of chemical to be added; and a chemical addition module configured to control an automatic chemical addition device to add chemicals to the electrophoresis tank based on the amount of chemical to be added.

[0018] An electrophoresis system according to an embodiment of the present invention includes: an acquisition module configured to acquire tank parameters of the electrophoresis bath and process parameters of the electrophoresis process; a prediction module configured to input the tank parameters and process parameters into a pre-built dosing prediction model to predict the amount of reagent to be added; and a dosing module configured to control an automatic dosing device to add reagent to the electrophoresis bath based on the amount of reagent to be added. Therefore, this system can improve the stability of membrane thickness, increase work efficiency and product quality, reduce operating costs, and enhance the overall digitalization capabilities of the process.

[0019] To achieve the above objectives, a third aspect of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a program or instructions executable on the processor, and the program or instructions, when executed by the processor, implement the steps of the above-described automatic dosing method for an electrophoresis tank.

[0020] The electronic device according to the embodiments of the present invention, by executing the above-described automatic dosing method for the electrophoresis tank, can improve the stability of the membrane thickness, enhance work efficiency and product quality, reduce usage costs, and improve the overall digitalization capabilities.

[0021] To achieve the above objectives, a fourth aspect of the present invention provides a computer-readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the above-described automatic dosing method for an electrophoresis tank.

[0022] According to the computer-readable storage medium of the present invention, by executing the above-described automatic dosing method for an electrophoresis tank, the stability of membrane thickness can be improved, work efficiency and product quality can be enhanced, usage costs can be reduced, and the overall digitalization capability of the process can be improved.

[0023] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0024] Figure 1 A flowchart of an automatic dosing method for an electrophoresis tank according to some embodiments of the present invention; Figure 2 This is a block diagram of an electrophoresis system according to some embodiments of the present invention; Figure 3 This is a block diagram of an electronic device according to some embodiments of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to specific embodiments and accompanying drawings.

[0026] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0027] As mentioned in the background section, in the field of electrophoretic coating, the thickness of the electrophoretic film directly affects the corrosion resistance of the workpiece and is one of the core quality indicators. Currently, the industry generally adopts the "sampling confirmation + manual addition" model for electrophoretic bath management, but this model can cause problems such as large parameter fluctuations, unpredictable dosing, uneven bath composition, low efficiency, and high quality costs.

[0028] Specifically, large parameter fluctuations generally refer to film thickness fluctuations exceeding 5μm, making it impossible to stably guarantee anti-corrosion performance; unpredictable chemical dosing is generally due to reliance on manual test results for dosing, lacking prediction of the trend of changes in bath parameters, resulting in inaccurate timing and dosage of dosing; uneven bath composition is generally due to the randomness of manual dosing, which easily leads to uneven distribution of bath composition, further aggravating film thickness fluctuations; low efficiency and high quality costs are generally due to the time-consuming manual dosing, and due to differences in human operation, it is easy to cause subsequent defects (such as particle defects). If rework is required, additional labor time and parts costs are required (for example, rework of metal cover plates requires disassembling multiple peripheral parts, which takes about 1 hour per vehicle and may also cause damage and scratches to parts).

[0029] The root cause of these problems lies in the lack of a precise quantitative model for the relationship between bath parameters, dosage, and film thickness, as well as automated control methods for the entire process. This results in a break in the process from "data acquisition" to "dosing execution," relying on experience rather than data-driven approaches.

[0030] Therefore, this invention can solve the problems of "large film thickness fluctuation, unpredictable chemical addition, uneven bath composition, and high dependence on manual labor" in current electrophoretic coating, improve film thickness stability, enhance work efficiency and product quality, reduce usage costs, and improve the digitalization capabilities of the entire process.

[0031] The following description, with reference to the accompanying drawings, outlines an automatic dosing method, electrophoresis system, electronic device, and computer-readable storage medium for an electrophoresis tank, as proposed in embodiments of the present invention.

[0032] refer to Figure 1 This is a flowchart of an automatic dosing method for an electrophoresis tank according to some embodiments of the present invention.

[0033] like Figure 1 As shown, the automatic dosing method for an electrophoresis tank according to an embodiment of the present invention may include the following steps: S101, Obtain the parameters of the electrophoresis tank solution and the process parameters of the electrophoresis process.

[0034] Specifically, the parameters of the electrophoresis bath solution and the process parameters of the electrophoresis process are collected in real time. The parameters of the bath solution can include the solid content (%), temperature (°C), pH value, and conductivity (μS / cm) of the bath solution. The process parameters of the electrophoresis process can include the electrophoretic film thickness, coating time, and coating voltage.

[0035] S102, input the tank liquid parameters and process parameters into the pre-built dosing prediction model to predict the amount of chemical to be added.

[0036] Specifically, after obtaining the parameters of the electrophoresis bath solution and the process parameters of the electrophoresis process, the bath solution parameters and process parameters are input into a pre-built dosage prediction model to provide input for the dosage prediction model. The pre-built dosage prediction model is processed and the parameter trends are analyzed to accurately calculate the current dosage to be added. The pre-built dosage prediction model is a mathematical tool based on historical data and algorithm training. Its core objective is to quickly and accurately predict the dosage of chemicals that need to be added by inputting key parameters in the current production process (such as bath solution composition, process conditions, etc.) in order to maintain the stability of the production process and product quality.

[0037] S103, based on the amount of chemical to be added, an automatic dosing device adds chemicals to the electrophoresis tank.

[0038] Specifically, after obtaining the amount of reagent to be added, the corresponding dosage is added to the electrophoresis tank based on the calculated dosage from the model. This allows automatic dosing equipment (such as metering pumps and feeding tanks) to add the reagent into the electrophoresis tank, automatically completing the dosing process. Initially, the automatic dosing equipment does this at a frequency of 1.5 hours per cycle. This solves the current problems in electrophoretic coating, such as "large film thickness fluctuations, lack of predictable dosing, uneven tank composition, and high reliance on manual labor," achieving automatic dosing, improving film thickness stability, increasing work efficiency and product quality, reducing operating costs, and enhancing the overall digitalization capabilities of the process.

[0039] In some embodiments of the present invention, the bath parameters include the solids content of the bath, the temperature of the bath, the pH value of the bath, and the conductivity of the bath.

[0040] Specifically, the solid content of the bath solution is measured in real time using an online refractometer or densitometer, reflecting the coating concentration and directly affecting the film thickness; fluctuations in the bath solution temperature affect the rheology and electrophoretic penetration of the coating; the pH value of the bath solution can maintain electrophoretic stability, while an excessively high pH value will lead to a rough coating, and an excessively low pH value may corrode the equipment; the conductivity of the bath solution reflects the ion concentration of the bath solution and is directly related to the voltage setting and electrophoretic efficiency.

[0041] In some embodiments of the present invention, the process parameters include the target electrophoretic film thickness, coating time, and coating voltage.

[0042] Specifically, the target electrophoretic film thickness, as the ultimate control target for the dosage, is directly related to product quality (such as corrosion resistance and appearance); extending the coating time can increase the film thickness, but exceeding the critical value will lead to a rough coating or edge buildup; increasing the coating voltage can improve the penetration, but too high a voltage will lead to coating breakdown or excessively rapid solvent evaporation.

[0043] In some embodiments of the present invention, the dosage prediction model is expressed as follows:

[0044] in, This indicates the amount of pesticide to be added, predicted by the pesticide dosage prediction model. This indicates the various input tank liquid parameters and process parameters; This represents the dosing baseline value when all bath parameters and process parameters remain unchanged. This indicates the weighting of the influence of bath parameters and process parameters on the dosage. This represents the error term, indicating the deviation caused by minor parameters not covered by the dosage prediction model.

[0045] Specifically, through the formula A dosage prediction model can be obtained, in which... As the dependent variable, it is directly related to the stability of the electrophoretic membrane thickness; As the independent variable; This is a constant term, representing the baseline dosage when all independent variables are 0, reflecting a benchmark value that does not depend on specific parameters; For regression coefficients, the weight of the influence of each independent variable on the dosage (e.g., This represents the change in dosage when the solids content of the bath solution changes by 1%, calculated from historical data, reflecting the strength of the correlation (positive / negative) between the parameter and the dosage. The deviation between the predicted and actual values ​​of the dosage prediction model represents the impact of minor factors (such as slight environmental fluctuations) that are not included in the model. The error range can be reduced by optimizing the model.

[0046] In some embodiments of the present invention, the above method further includes: collecting electrophoresis production data of the electrophoresis tank within a historical time period; wherein, the electrophoresis production data includes tank solution parameters, process parameters, historical dosage, and electrophoresis film thickness detection results of the electrophoresis tank within a historical time period; training a basic model based on the electrophoresis production data to obtain the dosage benchmark value, influence weight, and error term; and constructing a dosage prediction model based on the dosage benchmark value, influence weight, and error term.

[0047] Specifically, real-time data collection is performed on the electrophoresis tank, including the solids content, temperature, pH, conductivity, coating time, coating voltage, historical dosage, and electrophoretic film thickness over historical periods. This ensures data integrity and accuracy. Missing or outlier data is appropriately processed, such as filling missing values, removing outliers, or smoothing the data. Data cleaning removes duplicate, erroneous, and irrelevant data. Data standardization or normalization eliminates dimensional differences between features, improving model training effectiveness. The dataset is divided into training, validation, and test sets, typically in a 70%, 15%, and 15% ratio, for model training, validation, and testing. A suitable model is selected for training based on data characteristics and business needs. Considering the complex influence of multiple factors on electrophoretic film thickness, ensemble learning methods, such as random forests or gradient boosting trees, can be used to improve the model's prediction accuracy and generalization ability. The training set is used to train the model, adjusting model parameters to optimize performance and obtaining the dosage baseline, influencing weights, and error terms. Then, a dosage prediction model is constructed based on the dosage baseline, influence weights, and error terms.

[0048] In some embodiments of the present invention, the method further includes: periodically acquiring actual membrane thickness data of the electrophoresis system and predicted membrane thickness data determined based on the output of the dosage prediction model according to a preset cycle; determining whether the difference between the actual membrane thickness data and the predicted membrane thickness data reaches a preset membrane thickness fluctuation threshold; and triggering recalibration of the model parameters and error terms of the dosage prediction model in response to the difference between the actual membrane thickness data and the predicted membrane thickness data reaching the preset membrane thickness fluctuation threshold, so as to optimize the dosage logic of the electrophoresis system.

[0049] Specifically, the actual membrane thickness data and bath parameters of the electrophoresis system are reviewed cyclically using PDCA (Plan, Do, Check, Act) according to a preset period (e.g., seven days), along with the predicted membrane thickness data (e.g., 2 μm) determined by the output of the dosage prediction model. The actual membrane thickness data and the predicted membrane thickness data are compared to determine whether the difference between the actual and predicted membrane thickness data reaches a preset membrane thickness fluctuation threshold. When the difference between the actual and predicted membrane thickness data reaches the preset membrane thickness fluctuation threshold, the system is considered to have completed the process. At this point, the model parameters and error terms of the dosage prediction model are recalibrated to optimize the dosing logic of the electrophoresis system (such as adjusting the triggering conditions for F1 / F2 dosing, where the triggering conditions for F1 / F2 dosing can be customized based on the membrane thickness prediction results to implement a graded dosing strategy. For example, F1 logic: when the predicted membrane thickness deviates from the target value by ±1μm, a small dose supplement is triggered (e.g., 0.5kg / time); F2 logic: when it deviates by ±2μm, a large dose supplement is triggered (e.g., 1.5kg / time), and the coating voltage / coating time is adjusted accordingly), further improving the accuracy of dosing.

[0050] In some embodiments of the present invention, the above method further includes: in response to the error term of the dosage prediction model exceeding a preset error range, triggering a recalibration of the model parameters and error term of the dosage prediction model to optimize the dosing logic of the electrophoresis system.

[0051] Specifically, the error terms of the dosage prediction model are compared with the preset error range to determine whether the error terms of the dosage prediction model exceed the preset error range. When the error terms of the dosage prediction model exceed the preset error range, the model parameters and error terms of the dosage prediction model are recalibrated to optimize the dosage logic of the electrophoresis system.

[0052] In some embodiments, the film thickness fluctuation can be controlled within 2μm, ensuring consistent anti-corrosion performance; reducing manual feeding time, saving 248 hours of feeding time per year; reducing the probability of defects, with 3-5 fewer particle defect points per vehicle; reducing sandpaper usage by 0.5 sheets per vehicle (each sheet costs 0.44 yuan), resulting in annual cost savings of 44,000 yuan based on an annual production of 200,000 units; avoiding part damage and wasted time due to rework; and achieving closed-loop management from "data acquisition (tank parameters) → model calculation → automatic feeding execution," promoting the upgrade of the process from "experience-driven" to "data-driven," and reducing human interference.

[0053] In some embodiments, the pre-built dosage prediction model can be replaced by other mathematical models that correlate the dosage with the bath parameters (such as neural network models, support vector machine models, etc.), as long as it can accurately predict the dosage and ensure film thickness stability; the cyclical improvement method for full-process control can be replaced by other lean / digital methods such as DMAIC (Define, Measure, Analyze, Improve, Control), as long as it can achieve closed-loop optimization of "data-model-execution".

[0054] As a specific embodiment, sensors are deployed next to the electrophoresis tank. The data acquisition module collects data on the solids content, temperature, pH value, and conductivity of the electrophoresis solution every 10 minutes, simultaneously monitoring process parameters such as coating time and voltage on the production line, and transmitting this data in real time to the model calculation module. The model calculation module uses one year's worth of electrophoresis production data from the workshop (including tank parameters, chemical dosage, and film thickness detection results) to train a regression analysis model and calculate the regression coefficients for each parameter (such as the regression coefficient for the solids content of the tank solution). =0.8, indicating that for every 1% increase in the solids content of the bath solution, the dosage needs to be increased by 0.8L), determine the constant term. =5L, Based on the baseline dosage, when the pre-built dosage prediction model is running, the parameters collected in real time are substituted into the formula. In this process, the current dosage is accurately calculated, and the dosing calculation and execution are performed every 1.5 hours initially. The automatic dosing execution module controls the automatic dosing equipment to receive the dosing dosage instruction output by the model, automatically starts the metering pump, adds the corresponding dose of reagent to the electrophoresis tank, and feeds back the execution result to the system. The hardware of the model calculation module can use industrial-grade servers or edge computing devices to ensure data processing efficiency; the metering pumps and valves of the automatic dosing execution module must have corrosion-resistant and precise metering characteristics to ensure dosing accuracy.

[0055] Therefore, this invention is applicable to various electrophoretic coating processes, especially coating production lines with high requirements for film thickness stability and a pursuit of digital and intelligent upgrades (such as electrophoretic processes in the automotive and construction machinery industries). By combining the PDCA cycle to build a digital and intelligent toolchain of "data acquisition - model calculation - automatic feeding," the accuracy of the model and the effect of dosing are continuously verified, and model parameters (such as regression coefficients and error range) are optimized to ensure film thickness stability. It achieves a quantitative correlation between "battery parameters - dosing amount - film thickness," replacing manual experience-based judgment and transforming dosing from "unpredictable" to "precisely predictive," directly reducing film thickness fluctuations. The automatic dosing equipment replaces manual operation, improving dosing efficiency (reducing manual time) and reducing the interference of human operation on bath parameters and film thickness, thus lowering the probability of defects. Closed-loop management throughout the entire process ensures seamless "data-model-execution," fundamentally solving the problem of uneven bath composition. Simultaneously, continuous optimization through the PDCA cycle ensures long-term stable system operation, further enhancing quality and cost advantages.

[0056] In summary, the automatic dosing method for an electrophoresis tank according to embodiments of the present invention includes: acquiring the tank solution parameters and the electrophoresis process parameters; inputting the tank solution parameters and process parameters into a pre-constructed dosing prediction model to predict the amount of chemical to be added; and controlling an automatic dosing device to add chemical to the electrophoresis tank based on the amount of chemical to be added. Therefore, this method can improve the stability of the membrane thickness, increase work efficiency and product quality, reduce operating costs, and enhance the overall digitalization capabilities of the process.

[0057] It should be noted that the method of this embodiment can be executed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method of this embodiment, and the multiple devices will interact with each other to complete the above method.

[0058] It should be noted that the above description describes some embodiments of the present invention. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the above embodiments and still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0059] Corresponding to the above embodiments, the present invention also proposes an electrophoresis system.

[0060] like Figure 2As shown, the electrophoresis system of this embodiment includes: an acquisition module 210, a prediction module 220, and a dosing module 230.

[0061] The acquisition module 210 is configured to acquire the tank liquid parameters and the process parameters of the electrophoresis process in the electrophoresis tank; the prediction module 220 is configured to input the tank liquid parameters and process parameters into a pre-built dosing prediction model to predict the amount of dosing to be added; and the dosing module 230 is configured to control the automatic dosing equipment to add chemicals to the electrophoresis tank based on the amount of dosing to be added.

[0062] In some embodiments of the present invention, the bath parameters include the solids content of the bath, the temperature of the bath, the pH value of the bath, and the conductivity of the bath.

[0063] In some embodiments of the present invention, the process parameters include the target electrophoretic film thickness, coating time, and coating voltage.

[0064] In some embodiments of the present invention, the dosage prediction model is expressed as follows:

[0065] in, This indicates the amount of pesticide to be added, predicted by the pesticide dosage prediction model. This indicates the various input tank liquid parameters and process parameters; This represents the dosing baseline value when all bath parameters and process parameters remain unchanged. This indicates the weighting of the influence of bath parameters and process parameters on the dosage. This represents the error term, indicating the deviation caused by minor parameters not covered by the dosage prediction model.

[0066] In some embodiments of the present invention, the acquisition module 210 is further configured to collect electrophoresis production data of the electrophoresis tank within a historical time period; wherein, the electrophoresis production data includes tank liquid parameters, process parameters, historical dosage, and electrophoresis film thickness detection results of the electrophoresis tank within a historical time period; a basic model is trained based on the electrophoresis production data to obtain the dosage benchmark value, influence weight, and error term; and a dosage prediction model is constructed based on the dosage benchmark value, influence weight, and error term.

[0067] In some embodiments of the present invention, the prediction module 220 is further configured to periodically acquire the actual membrane thickness data of the electrophoresis system and the predicted membrane thickness data determined based on the output of the dosage prediction model according to a preset cycle; determine whether the difference between the actual membrane thickness data and the predicted membrane thickness data reaches a preset membrane thickness fluctuation threshold; and, in response to the difference between the actual membrane thickness data and the predicted membrane thickness data reaching the preset membrane thickness fluctuation threshold, trigger the recalibration of the model parameters and error terms of the dosage prediction model to optimize the dosage logic of the electrophoresis system.

[0068] In some embodiments of the present invention, the prediction module 220 is further configured to, in response to the error term of the dosage prediction model exceeding a preset error range, trigger a recalibration of the model parameters and error term of the dosage prediction model to optimize the dosing logic of the electrophoresis system.

[0069] It should be noted that for details not disclosed in the electrophoresis system of this embodiment, please refer to the details disclosed in the automatic dosing method for the electrophoresis tank of this embodiment, which will not be repeated here.

[0070] In summary, the electrophoresis system according to embodiments of the present invention includes: an acquisition module configured to acquire the tank parameters of the electrophoresis bath and the process parameters of the electrophoresis process; a prediction module configured to input the tank parameters and process parameters into a pre-built dosing prediction model to predict the amount of reagent to be added; and a dosing module configured to control an automatic dosing device to add reagent to the electrophoresis bath based on the amount of reagent to be added. Therefore, this system can improve the stability of the membrane thickness, increase work efficiency and product quality, reduce operating costs, and enhance the overall digitalization capabilities of the process.

[0071] For ease of description, the above system is described by dividing it into various modules based on their functions. Of course, in implementing this invention, the functions of each module can be implemented in one or more software and / or hardware components.

[0072] The system described in the above embodiments is used to implement the corresponding method in any of the foregoing embodiments and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0073] Corresponding to the above embodiments, the present invention also proposes an electronic device.

[0074] refer to Figure 3 The diagram below is a block diagram of an electronic device according to some embodiments of the present invention. It illustrates a more specific hardware structure of the electronic device provided in this embodiment. The device may include: a processor 310, a memory 320, an input / output interface 330, a communication interface 340, and a bus 350. The processor 310, memory 320, input / output interface 330, and communication interface 340 are interconnected internally via the bus 350.

[0075] The processor 310 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0076] The memory 320 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 320 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 320 and is called and executed by the processor 310.

[0077] Input / output interface 330 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0078] The communication interface 340 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0079] Bus 350 includes a pathway for transmitting information between various components of the device, such as processor 310, memory 320, input / output interface 330, and communication interface 340.

[0080] It should be noted that although the above-described device only shows the processor 310, memory 320, input / output interface 330, communication interface 340, and bus 350, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0081] The electronic devices described above are used to implement the corresponding methods in any of the foregoing embodiments and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0082] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, the present invention also provides a computer-readable storage medium storing computer instructions for causing a computer to perform the methods of any of the above embodiments.

[0083] The aforementioned computer-readable storage medium can be any available medium or data storage device that a computer can access, including but not limited to magnetic storage (e.g., floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical storage (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND flash), solid-state drives (SSDs)).

[0084] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to perform the methods of any of the above exemplary method sections, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0085] Furthermore, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Rather, the steps depicted in the flowchart may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0086] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0087] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this invention should have the ordinary meaning understood by those skilled in the art. The terms "first," "second," and similar terms used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word covers the element or object listed after the word and its equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are only used to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0088] While the spirit and principles of the invention have been described with reference to several specific embodiments, it should be understood that the invention is not limited to the disclosed specific embodiments, and the division of aspects does not imply that features in these aspects cannot be combined for benefit; such division is merely for ease of description. The invention is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims. The scope of the appended claims is to be interpreted in the broadest sense, thereby encompassing all such modifications and equivalent structures and functions.

Claims

1. An automatic dosing method for an electrophoresis tank, applied to an electrophoresis system, characterized in that, The method comprises: obtaining the parameters of the tank solution in the electrophoresis tank and the process parameters of the electrophoresis process; inputting the tank solution parameters and the process parameters into a pre-constructed dosing amount prediction model to obtain a to-be-supplemented dosing amount; controlling an automatic dosing device to add chemicals into the electrophoresis tank based on the to-be-supplemented dosing amount.

2. The method for automatic dosing of an electrophoresis tank according to claim 1, characterized in that, The tank solution parameters include tank solution solids, tank solution temperature, tank solution pH value, and tank solution conductivity.

3. The method for automatic dosing of an electrophoresis tank according to claim 1, characterized in that, The process parameters include target electrophoresis film thickness, coating time, and coating voltage.

4. The method for automatic dosing of an electrophoresis tank according to claim 1, characterized in that, The dosing amount prediction model is represented as: wherein, represents the amount of the additive to be added predicted by the additive amount prediction model; represents the inputted each item of bath liquid parameter and process parameter; represents the reference value of the additive amount when each item of bath liquid parameter and process parameter is unchanged; represents the influence weight of the bath liquid parameter and process parameter on the additive amount; represents the error term, and represents the deviation caused by the secondary parameter not covered by the additive amount prediction model.

5. The method for automatic dosing of an electrophoresis tank according to claim 4, characterized in that, The method further comprises: collecting electrophoresis production data of the electrophoresis tank in a historical time period; wherein the electrophoresis production data includes tank solution parameters, process parameters, historical dosing amount, and electrophoresis film thickness detection results of the electrophoresis tank in the historical time period; training a base model based on the electrophoresis production data to obtain the dosing reference value, the influence weight, and the error term; constructing the dosing amount prediction model based on the dosing reference value, the influence weight, and the error term.

6. The method for automatic dosing of an electrophoresis tank according to claim 5, characterized in that, The method further comprises: periodically obtaining actual film thickness data of the electrophoresis system and predicted film thickness data determined based on the output of the dosing amount prediction model according to a preset period; determining whether the difference between the actual film thickness data and the predicted film thickness data reaches a preset film thickness fluctuation threshold; in response to the difference between the actual film thickness data and the predicted film thickness data reaching the preset film thickness fluctuation threshold, triggering re-calibration of the model parameters and error term of the dosing amount prediction model to optimize the dosing logic of the electrophoresis system.

7. The method for automatic dosing of an electrophoresis tank according to claim 5, characterized in that, The method further comprises: in response to the error term of the dosing amount prediction model exceeding a preset error range, triggering re-calibration of the model parameters and error term of the dosing amount prediction model to optimize the dosing logic of the electrophoresis system.

8. An electrophoretic system characterized by, comprises: an acquisition module configured to obtain the parameters of the tank solution in the electrophoresis tank and the process parameters of the electrophoresis process; a prediction module configured to input the tank solution parameters and the process parameters into a pre-constructed dosing amount prediction model to obtain a to-be-supplemented dosing amount; a dosing module configured to control an automatic dosing device to add chemicals into the electrophoresis tank based on the to-be-supplemented dosing amount.

9. An electronic device, comprising: comprises: a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the automatic dosing method for the electrophoresis tank according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The readable storage medium stores programs or instructions, which are executed by the processor to implement the steps of the automatic dosing method for the electrophoresis tank according to any one of claims 1 to 7.

Images