Coating thinning area thickness control method, device and equipment and storage medium

Abstract

The invention discloses a coating thinning area thickness control method, device and equipment and a storage medium. Comprising the following steps: collecting real-time thinning data of a target coating thinning area; calculating a deviation value based on the thickness data; determining an over-limit judgment result according to the deviation value, and when the over-limit judgment result is no over-limit, calculating an error absolute value of the thickness error value; judging whether the error absolute value is greater than a preset error threshold value, if so, calculating a ratio of the thickness error value to the transfer function as a thickness adjustment amount, and performing filtering smooth output based on the thickness adjustment amount; otherwise, keeping the current state. By collecting data in real time and identifying a transfer function on line, working condition changes can be rapidly adapted, and it is ensured that the model fits the reality. And through deviation value calculation, the overall and local thickness deviation is accurately reflected. Thickness control is carried out according to the overrun judgment result, abnormal quick response and accurate adjustment are achieved, the debugging time is shortened, the labor cost is reduced, and the production efficiency and the resource utilization rate are improved.

Description

Technical Field

[0001] The present invention relates to the field of lithium battery coating technology, and in particular to a method, device, equipment and storage medium for controlling the thickness of a coating thinning area. Background Art

[0002] In coating processes, especially in high-precision applications like lithium-ion battery electrode coating and electronic thin film coating, the thickness uniformity and accuracy of the skived area directly impact product performance and safety. As industry demands for product consistency increase, traditional thickness control methods that rely on manual experience are no longer sufficient for large-scale production. Automated control technology capable of real-time monitoring and dynamic adjustment is urgently needed.

[0003] Currently, in the slot extrusion coating process, the thickness of the thinning area is mainly achieved through mechanical adjustment of the baffle and push-pull rod. Before production, the gasket structure needs to be manually debugged, and the baffle position needs to be repeatedly measured and adjusted during the first production until the thinning weight meets the specifications. However, manual debugging is costly and difficult to cope with the switching of multiple batches and multiple specifications of products, resulting in low production efficiency. Some automated equipment attempts to perform open-loop control through fixed parameters, but fixed parameters cannot adapt to dynamic working conditions such as changes in slurry viscosity and equipment wear, resulting in limited control accuracy. Summary of the Invention

[0004] The present invention provides a coating skived area thickness control method, device, equipment and storage medium, which can achieve real-time adjustment of the skived area thickness, thereby significantly improving the consistency and quality stability of the product.

[0005] According to one aspect of the present invention, a method for controlling the thickness of a coating thinning area is provided, the method comprising:

[0006] Collecting real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data and baffle displacement at each designated position;

[0007] Calculating a deviation value based on the thickness data, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value;

[0008] Determine the over-limit judgment result according to the deviation value, and when the over-limit judgment result is no over-limit, calculate the absolute value of the thickness error value;

[0009] Determine whether the absolute value of the error is greater than a preset error threshold. If so, calculate the ratio of the thickness error value to the transfer function as the thickness adjustment amount, and perform filtering and smoothing output based on the thickness adjustment amount.

[0010] Otherwise, keep the current state.

[0011] Optionally, the method also includes: obtaining historical thinning data, determining the thinning data change based on the historical thinning data and the real-time thinning data, wherein the thinning data change includes the thickness change and the displacement change; online identifying the transfer function of the thickness change and the displacement change through FFRLS with a dynamic factor, and verifying the validity of the transfer function through the residual.

[0012] Optionally, the validity of the transfer function is verified by residuals, including: substituting historical displacement changes into the transfer function, calculating a first predicted thickness change, subtracting the first predicted thickness change from the actual thickness change to obtain a residual value, calculating the standard deviation of the residual value, and using three times the standard deviation as the residual threshold; substituting the real-time displacement change of the baffle into the transfer function, calculating a second predicted thickness change, subtracting the second predicted thickness change from the actual thickness change to obtain a new residual value; judging whether the new residual value is greater than the residual threshold, and if so, determining that the transfer function verification is invalid; otherwise, determining that the transfer function verification is valid.

[0013] Optionally, the deviation value is calculated based on the thickness data, including: taking each designated position as the target position; obtaining the position weight, target thickness, configuration upper limit value and configuration lower limit value corresponding to the target position; performing weighted calculation on each thickness data according to the position weight to determine the weighted thickness mean; calculating the difference between the weighted thickness mean of the target position and the target thickness as the thickness error value; calculating the difference between the thickness data of the target position and the configuration upper limit value as the upper limit difference; calculating the difference between the thickness data of the target position and the configuration lower limit value as the lower limit difference.

[0014] Optionally, the over-limit judgment result is determined based on the deviation value, including: taking each designated position as the target position respectively; judging whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit; if so, when the upper limit difference of the same target position exceeds the upper limit and the lower limit difference exceeds the lower limit, or different target positions exceed the upper limit and the lower limit respectively, the over-limit judgment result of the target position is determined to be multiple over-limit; when the upper limit difference of the same target position exceeds the upper limit or the lower limit difference exceeds the lower limit, the over-limit judgment result of the target position is determined to be single-point over-limit; otherwise, the over-limit judgment result of the target position is determined to be no over-limit.

[0015] Optionally, the method further includes: when the over-limit judgment result is multiple over-limits, generating prompt information according to the over-limit judgment result, triggering an alarm and interrupting automatic control according to the prompt information to prompt user intervention.

[0016] Optionally, the method further includes: when the over-limit judgment result is a single-point over-limit, calculating a safety adjustment amount based on a quadratic programming algorithm, and applying a rate limit based on the safety adjustment amount.

[0017] According to another aspect of the present invention, there is provided a device for controlling the thickness of a coating thinning area, the device comprising:

[0018] A transfer function determination module is used to collect real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data of each specified position and displacement of the flow block;

[0019] a deviation value calculation module, configured to calculate a deviation value based on the thickness data, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value;

[0020] The thinning area thickness control module is used to determine the over-limit judgment result based on the deviation value. When the over-limit judgment result is no over-limit, the module calculates the absolute value of the thickness error value; determines whether the absolute value of the error is greater than a preset error threshold; if so, calculates the ratio of the thickness error value and the transfer function as the thickness adjustment amount, and performs filtering and smoothing output based on the thickness adjustment amount; otherwise, maintains the current state.

[0021] According to another aspect of the present invention, an electronic device is provided, comprising:

[0022] at least one processor;

[0023] and a memory communicatively coupled to the at least one processor;

[0024] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute a coating thinning area thickness control method described in any embodiment of the present invention.

[0025] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement a coating thinning area thickness control method described in any embodiment of the present invention when executed.

[0026] The technical solution of this embodiment of the present invention, through real-time data acquisition and online transfer function identification, can rapidly adapt to changing operating conditions and ensure that the model is accurate to the actual situation. Deviation calculation accurately reflects overall and local thickness deviations. Thickness control based on over-limit determination results enables rapid response to anomalies and precise adjustment, shortening commissioning time, reducing labor costs, and improving production efficiency and resource utilization.

[0027] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 This is a flow chart of a method for controlling the thickness of a coating skived area according to the first embodiment of the present invention;

[0030] Figure 2 This is a flow chart of another method for controlling the thickness of a coating skived area provided according to the second embodiment of the present invention;

[0031] Figure 3 2 is a schematic structural diagram of a coating thinning zone thickness control device provided according to a third embodiment of the present invention;

[0032] Figure 4 It is a structural schematic diagram of an electronic device for implementing a coating skived area thickness control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] Example 1

[0036] Figure 1A flowchart of a coating thinning area thickness control method is provided for the first embodiment of the present invention. This embodiment is applicable to the scenario of real-time adjustment of the thickness of the thinning area. The method can be executed by a coating thinning area thickness control device. The coating thinning area thickness control device can be implemented in the form of hardware and / or software. The coating thinning area thickness control device can be configured in a computer controller. Figure 1 As shown, the method includes:

[0037] S110 , collecting real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data of each designated position and displacement of the baffle.

[0038] Among them, the thinning area refers to a specific area on the foil that needs to be thinned in addition to the main coating area in the slit extrusion coating process, such as the coating edge or a specific functional area. The thickness data h(t) refers to the thickness value of each specified position in the thinning area at time t, which is collected in real time with the help of detection equipment such as laser thickness gauges and beta-ray thickness gauges, and the unit is micrometer (μm). The baffle is a component inside the coating head used to adjust the slurry flow. The baffle displacement d(t) refers to the displacement of the baffle relative to the initial position at time t, and the unit is millimeter (mm). The displacement direction includes lifting or pressing down, which will have a direct impact on the amount of slurry passing through the thinning area.

[0039] Optionally, the method also includes: obtaining historical thinning data, determining the thinning data change based on the historical thinning data and the real-time thinning data, wherein the thinning data change includes the thickness change and the displacement change; online identifying the transfer function of the thickness change and the displacement change through FFRLS with a dynamic factor, and verifying the validity of the transfer function through the residual.

[0040] Among them, online identification refers to the process of dynamically updating model parameters using real-time data. Specifically, the FFRLS algorithm with a dynamic forgetting factor can be used, that is, the recursive least squares method can be used to adapt the model to real-time changes in slurry properties, equipment operating conditions, etc. by assigning different weights to historical data. The transfer function k(t) represents the dynamic proportional relationship between the displacement change of the baffle and the thickness change, and the unit is μm / mm. For example, k(t) = 5 means that if the baffle is lifted by 1mm, the thickness of the thinning area will increase by 5μm. The residual refers to the error between the model prediction value and the actual measurement value. If the residual exceeds the threshold, anomaly detection is triggered, indicating that the model is inaccurate and needs to be recalibrated.

[0041] Historical skiving data refers to the skiving zone thickness and baffle displacement data recorded by the coating equipment over a specified historical period. Thickness change Δh is the difference between the real-time thickness and the historical thickness, reflecting the thickness fluctuation. Displacement change Δd is the difference between the real-time baffle displacement and the historical displacement, reflecting the magnitude and direction of the baffle adjustment.

[0042] Specifically, online transfer function identification involves establishing a dynamic relationship between the displacement change Δd and the thickness change Δh of the block: Δh = k(t)·Δd, where k(t) is the transfer function. The controller then performs residual verification on the identified transfer function k(t), calculating the error between the predicted and actual values—that is, the difference between the actual thickness change and the thickness change predicted by the transfer function model. The residual value is ||Δh - k(t)·Δd||, where Δh is the actual thickness change and k(t)·Δd is the thickness change predicted by the model.

[0043] Optionally, the validity of the transfer function is verified by residuals, including: substituting historical displacement changes into the transfer function, calculating a first predicted thickness change, subtracting the first predicted thickness change from the actual thickness change to obtain a residual value, calculating the standard deviation of the residual value, and using three times the standard deviation as the residual threshold; substituting the real-time displacement change of the baffle into the transfer function, calculating a second predicted thickness change, subtracting the second predicted thickness change from the actual thickness change to obtain a new residual value; judging whether the new residual value is greater than the residual threshold, and if so, determining that the transfer function verification is invalid; otherwise, determining that the transfer function verification is valid.

[0044] Specifically, when verifying the validity of the transfer function through residuals, the historical displacement changes must first be substituted into the identified transfer function to calculate the first predicted thickness change, which is then subtracted from the actual thickness change to obtain the residual value. The residual threshold is 3 times the standard deviation, 3σ, meaning that a normal residual value should fall within the range of ±3σ from the mean. The controller then substitutes the real-time displacement changes of the block into the transfer function to calculate the second predicted thickness change, which is also subtracted from the actual thickness change to obtain a new residual value. When the new residual value is greater than the residual threshold, it indicates that the deviation between the transfer function predicted value and the actual value exceeds the normal fluctuation range, and the transfer function verification is determined to be invalid. When the new residual value is less than or equal to the residual threshold, it indicates that the transfer function predicted value is in good agreement with the actual value, and the transfer function verification is determined to be valid and the model is credible. The current transfer function k(t) can then be used for thickness control.

[0045] S120 . Calculate a deviation value based on the thickness data, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value.

[0046] Among them, the thickness error value refers to the difference between the weighted average thickness of the thinning area and the target thickness, the upper limit difference refers to the difference between the thickness of each specified position and the maximum thickness allowed by the process, and the lower limit difference refers to the difference between the thickness of each specified position and the minimum thickness allowed by the process.

[0047] S130 , determining an over-limit judgment result according to the deviation value, and when the over-limit judgment result is no over-limit, calculating an absolute value of the thickness error value.

[0048] The over-limit judgment results include multiple over-limits, single-point over-limits, and no over-limits. Multiple over-limits refer to situations where the thickness exceeds both the upper and lower limits simultaneously in the same thinning zone, or where multiple locations exceed the limits in the same direction. This triggers an alarm, interrupts automatic control, and switches to manual processing. Single-point over-limits refer to situations where the thickness exceeds the upper or lower limit at only a single location. A quadratic programming algorithm is used to calculate the maximum safe adjustment range for the flow block and limit the adjustment rate to avoid drastic adjustments that may cause slurry fluctuations.

[0049] Optionally, the over-limit judgment result is determined based on the deviation value, including: taking each designated position as the target position respectively; judging whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit; if so, when the upper limit difference of the same target position exceeds the upper limit and the lower limit difference exceeds the lower limit, or different target positions exceed the upper limit and the lower limit respectively, the over-limit judgment result of the target position is determined to be multiple over-limit; when the upper limit difference of the same target position exceeds the upper limit or the lower limit difference exceeds the lower limit, the over-limit judgment result of the target position is determined to be single-point over-limit; otherwise, the over-limit judgment result of the target position is determined to be no over-limit.

[0050] The target position refers to a key monitoring point in the coating and skiving area, pre-set according to process requirements. It is usually a fixed distance from the foil edge or a specific functional area, such as 5mm, 7mm, and 10mm. Each target position corresponds to a set of deviation values. Exceeding the upper limit means the upper limit difference is greater than 0, and exceeding the lower limit means the lower limit difference is less than 0.

[0051] Specifically, the controller uses each designated location as a target location for over-limit determination. It first checks whether over-limit conditions exist at each target location: whether the upper limit difference exceeds the upper limit or the lower limit difference exceeds the lower limit. Multiple over-limit conditions refer to one of the following abnormal conditions occurring in the coating skiving area: 1. The thickness at the same target location simultaneously exceeds the process upper limit and falls below the process lower limit. This is theoretically impossible and is actually a false alarm caused by sensor anomalies or data jumps. 2. The thickness at different target locations exceeds the upper limit and falls below the lower limit. For example, if the thickness at 5mm exceeds the upper limit and at least one other target location exceeds the lower limit, this indicates extremely uneven thickness distribution in the skiving area and a high risk of process loss of control. This means that if any target location exceeds the upper limit and at least one other target location exceeds the lower limit, or if the system detects inconsistent data at the same location, such as thickness measurements showing both an upper limit and a lower limit, it may be due to a sensor malfunction and is therefore considered a multiple over-limit condition. If the upper limit difference exceeds the upper limit or the lower limit difference exceeds the lower limit, the target location's over-limit determination is determined to be a single point over-limit condition. When the upper limit difference does not exceed the upper limit and the lower limit difference does not exceed the lower limit, the over-limit judgment result of the target position is determined to be no over-limit.

[0052] S140 , determine whether the absolute value of the error is greater than a preset error threshold; if so, execute S150 ; otherwise, execute S160 .

[0053] S150 , calculating a ratio of the thickness error value to the transfer function as a thickness adjustment amount, and performing filtering and smoothing based on the thickness adjustment amount to output.

[0054] S160. Maintain the current state.

[0055] It should be noted that when the thickness of all pre-set target locations in the coating thinning area is within the process specification range, that is, neither exceeding the upper limit nor falling below the lower limit, it is determined to be within the limit. In the case of no limit, although the thickness at each location is qualified, the overall thickness of the thinning area may differ slightly from the target thickness.

[0056] Specifically, the controller assigns different weights to each target location based on its importance in the process and calculates a comprehensive thickness value. The target thickness is then subtracted from the comprehensive thickness value to obtain a thickness error. The absolute value of the thickness error is then compared to a preset error threshold, perhaps 0.005. If the absolute value exceeds the threshold, the thickness deviation from the target value exceeds the acceptable range of minor fluctuations, requiring fine-tuning. The controller then calculates the thickness adjustment based on a real-time transfer function. This transfer function represents the relationship between the displacement of the baffle and the change in thickness. Dividing the thickness error by the transfer function yields the theoretically required baffle displacement adjustment, or thickness adjustment. To avoid unnecessary fluctuations during the adjustment process, the adjustment is filtered and smoothed. If the adjustment is large, it is executed incrementally over multiple cycles, with each cycle executing at a rate not exceeding a specified maximum rate. If the absolute value of the error is within the preset threshold, the thickness is considered ideal and no adjustment is required, and the system maintains its current operating state.

[0057] In one specific embodiment, when the over-limit judgment result is no over-limit, the controller acquires the thickness data for each target position in real time, calculates the weighted mean and error value, and then compares the absolute value of the error with a preset threshold to determine whether to initiate fine-tuning. When fine-tuning is required, the theoretical adjustment amount can be further calculated based on the transfer function, the direction and amplitude of the baffle movement can be determined, and a smooth adjustment signal can be generated through a filtering algorithm to drive the baffle to execute. Finally, after the adjustment is completed, data is collected again. If the absolute value of the error drops below the threshold, the adjustment is stopped. If the error does not meet the requirement, the above process is repeated until the requirement is met.

[0058] Optionally, the method further includes: when the over-limit judgment result is multiple over-limits, generating prompt information according to the over-limit judgment result, triggering an alarm and interrupting automatic control according to the prompt information to prompt user intervention.

[0059] Specifically, when the over-limit judgment result is multiple over-limits, the controller can output prompt information through the human-machine interface or background log. The prompt information may include the over-limit position, deviation value, trigger time and recommended operation, among which the over-limit position refers to the target position with clear marking of the upper limit and lower limit, such as the thickness exceeds the upper limit at 5mm; the deviation value refers to the specific deviation value displayed at each position, such as the upper limit deviation value = +1.2μm; the trigger time refers to the specific time when the abnormality is recorded, such as 2025-04-2414:30:15; the recommended operation refers to the processing suggestion to the user, for example, the prompt "Please check the slurry supply, the mechanical state of the baffle and the sensor accuracy."

[0060] Furthermore, triggering alarms can include audible and visual alarms, as well as remote alarms. An audible and visual alarm involves the on-site device emitting a buzzer alarm and flashing a red warning light on the operation panel to attract the operator's attention. A remote alarm involves sending an alarm notification to an engineer via the MES system or SMS platform, with content such as "Multiple limits exceeded in the skiving area of ​​the coating machine, requiring immediate attention."

[0061] In addition, the controller will also interrupt automatic control, that is, stop the action of the actuator, including immediately freezing the displacement adjustment system of the choke block to prevent the abnormal expansion due to misadjustment, and maintain the current state, that is, maintain other parameters of the coating head unchanged to avoid greater fluctuations caused by shutdown.

[0062] It's important to note that when the same type of overrun occurs simultaneously at multiple target locations in the coating thinning zone, adjustments are prioritized for the most severe location. The most severe location is the one with the largest absolute deviation among multiple locations exceeding the limit in the same direction, meaning it has the most significant impact on product quality. In this case, the controller prioritizes adjusting the thickness of the most severe location to within process specifications before adjusting other locations.

[0063] Optionally, the method further includes: when the over-limit judgment result is a single-point over-limit, calculating a safety adjustment amount based on a quadratic programming algorithm, and applying a rate limit based on the safety adjustment amount.

[0064] Specifically, if the thickness of a target location in the coating thinning zone exceeds the upper or lower limit individually, it will be considered a single point overrun. In this case, the baffle displacement adjustment must be calculated to quickly restore the thickness at the overrun location to the specification range without affecting the thickness at other locations. This also prevents further fluctuations caused by excessive or rapid adjustments.

[0065] Among them, the quadratic programming algorithm is a mathematical optimization method that solves the optimal baffle displacement adjustment amount Δd by setting the objective function and constraints. Its goal is to make the adjustment amplitude as small as possible under the premise of eliminating overlimit, so as to reduce the disturbance to the coating process. If the thickness exceeds the upper limit, it is necessary to reduce the slurry flow by pressing down the baffle to reduce the thickness, and if the thickness is lower than the lower limit, it is necessary to increase the slurry flow by lifting the baffle to increase the thickness. Constraints include process constraints and mechanical constraints. The process constraint means that the thickness at this position must return to between the upper and lower limits after adjustment. The mechanical constraint means that the displacement of the baffle cannot exceed its physical range of motion. Under the premise of meeting the above constraints, the displacement of the baffle is minimized as much as possible to reduce interference with the coating process.

[0066] Furthermore, in order to avoid the rapid movement of the baffle causing unstable slurry flow or equipment wear, the adjustment rate needs to be limited, specifically including limiting the single adjustment range and smooth adjustment. Limiting the single adjustment range is to stipulate the maximum displacement of the baffle in each control cycle, such as a maximum movement of 0.05mm each time. If the calculated total adjustment amount is large, such as requiring a downward pressure of 0.3mm, it will be executed multiple times, with an adjustment of 0.05mm each time until the target is reached. Smooth adjustment means making the displacement change of the baffle smoother through a filtering algorithm. For example, the adjustment amount will not reach the calculated value instantly, but will gradually approach it, such as completing 50% of the adjustment in the first second, 30% in the second second, and gradually completing the remaining part to reduce the impact on the coating thickness. In addition, during the adjustment process, the controller will continuously check whether the thickness at that position has returned to the normal range. If the adjustment effect does not meet expectations due to factors such as slurry fluctuations, it will automatically recalculate and adjust the strategy.

[0067] The technical solution of the embodiment of the present invention can quickly adapt to changing working conditions and ensure that the model is realistic by collecting data in real time and identifying transfer functions online. Residual testing verifies the reliability of the model, enabling timely detection of anomalies and effectively reducing the defective product rate. Deviation value calculation accurately reflects overall and local thickness deviations. Thickness control is performed based on over-limit judgment results, achieving rapid response to anomalies and precise adjustment, shortening commissioning time, reducing labor costs, and improving production efficiency and resource utilization.

[0068] Example 2

[0069] Figure 2 This is a flowchart of a coating thinning area thickness control method provided in the second embodiment of the present invention. This embodiment adds a specific process for calculating the deviation value based on the thickness data on the basis of the above-mentioned first embodiment. Among them, the specific contents of steps S210 and S280 are roughly the same as those of steps S110 and S130 in the first embodiment, so they will not be repeated in this embodiment. Figure 2 As shown, the method includes:

[0070] S210 , collecting real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data of each designated position and displacement of the flow block.

[0071] Optionally, the method also includes: obtaining historical thinning data, determining the thinning data change based on the historical thinning data and the real-time thinning data, wherein the thinning data change includes the thickness change and the displacement change; online identifying the transfer function of the thickness change and the displacement change through FFRLS with a dynamic factor, and verifying the validity of the transfer function through the residual.

[0072] Optionally, the validity of the transfer function is verified by residuals, including: substituting historical displacement changes into the transfer function, calculating a first predicted thickness change, subtracting the first predicted thickness change from the actual thickness change to obtain a residual value, calculating the standard deviation of the residual value, and using three times the standard deviation as the residual threshold; substituting the real-time displacement change of the baffle into the transfer function, calculating a second predicted thickness change, subtracting the second predicted thickness change from the actual thickness change to obtain a new residual value; judging whether the new residual value is greater than the residual threshold, and if so, determining that the transfer function verification is invalid; otherwise, determining that the transfer function verification is valid.

[0073] S220: Set each designated position as a target position.

[0074] S230: Obtain a position weight, a target thickness, a configuration upper limit value, and a configuration lower limit value corresponding to the target position.

[0075] The position weight refers to the impact of the target position on product performance. Higher sensitivity indicates a greater weight, and the sum of all target position weights is 1. The target thickness is the ideal thickness for the target position, serving as the basis for deviation calculations. The upper limit is the maximum allowable thickness; thickness exceeding this value is considered out of specification. The lower limit is the minimum allowable thickness; thickness below this value is considered out of specification.

[0076] S240 , performing weighted calculation on each thickness data according to the position weight to determine a weighted thickness mean.

[0077] Weighted calculation involves multiplying the thickness data at each location by its weight and then summing the results to obtain a composite thickness value. For example, for locations 1 (5mm), 2 (7mm), and 3 (10mm), the weighted average thickness value is ((thickness at location 1 × weight 1) + (thickness at location 2 × weight 2) + (thickness at location 3 × weight 3)).

[0078] S250: Calculate the difference between the weighted thickness mean value at the target position and the target thickness as a thickness error value.

[0079] Specifically, the thickness error reflects the overall deviation. It is the difference between the weighted mean thickness and the target thickness. It is used to measure whether the overall thickness of the thinned area deviates from the ideal state. Thickness error = weighted mean thickness - target thickness.

[0080] S260: Calculate the difference between the thickness data of the target position and the configured upper limit value as the upper limit difference.

[0081] Specifically, the limit difference reflects the risk of exceeding the upper limit. It is the difference between the measured thickness at a single target location and the configured upper limit, and is used to determine whether the thickness at that location is excessive. Upper limit difference = target location thickness - configured upper limit.

[0082] S270: Calculate the difference between the thickness data of the target position and the configured lower limit value as the lower limit difference.

[0083] Specifically, the lower limit difference reflects the risk of a low lower limit. It is the difference between the measured thickness at a single target location and the configured lower limit, and is used to determine whether the thickness at that location is too thin. Lower limit difference = target location thickness - configured lower limit.

[0084] S280: Determine an over-limit judgment result according to the deviation value, and when the over-limit judgment result is no over-limit, calculate the absolute value of the thickness error value.

[0085] S290 , determine whether the absolute value of the error is greater than a preset error threshold; if so, execute S300 ; otherwise, execute S310 .

[0086] S300 , calculating a ratio of the thickness error value to the transfer function as a thickness adjustment amount, and performing filtering and smoothing output based on the thickness adjustment amount.

[0087] S310. Maintain the current state.

[0088] Optionally, the over-limit judgment result is determined based on the deviation value, including: taking each designated position as the target position respectively; judging whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit; if so, when the upper limit difference of the same target position exceeds the upper limit and the lower limit difference exceeds the lower limit, or different target positions exceed the upper limit and the lower limit respectively, the over-limit judgment result of the target position is determined to be multiple over-limit; when the upper limit difference of the same target position exceeds the upper limit or the lower limit difference exceeds the lower limit, the over-limit judgment result of the target position is determined to be single-point over-limit; otherwise, the over-limit judgment result of the target position is determined to be no over-limit.

[0089] Optionally, the method further includes: when the over-limit judgment result is multiple over-limits, generating prompt information according to the over-limit judgment result, triggering an alarm and interrupting automatic control according to the prompt information to prompt user intervention.

[0090] Optionally, the method further includes: when the over-limit judgment result is a single-point over-limit, calculating a safety adjustment amount based on a quadratic programming algorithm, and applying a rate limit based on the safety adjustment amount.

[0091] The technical solution of this embodiment of the present invention, through real-time data acquisition and online transfer function identification, can rapidly adapt to changing operating conditions and ensure that the model is accurate to the actual situation. Deviation calculation accurately reflects overall and local thickness deviations. Thickness control based on over-limit determination results enables rapid response to anomalies and precise adjustment, shortening commissioning time, reducing labor costs, and improving production efficiency and resource utilization.

[0092] Example 3

[0093] Figure 3 This is a schematic diagram of the structure of a coating thinning area thickness control device provided in Example 3 of the present invention. Figure 3 As shown, the device includes: a transfer function determination module 310, which is used to collect real-time thinning data of the target coating thinning area, identify the transfer function online based on the real-time thinning data, and verify the validity of the residual test model, wherein the real-time thinning data includes thickness data of each specified position and the displacement of the flow block;

[0094] a deviation value calculation module 320, configured to calculate a deviation value based on the thickness data when verifying that the residual error test model is valid, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value;

[0095] The thinning area thickness control module 330 is used to determine the over-limit judgment result based on the deviation value. When the over-limit judgment result is no over-limit, the absolute value of the thickness error value is calculated; whether the absolute value of the error is greater than a preset error threshold is determined; if so, the ratio of the thickness error value and the transfer function is calculated as the thickness adjustment amount, and a filtering and smoothing output is performed based on the thickness adjustment amount; otherwise, the current state is maintained.

[0096] Optionally, the device also includes: an online identification transfer function module, which is used to: obtain historical thinning data, determine the thinning data change based on the historical thinning data and real-time thinning data, wherein the thinning data change includes the thickness change and the displacement change; identify the transfer function of the thickness change and the displacement change online through FFRLS with dynamic factors, and verify the validity of the transfer function through the residual.

[0097] Optionally, an online identification transfer function module specifically includes: a residual verification unit, used to: substitute the historical displacement change into the transfer function, calculate the first predicted thickness change, subtract the first predicted thickness change from the actual thickness change to obtain a residual value, calculate the standard deviation of the residual value, and use three times the standard deviation as the residual threshold; substitute the real-time collected displacement change of the flow control block into the transfer function, calculate the second predicted thickness change, subtract the second predicted thickness change from the actual thickness change to obtain a new residual value; determine whether the new residual value is greater than the residual threshold, and if so, determine that the transfer function verification is invalid; otherwise, determine that the transfer function verification is valid.

[0098] Optionally, the deviation value calculation module 320 is specifically used to: take each designated position as the target position respectively; determine whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit; if so, when the upper limit difference of the same target position exceeds the upper limit and the lower limit difference exceeds the lower limit, or different target positions exceed the upper limit and the lower limit respectively, determine that the over-limit judgment result of the target position is multiple over-limit; when the upper limit difference of the same target position exceeds the upper limit or the lower limit difference exceeds the lower limit, determine that the over-limit judgment result of the target position is single-point over-limit; otherwise, determine that the over-limit judgment result of the target position is no over-limit.

[0099] Optionally, the thinning zone thickness control module 330 specifically includes: an over-limit judgment result determination unit, used to: respectively take each designated position as the target position; judge whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit; if so, when the upper limit difference exceeds the upper limit and the lower limit difference exceeds the lower limit, determine that the over-limit judgment result of the target position is multiple over-limit; otherwise, determine that the over-limit judgment result of the target position is single-point over-limit; otherwise, determine that the over-limit judgment result of the target position is no over-limit.

[0100] Optionally, the device also includes: a multiple over-limit control unit, which is used to: when the over-limit judgment result is multiple over-limit, generate prompt information according to the over-limit judgment result, trigger an alarm and interrupt automatic control according to the prompt information to prompt user intervention.

[0101] Optionally, the device further includes: a single-point over-limit control unit, configured to: when the over-limit judgment result is a single-point over-limit, calculate a safety adjustment amount based on a quadratic programming algorithm, and impose a rate limit based on the safety adjustment amount.

[0102] The technical solution of this embodiment of the present invention, through real-time data acquisition and online transfer function identification, can rapidly adapt to changing operating conditions and ensure that the model is accurate to the actual situation. Deviation calculation accurately reflects overall and local thickness deviations. Thickness control based on over-limit determination results enables rapid response to anomalies and precise adjustment, shortening commissioning time, reducing labor costs, and improving production efficiency and resource utilization.

[0103] A coating thinning area thickness control device provided in an embodiment of the present invention can execute a coating thinning area thickness control method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects of the execution method.

[0104] Example 4

[0105] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0106] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0107] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0108] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a method for controlling the thickness of a coating skived area.

[0109] In some embodiments, a coating skim area thickness control method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the coating skim area thickness control method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to execute a coating skim area thickness control method in any other appropriate manner (e.g., by means of firmware).

[0110] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0115] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0116] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0117] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for controlling the thickness of a coating thinning area, characterized in that: include: Collecting real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data and baffle displacement at each designated position; Calculating a deviation value based on the thickness data, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value; Determine an over-limit judgment result according to the deviation value, and when the over-limit judgment result is no over-limit, calculate an absolute value of the thickness error value; Determine whether the absolute value of the error is greater than a preset error threshold; if so, calculate a ratio of the thickness error value to the transfer function as a thickness adjustment amount, and perform filtering and smoothing based on the thickness adjustment amount to output; Otherwise, keep the current state.

2. The method according to claim 1, characterized in that The method further comprises: Acquiring historical thinning data, and determining a thinning data variation according to the historical thinning data and the real-time thinning data, wherein the thinning data variation includes a thickness variation and a displacement variation; The transfer functions of thickness variation and displacement variation are identified online by FFRLS with dynamic factors, and the validity of the transfer functions is verified by the residuals.

3. The method according to claim 2, characterized in that Verifying the validity of the transfer function through residuals includes: Substituting the historical displacement change into the transfer function to calculate a first predicted thickness change, subtracting the first predicted thickness change from the actual thickness change to obtain a residual value, calculating the standard deviation of the residual value, and using three times the standard deviation as a residual threshold; Substituting the displacement change of the baffle block collected in real time into the transfer function to calculate a second predicted thickness change, and subtracting the second predicted thickness change from the actual thickness change to obtain a new residual value; determining whether the new residual value is greater than the residual threshold, and if so, determining that the transfer function verification is invalid; Otherwise, the transfer function verification is determined to be valid.

4. The method according to claim 1, wherein The calculating of the deviation value based on the thickness data includes: taking each of the designated positions as a target position respectively; Obtaining a position weight, a target thickness, a configuration upper limit value, and a configuration lower limit value corresponding to the target position; Performing weighted calculation on each thickness data according to the position weight to determine a weighted thickness mean; Calculating the difference between the weighted thickness mean value at the target position and the target thickness as a thickness error value; Calculating the difference between the thickness data of the target position and the configured upper limit value as the upper limit difference; The difference between the thickness data of the target position and the configured lower limit value is calculated as the lower limit difference.

5. The method according to claim 4, characterized in that Determining the over-limit judgment result according to the deviation value includes: taking each of the designated positions as a target position respectively; Determine whether the upper limit difference exceeds the upper limit or whether the lower limit difference exceeds the lower limit. If so, when the upper limit difference of the same target position exceeds the upper limit and the lower limit difference exceeds the lower limit, or different target positions exceed the upper limit and the lower limit respectively, determine that the over-limit judgment result of the target position is multiple over-limit; when the upper limit difference of the same target position exceeds the upper limit or the lower limit difference exceeds the lower limit, determine that the over-limit judgment result of the target position is single-point over-limit; Otherwise, the over-limit judgment result of the target position is determined to be no over-limit.

6. The method according to claim 5, characterized in that The method further comprises: When the over-limit judgment result is multiple over-limits, prompt information is generated according to the over-limit judgment result, an alarm is triggered according to the prompt information, and automatic control is interrupted to prompt the user to intervene.

7. The method according to claim 5, characterized in that The method further comprises: When the limit-exceeding judgment result is a single-point limit-exceeding, a safety adjustment amount is calculated based on a quadratic programming algorithm, and a rate limit is imposed based on the safety adjustment amount.

8. A coating thinning area thickness control device, characterized in that: include: A transfer function determination module is used to collect real-time thinning data of the target coating thinning area, wherein the real-time thinning data includes thickness data of each specified position and displacement of the flow block; a deviation value calculation module, configured to calculate a deviation value based on the thickness data, wherein the deviation value includes a thickness error value, an upper limit difference value, and a lower limit difference value; The thinning area thickness control module is used to determine the over-limit judgment result based on the deviation value. When the over-limit judgment result is no over-limit, the module calculates the absolute value of the thickness error value; determines whether the absolute value of the error is greater than a preset error threshold; if so, calculates the ratio of the thickness error value and the transfer function as the thickness adjustment amount, and performs filtering and smoothing output based on the thickness adjustment amount; otherwise, maintains the current state.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method according to any one of claims 1 to 7 when executed.

Images