Lithium battery coating device key parameter-based quality early warning method, apparatus, and device

Abstract

Provided are a lithium battery coating device key parameter-based quality early warning method, apparatus, and device. The method comprises: determining coating process control parameters (S1); acquiring key control parameter process data, and transmitting the process data to a high-performance storage unit (S2); on the basis of the process data, acquiring different control parameter configurations, and selecting an applicable early warning model from no less than two early warning models (S3); selecting corresponding early warning criteria for the applicable early warning model (S4); performing a preprocessing check on coating process control state data in the process data to obtain control parameter check data (S6); on the basis of the corresponding early warning criteria, using a Flink big data computation framework to perform window computation on the control parameter check data by using a Flink big data computation framework, so as to obtain real-time key parameter early warning information (S7); and analyzing and processing the real-time key parameter early warning information to obtain coating process control data, so as to control coating process key control parameters to be in an applicable range (S8). The early warning method and device solve the technical problems of insufficient immediacy of early warning information and the inability to customize quality abnormality criteria.

Description

Quality early warning method, device and equipment based on key parameters of lithium battery coating equipment Technical Field

[0001] The present invention relates to the field of lithium battery production, and in particular to a quality early warning method, device and equipment based on key parameters of lithium battery coating equipment. Background Art

[0002] Coating is a front-end process in the lithium battery production process. Improper coating quality control can lead to waste of raw materials due to rework and the flow of substandard coated rolls downstream, significantly impacting batch quality. Therefore, coating quality significantly impacts cell quality. For example, excessive areal density can lead to overweight cells, while uneven coating can lead to abnormal capacity. Therefore, early warning and control of coating quality during lithium battery production are crucial.

[0003] The lithium battery coating process involves many key parameters, such as ambient temperature, ambient humidity, air cleanliness, magnetic flux, oven temperature, single-sided surface density, double-sided surface density, coating width, edge margin width, symmetrical misalignment, peel strength, electrode moisture, etc. Any control parameter exceeding the specification limit will lead to the production of unqualified products. During the flow production process, early warning of abnormal processing parameters will be issued, which will facilitate on-site personnel to detect problems in time and reduce the production of unqualified products.

[0004] The existing invention patent application document, "A Method for Predicting the Thickness of Soft-Pack Lithium-Ion Batteries," with publication number CN115701851A, includes the following steps: creating a particle filter and establishing a thickness model for the soft-pack lithium-ion battery; setting the number of charge and discharge cycles of the soft-pack lithium-ion battery as the starting point for prediction, calculating the model parameters of the thickness model, and thereby confirming the relationship between the number of charge and discharge cycles of the soft-pack lithium-ion battery and the fully charged thickness of the soft-pack lithium-ion battery; predicting the fully charged thickness of the soft-pack lithium-ion battery using the thickness model, recording the number of charge and discharge cycles of the soft-pack lithium-ion battery and using it as the service life of the soft-pack lithium-ion battery. The aforementioned existing quality control methods employ offline analysis and training, and are unable to perform real-time analysis of streaming data during the production process. Process quality control charts are drawn offline, and early warning information is not timely, which can easily lead to unqualified products flowing into downstream processes, amplifying product quality issues. And the existing invention patent application document with publication number CN115876589A "A simple evaluation method for the flexibility of lithium battery pole pieces", the method includes the following steps: (1) dispersing the positive electrode active material, conductive agent, binder and solvent into a uniform and stable positive electrode slurry; (2) coating the positive electrode slurry on the surface of the foil according to a double-sided surface density of 340 to 400 g / m2; (3) using a small roller press to roll to obtain a finished electrode membrane of a certain thickness; (4) according to the conventional A5 paper size specification, cut out the electrode membranes A1, A2, A3, A4 with flat interfaces and place them flatly on a smooth glass plate, use a feeler gauge to measure the gap thickness ΔH1, AH2, ΔH3, AH4 of the electrode membranes A1, A2, A3, A4, and record 15 data in the rolling direction, and use Minitab software to draw a box plot. The aforementioned existing technologies cannot customize quality error detection rules. Quality management tools like Minitab cannot integrate existing quality error detection rules to customize dynamic verification rules for quality early warning control. Therefore, a simple, fast, and effective quality early warning method is needed to monitor production process parameters in real time and improve coating quality.

[0005] In summary, the existing technology has technical problems such as poor real-time warning information and the inability to customize quality abnormality criteria.

[0006] Summary of the Invention

[0007] The technical problem to be solved by the present invention is: how to solve the technical problems in the prior art of poor real-time warning information and the inability to customize quality abnormality criteria.

[0008] The present invention adopts the following technical solutions to solve the above technical problems:

[0009] In the first aspect, the key parameter quality warning method based on lithium battery coating equipment provided by an embodiment of the present invention includes: confirming the control parameters of the coating process; collecting process data of the key control parameters, and transmitting the process data to a high-performance storage unit; obtaining different control parameter configurations according to the process data, and selecting an applicable warning model from no less than 2 SPC process quality warning models; selecting corresponding warning criteria for the applicable warning model; pre-processing and verifying the coating process control status data in the process data to obtain control parameter verification data; using the Flink big data computing framework, window calculation is performed on the control parameter verification data according to the corresponding warning criteria to obtain real-time warning information of key parameters; analyzing and processing the real-time warning information of key parameters to obtain coating process control data, thereby controlling the key control parameters of the coating process to be within the applicable range.

[0010] In the second aspect, the key parameter quality warning system based on lithium battery coating equipment provided by the embodiment of the present invention includes: a parameter determination module for confirming the control parameters of the coating process; a process data acquisition and storage module for acquiring process data of key control parameters and transmitting the process data to a high-performance storage unit, the process data acquisition and storage module is connected to the parameter determination module; a model selection module for obtaining different control parameter configurations according to the process data, and selecting an applicable warning model from no less than 2 SPC process quality warning models, the model selection module is connected to the process data acquisition and storage module; a warning rule selection module for selecting corresponding warning criteria for the applicable warning model, the warning rule selection module is connected to the model selection module; control The status data verification module is used to pre-process and verify the coating process control status data in the process data to obtain control parameter verification data. The control status data verification module is connected to the process data acquisition and storage module; the real-time warning information acquisition module is used to use the Flink big data computing framework to perform window calculation on the control parameter verification data according to the corresponding warning criteria to obtain real-time warning information of key parameters. The real-time warning information acquisition module is connected to the control status data verification module and the warning rule selection module; the process control module is used to analyze and process the real-time warning information of key parameters to obtain coating process control data, thereby controlling the key control parameters of the coating process to be within the applicable range. The process control module is connected to the real-time warning information acquisition module.

[0011] In a third aspect, the quality early warning device based on the key parameters of the lithium battery coating equipment provided by the embodiment of the present invention includes a memory, a processor, a communication interface and a bus. Among them, the memory may include a large-capacity memory for data or instructions. For example, but not limitation, the memory may include an HDD, a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory may be inside or outside the device for determining the battery operating voltage curve. In a specific embodiment, the memory is a non-volatile solid-state memory. In a specific embodiment, the memory includes a read-only memory (ROM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0012] Compared to existing technologies, this invention offers the following advantages: It collects and preprocesses the massive amounts of data from the production process, fully utilizing cluster resources and employing a big data computing framework for real-time computational warnings. It also employs a simple and effective quality control method to provide quality warnings for the coating process, improving coating quality. This invention leverages SPC process quality control theory and user-defined abnormality detection rules to provide quality warnings for key control parameters in the coating process, facilitating early detection and warning of coating process anomalies.

[0013] The present invention uses the Flink big data computing framework to provide real-time early warning for the coating production process. The early warning model and early warning rules are configurable, and the calculation is triggered according to the time window. The coverage is wide, and the early warning information is real-time and accurate.

[0014] The method of the present invention makes full use of SPC process quality control theory and big data real-time calculation framework, and combines the coating process in the lithium battery production process to perform quality early warning control. The method of the present invention has the advantages of being simple, effective and highly operable, which is conducive to improving the quality of the coating process and is easy to promote and apply.

[0015] The present invention adopts the mean range chart in the SPC quantitative control chart The control objects include: length, weight, strength, thickness, time and other measurement values. The mean range chart has a wide range of applications and high sensitivity.

[0016] In specific cases where the measurement cost is very high and the output properties at any time point are relatively consistent, the present invention applies the single value moving range control chart (X-MR) in the SPC control chart to perform process monitoring, thereby ensuring the accuracy of measurement operations in specific scenarios.

[0017] The present invention solves the technical problems in the prior art of poor real-time warning information and inability to customize quality abnormality criteria. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] FIG1 is a schematic diagram of the basic steps of a quality early warning method based on key parameters of lithium battery coating equipment in one embodiment of the present invention;

[0019] FIG2 is a schematic diagram of a big data computing framework according to an embodiment of the present invention;

[0020] FIG3 is a schematic diagram of specific steps for calculating the distribution of quality data and estimating the defective product rate of a process using a histogram in one embodiment of the present invention;

[0021] FIG4 is a schematic diagram of specific implementation steps of a quality early warning control method according to another embodiment of the present invention;

[0022] FIG5 is a schematic structural diagram of a key parameter quality warning device based on lithium battery coating equipment in one embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] Example 1

[0025] FIG1 is a schematic diagram of the basic steps of a quality early warning method for key parameters of lithium battery coating equipment according to an embodiment of the present invention. As shown in FIG1 , the quality early warning method for key parameters of lithium battery coating equipment provided by the present invention includes the following basic steps:

[0026] S1. Confirm the key control parameters of the coating process through expert scoring method, brainstorming method, FMEA, historical problem statistical analysis method, etc.

[0027] In this example, key quality control parameters of the coating process were used.

[0028] In this embodiment, the expert scoring method includes: inviting the company and coating process experts in the lithium battery industry to perform graded screening of parameters controlling coating quality, and using expert knowledge to identify key control parameters;

[0029] In this embodiment, the historical problem statistical analysis operation includes: refining key quality control points as key control parameters based on the knowledge base formed by the company and the industry regarding coating defect analysis.

[0030] S2. Through manual detection and automatic reporting by the equipment, the IoT platform collects key control parameter process data into a high-performance storage unit. In this embodiment, the high-performance storage unit can be, for example, a time series database.

[0031] S3. Select appropriate early warning model according to different control parameters;

[0032] S4. Select appropriate warning rules for the warning model configured with control parameters;

[0033] S5. Connect the data acquisition system with the equipment for key control parameters to ensure timely data reporting;

[0034] S6. Preprocess and verify the data collected in real time;

[0035] S7. Use the Flink big data computing framework to perform window computing and provide real-time warnings for key parameters.

[0036] FIG2 is a schematic diagram of a big data computing framework principle in an embodiment of the present invention. As shown in FIG2 , in this embodiment, the big data computing framework principle includes:

[0037] The Flink real-time computing engine is used to monitor production and processing parameters, and real-time warnings are issued in combination with the warning rules for each control parameter to ensure the accuracy of warning implementation.

[0038] Use CDC and other technologies to monitor MySQL control chart information and warning rule information in real time and form a broadcast stream;

[0039] The main stream reads the Kafka data source and joins it with the broadcast stream;

[0040] The rolling window is calculated according to the customized warning rule time;

[0041] Calculate by grouping the process, step, and control parameter information of each tenant in the flow;

[0042] Data that does not meet the configured warning rules will be warned via email or other means;

[0043] Write to different tenant information tables at the same time.

[0044] S8. On-site production personnel analyze and process the early warning information to ensure that the key control parameters of a single process are processed normally.

[0045] In this embodiment, the key control parameters of the coating process belonging to the front-end process include but are not limited to: ambient temperature, ambient humidity, air cleanliness, magnetic flux, oven temperature, single-sided surface density, double-sided surface density, coating width, edge margin width, symmetrical dislocation, peel strength and electrode moisture. Quality warning based on the key parameters of the lithium battery coating process requires real-time monitoring of the above-mentioned key control parameters and configuration of corresponding warning rules to achieve the purpose of real-time warning of coating quality.

[0046] In this embodiment, the early warning models available for selection include but are not limited to the following SPC process quality control charts: mean-range control chart, mean-standard deviation control chart, single value-moving range control chart, pass rate chart, histogram and shift chart.

[0047] In this embodiment, in the mean-range control model, the mean-range chart in the SPC variable control chart is used. In this embodiment, the measurement values ​​used as control objects of the mean range chart include but are not limited to: measurement values ​​such as length, weight, strength, thickness, and time.

[0048] In this embodiment, The control chart includes the following indicators: Control chart, subgroup sample mean, between-group mean, sample range, range mean, Upper control limit, Center line of the figure, chart lower control limit, R chart upper control limit, R chart center line, and R chart lower control limit.

[0049] In this embodiment, Control chart: n is the sample size within the group, and m is the number of sampling groups.

[0050] In this example, the subgroup sample means are calculated:

[0051] In this example, the between-group means are calculated:

[0052] In this embodiment, the sample range is calculated: R i =max{X i}-min{X i};

[0053] In this example, the mean of the range is calculated:

[0054] In this embodiment, Chart upper control limit:

[0055] In this embodiment, Figure center line:

[0056] In this embodiment, Chart lower control limit:

[0057] In this example, the R chart upper control limit is:

[0058] In this embodiment, the center line of the R diagram:

[0059] In this example, the R chart lower control limit is:

[0060] Among them, D4, D3, and A2 are constants that change with the sample size, and the specific values ​​can be obtained by looking up the table.

[0061] In this embodiment, the mean-standard deviation control chart Includes: mean (X) graph and standard deviation (S) graph. The X chart is mainly used to judge whether the mean of the production process is stable; the S chart is used to judge the stability of the standard deviation of the production process. In this embodiment, when the sample size in the group is greater than 5, picture.

[0062] In this embodiment, the mean-standard deviation control chart The indicators include: Control chart, subgroup sample mean, between-group mean, subgroup standard deviation, mean standard deviation, estimated standard deviation, Upper limit of control chart, Control chart center line, Lower control limit, upper limit of S chart, center line of S chart, and lower limit of S chart.

[0063] In this embodiment, Control chart: n is the sample size within the group, and m is the number of sampling groups.

[0064] In this example, the subgroup sample means are calculated:

[0065] In this example, the between-group means are calculated:

[0066] In this example, the subgroup standard deviation is:

[0067] In this example, the standard deviation is:

[0068] In this example, the standard deviation is estimated: The control chart coefficients can be obtained by looking up the table;

[0069] In this embodiment, Upper limit of control chart: The control chart coefficients can be obtained by looking up the table;

[0070] In this embodiment, Control chart center line:

[0071] In this embodiment, Lower control chart limit:

[0072] In this example, the upper limit of the S control chart is: The control chart coefficients can be obtained by looking up the table;

[0073] In this example, the S control chart center line:

[0074] In this example, the lower limit of the S control chart is: The control chart coefficients can be obtained by looking up the table;

[0075] Among them, B4, B3, and A3 are constants that change with the sample size, and the specific values ​​can be obtained by looking up the table.

[0076] In this embodiment, in scenarios where process control requires the use of application units rather than subgroups, the variation within the subgroup is effectively zero. This typically occurs when measurement costs are high (e.g., destructive experiments) or when the output properties are relatively consistent at any point in time (e.g., the pH value of a chemical solution). In these cases, the X-MR chart, an SPC control chart, can be used for process monitoring.

[0077] In this embodiment, the process mean of the single value moving range control chart (X-MR) includes: mean, upper control limit, center line, lower control limit, moving range, moving range mean, upper control limit, center line and lower control limit.

[0078] In this embodiment, the mean in the single value plot is the sum of the single value readings divided by the number of readings, which is conventionally expressed as . Note that for a moving range of sample size 2, the number of moving ranges (MR) is 1 less than the number of single value readings.

[0079] In this example, the mean is calculated:

[0080] In this example, the upper control limit is calculated: The control chart coefficients can be obtained by looking up the table;

[0081] In this example, the centerline:

[0082] In this example, the lower control limit is calculated:

[0083] In this embodiment, the moving range is calculated: MR i =|x i -x i-1 |;

[0084] In this example, the moving mean range is calculated:

[0085] In this example, the upper control limit is calculated: The control chart coefficients can be obtained by looking up the table;

[0086] In this example, the centerline:

[0087] In this example, the lower control limit is calculated: The control chart coefficients can be obtained by looking up the table;

[0088] Among them, D4, D3, and E2 are constants used to group the calculated moving range and change with the sample size.

[0089] In this embodiment, specific parameters can be obtained by looking up the table. For example, when the subgroup capacity n=2, E2=2.660, D3=0.000, and D4=3.267.

[0090] FIG3 is a schematic diagram of specific steps for calculating the distribution of quality data and estimating the defective product rate of a process using a histogram in one embodiment of the present invention. As shown in FIG3 , in this embodiment, a histogram is used to process and organize data, analyze and grasp the distribution of quality data, and estimate the defective product rate of a process. The specific calculation steps include:

[0091] S31, data collection, samples greater than 50;

[0092] S32. Find the maximum and minimum values ​​and calculate the range;

[0093] S33. Determine the number of groups and group distance: K = 1 + 3.322*lqg(N);

[0094] S34. Determine the group boundaries: the lower boundary value of the first group = minimum value - measurement unit / 2;

[0095] S35. Count the frequencies and draw histograms.

[0096] In this embodiment, a transition chart is used to observe whether a variable shows a certain trend over time. This chart, with time as the horizontal axis and the variable as the vertical axis, allows managers to monitor the dynamic trends of management effectiveness or key product performance parameters, allowing them to conduct analysis and improvements.

[0097] In this embodiment, the judgment rules used can be customized by the user. Common process quality judgment criteria are listed as follows:

[0098] (1) Criterion 1: Point 1 is above (or below) the control line

[0099] (2) Criterion 2: 9 or more consecutive points on the same side of the center line

[0100] (3) Criterion 3: There is an upward or downward trend for 6 or more consecutive points

[0101] (4) Principle 4: 14 consecutive adjacent points alternate above and below the center line

[0102] (5) Criterion 5: Points are often close to the control limit.

[0103] 5a. At least two of the three consecutive points are close to the control limit (outside zone B);

[0104] 5b. At least three of the seven consecutive points are close to the control limit (outside zone B);

[0105] 5c. Among 10 consecutive points, at least 4 points are close to the control limit (outside area B).

[0106] (6) Rule 6: 4 out of 5 consecutive points fall outside Zone C on the same side of the center line

[0107] (7) Rule 7: Fluctuation within Zone C for 15 consecutive points

[0108] (8) Rule 8: 8 consecutive points on both sides of the center line, but none of them are in area C

[0109] (9) Principle 9: Interrupted chain, non-random arrangement

[0110] 9a. Among the 11 consecutive points, at least 10 points are on one side of the center line;

[0111] 9b. Of the 14 consecutive points, at least 12 are on one side of the center line;

[0112] 9c. Of the 17 consecutive points, at least 14 are on one side of the center line;

[0113] 9d. Among 20 consecutive points, at least 16 points are on one side of the center line.

[0114] Example 2

[0115] In addition to the process quality deviation criteria described in Example 1 above, deviations must also be determined based on the upper and lower limits of the process control plan, i.e., key parameters, during lithium battery production. For example, the deviation must not exceed 80% of the process control plan. These rules are customizable and configurable in specific early warning models.

[0116] FIG4 is a schematic diagram of the specific implementation steps of the quality early warning control method in another embodiment of the present invention. As shown in FIG4 , in this embodiment, after the early warning information is generated, process and quality-related engineers will intervene to analyze and process the information to ensure the entire quality early warning control loop is closed. The implementation steps of the entire quality early warning control method include:

[0117] S1', in the early warning system, select control parameters to configure the early warning model;

[0118] S2', data collection of key control parameters of coating;

[0119] S3', data preprocessing to ensure data quality;

[0120] S4', big data real-time warning;

[0121] S5', the process engineer receives an alarm;

[0122] S6', process engineer handles the alarm;

[0123] S7', quality engineers conduct improvement audits;

[0124] S8', if the review is passed, the task ends and it is displayed as processed; if not, jump to step S6'.

[0125] Figure 5 is a structural diagram of a key parameter quality warning device based on lithium battery coating equipment in an embodiment of the present invention. As shown in Figure 5, the device 300 for determining the battery operating voltage curve includes a memory 301, a processor 302, a communication interface 303 and a bus 304.

[0126] Memory 301 may include a large-capacity memory for data or instructions. By way of example, and not limitation, memory 301 may include an HDD, a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 301 may include removable or non-removable (or fixed) media. Where appropriate, memory 301 may be internal or external to device 300 for determining the battery operating voltage curve. In certain embodiments, memory 301 is a non-volatile solid-state memory. In certain embodiments, memory 301 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0127] In one example, the processor 302 may include a central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0128] Alternatively, it may be configured as one or more integrated circuits implementing the embodiments of the present invention.

[0129] The communication interface 303 is mainly used to implement communication between modules and units in the embodiment of the present invention.

[0130] The memory 301 , the processor 302 and the communication interface 303 are connected via the bus 304 and communicate with each other.

[0131] That is, the memory 301 is used to store program code. The processor 302 runs the program corresponding to the executable program code by reading the executable program code stored in the memory 301, so as to execute the quality early warning method based on the key parameters of the lithium battery coating equipment. The quality early warning method based on the key parameters of the lithium battery coating equipment includes but is not limited to steps S1 to S8 in the above embodiment.

[0132] It should be understood that the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For the device embodiments, the relevant parts can be referred to the method embodiment description part. The present invention is not limited to the specific steps and structures described above and shown in the figures. Those skilled in the art can make various changes, modifications and additions, or change the order of the steps after understanding the spirit of the present invention. In addition, for the sake of brevity, a detailed description of known method technologies is omitted here.

[0133] The functional modules and functional units shown in the above-described structured block diagram can be implemented as hardware, software, firmware or their combination. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), suitable firmware, a plug-in unit, a function card or the like. When implemented in software, elements of the present invention are programs or code segments that are used to perform the required tasks. Programs or code segments can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by the data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information.

Claims

1. A quality early warning method based on key parameters of lithium battery coating equipment, characterized in that: The method comprises: S1. Confirm coating process control parameters; S2, collecting process data of the key control parameters, and transmitting the process data to a high-performance storage unit; S3. According to the process data, different control parameter configurations are obtained, and an applicable warning model is selected from at least two SPC process quality warning models; S4. Select corresponding warning criteria for the applicable warning model; S5, pre-processing and verifying the coating process control state data in the process data to obtain control parameter verification data; S6. Using the Flink big data computing framework, perform window calculation on the control parameter verification data according to the corresponding warning criterion to obtain real-time warning information of key parameters; S7. Analyze and process the real-time warning information of the key parameters to obtain coating process control data, thereby controlling the key control parameters of the coating process to be within an applicable range.

2. The method for early warning of key parameters of lithium battery coating equipment according to claim 1 is characterized in that: In the step S1, the method for confirming the key control parameters of the coating process includes: expert scoring method, FMEA and historical problem statistical analysis method.

3. The method for early warning of key parameters of lithium battery coating equipment according to claim 1 is characterized in that: The process data collection method in step S2 includes: automatic reporting by equipment and IOT platform.

4. The method for early warning of key parameters quality of lithium battery coating equipment according to claim 1 is characterized in that: In step S3, the SPC process quality early warning model includes: mean-range control chart, mean-standard deviation control chart, single value-moving range control chart, pass rate chart, histogram and shift chart.

5. The quality early warning method based on key parameters of lithium battery coating equipment according to claim 4 is characterized in that: In the mean-range control chart, the following logic is used to calculate the subgroup sample mean Mean between groups Sample range R i and the mean range R i =max{X i }-min{X i }; The mean is calculated using the following logic The upper control limit UCL, center line CL and lower control limit LCL of the chart: The following logic is used to calculate the upper control limit UCL, center line CL, and lower control limit LCL of the range R chart: In the formula, D4, D3, and A2 are constants that change with the sample size, n is the sample size within the group, and m is the number of sampling groups.

6. The method for early warning of key parameters of lithium battery coating equipment according to claim 4 is characterized in that: In the mean-standard deviation control chart, the following logic is used to calculate the subgroup sample mean: Mean between groups Subgroup standard deviation S i , standard deviation mean Standard deviation σ: Using the following logic, calculate the mean The upper limit UCL, center line CL, and lower limit LCL of the control chart: The upper limit UCLs, center line CLs, and lower limit LCLs of the standard deviation S control chart are calculated using the following logic: In the formula, B4, B3, and A3 are constants that change with the sample size.

7. The method for early warning of key parameters of lithium battery coating equipment according to claim 4 is characterized in that: In the single value-moving range control chart, the following logic is used to calculate the mean range: Upper control limit UCL X , center line CL, lower control limit LCL X , Moving Range MR i , moving range mean Moving range upper control limit UCL MR , moving range center line CL, moving range lower control limit: MR i =|x i -x i-1 |; In the formula, D4, D3, and E2 are used to group the calculated moving range.

8. The method for early warning of key parameters quality of lithium battery coating equipment according to claim 1, characterized in that: The step S3 comprises: S31, collecting a preset number of coating process control data samples; S32, obtaining the sample maximum value, sample minimum value and sample range of the coating process control data sample; S33, determining the number of groups and group distances of the coating process control data samples; S34, determining the group boundary of the coating process control data sample; S35. Draw a histogram according to the preset statistical frequency, based on the sample maximum value, the sample minimum value, the sample range, the number of groups, the group interval and the group boundary.

9. The method for early warning of key parameters of lithium battery coating equipment according to claim 8, characterized in that: In step S33, the number of groups and the group distance are determined using the following logic: K = 1 + 3.322*lqg (N) In the formula, N represents the number of samples and K is the number of groups.

10. Based on the key parameter quality warning device of lithium battery coating equipment, it is characterized by: The device comprises: A parameter determination module is used to confirm the coating process control parameters; A process data acquisition and storage module, used for acquiring process data of the key control parameters and transmitting the process data to a high-performance storage unit, wherein the process data acquisition and storage module is connected to the parameter determination module; A model selection module, used for obtaining different control parameter configurations according to the process data, and selecting an applicable warning model from at least two SPC process quality warning models, wherein the model selection module is connected to the process data acquisition and storage module; An early warning rule selection module, used for selecting a corresponding early warning criterion for the applicable early warning model, wherein the early warning rule selection module is connected to the model selection module; A control status data verification module, used for pre-processing and verifying the coating process control status data in the process data to obtain control parameter verification data, the control status data verification module is connected to the process data acquisition and storage module; The real-time warning information acquisition module is used to use the Flink big data computing framework to perform window calculations on the control parameter verification data according to the corresponding warning criteria to obtain real-time warning information of key parameters. The information acquisition module is connected with the control state data verification module and the warning rule selection module; The process control module is used to analyze and process the real-time warning information of the key parameters to obtain coating process control data, thereby controlling the key control parameters of the coating process to be within an applicable range. The process control module is connected to the real-time warning information obtaining module.

11. The key parameter quality warning device based on lithium battery coating equipment according to claim 10 is characterized in that: In the parameter determination module, methods for confirming key control parameters of the coating process include: expert scoring method, FMEA and historical problem statistical analysis method.

12. The key parameter quality warning device based on lithium battery coating equipment according to claim 10 is characterized in that: The process data collection method in the process data collection and storage module includes: automatic reporting of equipment and IOT platform.

13. The key parameter quality warning device based on lithium battery coating equipment according to claim 10 is characterized in that: In the model selection module, the SPC process quality warning model includes: mean-range control chart, mean-standard deviation control chart, single value-moving range control chart, qualified rate chart, histogram and shift chart.

14. The key parameter quality warning device based on lithium battery coating equipment according to claim 13, characterized in that: The model selection module includes: The mean processing unit of the mean-range control chart is used to calculate the subgroup sample mean in the mean-range control chart using the following logic Mean between groups Sample range R i and the mean range R i =max{X i }-min{X i }; Control upper and lower limits and center line processing unit to calculate the mean using the following logic The upper control limit UCL, center line CL and lower control limit LCL of the chart: The upper and lower limits and center line processing unit of the range R chart is used to calculate the upper control limit UCL, center line CL and lower control limit LCL of the range R chart using the following logic: In the formula, D4, D3, and A2 are constants that change with the sample size, n is the sample size within the group, and m is the number of sampling groups.

15. The key parameter quality warning device based on lithium battery coating equipment according to claim 13, characterized in that: The model selection module also includes: The mean processing unit of the mean-standard deviation control chart is used to calculate the subgroup sample mean in the mean-standard deviation control chart using the following logic: Mean between groups Subgroup standard deviation S i , standard deviation mean Standard deviation σ: The upper and lower limits and center line processing unit of the mean control chart is used to calculate the mean using the following logic The upper limit UCL, center line CL, and lower limit LCL of the control chart: The upper and lower limits and center line processing unit of the standard deviation S control chart is used to calculate the upper limit UCLs, center line CLs and lower limit LCLs of the standard deviation S control chart using the following logic: In the formula, B4, B3, and A3 are constants that change with the sample size.

16. The key parameter quality warning device based on lithium battery coating equipment according to claim 13, characterized in that: The model selection module also includes: A single value-moving range control chart processing unit is used to calculate the range mean in the single value-moving range control chart using the following logic: Upper control limit UCL X , center line CL, lower control limit LCL X , Moving Range MR i , moving range mean Moving range upper control limit UCL MR , moving range center line CL, moving range lower control limit: MR i =|x i -x i-1 |; In the formula, D4, D3, and E2 are used to group the calculated moving range.

17. The key parameter quality warning device based on lithium battery coating equipment according to claim 10, characterized in that: The model selection module also includes: A sample collection unit, used to collect a preset number of coating process control data samples; An extreme value and extreme difference processing unit, used for obtaining a sample maximum value, a sample minimum value and a sample extreme difference of the coating process control data sample; A sample group spacing determination unit, used to determine the number of groups and the group spacing of the coating process control data samples; A group boundary driving unit, which determines a group boundary of the coating process control data sample; The histogram generating unit is used to draw a histogram according to the preset statistical frequency, the sample maximum value, the sample minimum value, the sample range, the number of groups, the group interval and the group boundary.

18. The key parameter quality warning device based on lithium battery coating equipment according to claim 17 is characterized in that: In the sample group spacing determination unit, the number of groups and the group spacing are determined using the following logic: K = 1 + 3.322*lqg (N) In the formula, N represents the number of samples and K is the number of groups.

19. Quality warning equipment based on key parameters of lithium battery coating equipment, characterized in that: include: Memory, processor, communication interface and bus; The memory, the processor and the communication interface are connected via the bus and communicate with each other; The memory is used to store program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute a quality early warning method based on key parameters of lithium battery coating equipment, wherein the quality early warning method based on key parameters of lithium battery coating equipment includes: Confirm coating process control parameters; Collecting process data of the key control parameters, and transmitting the process data to a high-performance storage unit; According to the process data, different control parameter configurations are obtained, and an applicable early warning model is selected from at least two SPC process quality early warning models; According to the applicable early warning model, select corresponding early warning criteria; Preprocess and verify the coating process control status data in the process data to obtain control parameter verification data; Using the Flink big data computing framework, window calculation is performed on the control parameter verification data according to the corresponding warning criteria to obtain real-time warning information of key parameters; The real-time warning information of the key parameters is analyzed and processed to obtain coating process control data, thereby controlling the key control parameters of the coating process to be within an applicable range.

Images