Intelligent mistake-proofing system for intelligent manufacturing production process based on real-time data interaction and method thereof

Abstract

The application provides an intelligent manufacturing production process intelligent mistake-proofing system and method based on real-time data interaction, relates to the technical field of intelligent manufacturing control, and realizes real-time monitoring on a new energy automobile power battery cell winding production process, collects winding equipment operation state basic data, and pre-processes the data; winding coordination deviation indexes, equipment operation coupling stability indexes and winding quality risk prediction indexes are respectively constructed, comparison with corresponding threshold values is carried out, layered evaluation on winding coordination operation states, equipment load stability states and production quality risks is realized, and equipment coordination adjustment, stable operation adjustment and quality mistake-proofing control strategies are triggered when indexes are abnormal; meanwhile, operation data and adjustment results are written into a quality database, and a feedback optimization mechanism is formed. The application can realize real-time monitoring, risk prediction and intelligent mistake-proofing control on the winding production process, and improve winding production stability and product consistency.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing control technology, specifically to an intelligent error prevention system and method for intelligent manufacturing production processes based on real-time data interaction. Background Technology

[0002] With the rapid development of the new energy vehicle industry, the manufacturing quality of power batteries, as a core component of new energy vehicles, directly affects the safety, reliability, and service life of the entire vehicle. In the manufacturing process of power battery cells, the electrode winding process is a crucial step in forming the internal structure of the cell. This typically involves continuously winding the positive electrode, separator, and negative electrode under controlled tension and speed conditions to create a structurally stable cell core. During this process, factors such as electrode tension, winding spindle speed, electrode unwinding speed, and electrode guide position stability are interdependent, collectively affecting the alignment accuracy between winding layers and the consistency of the cell structure. When tension control is unbalanced, speed matching is inconsistent, or electrode position shifts, problems such as electrode edge misalignment and interlayer shifts can easily occur, thus affecting the consistency of the cell stack and the stability of product quality.

[0003] Existing power battery winding production lines typically monitor single equipment parameters or rely on equipment alarm mechanisms to determine production status, such as independently detecting tension, speed, or motor load. However, these monitoring methods focus primarily on changes in a single parameter and cannot comprehensively reflect the synergistic relationship between tension, speed, and electrode position during the winding process. Furthermore, in actual production, there is still a significant reliance on operator experience for anomaly detection and parameter adjustments, lacking the ability to comprehensively analyze multi-source operational data and promptly identify potential quality risks during the winding process. This can easily lead to fluctuations in winding quality or even batch production defects. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent error prevention system and method for intelligent manufacturing production processes based on real-time data interaction, so as to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: The intelligent error prevention method for intelligent manufacturing processes based on real-time data interaction includes the following steps: Step 1: Real-time monitoring of the production process of new energy vehicle power battery cells, collecting raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time electrode position offset, and motor load current, and performing unified time synchronization marking to establish a basic dataset of winding equipment operating status. Step 2: Perform time synchronization and alignment processing, abnormal sampling point removal processing, time-series filtering and smoothing processing, and dimensionless normalization processing on the basic dataset of the winding equipment's operating status. Step 3: Calculate the winding cooperative offset index and compare it with the cooperative offset threshold to determine whether the cooperative operation status of the winding process is qualified. If it is not qualified, a cooperative adjustment strategy for the winding equipment is given. Step 4: Calculate the equipment operation coupling stability index and compare it with the stable operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, provide a stable operation adjustment strategy for the equipment. Step 5: Calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If not, implement quality error prevention control strategies, record and analyze the data to form a closed-loop control mechanism for quality feedback optimization in the winding production process.

[0006] Further, step one includes: S11. Real-time monitoring of the operation status of the electrode unwinding process during the production of power battery cells for new energy vehicles. By installing a strain gauge tension sensor at the guide roller bearing seat of the electrode unwinding mechanism, the tensile tension generated by the electrode during the unwinding process is continuously collected to obtain the original data of the electrode tension. S12. Real-time monitoring of the operation status of the diaphragm unwinding process during the production of power battery cells for new energy vehicles. By installing a cantilever beam tension sensor at the tension control roller position of the diaphragm unwinding mechanism, the force change of the diaphragm material during the unwinding and conveying process is detected in real time, and the raw data of the diaphragm tension is collected. S13. Real-time monitoring of the driving status of the winding spindle during the production of power battery cells for new energy vehicles. By installing an incremental rotary encoder at the output end of the servo motor of the winding spindle, the real-time speed change of the winding spindle is continuously sampled to obtain the original data of the winding spindle speed. S14. Real-time monitoring of the electrode unwinding and conveying speed during the production of power battery cells for new energy vehicles. By installing a photoelectric rotary encoder at the output shaft of the electrode unwinding drive motor, the conveying speed of the electrode unwinding drive mechanism is collected in real time to obtain the raw data of the electrode unwinding speed. S15. Real-time monitoring of the electrode winding position during the production of power battery cells for new energy vehicles. By installing an industrial line array camera in the electrode guide area of ​​the winding station, continuous image acquisition is performed on the electrode edge position. Gray-scale threshold segmentation, Canny edge detection, and sub-pixel edge positioning algorithms are used to extract the electrode edge contour. The pixel offset between the electrode edge contour and the preset reference boundary is calculated and geometric scale conversion is performed to obtain the original data of the electrode real-time position offset. At the same time, by installing a Hall current sensor at the power input end of the winding spindle driver, the operating load current of the winding spindle drive motor is detected in real time to obtain the original data of the motor load current. S16. The collected raw data of electrode tension, diaphragm tension, winding spindle speed, electrode unwinding speed, real-time position offset of electrode, and motor load current are uniformly time-stamped. By installing an industrial time synchronization clock device in the control cabinet of the winding equipment and connecting it to the production equipment control network, the data collected by each sensor are time-stamped according to the unified clock, a unified timestamp is added to each sampled data, and a basic dataset of the winding equipment operating status is established.

[0007] Furthermore, step two includes: S21. Based on the basic dataset of the winding equipment's operating status, various types of raw operating data are time-synchronized and aligned according to a unified timestamp t, abnormal sampling points are removed, time-series filtering and smoothing are performed, and dimensionless normalization is applied. The collected electrode tension raw data are processed according to the time series. The sliding window weighted moving average algorithm is used to perform time-series smoothing on the continuously sampled tension data to eliminate the influence of instantaneous vibration and sampling noise on the tension data, resulting in a smoothed electrode tension sequence. Then, the range normalization method is used to perform dimensionless processing on the smoothed tension data. By calculating the proportional relationship between the current electrode tension value and the historical minimum and maximum values ​​of the electrode tension, the tension parameters are mapped to the [0,1] interval to obtain the electrode tension stability parameters. S22. The collected raw diaphragm tension data is processed by synchronous signal filtering. A second-order Butterworth low-pass filtering algorithm is used to filter out high-frequency disturbances in the tension signal to obtain a stable diaphragm tension signal. Then, the range normalization method is used to perform dimensionless processing on the filtered tension signal. By mapping the real-time value of diaphragm tension with the historical minimum and maximum values ​​of diaphragm tension, it is converted into a dimensionless value of a uniform scale to obtain the diaphragm tension stability parameter. S23. The raw data of the collected winding spindle speed is processed using a periodic averaging algorithm. The continuously sampled speed data is periodically averaged to eliminate the influence of instantaneous fluctuations on speed stability. The rated speed of the winding spindle is obtained by reading the rated speed parameters calibrated on the nameplate of the winding spindle servo motor. Then, the speed data is standardized using the standard deviation normalization method. By proportionally converting the current speed value with the rated speed of the winding spindle, the speed parameters are converted into dimensionless parameters of a uniform scale, thus obtaining the stable speed parameters of the winding spindle. S24. The raw data of electrode unwinding speed is processed using a speed consistency correction algorithm. The difference between the electrode unwinding speed and the theoretical synchronous speed of the winding spindle is calculated, and the speed difference is compensated and corrected to eliminate the speed deviation between the unwinding drive mechanism and the winding spindle. Then, the range normalization method is used to proportionally convert the corrected unwinding speed value with the historical minimum and maximum unwinding speeds to convert the speed parameters into dimensionless values, thus obtaining the unwinding speed parameters. S25. Perform image feature processing on the collected raw data of electrode position offset. Use the Canny edge detection algorithm combined with the sub-pixel edge positioning algorithm to extract the edge contour position of the electrode and calculate the geometric distance deviation between the actual edge position of the electrode and the preset standard edge position of the winding equipment. By reading the allowable offset tolerance parameter of the electrode edge set by the winding equipment during the production debugging stage, obtain the maximum allowable offset of the equipment. Then, through geometric scale conversion and normalization processing methods, convert the pixel offset into the actual physical distance. And by performing proportional normalization processing with the maximum allowable offset of the equipment, obtain the electrode position deviation parameter. S26. The collected raw data of motor load current is processed according to time series. The sliding window averaging algorithm is used to smooth the continuous sampled current values ​​to reduce the impact of instantaneous load fluctuations of the motor on data stability. The rated current of the motor is obtained by reading the rated working current parameters marked on the nameplate of the winding spindle drive motor. Then, the rated current normalization method is used to perform dimensionless processing on the current data. By converting the current motor current value with the rated current of the motor, the current parameters are mapped to a uniform scale range to obtain the load current of the winding spindle drive motor.

[0008] Furthermore, step three includes: S31. By extracting the electrode tension stability parameters, diaphragm tension stability parameters, winding spindle stable speed parameters, unwinding speed parameters, electrode position deviation parameters, and the maximum allowable offset of the equipment, and after dimensionless processing, the winding cooperative offset index is calculated and obtained.

[0009] Furthermore, step three also includes: S32. By setting a preset cooperative offset threshold and comparing the winding cooperative offset index with the cooperative offset threshold, the first evaluation result is obtained, including: When the winding coordination offset index is less than or equal to the coordination offset threshold, it indicates that the coordination operation status of the winding process is qualified, and the actuators of the winding equipment are in a stable coordination operation state, which is continuously monitored. When the winding collaborative offset index exceeds the collaborative offset threshold, it indicates that the collaborative operation status of the winding process is unqualified, and there is a collaborative operation deviation in the winding equipment, which may lead to the risk of misalignment of the winding electrode edge or stacking offset. This triggers the first warning command and generates the first strategy: based on the comprehensive excess ratio of the winding collaborative offset index relative to the collaborative offset threshold, a comprehensive adjustment ratio for equipment operation is generated, and the winding-related actuators are adjusted collaboratively according to a unified ratio. The electrode unwinding tension is dynamically adjusted by 4% to 10%; the winding spindle running speed is synchronously compensated by 3% to 7%; and the electrode guide mechanism position is automatically corrected by 2% to 5%. After adjustment, the calculation is repeated until the winding collaborative offset index is ≤ the collaborative offset threshold, so that the winding tension, running speed, and electrode guide position converge synchronously to a stable operating range.

[0010] Furthermore, step four includes: S41. By extracting the electrode tension stability parameters, diaphragm tension stability parameters, winding spindle stable speed parameters, and winding spindle drive motor load current, and combining the winding spindle rated speed and motor rated current, the parameters are dimensionlessly normalized, and the equipment operation coupling stability index is calculated.

[0011] Furthermore, step four also includes: S42. By setting a stable operation threshold and comparing the equipment operation coupling stability index with the stable operation threshold, the second evaluation result is obtained, including: When the equipment operation coupling stability index is less than or equal to the stable operation threshold, it indicates that the winding equipment is in a stable load state and that the equipment tension level, winding speed and drive load maintain a stable coupling relationship, which is continuously monitored. When the equipment operation coupling stability index exceeds the stable operation threshold, it indicates that the winding equipment's operating load stability is unqualified, and the equipment faces the risk of operating load coupling, leading to equipment overload operation, decreased winding efficiency, or production cycle fluctuations. This triggers a second warning instruction and generates a second strategy: based on the comprehensive deviation ratio of the equipment operation coupling stability index relative to the stable operation threshold, a comprehensive equipment operation adjustment ratio is generated, and coordinated adjustment is performed on the winding equipment according to a unified ratio. This includes a 5%–15% speed reduction adjustment on the winding spindle running speed; a 3%–10% synchronous compensation adjustment on the electrode unwinding speed; and a 2%–8% tension compensation adjustment on the tension control system. After adjustment, the calculation is repeated until the equipment operation coupling stability index is ≤ the stable operation threshold, so that the winding equipment's tension level, running speed, and drive load converge to the stable operation range.

[0012] Furthermore, step five includes: S51. Based on the obtained winding cooperative offset index and equipment operation coupling stability index, a comprehensive fusion analysis of the winding process cooperative state and equipment operation load state is performed. After dimensionless processing, the winding quality risk prediction index is calculated and obtained.

[0013] Furthermore, step five also includes: S52. By setting a preset quality risk threshold and comparing the winding quality risk prediction index with the quality risk threshold, the third assessment results are obtained, including: When the winding quality risk prediction index is less than or equal to the quality risk threshold, it indicates that the current winding production process is in a stable production state, and the winding process coordination and equipment operation status are both within a reasonable range, and continuous monitoring is required. When the winding quality risk prediction index exceeds the quality risk threshold, it indicates that the current winding production process is not in a stable production state and there is a potential risk of quality defects, leading to electrode edge misalignment, interlayer offset, or decreased cell stacking consistency. This triggers a third early warning instruction and generates a third strategy: based on the comprehensive deviation ratio of the winding quality risk prediction index relative to the quality risk threshold, quality error prevention control is implemented in the winding production process, including: adaptive optimization of the production cycle, dynamically adjusting the winding production cycle by 6% to 15% to ensure the winding process operates under a stable cycle, thereby reducing the risk of quality fluctuations caused by high-speed operation; optimization of the winding path, performing accuracy correction of 3% to 8% on the electrode guide path and winding trajectory parameters to improve the interlayer alignment accuracy during the electrode winding process; after adjustment, recalculation is performed. If the winding quality risk prediction index still exceeds the quality risk threshold, manual intervention is initiated, automatically sending a manual inspection prompt to the equipment management terminal, prompting equipment maintenance personnel to conduct on-site inspection and maintenance of the winding equipment guide mechanism, tension control module, and drive system. S53. Once the winding quality risk prediction index returns to a reasonable range, the operating data, evaluation results, and adjustment strategy execution results of this cycle will be automatically written into the production process quality database for subsequent production process analysis and equipment process optimization, forming a closed-loop control mechanism for winding production process quality feedback optimization.

[0014] Furthermore, an intelligent error-proofing system for intelligent manufacturing processes based on real-time data interaction includes: The winding operation data acquisition module is used to monitor the winding production process of power battery cells for new energy vehicles in real time. It collects raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time position offset of electrode, and motor load current, and performs unified time synchronization marking to establish a basic dataset of winding equipment operation status. The runtime data preprocessing module is used to perform time synchronization alignment, abnormal sampling point removal, time-series filtering and smoothing, and dimensionless normalization on the basic dataset of the winding equipment's operating status. The winding coordination status assessment module is used to calculate the winding coordination offset index and compare it with the coordination offset threshold to determine whether the coordination operation status of the winding process is qualified. If it is not qualified, a coordination adjustment strategy for the winding equipment is given. The equipment stability assessment module is used to calculate the equipment operation coupling stability index and compare it with the stability operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, an equipment stability adjustment strategy is given. The winding quality risk control module is used to calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If it is not, it will provide quality error prevention control strategies, record data and perform feedback analysis to form a closed-loop control mechanism for quality feedback optimization of the winding production process.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention collects multi-source operating data in real time, including electrode tension, diaphragm tension, winding spindle speed, electrode unwinding speed, electrode position offset, and motor load current, and performs unified time synchronization and data preprocessing to construct a basic dataset of the winding equipment's operating status. This allows for a comprehensive reflection of the real-time operating status of each key process parameter during the winding production process. Compared to existing technologies that only monitor a single equipment parameter, this invention enables a comprehensive perception of the multi-dimensional operating status of the winding production process, improving the comprehensiveness and accuracy of monitoring the production process's operating status.

[0016] This invention also constructs a winding cooperative offset index and an equipment operation coupling stability index to comprehensively analyze the cooperative relationship between tension control, operating speed matching, and electrode guide position during the winding production process. At the same time, it combines the equipment operating load status to evaluate the degree of stable equipment operation. This enables joint analysis of the process cooperative status and equipment operating status during the winding production process, effectively identifying the cooperative offset risk and abnormal equipment operating load that may occur during the winding process, and improving the accuracy and reliability of the operating status assessment of the winding production process.

[0017] This invention also constructs a winding quality risk prediction index by integrating the winding collaborative offset index and the equipment operation coupling stability index. Based on this index, a comparative analysis is performed with a preset quality risk threshold. When a winding quality risk is detected, a production error prevention control strategy is automatically triggered to coordinately adjust key parameters such as winding tension, running speed, and electrode guide position. This enables early warning and proactive control before winding quality defects occur, effectively reducing the probability of quality problems such as electrode edge misalignment and interlayer offset, and improving the stability of the power battery winding production process and the consistency of product quality. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the overall method flow of the present invention; Figure 2 This is a schematic diagram of the overall system flow of the present invention; Figure 3 A schematic diagram illustrating the preprocessing flow and curve comparison of multi-source operational data; Figure 4 This is a schematic diagram of electrode edge image recognition and position offset calculation. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below. Example

[0021] Please see Figures 1 to 4 This invention provides a technical solution: an intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction, the specific steps of which include: Step 1: Real-time monitoring of the production process of new energy vehicle power battery cells, collecting raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time electrode position offset, and motor load current, and performing unified time synchronization marking to establish a basic dataset of winding equipment operating status. Step 2: Perform time synchronization and alignment processing, abnormal sampling point removal processing, time-series filtering and smoothing processing, and dimensionless normalization processing on the basic dataset of the winding equipment's operating status. Step 3: Calculate the winding cooperative offset index and compare it with the cooperative offset threshold to determine whether the cooperative operation status of the winding process is qualified. If it is not qualified, a cooperative adjustment strategy for the winding equipment is given. Step 4: Calculate the equipment operation coupling stability index and compare it with the stable operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, provide a stable operation adjustment strategy for the equipment. Step 5: Calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If not, implement quality error prevention control strategies, record and analyze the data to form a closed-loop control mechanism for quality feedback optimization in the winding production process.

[0022] Figure 1 The core content shown is divided into two parts: the physical mechanical structure and the logical flow route. It demonstrates the power battery cell winding equipment from an isometric perspective, including the positive and negative electrode unwinding shafts, the separator unwinding mechanism, and the central winding spindle. This corresponds to the physical entity object monitored in real time in step one, namely the equipment layer that generates raw data such as electrode tension and spindle speed. The technical roadmap consists of four flow boxes. The first box, "Operational Data Acquisition and Preprocessing," corresponds to steps one and two, demonstrating the establishment of the basic dataset of equipment operation status and the time-series synchronization processing. The second box, "Cooperative Offset Assessment and Adjustment," corresponds to step three, demonstrating the mechanism of judging the operation status and triggering cooperative adjustment through the winding cooperative offset index. The third box, "Coupled Stability Assessment and Adjustment," corresponds to step four, demonstrating the mechanism of judging the equipment load status and triggering stable operation adjustment based on the coupling stability index. The fourth box, "Risk Prediction and Error Prevention Closed Loop," corresponds to step five, demonstrating the final control closed loop of calculating the quality risk prediction index, executing error prevention control strategies when an anomaly is detected, recording data, and forming feedback optimization.

[0023] In this embodiment, by constructing a multi-level evaluation mechanism consisting of a winding collaborative offset index, an equipment operation coupling stability index, and a winding quality risk prediction index, a comprehensive analysis of the process collaboration status, equipment operation status, and product quality risks during the winding production of power battery cells is achieved. This enables the early identification of potential anomalies in the production process and the implementation of intelligent error prevention control, thereby improving the stability of the winding production process and the consistency of the products. Example

[0024] Please see Figures 1 to 4 In this embodiment, as explained in Embodiment 1, step one specifically includes: S11. Real-time monitoring of the operation status of the electrode unwinding process during the production of power battery cells for new energy vehicles. By installing a strain gauge tension sensor at the guide roller bearing seat of the electrode unwinding mechanism, the tensile tension generated by the electrode during the unwinding process is continuously collected to obtain the original data of the electrode tension, which is denoted as Tp0. S12. Real-time monitoring of the operation status of the diaphragm unwinding process during the production of power battery cells for new energy vehicles. By installing a cantilever beam tension sensor at the tension control roller position of the diaphragm unwinding mechanism, the force change of the diaphragm material during the unwinding and conveying process is detected in real time, and the original diaphragm tension data is collected and recorded as Ts0. S13. Real-time monitoring of the driving status of the winding spindle during the production of power battery cells for new energy vehicles. By installing an incremental rotary encoder at the output end of the servo motor of the winding spindle, the real-time speed change of the winding spindle is continuously sampled to obtain the original data of the winding spindle speed, which is denoted as Vw0. S14. Real-time monitoring of the electrode unwinding and conveying speed during the production of power battery cells for new energy vehicles. By installing a photoelectric rotary encoder at the output shaft of the electrode unwinding drive motor, the conveying speed of the electrode unwinding drive mechanism is collected in real time, and the raw data of the electrode unwinding speed is obtained and denoted as Vu0. S15. Real-time monitoring of the electrode winding position during the production of power battery cells for new energy vehicles is performed. An industrial line array camera is installed in the electrode guide area of ​​the winding station to continuously acquire images of the electrode edge position. Gray-scale threshold segmentation, Canny edge detection, and sub-pixel edge positioning algorithms are used to extract the electrode edge contour. The pixel offset between the electrode edge contour and the preset reference boundary is calculated and geometric scale conversion is performed to obtain the original data of the real-time electrode position offset, denoted as ΔP0. At the same time, a Hall current sensor is installed at the power input end of the winding spindle driver to detect the operating load current of the winding spindle drive motor in real time and obtain the original data of the motor load current, denoted as I0. S16. The collected raw data of electrode tension Tp0, diaphragm tension Ts0, winding spindle speed Vw0, electrode unwinding speed Vu0, real-time electrode position offset ΔP0, and motor load current I0 are uniformly time-stamped. By installing an industrial time synchronization clock device in the winding equipment control cabinet and connecting it to the production equipment control network, the data collected by each sensor are time-stamped according to a unified clock, a unified timestamp t is added to each sampled data, and a basic dataset of the winding equipment operating status is established.

[0025] In this embodiment, by collecting key operating parameters such as electrode tension, diaphragm tension, winding spindle speed, electrode unwinding speed, electrode position offset, and motor load current in real time and uniformly synchronizing them, a complete and time-consistent basic dataset of the winding equipment's operating status can be established. This provides a reliable data foundation for subsequent operating status assessment and quality risk prediction, and improves the accuracy of data analysis. Example

[0026] Please see Figures 1 to 4 In the explanation of Example 2, this embodiment specifically includes the following steps: S21. Based on the basic dataset of the winding equipment's operating status, various types of raw operating data are time-synchronized and aligned according to a unified timestamp t, abnormal sampling points are removed, time-series filtering and smoothing are performed, and dimensionless normalization is applied. The collected electrode tension raw data Tp0 is processed according to the time series. The sliding window weighted moving average algorithm is used to perform time-series smoothing on the continuous sampled tension data to eliminate the influence of instantaneous vibration and sampling noise on the tension data, resulting in a smoothed electrode tension sequence. Then, the range normalization method is used to perform dimensionless processing on the smoothed tension data. By calculating the proportional relationship between the current electrode tension value and the historical minimum electrode tension value, denoted as Tpmin, and the historical maximum value, denoted as Tpmax, the tension parameters are mapped to the [0,1] interval to obtain the electrode tension stability parameter, denoted as Tp. S22. The raw diaphragm tension data Ts0 is processed by synchronous signal filtering. A second-order Butterworth low-pass filtering algorithm is used to filter out high-frequency disturbances in the tension signal to obtain a stable diaphragm tension signal. Then, the range normalization method is used to perform dimensionless processing on the filtered tension signal. By proportionally mapping the real-time diaphragm tension value with the historical minimum diaphragm tension value, denoted as Tsmin, and the historical maximum diaphragm tension value, denoted as Tsmax, the diaphragm tension stability parameter is obtained and denoted as Ts. S23. The raw data Vw0 of the collected winding spindle speed is processed using a periodic averaging algorithm. The continuously sampled speed data is periodically averaged to eliminate the influence of instantaneous fluctuations on speed stability. The rated speed of the winding spindle is obtained by reading the rated speed parameter calibrated on the nameplate of the winding spindle servo motor, and is denoted as Vwref. The speed data is then standardized using the standard deviation normalization method. By proportionally converting the current speed value with the rated speed Vwref of the winding spindle, the speed parameter is converted into a dimensionless parameter of a uniform scale, and the stable speed parameter of the winding spindle is obtained, denoted as Vw. S24. The raw data of electrode unwinding speed Vu0 is processed using a speed consistency correction algorithm. By calculating the difference between the electrode unwinding speed and the theoretical synchronous speed of the winding spindle, and performing error compensation correction on the speed difference, the speed deviation between the unwinding drive mechanism and the winding spindle is eliminated. Then, the range normalization method is used to proportionally convert the corrected unwinding speed value with the historical minimum unwinding speed, denoted as Vumin, and the maximum unwinding speed, denoted as Vumax, so that the speed parameter is converted into a dimensionless value, and the unwinding speed parameter, denoted as Vu, is obtained. S25. The original data ΔP0 of the collected electrode position offset is processed for image features. The Canny edge detection algorithm combined with the sub-pixel edge positioning algorithm is used to extract the edge contour position of the electrode and calculate the geometric distance deviation between the actual edge position of the electrode and the preset standard edge position of the winding equipment. By reading the allowable offset tolerance parameter of the electrode edge set by the winding equipment during the production debugging stage, the maximum allowable offset of the equipment is obtained and recorded as Pmax. Then, the pixel offset is converted into the actual physical distance through geometric scale conversion and normalization processing. By performing proportional normalization processing with the maximum allowable offset of the equipment Pmax, the electrode position deviation parameter is obtained and recorded as ΔP. S26. The collected raw data I0 of the motor load current is processed according to the time series. The sliding window averaging algorithm is used to smooth the continuous sampled current values ​​to reduce the impact of instantaneous load fluctuations of the motor on data stability. The rated current of the motor is obtained by reading the rated working current parameter marked on the nameplate of the winding spindle drive motor, and is denoted as Iref. Then, the rated current normalization method is used to perform dimensionless processing on the current data. By proportionally converting the current motor current value with the rated current Iref of the motor, the current parameter is mapped to a uniform scale range to obtain the load current of the winding spindle drive motor, denoted as I.

[0027] In this embodiment, by performing time synchronization alignment, abnormal sampling point removal, time-series filtering smoothing, and dimensionless normalization on the collected winding equipment operation data, sensor noise interference and data scale differences can be effectively eliminated, improving the stability and comparability of the operation data, thereby enhancing the accuracy and reliability of subsequent operation status analysis results. Example

[0028] Please see Figures 1 to 4 In the explanation of Example 3, this embodiment specifically includes the following steps: S31. By extracting the electrode tension stability parameter Tp, diaphragm tension stability parameter Ts, winding spindle stable speed parameter Vw, unwinding speed parameter Vu, electrode position deviation parameter ΔP, and the maximum allowable offset Pmax of the equipment, after dimensionless processing, the winding cooperative offset index, denoted as CSI, is calculated and obtained, as follows: In the formula, w1, w2 and w3 represent weighting coefficients. The tension difference index, which characterizes the effect of electrode tension difference on the winding synergistic offset index, has a high weight and is a key indicator in winding stability control. The tension difference directly affects the synchronous stretching state of the electrode and the separator during the winding process. When the tension is mismatched, interlayer misalignment or material stretching deformation is likely to occur. Therefore, the tension difference index is set as the highest weight to highlight its core role in the stability of winding quality. The difference between the winding spindle speed and the electrode unwinding speed represents the influence of the winding cooperative offset index and has a medium weight. The speed difference reflects the degree of speed matching between the drive mechanism and the unwinding mechanism in the winding system. When the speeds are inconsistent, it is easy to cause material stacking or uneven stretching, which will affect the alignment state between the winding layers of the electrode. Therefore, it is given a relatively important weight. The position offset characterizes the impact of electrode position offset on the winding cooperative offset index, and has a medium weight. Position offset directly reflects the lateral stability of the electrode in the guiding mechanism. When the offset is too large, it will cause the electrode edge to be misaligned or the core to be skewed, thus affecting the stacking accuracy of the battery electrode. Therefore, it is given a weight similar to that of the speed difference to reflect its important role. By constructing a winding cooperative offset index (CSI) that is a weighted fusion of the tension difference ratio, speed difference ratio, and electrode position offset ratio, the cooperative relationship between tension control, speed control, and electrode guidance control in the winding system can be comprehensively reflected. When the CSI value increases, it indicates that the degree of cooperation between the actuators decreases, and the risk of electrode offset or interlayer misalignment during the winding process increases, thus providing a quantitative basis for evaluating the operating status of the winding equipment and triggering error prevention adjustment strategies.

[0029] In this embodiment, by constructing a winding cooperative offset index formed by weighted fusion of tension difference ratio, speed difference ratio and electrode position offset ratio, the cooperative relationship between tension control, speed control and electrode guidance control in the winding system can be quantitatively characterized, thereby realizing real-time quantitative evaluation of the cooperative operation status of the winding process.

[0030] Example 5 Please see Figures 1 to 4In the explanation of Example 4, specifically, step three further includes: S32. By setting a pre-defined cooperative offset threshold, denoted as Cth, and comparing the winding cooperative offset index CSI with the cooperative offset threshold Cth, the first evaluation result is obtained, including: When the winding cooperative offset index CSI ≤ cooperative offset threshold Cth, it indicates that the cooperative operation status of the winding process is qualified, and the actuators of the winding equipment are in a stable cooperative operation state, which is continuously monitored. When the Cooperative Misalignment Index (CSI) exceeds the Cooperative Misalignment Threshold (Cth), it indicates that the cooperative operation of the winding process is unqualified, and there is a cooperative operation deviation in the winding equipment, which may lead to the risk of misalignment of the edge of the wound electrode or the offset of the stacked sheets. This triggers the first warning command and generates the first strategy: based on the comprehensive excess ratio of the Cooperative Misalignment Index (CSI) relative to the Cooperative Misalignment Threshold (Cth), a comprehensive adjustment ratio for equipment operation is generated, and the winding-related actuators are adjusted in a coordinated manner according to a unified ratio. The unwinding tension of the electrode is dynamically adjusted by 4% to 10%; the running speed of the winding spindle is synchronously compensated by 3% to 7%; and the position of the electrode guide mechanism is automatically corrected by 2% to 5%. After adjustment, the calculation is repeated until the Cooperative Misalignment Index (CSI) is less than or equal to the Cooperative Misalignment Threshold (Cth), so that the winding tension, running speed, and electrode guide position converge synchronously to a stable operating range.

[0031] Method for obtaining the cooperative offset threshold Cth: The goal of the calibration process for the cooperative offset threshold Cth is to determine a critical winding cooperative offset index (CSI) value that can effectively distinguish between "stable winding operation" and "state with cooperative offset risk". First, a standard data database of the cooperative operation status of winding equipment is constructed. This database is formed by continuously collecting operating data of winding equipment on the power battery electrode winding production line. The database has no fewer than 600 sample groups, covering various operating states such as normal stable production conditions, slight offset conditions, and significant offset conditions. Each sample group in the database includes electrode tension stability parameters Tp, separator tension stability parameters Ts, winding spindle stable speed parameters Vw, electrode unwinding speed parameters Vu, and electrode position deviation parameters ΔP. ​​Simultaneously, three or more equipment engineers and quality engineers with experience in lithium battery winding processes, based on production quality inspection results and electrode alignment inspection standards, label the operating status of each sample group with a "gold standard", clearly classifying it as either a "cooperative stable state" or a "cooperative offset risk state" (including electrode edge misalignment, inter-layer winding offset, and tension mismatch).

[0032] Subsequently, the winding cooperative offset index (CSI) was uniformly calculated for all sample running data in the database according to the formula in step three, yielding the quantified cooperative offset index value for each sample group. Next, a statistical distribution analysis was performed on the winding cooperative offset index (CSI) values ​​of the "cooperative stable state" group and the "cooperative offset risk state" group, and their probability density function curves were plotted. Theoretically, the two data distributions will form two probability peaks with some overlap, where the winding cooperative offset index (CSI) value for the stable running state is generally lower, while the winding cooperative offset index (CSI) value for the offset risk state is generally higher.

[0033] Based on this, the classification performance was evaluated by constructing an ROC curve, and the point with the largest Youden Index was selected as the optimal split point. The winding cooperative offset index (CSI) value corresponding to this point achieves the optimal balance between sensitivity and specificity, thereby enabling efficient identification of cooperative operation risks. Simultaneously, long-term operational experience from the production site was considered. For example, when the winding cooperative offset index (CSI) exceeds a certain value, the probability of electrode edge offset increases significantly, easily causing winding quality defects. Therefore, a final determination needs to be made by comprehensively considering statistical results and process experience.

[0034] Based on the above statistical analysis and process experience, the optimal cooperative offset threshold Cth is determined to be 0.32. When the winding cooperative offset index CSI ≤ 0.32, the various actuators of the equipment maintain a good tension-speed-position coordination relationship, and the winding process is stable and reliable. When the winding cooperative offset index CSI > 0.32, the system determines that there is a risk of cooperative offset in the winding process. At this time, the probability of electrode edge misalignment or stacking deviation increases significantly, and the equipment cooperative adjustment strategy needs to be triggered.

[0035] When the Cooperative Misalignment Index (CSI) is detected to be greater than 0.32, the system will trigger the cooperative misalignment control strategy and perform a comprehensive adjustment operation on the winding system with a uniform ratio. This includes: dynamically adjusting the electrode unwinding tension by 4% to 10%; synchronously compensating the winding spindle speed by 3% to 7%; and automatically correcting the electrode guide mechanism position by 2% to 5%. Through the above cooperative adjustment methods, the winding tension, speed, and electrode guide position are brought back to the stable operating range, thereby reducing the risk of electrode winding misalignment.

[0036] In this embodiment, by comparing the winding cooperative offset index with the preset cooperative offset threshold, and automatically triggering the winding equipment cooperative adjustment strategy when the index exceeds the limit, the electrode unwinding tension, winding spindle speed and guide mechanism position can be adjusted synchronously, thereby effectively reducing the risk of electrode edge misalignment and winding interlayer offset.

[0037] Example 6 Please see Figures 1 to 4 In the explanation of Example 5, specifically, step four includes: S41. By extracting the electrode tension stability parameter Tp, diaphragm tension stability parameter Ts, winding spindle stable speed parameter Vw, and winding spindle drive motor load current I, and combining the winding spindle rated speed Vwref and motor rated current Iref, after performing dimensionless normalization on each parameter, the equipment operation coupling stability index is calculated and obtained, denoted as ESI, as follows: In the formula, a1, a2, and a3 represent weighting coefficients; Tref represents the standard tension reference value of the winding equipment, which is the standard tension benchmark value obtained by statistically averaging the tension data during the stable production stage of the equipment through process calibration trial operation under the rated production conditions of the winding equipment. : Characterizes the influence of electrode tension level on the coupling stability index of equipment operation, and has a high weight; tension level reflects the matching relationship between the material stress state and the equipment operating load during the winding process. When the tension deviates from the standard reference value, it will cause changes in winding resistance and increase the equipment driving load. Therefore, it is given a high weight to reflect its key influence on the stability of equipment operation. The winding spindle speed represents the impact of the coupling stability index of the equipment operation and has a high weight. The winding speed directly determines the equipment's operating cycle time and production efficiency. When the operating speed is too high or too low, it will affect the tension control and material synchronous delivery, thus having a significant impact on the stable operation of the equipment. Therefore, it is set as an important weight with the tension index. : Characterizes the impact of drive motor load current on the coupling stability index of equipment operation, and has a medium weight; motor load current can directly reflect the load level of the equipment drive system. When the load current is close to or exceeds the rated current, it indicates that the equipment may be in a high load operating state. Therefore, it is given an important weight, but slightly lower than the weight of tension and speed. By constructing a weighted fusion of the tension level ratio, winding speed ratio, and motor load ratio, the Equipment Operation Coupling Stability Index (ESI) can comprehensively reflect the coupling stability relationship between tension control, operating speed, and drive load of the winding equipment. When the ESI value increases, it indicates a decrease in the matching degree between the equipment load and operating parameters, potentially leading to decreased operating efficiency or excessive load.

[0038] In this embodiment, by constructing a coupling stability index for equipment operation and conducting a comprehensive analysis of tension level, winding speed, and drive motor load current, the coupling relationship between process parameters and drive load of the winding equipment can be reflected, thereby achieving a quantitative assessment of equipment operation stability.

[0039] Example 7 Please see Figures 1 to 4In the explanation of Example Six, specifically, step four further includes: S42. By setting a preset stable operation threshold, denoted as Eth, and comparing the equipment operation coupling stability index ESI with the stable operation threshold Eth, the second evaluation results are obtained, including: When the equipment operation coupling stability index ESI ≤ stable operation threshold Eth, it indicates that the winding equipment is in a stable load state and the equipment tension level, winding speed and drive load maintain a stable coupling relationship, which is continuously monitored. When the equipment operation coupling stability index (ESI) exceeds the stable operation threshold (Eth), it indicates that the winding equipment's operating load stability is unqualified, and the equipment faces the risk of operating load coupling, leading to equipment overload operation, decreased winding efficiency, or production cycle fluctuations. This triggers a second warning instruction and generates a second strategy: based on the comprehensive deviation ratio of the equipment operation coupling stability index (ESI) relative to the stable operation threshold (Eth), a comprehensive equipment operation adjustment ratio is generated, and coordinated adjustment is performed on the winding equipment according to a unified ratio. This includes a 5%–15% speed reduction adjustment on the winding spindle operating speed; a 3%–10% synchronous compensation adjustment on the electrode unwinding speed; and a 2%–8% tension compensation adjustment on the tension control system. After adjustment, the calculation is repeated until the equipment operation coupling stability index (ESI) is ≤ the stable operation threshold (Eth), causing the winding equipment's tension level, operating speed, and drive load to converge to the stable operating range.

[0040] Method for obtaining the stable operation threshold Eth: The goal of the calibration process of the stable operation threshold Eth is to determine a critical equipment operation coupling stability index (ESI) value that can effectively distinguish between "stable equipment operation state" and "equipment operation load coupling risk state".

[0041] First, a standard data database of equipment operating status is constructed. This database is formed by continuously collecting equipment operating data on the power battery electrode winding production line. The database has no fewer than 800 sample sets, covering various operating conditions such as stable operation, slight load fluctuation, and equipment overload risk. Each sample set in the database includes the electrode tension stability parameter Tp, the separator tension stability parameter Ts, the winding spindle stable speed parameter Vw, and the drive motor load current I.

[0042] Meanwhile, three or more equipment engineers and production quality engineers with experience in the operation and maintenance of winding equipment will use equipment operation logs, equipment maintenance records and production quality test results to mark the operating status of each sample with the "gold standard" and clearly classify it as "stable operating status" or "operating load coupling risk status" (including excessive equipment load, abnormal winding speed and unstable tension control).

[0043] Subsequently, the Equipment Operation Coupling Stability Index (ESI) was uniformly calculated for all sample data in the database according to the formula in step four, yielding the quantified stability index value for each sample group. Next, a statistical distribution analysis was performed on the ESI values ​​of the "Stable Operation State" group and the "Load Coupling Risk State" group, and their probability density function curves were plotted. Theoretically, the two data distributions will form two probability peaks with partially overlapping intervals. The ESI value for the stable operation state is generally close to 1, while the ESI value for the load coupling risk state is generally higher.

[0044] Based on this, the classification performance is evaluated by constructing ROC curves, and the point with the largest Youden Index is selected as the optimal split point. The ESI value of the device operation coupling stability index corresponding to this point can achieve the best balance between sensitivity and specificity, thereby realizing the effective identification of device load coupling risks.

[0045] Based on the above statistical analysis and equipment operation experience, the optimal stable operation threshold Eth is determined to be 1.05. When the equipment operation coupling stability index ESI ≤ 1.05, a reasonable matching relationship is maintained between the equipment tension level, winding speed and drive load, and the equipment operation is stable and reliable; when the equipment operation coupling stability index ESI > 1.05, the system determines that there is a risk of operation load coupling, and it is necessary to trigger the equipment stable operation adjustment strategy.

[0046] In this embodiment, by comparing and analyzing the equipment operation coupling stability index with the stable operation threshold, and automatically executing the equipment operation adjustment strategy when the index exceeds the limit, the winding spindle speed, unwinding speed and tension control system can be coordinated and adjusted, thereby avoiding equipment overload operation and improving production operation stability.

[0047] Example 8 Please see Figures 1 to 4 In the explanation of Example 7, specifically, step five includes: S51. Based on the obtained winding cooperative offset index (CSI) and equipment operation coupling stability index (ESI), a comprehensive fusion analysis of the winding process cooperative state and equipment operation load state is performed. After dimensionless processing, the winding quality risk prediction index, denoted as QRI, is calculated and obtained, as follows: In the formula, s1 and s2 represent weighting coefficients. The winding collaborative offset index, which characterizes the impact of the winding collaborative offset state on the winding quality risk prediction index, has a high weight. The winding collaborative offset index mainly reflects the stability of electrode tension matching, winding speed matching, and electrode guide position. When this index increases, the risk of electrode edge misalignment or interlayer offset increases significantly. Therefore, it is set as the main risk contribution factor to highlight the direct impact of the winding process collaborative stability on product quality. The second highest weight is given to the equipment operation coupling stability index, which characterizes the impact of equipment operation coupling stability on the winding quality risk prediction index. The equipment operation coupling stability index reflects the matching degree between equipment tension control, winding speed and motor load. When the equipment load coupling relationship is unbalanced, it may lead to fluctuations in the winding process or unstable equipment operation, thereby indirectly affecting the winding quality. Therefore, it is given an important but slightly lower weight than the process coordination state. By constructing a winding quality risk prediction index (QRI) that is a weighted fusion of the winding collaborative offset index and the equipment operation coupling stability index, the combined impact of process collaborative stability and equipment operation stability on product quality during the winding production process can be comprehensively reflected. An increase in the QRI value indicates a higher probability of quality deviations occurring during the winding production process.

[0048] In this embodiment, the winding quality risk prediction index is formed by merging the winding collaborative offset index and the equipment operation coupling stability index. This allows for a comprehensive assessment of the quality risk in the winding production process from two dimensions: process collaboration status and equipment operation status, thereby enabling early prediction of potential quality defects.

[0049] Example 9 Please see Figures 1 to 4 In the explanation of Example 8, specifically, step five further includes: S52. By setting a preset quality risk threshold, denoted as Qth, and comparing the winding quality risk prediction index QRI with the quality risk threshold Qth, the third evaluation results are obtained, including: When the winding quality risk prediction index QRI ≤ quality risk threshold Qth, it indicates that the current winding production process is in a stable production state, and the winding process coordination and equipment operation status are both within a reasonable range, and continuous monitoring is required. When the winding quality risk prediction index QRI > the quality risk threshold Qth, it indicates that the current winding production process is not in a stable production state and there is a potential risk of quality defects, leading to electrode edge misalignment, interlayer offset, or decreased cell stacking consistency. This triggers a third early warning instruction and generates a third strategy: based on the comprehensive deviation ratio of the winding quality risk prediction index QRI relative to the quality risk threshold Qth, quality error prevention control is implemented in the winding production process, including: adaptive optimization of the production cycle, dynamically adjusting the winding production cycle by 6% to 15% to ensure the winding process operates under a stable cycle, thereby reducing the risk of quality fluctuations caused by high-speed operation; optimization of the winding path, correcting the electrode guide path and winding trajectory parameters by 3% to 8% to improve the interlayer alignment accuracy during the electrode winding process; after adjustment, recalculation is performed. If the winding quality risk prediction index QRI is still > the quality risk threshold Qth, manual intervention is initiated, automatically sending a manual inspection prompt to the equipment management terminal, prompting equipment maintenance personnel to conduct on-site inspection and maintenance of the winding equipment guide mechanism, tension control module, and drive system. S53. Once the winding quality risk prediction index returns to a reasonable range, the operating data, evaluation results, and adjustment strategy execution results of this cycle will be automatically written into the production process quality database for subsequent production process analysis and equipment process optimization, forming a closed-loop control mechanism for winding production process quality feedback optimization.

[0050] How to obtain the quality risk threshold Qth: The goal of the calibration process of the quality risk threshold Qth is to determine a critical winding quality risk prediction index QRI value that can effectively distinguish between "stable winding quality state" and "risk winding quality state".

[0051] First, a database of standard data for winding quality risk assessment was constructed. This database was formed by continuously collecting production operation data on the power battery electrode winding production line. The database has a sample size of no less than 1,000 sets, covering various production states such as stable production conditions, slight quality fluctuation conditions, and obvious quality anomaly conditions. Each sample in the database includes the winding cooperative offset index (CSI), the equipment operation coupling stability index (ESI), and the corresponding quality inspection results.

[0052] Meanwhile, three or more quality engineers with experience in power battery production quality management will use the cell appearance inspection standards, electrode alignment inspection results and production quality records to mark the production status of each sample with the "gold standard" and clearly classify it as "quality stable state" or "quality risk state" (including electrode edge offset, winding layer misalignment and winding consistency abnormalities, etc.).

[0053] Subsequently, the QRI (Quality Risk Prediction Index) for winding quality is calculated uniformly for all samples in the database according to the formula in step five, yielding the quantified quality risk index value for each group of samples. Next, a statistical distribution analysis is performed on the QRI values ​​of the "stable quality state" group and the "risk quality state" group, and their probability density function curves are plotted. Theoretically, the two data distributions will form two probability peaks with partially overlapping intervals, where the QRI value for the stable quality state is generally lower, while the QRI value for the risk quality state is generally higher.

[0054] Based on this, the classification performance is evaluated by constructing an ROC curve, and the point with the largest Youden Index is selected as the optimal split point. The winding quality risk prediction index (QRI) value corresponding to this point can achieve the best balance between sensitivity and specificity, thereby realizing the effective identification of winding quality risks.

[0055] Based on the above statistical analysis and production experience, the optimal quality risk threshold Qth is determined to be 0.85. When the winding quality risk prediction index QRI ≤ 0.85, the quality risk in the winding production process is within a controllable range; when the winding quality risk prediction index QRI > 0.85, the system determines that there is a quality risk in the winding production process, and it is necessary to trigger the production error prevention control strategy to effectively reduce the probability of winding quality defects.

[0056] In this embodiment, by comparing the winding quality risk prediction index with the quality risk threshold, and implementing quality error prevention and control strategies such as production cycle optimization, winding path correction, and manual inspection prompts when the index exceeds the limit, the probability of quality defects such as electrode misalignment and interlayer displacement during the winding process can be effectively reduced.

[0057] Example 10 For an intelligent error-proofing system for intelligent manufacturing processes based on real-time data interaction, please refer to [link / reference]. Figures 1 to 4 Specifically, including: The winding operation data acquisition module is used to monitor the winding production process of power battery cells for new energy vehicles in real time. It collects raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time position offset of electrode, and motor load current, and performs unified time synchronization marking to establish a basic dataset of winding equipment operation status. The runtime data preprocessing module is used to perform time synchronization alignment, abnormal sampling point removal, time-series filtering and smoothing, and dimensionless normalization on the basic dataset of the winding equipment's operating status. The winding coordination status assessment module is used to calculate the winding coordination offset index and compare it with the coordination offset threshold to determine whether the coordination operation status of the winding process is qualified. If it is not qualified, a coordination adjustment strategy for the winding equipment is given. The equipment stability assessment module is used to calculate the equipment operation coupling stability index and compare it with the stability operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, an equipment stability adjustment strategy is given. The winding quality risk control module is used to calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If it is not, it will provide quality error prevention control strategies, record data and perform feedback analysis to form a closed-loop control mechanism for quality feedback optimization of the winding production process.

[0058] In this embodiment, a complete intelligent error prevention system architecture for the winding production process is formed by setting up a winding operation data acquisition module, an operation data preprocessing module, a winding collaborative status assessment module, an equipment stable operation assessment module, and a winding quality risk control module, thereby realizing real-time monitoring, intelligent assessment, and closed-loop optimization control of the winding production process.

[0059] It should be noted that all calculation formulas in this application employ regression analysis, including but not limited to machine learning algorithms, to deeply analyze the collected parameters and identify their natural trends and interrelationships. Specialized software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Then, cross-validation and other methods are used to objectively evaluate the model performance, and continuous feedback and optimization are combined to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their effectiveness and accuracy. In all calculation formulas in this application, the parameters in each formula undergo dimensionless processing within a consistent range to ensure that different physical quantities are compared on the same scale; dimensionless processing techniques include, but are not limited to, min-max-normalization and Z-score standardization. The algorithm of this invention is implemented as a Python script. Before executing the core logic, the program first executes a data loading module (e.g., using the widely used pandas library in Python) configured to read the aforementioned spreadsheet file and load its contents into the program's working memory (e.g., a DataFrame data structure). Subsequent algorithm steps will directly query and retrieve the required configuration parameters from this in-memory data structure.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent error prevention method for intelligent manufacturing processes based on real-time data interaction, characterized in that: The specific steps include: Step 1: Real-time monitoring of the production process of new energy vehicle power battery cells, collecting raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time electrode position offset, and motor load current, and performing unified time synchronization marking to establish a basic dataset of winding equipment operating status. Step 2: Perform time synchronization and alignment processing, abnormal sampling point removal processing, time-series filtering and smoothing processing, and dimensionless normalization processing on the basic dataset of the winding equipment's operating status. Step 3: Calculate the winding cooperative offset index and compare it with the cooperative offset threshold to determine whether the cooperative operation status of the winding process is qualified. If it is not qualified, a cooperative adjustment strategy for the winding equipment is given. Step 4: Calculate the equipment operation coupling stability index and compare it with the stable operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, provide a stable operation adjustment strategy for the equipment. Step 5: Calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If not, implement quality error prevention control strategies, record and analyze the data to form a closed-loop control mechanism for quality feedback optimization in the winding production process.

2. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 1, characterized in that: Step one includes: S11. Real-time monitoring of the operation status of the electrode unwinding process during the production of power battery cells for new energy vehicles. By installing a strain gauge tension sensor at the guide roller bearing seat of the electrode unwinding mechanism, the tensile tension generated by the electrode during the unwinding process is continuously collected to obtain the original data of the electrode tension. S12. Real-time monitoring of the operation status of the diaphragm unwinding process during the production of power battery cells for new energy vehicles. By installing a cantilever beam tension sensor at the tension control roller position of the diaphragm unwinding mechanism, the force change of the diaphragm material during the unwinding and conveying process is detected in real time, and the raw data of the diaphragm tension is collected. S13. Real-time monitoring of the driving status of the winding spindle during the production of power battery cells for new energy vehicles. By installing an incremental rotary encoder at the output end of the servo motor of the winding spindle, the real-time speed change of the winding spindle is continuously sampled to obtain the original data of the winding spindle speed. S14. Real-time monitoring of the electrode unwinding and conveying speed during the production of power battery cells for new energy vehicles. By installing a photoelectric rotary encoder at the output shaft of the electrode unwinding drive motor, the conveying speed of the electrode unwinding drive mechanism is collected in real time to obtain the raw data of the electrode unwinding speed. S15. Real-time monitoring of the electrode winding position during the production of power battery cells for new energy vehicles. By installing an industrial line array camera in the electrode guide area of ​​the winding station, continuous image acquisition is performed on the electrode edge position. Gray-scale threshold segmentation, Canny edge detection, and sub-pixel edge positioning algorithms are used to extract the electrode edge contour. The pixel offset between the electrode edge contour and the preset reference boundary is calculated and geometric scale conversion is performed to obtain the original data of the electrode real-time position offset. At the same time, by installing a Hall current sensor at the power input end of the winding spindle driver, the operating load current of the winding spindle drive motor is detected in real time to obtain the original data of the motor load current. S16. The collected raw data of electrode tension, diaphragm tension, winding spindle speed, electrode unwinding speed, real-time position offset of electrode, and motor load current are uniformly time-stamped. By installing an industrial time synchronization clock device in the control cabinet of the winding equipment and connecting it to the production equipment control network, the data collected by each sensor are time-stamped according to the unified clock, a unified timestamp is added to each sampled data, and a basic dataset of the winding equipment operating status is established.

3. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 2, characterized in that: Step two includes: S21. Based on the basic dataset of the winding equipment's operating status, various types of raw operating data are time-synchronized and aligned according to a unified timestamp t, abnormal sampling points are removed, time-series filtering and smoothing are performed, and dimensionless normalization is applied. The collected electrode tension raw data are processed according to the time series. The sliding window weighted moving average algorithm is used to perform time-series smoothing on the continuously sampled tension data to eliminate the influence of instantaneous vibration and sampling noise on the tension data, resulting in a smoothed electrode tension sequence. Then, the range normalization method is used to perform dimensionless processing on the smoothed tension data. By calculating the proportional relationship between the current electrode tension value and the historical minimum and maximum values ​​of the electrode tension, the tension parameters are mapped to the [0,1] interval to obtain the electrode tension stability parameters. S22. The collected raw diaphragm tension data is processed by synchronous signal filtering. A second-order Butterworth low-pass filtering algorithm is used to filter out high-frequency disturbances in the tension signal to obtain a stable diaphragm tension signal. Then, the range normalization method is used to perform dimensionless processing on the filtered tension signal. By mapping the real-time value of diaphragm tension with the historical minimum and maximum values ​​of diaphragm tension, it is converted into a dimensionless value of a uniform scale to obtain the diaphragm tension stability parameter. S23. The raw data of the collected winding spindle speed is processed using a periodic averaging algorithm. The continuously sampled speed data is periodically averaged to eliminate the influence of instantaneous fluctuations on speed stability. The rated speed of the winding spindle is obtained by reading the rated speed parameters calibrated on the nameplate of the winding spindle servo motor. Then, the speed data is standardized using the standard deviation normalization method. By proportionally converting the current speed value with the rated speed of the winding spindle, the speed parameters are converted into dimensionless parameters of a uniform scale, thus obtaining the stable speed parameters of the winding spindle. S24. The raw data of electrode unwinding speed is processed using a speed consistency correction algorithm. The difference between the electrode unwinding speed and the theoretical synchronous speed of the winding spindle is calculated, and the speed difference is compensated and corrected to eliminate the speed deviation between the unwinding drive mechanism and the winding spindle. Then, the range normalization method is used to proportionally convert the corrected unwinding speed value with the historical minimum and maximum unwinding speeds to convert the speed parameters into dimensionless values, thus obtaining the unwinding speed parameters. S25. Perform image feature processing on the collected raw data of electrode position offset. Use the Canny edge detection algorithm combined with the sub-pixel edge positioning algorithm to extract the edge contour position of the electrode and calculate the geometric distance deviation between the actual edge position of the electrode and the preset standard edge position of the winding equipment. By reading the allowable offset tolerance parameter of the electrode edge set by the winding equipment during the production debugging stage, obtain the maximum allowable offset of the equipment. Then, through geometric scale conversion and normalization processing methods, convert the pixel offset into the actual physical distance. And by performing proportional normalization processing with the maximum allowable offset of the equipment, obtain the electrode position deviation parameter. S26. The collected raw data of motor load current is processed according to time series. The sliding window averaging algorithm is used to smooth the continuous sampled current values ​​to reduce the impact of instantaneous load fluctuations of the motor on data stability. The rated current of the motor is obtained by reading the rated working current parameters marked on the nameplate of the winding spindle drive motor. Then, the rated current normalization method is used to perform dimensionless processing on the current data. By converting the current motor current value with the rated current of the motor, the current parameters are mapped to a uniform scale range to obtain the load current of the winding spindle drive motor.

4. The intelligent error prevention method for intelligent manufacturing production process based on real-time data interaction according to claim 3, characterized in that: Step three includes: S31. By extracting the electrode tension stability parameters, diaphragm tension stability parameters, winding spindle stable speed parameters, unwinding speed parameters, electrode position deviation parameters, and the maximum allowable offset of the equipment, and after dimensionless processing, the winding cooperative offset index is calculated and obtained.

5. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 4, characterized in that: Step three also includes: S32. By setting a preset cooperative offset threshold and comparing the winding cooperative offset index with the cooperative offset threshold, the first evaluation result is obtained, including: When the winding coordination offset index is less than or equal to the coordination offset threshold, it indicates that the coordination operation status of the winding process is qualified, and the actuators of the winding equipment are in a stable coordination operation state, which is continuously monitored. When the winding collaborative offset index exceeds the collaborative offset threshold, it indicates that the collaborative operation status of the winding process is unqualified, and there is a collaborative operation deviation in the winding equipment, which may lead to the risk of misalignment of the winding electrode edge or stacking offset. This triggers the first warning command and generates the first strategy: based on the comprehensive excess ratio of the winding collaborative offset index relative to the collaborative offset threshold, a comprehensive adjustment ratio for equipment operation is generated, and the winding-related actuators are adjusted collaboratively according to a unified ratio. The electrode unwinding tension is dynamically adjusted by 4% to 10%; the winding spindle running speed is synchronously compensated by 3% to 7%; and the electrode guide mechanism position is automatically corrected by 2% to 5%. After adjustment, the calculation is repeated until the winding collaborative offset index is ≤ the collaborative offset threshold, so that the winding tension, running speed, and electrode guide position converge synchronously to a stable operating range.

6. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 5, characterized in that: Step four includes: S41. By extracting the electrode tension stability parameters, diaphragm tension stability parameters, winding spindle stable speed parameters, and winding spindle drive motor load current, and combining the winding spindle rated speed and motor rated current, the parameters are dimensionlessly normalized, and the equipment operation coupling stability index is calculated.

7. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 6, characterized in that: Step four also includes: S42. By setting a stable operation threshold and comparing the equipment operation coupling stability index with the stable operation threshold, the second evaluation result is obtained, including: When the equipment operation coupling stability index is less than or equal to the stable operation threshold, it indicates that the winding equipment is in a stable load state and that the equipment tension level, winding speed and drive load maintain a stable coupling relationship, which is continuously monitored. When the equipment operation coupling stability index exceeds the stable operation threshold, it indicates that the winding equipment's operating load stability is unqualified, and the equipment faces the risk of operating load coupling, leading to equipment overload operation, decreased winding efficiency, or production cycle fluctuations. This triggers a second warning instruction and generates a second strategy: based on the comprehensive deviation ratio of the equipment operation coupling stability index relative to the stable operation threshold, a comprehensive equipment operation adjustment ratio is generated, and coordinated adjustment is performed on the winding equipment according to a unified ratio. This includes a 5%–15% speed reduction adjustment on the winding spindle operating speed; a 3%–10% synchronous compensation adjustment on the electrode unwinding speed; and a 2%–8% tension compensation adjustment on the tension control system. After adjustment, the calculation is repeated until the equipment operation coupling stability index is ≤ the stable operation threshold, so that the winding equipment's tension level, operating speed, and drive load converge to the stable operation range.

8. The intelligent error prevention method for intelligent manufacturing production processes based on real-time data interaction according to claim 7, characterized in that: Step five includes: S51. Based on the obtained winding cooperative offset index and equipment operation coupling stability index, a comprehensive fusion analysis of the winding process cooperative state and equipment operation load state is performed. After dimensionless processing, the winding quality risk prediction index is calculated and obtained.

9. The intelligent error prevention method for intelligent manufacturing production process based on real-time data interaction according to claim 8, characterized in that: Step five also includes: S52. By setting a preset quality risk threshold and comparing the winding quality risk prediction index with the quality risk threshold, the third assessment results are obtained, including: When the winding quality risk prediction index is less than or equal to the quality risk threshold, it indicates that the current winding production process is in a stable production state, and the winding process coordination and equipment operation status are both within a reasonable range, and continuous monitoring is required. When the winding quality risk prediction index exceeds the quality risk threshold, it indicates that the current winding production process is not in a stable production state and there is a potential risk of quality defects, leading to electrode edge misalignment, interlayer offset, or decreased cell stacking consistency. This triggers a third early warning instruction and generates a third strategy: based on the comprehensive deviation ratio of the winding quality risk prediction index relative to the quality risk threshold, quality error prevention control is implemented in the winding production process, including: adaptive optimization of the production cycle, dynamically adjusting the winding production cycle by 6% to 15% to ensure the winding process operates under a stable cycle, thereby reducing the risk of quality fluctuations caused by high-speed operation; optimization of the winding path, performing accuracy correction of 3% to 8% on the electrode guide path and winding trajectory parameters to improve the interlayer alignment accuracy during the electrode winding process; after adjustment, recalculation is performed. If the winding quality risk prediction index still exceeds the quality risk threshold, manual intervention is initiated, automatically sending a manual inspection prompt to the equipment management terminal, prompting equipment maintenance personnel to conduct on-site inspection and maintenance of the winding equipment guide mechanism, tension control module, and drive system. S53. Once the winding quality risk prediction index returns to a reasonable range, the operating data, evaluation results, and adjustment strategy execution results of this cycle will be automatically written into the production process quality database for subsequent production process analysis and equipment process optimization, forming a closed-loop control mechanism for winding production process quality feedback optimization.

10. An intelligent error-proofing system for intelligent manufacturing processes based on real-time data interaction, applied to the intelligent error-proofing method for intelligent manufacturing processes based on real-time data interaction as described in any one of claims 1 to 9, characterized in that, include: The winding operation data acquisition module is used to monitor the winding production process of power battery cells for new energy vehicles in real time. It collects raw data of electrode tension, separator tension, winding spindle speed, electrode unwinding speed, real-time position offset of electrode, and motor load current, and performs unified time synchronization marking to establish a basic dataset of winding equipment operation status. The runtime data preprocessing module is used to perform time synchronization alignment, abnormal sampling point removal, time-series filtering and smoothing, and dimensionless normalization on the basic dataset of the winding equipment's operating status. The winding coordination status assessment module is used to calculate the winding coordination offset index and compare it with the coordination offset threshold to determine whether the coordination operation status of the winding process is qualified. If it is not qualified, a coordination adjustment strategy for the winding equipment is given. The equipment stability assessment module is used to calculate the equipment operation coupling stability index and compare it with the stability operation threshold to determine whether the load stability of the winding equipment is qualified. If it is not qualified, an equipment stability adjustment strategy is given. The winding quality risk control module is used to calculate the winding quality risk prediction index and compare it with the quality risk threshold to determine whether the current winding production process is in a stable production state. If it is not, it will provide quality error prevention control strategies, record data and perform feedback analysis to form a closed-loop control mechanism for quality feedback optimization of the winding production process.

Images