Nickel strip preparation optimization method and system based on production quality

Abstract

The invention relates to the technical field of nickel strap production, and discloses a nickel strap preparation optimization method and system based on production quality, and the method comprises the steps: obtaining real-time production data in a nickel strap preparation process, and constructing a nickel strap characteristic parameter factor and a process fluctuation factor; calculating a process deviation characterization value of the nickel strip based on the characteristic parameter factor and the process fluctuation factor; dividing a process state label based on the process deviation characterization value; and executing a parameter regulation and control path according to the process state label so as to adjust the rolling pressure, the tension control curve and the heat treatment temperature set value in the nickel strip process. According to the method, a closed-loop control mechanism driven by real-time quality deviation is constructed, and dynamic deviation correction of key process parameters in the nickel strap manufacturing process is achieved.

Description

Technical Field

[0001] This invention relates to the field of nickel strip production technology, and more specifically, to an optimized method and system for nickel strip preparation based on production quality. Background Technology

[0002] Nickel strip, as a metal strip with excellent conductivity, corrosion resistance and certain mechanical strength, is widely used in the manufacturing process of nickel-metal hydride batteries, nickel-cadmium batteries, lithium batteries, combined power modules and various precision instruments.

[0003] In the actual production process of nickel strip, it is usually stored and transported in coil form. In the downstream processing stage, the entire coil of nickel strip needs to be unwound by an unwinding device, and its ends are guided into a continuous stamping or cutting device to further process and shape its structure and dimensions. During this process, the nickel strip passes through multiple processing nodes at a constant speed, forming a continuous flow system of "unwinding-processing-rewinding".

[0004] However, traditional nickel strip preparation and processing systems generally employ open-loop control, meaning that during the strip-making stages such as rolling, annealing, and cleaning, fixed parameters are used, lacking the ability to dynamically monitor and adjust the actual output quality. When batch differences in raw materials, fluctuations in equipment status, or deviations in process execution cause uneven thickness, resistance fluctuations, or surface defects in the nickel strip, these issues are often not identified and reported to the source of the process in a timely manner. This results in substandard strip entering the stamping or cutting process, causing a series of problems such as dimensional errors in processed parts, welding failures, and abnormal connections.

[0005] Especially in multi-point parallel connection structures used in the manufacture of high-density battery modules, even minute dimensional deviations or conductive instabilities can severely affect overall current balance and thermal stability. Therefore, existing nickel strip preparation and processing procedures lack a closed-loop control mechanism that is driven by product quality and can monitor strip quality in real time during the unwinding process and optimize preparation parameters in reverse. Summary of the Invention

[0006] In view of this, the present invention proposes a nickel strip preparation optimization method and system based on production quality, in order to solve the problem that the lack of dynamic feedback and adaptive adjustment mechanism for preparation quality in the prior art leads to the difficulty in timely correction of dimensional deviations, electrical property fluctuations and surface defects in nickel strips during continuous unwinding, thereby affecting the accuracy of subsequent processing.

[0007] On the one hand, the present invention proposes an optimized method for nickel strip preparation based on production quality, comprising:

[0008] Real-time production data during the nickel strip manufacturing process is acquired to construct nickel strip characteristic parameter factors and process fluctuation factors;

[0009] Based on the aforementioned characteristic parameter factor and process fluctuation factor, the process deviation characterization value of the nickel strip is calculated.

[0010] Process status labels are assigned based on the process deviation characterization values;

[0011] The parameter control path is executed according to the process status label to adjust the rolling pressure, tension control curve and heat treatment temperature setting value in the nickel strip manufacturing process.

[0012] Furthermore, the process of constructing the feature parameter factors includes:

[0013] Calculate the ratio of the current nickel strip thickness to the preset thickness reference value, and determine it as the thickness factor;

[0014] Calculate the ratio of the current resistance per unit length to the reference resistance value, and determine it as the resistance factor;

[0015] Calculate the ratio of the current strip tension to the reference tension value, and determine it as the tension factor;

[0016] The thickness factor, resistance factor, and tension factor are weighted and summed to determine the characteristic parameter factor of the nickel strip.

[0017] Furthermore, the process for constructing the process fluctuation factor includes:

[0018] Extract the difference between the maximum and minimum resistance per unit length of the nickel strip, calculate its ratio to the preset resistance fluctuation threshold, and determine it as the first fluctuation factor;

[0019] The ratio of the average period of tension variation in nickel strip to a preset tension period threshold is used to determine the second fluctuation factor.

[0020] The ratio of the maximum temperature difference in the heat treatment zone to the temperature difference threshold is extracted and determined as the third fluctuation factor;

[0021] The process fluctuation factor of the nickel strip is obtained by weighted summation of the first fluctuation factor, the second fluctuation factor and the third fluctuation factor.

[0022] Furthermore, the process of calculating the process deviation characterization value includes:

[0023] The process deviation characterization value is obtained by weighted summation of the characteristic parameter factor and the process fluctuation factor.

[0024] Furthermore, the process of classifying the process status labels includes:

[0025] If the process deviation characterization value is less than the first threshold, it is marked as the first process status label;

[0026] If the process deviation characterization value is greater than or equal to the first threshold and less than the second threshold, it is marked as the second process status label;

[0027] If the process deviation characterization value is greater than or equal to the second threshold, it is marked as the third process status label.

[0028] Furthermore, the process of executing the parameter control path includes:

[0029] If it is marked as the first process status label, then the existing process parameters remain unchanged;

[0030] If it is marked as the second process status label, adjust the rolling pressure, tension control curve or heat treatment temperature setting;

[0031] If the label is marked as the third process status label, then tape production is suspended.

[0032] Furthermore, when it is necessary to adjust the rolling pressure, tension control curve, or heat treatment temperature setting:

[0033] Calculate the sensitivity of rolling pressure, tension control curves, and heat treatment temperature setpoints to the process deviation characterization value; select the parameter corresponding to the maximum sensitivity as the current adjustment target for adjustment.

[0034] After adjustment, repeat the sensitivity calculation, determine the current adjustment object, and adjust again until the real-time process deviation characterization value is less than the first threshold, or the real-time process deviation characterization value is greater than or equal to the second threshold.

[0035] The sensitivity is obtained by the following method:

[0036] For each parameter constituting the process deviation characterization value, take the partial derivative with respect to the target parameter, and determine the sensitivity of the current target parameter to the process deviation characterization value according to the chain rule.

[0037] Further, the difference between the process deviation characterization value and the first threshold is calculated and recorded as the first difference; the difference between the second threshold and the process deviation characterization value is calculated and recorded as the second difference.

[0038] When the current adjustment target is determined to be adjusted, the adjustment range is directly proportional to the first difference, or the adjustment range is inversely proportional to the second difference.

[0039] Furthermore, when calculating the weighted summation of characteristic parameter factors, process fluctuation factors, or process deviation characterization values, the weighting coefficients are obtained through statistical regression analysis of historical batch production data and test results, specifically including:

[0040] A linear regression model of the target quality deviation and each parameter factor is constructed. The parameter weights are fitted using the least squares method or principal component regression. After normalizing the weight coefficients, the final weight coefficients are obtained.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0042] This invention introduces two composite parameters—a characteristic parameter factor and a process fluctuation factor—to weightedly couple the intrinsic performance deviations of nickel strip in dimensions such as thickness, resistance, and tension with dynamic process fluctuations, forming a real-time traceable process deviation characterization value. This systematically reflects the comprehensive quality status of nickel strip during continuous strip production, providing a unified quantitative basis for subsequent decision-making.

[0043] By comparing the process deviation characterization value with the set first and second thresholds, the system can automatically determine whether the nickel strip is currently in a stable, slightly deviated or severely abnormal state, and trigger different levels of process response paths (parameter adjustment or shutdown protection) based on the tag, thus solving the problem that traditional systems can only be fully open or fully closed for control.

[0044] Based on the chain method of automatic derivative calculation of partial derivatives, a sensitivity model of the target parameters (rolling pressure, tension control curve, heat treatment temperature) on the process deviation characterization value is constructed in the field of nickel strip process control.

[0045] Linear regression and principal component regression are used to learn and train historical production batch data, and normalized weight coefficients are automatically generated. This makes the composition of characteristic parameter factors and process fluctuation factors more closely reflect the actual impact on finished product quality, and improves the sensitivity and discrimination accuracy of evaluation indicators to terminal performance.

[0046] On the other hand, the present invention proposes a nickel strip preparation optimization system based on production quality, comprising:

[0047] The acquisition module is configured to acquire real-time production data during the nickel strip preparation process in order to construct nickel strip characteristic parameter factors and process fluctuation factors;

[0048] The first calculation module is configured to calculate the process deviation characterization value of the nickel strip based on the characteristic parameter factor and the process fluctuation factor.

[0049] The second calculation module is configured to divide process status labels based on the process deviation characterization value;

[0050] The adjustment module is configured to execute a parameter control path based on the process status label to adjust the rolling pressure, tension control curve, and heat treatment temperature setting during the nickel strip manufacturing process.

[0051] It should be noted that the nickel strip preparation optimization system and method based on production quality of the present invention have the same beneficial effects, and will not be described in detail here. Attached Figure Description

[0052] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0053] Figure 1 This is a flowchart of an optimized method for nickel strip preparation based on production quality, provided as an embodiment of the present invention.

[0054] Figure 2 This is a functional block diagram of a nickel strip preparation optimization system based on production quality, provided for an embodiment of the present invention. Detailed Implementation

[0055] Exemplary embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, the embodiments and features described herein can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0056] See Figure 1 As shown, this embodiment of the invention provides an optimized method for nickel strip preparation based on production quality, including:

[0057] S1: Obtain real-time production data during the nickel strip preparation process to construct nickel strip characteristic parameter factors and process fluctuation factors;

[0058] S2: Calculate the process deviation characterization value of nickel strip based on characteristic parameter factor and process fluctuation factor;

[0059] S3: Classify process status labels based on process deviation characterization values;

[0060] S4: Executes parameter control path based on process status label to adjust rolling pressure, tension control curve and heat treatment temperature setting value during nickel strip manufacturing process.

[0061] It should be noted that real-time production data during the nickel strip manufacturing process is acquired, specifically including online monitoring data of nickel strip thickness, resistance, tension, and heat treatment temperature. This data, after preprocessing and standardization, is used to construct characteristic parameter factors reflecting the quality characteristics of the nickel strip. Simultaneously, resistance fluctuation amplitude, tension periodic changes, and heat treatment temperature fluctuations are extracted over time to form process fluctuation factors.

[0062] In some embodiments of this application, the process of constructing the feature parameter factors includes:

[0063] Calculate the ratio of the current nickel strip thickness to the preset thickness reference value, and determine it as the thickness factor;

[0064] Calculate the ratio of the current resistance per unit length to the reference resistance value, and determine it as the resistance factor;

[0065] Calculate the ratio of the current strip tension to the reference tension value, and determine it as the tension factor;

[0066] The thickness factor, resistance factor, and tension factor are weighted and summed to determine the characteristic parameter factors of the nickel strip.

[0067] It should be noted that the thickness reference value, resistance reference value, and tension reference value are standard values ​​in the target product design requirements. In this embodiment, the detection steps for resistance per unit length are as follows: a non-contact resistance detection station is set up on the unwinding or rewinding path of the nickel strip, and elastic clamps or roller electrodes are used to contact the strip, maintaining a constant measurement path length, and through... p An LC or industrial computer continuously reads voltage and current signals and calculates the resistance per unit length in real time. Additionally, a temperature compensation module can be set to correct for the effects of thermal drift.

[0068] In some embodiments of this application, the process for constructing the process fluctuation factor includes:

[0069] Extract the difference between the maximum and minimum resistance per unit length of the nickel strip, calculate its ratio to the preset resistance fluctuation threshold, and determine it as the first fluctuation factor;

[0070] The ratio of the average period of tension variation in nickel strip to a preset tension period threshold is used to determine the second fluctuation factor.

[0071] The ratio of the maximum temperature difference in the heat treatment zone to the temperature difference threshold is extracted and determined as the third fluctuation factor;

[0072] The process fluctuation factor of nickel strip is obtained by weighted summation of the first fluctuation factor, the second fluctuation factor and the third fluctuation factor.

[0073] It should be noted that, firstly, multiple real-time data points of the resistance per unit length of the nickel strip are acquired within a set detection time period, and the maximum and minimum values ​​within that time period are extracted. The difference between the maximum and minimum values ​​is taken as the resistance fluctuation amplitude within that time period. This resistance fluctuation amplitude is then compared with a preset resistance fluctuation threshold, and the result is defined as the first fluctuation factor, which is used to characterize the stability of the conductivity.

[0074] Secondly, tension data sequences recorded by tension sensors during the operation of the nickel strip are collected, and the periodicity of tension changes is analyzed based on these data sequences to extract the average value of the tension change period. The ratio of the average value of the tension change period to a preset tension period threshold is calculated, and the result is defined as the second fluctuation factor, which is used to characterize the mechanical stability of the strip during movement.

[0075] Next, temperature data from various temperature monitoring points in the heat treatment zone are acquired within the same time period, and the highest and lowest temperature values ​​are identified. The difference between the two values ​​is calculated as the maximum temperature difference within that time period. This maximum temperature difference is then compared with a set temperature difference threshold, and the result is defined as the third fluctuation factor, which reflects the uniformity of the temperature field during the heat treatment process.

[0076] Finally, the first, second, and third fluctuation factors are weighted and summed according to preset weighting coefficients. The resulting value is defined as the process fluctuation factor, which serves as the dynamic process state input variable in the calculation of process deviation characterization values, comprehensively reflecting the fluctuation degree of various key quality influencing factors during nickel strip production. This method of obtaining the process fluctuation factor can effectively characterize the stability of the nickel strip process, providing a quantitative basis for subsequent process adjustment strategies.

[0077] In some embodiments of this application, the process of calculating the process deviation characterization value includes:

[0078] The process deviation characterization value is obtained by weighting and summing the characteristic parameter factor and the process fluctuation factor.

[0079] In some embodiments of this application, the process of dividing process status labels includes:

[0080] If the process deviation characterization value is less than the first threshold, it is marked as the first process status label;

[0081] If the process deviation characterization value is greater than or equal to the first threshold and less than the second threshold, it is marked as the second process status label;

[0082] If the process deviation characterization value is greater than or equal to the second threshold, it is marked as the third process status label.

[0083] In some embodiments of this application, the process of executing the parameter control path includes:

[0084] If it is marked as the first process status label, then the existing process parameters remain unchanged;

[0085] If it is marked as the second process status label, adjust the rolling pressure, tension control curve or heat treatment temperature setting;

[0086] If the label is marked as the third process status label, then tape production is suspended.

[0087] It should be noted that the process status label classification process is based on the distribution of process deviation characterization values ​​within different threshold ranges to classify and judge the quality stability and its changing trend during the nickel strip manufacturing process.

[0088] The first process status label is used to indicate that the current process quality is stable and there is no significant deviation. Therefore, the existing process parameters are kept unchanged to avoid increased oscillation or disturbance in the control system caused by frequent adjustments.

[0089] The second process status label indicates that fluctuations within a controllable range in the process status indicate that the process is in a critical deviation stage. At this point, the parameter control path is triggered. By adjusting the rolling pressure, tension control curve, or heat treatment temperature setpoint, proactive intervention and correction of the process trend can be achieved to suppress potential quality risks. The adjustment of the three types of parameters has a certain priority selection order. Usually, the sensitivity of the target parameter to the process deviation characterization value is evaluated first, and then the adjustment object is determined according to the sensitivity magnitude to avoid instability of the feedback path caused by concurrent adjustment of multiple parameters.

[0090] The third process status label indicates that the process has exceeded the acceptable fluctuation range, posing a significant quality risk or potential non-conformity risk. The purpose of pausing the strip production process in this state is to prevent strip defects from continuing to propagate into downstream processing stages, while also providing a window for manual intervention or automatic fault diagnosis and analysis. Pausing not only halts the strip's movement but can also simultaneously trigger equipment status self-checks, data cache analysis, or alarm prompts in critical process stages, thereby enhancing the system's closed-loop error correction capabilities.

[0091] Furthermore, when the status label changes, a multi-cycle judgment mechanism can be selected, meaning the corresponding path is only executed if the same status occurs twice or more consecutively, reducing the risk of misjudgment caused by a single point of failure. In practical applications, a "fluctuation buffer" or "soft trigger threshold" can also be set to provide early warning or record fluctuation trends when the threshold is approached, assisting in state switching judgment and improving the system's response accuracy and stability.

[0092] It should be noted that the first threshold and the second threshold are calculated and obtained through the following steps:

[0093] Step 1: Obtain process performance requirements and product allowable deviation range: Based on the design specifications and usage requirements of the target product, preset the allowable deviation range of the following indicators: maximum allowable deviation of nickel strip thickness ΔHmax, maximum allowable deviation of nickel strip resistance per unit length ΔRmax, maximum allowable value of nickel strip tension fluctuation ΔNmax, and maximum allowable value of heat treatment zone temperature fluctuation ΔTmax.

[0094] The above indicators are derived from downstream welding adaptation requirements, electrical performance stability requirements, and structural assembly tolerance limits, respectively.

[0095] Step 2: Establish the correspondence between deviation tolerance and functional performance: Based on the impact of changes in nickel strip size, resistance, and tension on functional performance (such as solder joint reliability, current consistency, and module thermal uniformity) in practical applications, the following parameter mapping model is established:

[0096] Model of the influence of ΔH on the weld lap area S:

[0097] ;

[0098] Model of the influence of ΔR on the parallel flow capacity I:

[0099] ;

[0100] Model of the influence of ΔT on processing stability rate F:

[0101] ;

[0102] Where k1, k2, k3 are sensitivity coefficients obtained by fitting experimental data, and σ T This represents the standard deviation of tension fluctuation.

[0103] Step 3: Construct the risk tolerance function and deduce the process deviation characterization threshold: Based on the above performance function and deviation mapping, define the joint tolerance evaluation function:

[0104] ;

[0105] Where w1, w2, w3, and w4 are weighting coefficients set according to the importance of the process, and w1+w2+w3+w4=1.

[0106] Set the threshold values ​​for the risk tolerance function: the first threshold corresponds to a risk tolerance function Ψ of 0.6, which represents the upper limit of the acceptable range; the second threshold corresponds to a Ψ of 0.9, which indicates that the risk boundary has been significantly exceeded and the line needs to be stopped.

[0107] Then, based on historical process data and the current weighting system, the process deviation characterization values ​​corresponding to Ψ=0.6 and Ψ=0.9 are deduced and denoted as the first threshold D1 and the second threshold D2, respectively.

[0108] function This represents the total deviation contribution value derived from the Ψ function by reversing the combined parameter factors.

[0109] In some embodiments of this application, when it is necessary to adjust the rolling pressure, tension control curve, or heat treatment temperature setting:

[0110] Calculate the sensitivity of rolling pressure, tension control curves, and heat treatment temperature setpoints to the process deviation characterization value; select the parameter corresponding to the maximum sensitivity as the current adjustment target for adjustment.

[0111] After adjustment, repeat the sensitivity calculation, determine the current adjustment object, and adjust again until the real-time process deviation characterization value is less than the first threshold, or the real-time process deviation characterization value is greater than or equal to the second threshold.

[0112] The sensitivity was obtained using the following method:

[0113] For each parameter constituting the process deviation characterization value, take the partial derivative with respect to the target parameter, and determine the sensitivity of the current target parameter to the process deviation characterization value according to the chain rule.

[0114] Specifically, the sensitivity calculation of the target parameters involves calculating the sensitivity of the three key process control parameters—rolling pressure (P), tension control curve adjustment factor (T), and heat treatment temperature setpoint (θ)—to the process deviation characterization value (D), expressed as follows:

[0115] First sensitivity ;

[0116] Second sensitivity ;

[0117] Third Sensitivity ;

[0118] Since the process deviation characterization value D is composed of a weighted sum of multiple sub-factors (including thickness factor, resistance factor, tension factor, and process fluctuation factor, etc.), and these sub-factors are themselves indirectly affected by P, T, and θ, a sensitivity transmission path is constructed using the chain rule:

[0119] , ;

[0120] Where wi is the weighting coefficient. This is a component of process deviation.

[0121] The partial derivatives can be determined by the following methods:

[0122] Fitting and modeling are performed based on historical sample data; numerical differentiation is performed using real-time changing data; and numerical back-calculation is performed using process simulation models.

[0123] In some embodiments of this application, the difference between the process deviation characterization value and the first threshold is calculated and denoted as the first difference; the difference between the second threshold and the process deviation characterization value is calculated and denoted as the second difference.

[0124] When the current adjustment target is determined to be adjusted, the adjustment range is directly proportional to the first difference, or the adjustment range is inversely proportional to the second difference.

[0125] It should be noted that when automatically adjusting process parameters, a proportional or inverse amplitude adjustment strategy is adopted based on the distribution relationship between the process deviation characterization value and the set threshold, in order to adapt to the response sensitivity requirements under different operating conditions.

[0126] Definition and applicable situations of proportional adjustment:

[0127] Proportional adjustment means that the adjustment range has a positive linear relationship with the difference between the current process deviation value and the first threshold (i.e., the first difference). The larger the first difference, the further the current state deviates from the ideal process, so the adjustment range is automatically amplified to achieve rapid correction.

[0128] This strategy is suitable when the system is in a slightly deviated state and the adjustment of the selected target parameter has a clear monotonic trend. By adjusting the parameter by a large margin, the system can quickly approach the ideal state and reduce the response time.

[0129] Definition and applicable situations of inverse adjustment:

[0130] Inversely proportional adjustment refers to the inverse relationship between the adjustment magnitude and the difference between the process deviation characterization value and the second threshold (i.e., the second difference). As the current state gradually approaches the second threshold (i.e., nearing the severe anomaly boundary), the adjustment magnitude is automatically reduced to avoid drastic fluctuations in process parameters due to over-adjustment, thereby preventing unstable behavior.

[0131] This strategy is suitable for situations where the process is nearing its upper limit risk zone or where the system requires high adjustment accuracy, and can effectively suppress oscillation and over-adjustment risks.

[0132] In some embodiments of this application, when calculating the weighted summation of characteristic parameter factors, process fluctuation factors, or process deviation characterization values, the weighting coefficients are obtained through statistical regression analysis of historical batch production data and test results, specifically including:

[0133] A linear regression model of the target quality deviation and each parameter factor is constructed. The parameter weights are fitted using the least squares method or principal component regression. After normalizing the weight coefficients, the final weight coefficients are obtained.

[0134] Specifically, a multiple linear regression model is first constructed, with the target quality deviation as the response variable and various parameter factors (such as thickness factor, resistance factor, tension factor, and various process fluctuation factors) as explanatory variables. The goal of this model is to describe and quantify the influence of each parameter factor on the final process quality deviation. In the model solution phase, one of the following two methods can be used:

[0135] Least squares method: This method aims to minimize the sum of squared residuals between the predicted and actual quality deviations by fitting linear weights for each parameter factor. It is suitable for scenarios where the correlation between factors is low and the model structure is well-defined.

[0136] Principal component regression method: When there is multicollinearity or redundant information among multiple parameter factors, principal component analysis is first performed on the original factor set to extract the principal components before regression fitting, so as to improve the fitting stability and the model's anti-interference ability.

[0137] After completing the regression analysis, the original weight coefficients of each parameter factor obtained by fitting are uniformly normalized to ensure that all weight values ​​fall within a relatively controllable numerical range. They are usually uniformly converted into proportional coefficients with a sum of one, so that they can be directly used in the subsequent weighted calculation of characteristic parameter factors, process fluctuation factors and process deviation characterization values.

[0138] It is important to emphasize that this weight training process can be adaptively updated at set intervals. For example, data can be collected again and the regression model reconstructed after every 100 batches of products are produced, or incremental training and model iteration can be performed after a specific quality fluctuation event occurs. By introducing a data-driven weight learning mechanism, long-term adaptation to changes in production conditions and enhanced model robustness can be achieved.

[0139] See Figure 2 As shown, this embodiment of the invention provides a nickel strip preparation optimization system based on production quality, comprising:

[0140] The acquisition module is configured to acquire real-time production data during the nickel strip preparation process in order to construct nickel strip characteristic parameter factors and process fluctuation factors;

[0141] The first calculation module is configured to calculate the process deviation characterization value of nickel strip based on the characteristic parameter factor and the process fluctuation factor.

[0142] The second calculation module is configured to divide process status labels based on process deviation characterization values;

[0143] The adjustment module is configured to execute parameter control paths based on process status labels to adjust the rolling pressure, tension control curve, and heat treatment temperature settings during the nickel strip manufacturing process.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An optimized method for nickel strip preparation based on production quality, characterized in that, include: Real-time production data during the nickel strip manufacturing process is acquired to construct nickel strip characteristic parameter factors and process fluctuation factors; Based on the aforementioned characteristic parameter factor and process fluctuation factor, the process deviation characterization value of the nickel strip is calculated. Process status labels are assigned based on the process deviation characterization values; The parameter control path is executed according to the process status label to adjust the rolling pressure, tension control curve and heat treatment temperature setting value in the nickel strip manufacturing process.

2. The optimized method for nickel strip preparation based on production quality according to claim 1, characterized in that, The process of constructing the feature parameter factors includes: Calculate the ratio of the current nickel strip thickness to the preset thickness reference value, and determine it as the thickness factor; Calculate the ratio of the current resistance per unit length to the reference resistance value, and determine it as the resistance factor; Calculate the ratio of the current strip tension to the reference tension value, and determine it as the tension factor; The thickness factor, resistance factor, and tension factor are weighted and summed to determine the characteristic parameter factor of the nickel strip.

3. The optimized method for nickel strip preparation based on production quality according to claim 2, characterized in that, The process of constructing the process fluctuation factor includes: Extract the difference between the maximum and minimum resistance per unit length of the nickel strip, calculate its ratio to the preset resistance fluctuation threshold, and determine it as the first fluctuation factor; The ratio of the average period of tension variation in nickel strip to a preset tension period threshold is used to determine the second fluctuation factor. The ratio of the maximum temperature difference in the heat treatment zone to the temperature difference threshold is extracted and determined as the third fluctuation factor; The process fluctuation factor of the nickel strip is obtained by weighted summation of the first fluctuation factor, the second fluctuation factor and the third fluctuation factor.

4. The optimized method for nickel strip preparation based on production quality according to claim 1, characterized in that, The process of calculating the process deviation characterization value includes: The process deviation characterization value is obtained by weighted summation of the characteristic parameter factor and the process fluctuation factor.

5. The optimized method for nickel strip preparation based on production quality according to claim 4, characterized in that, The process of dividing the process status labels includes: If the process deviation characterization value is less than the first threshold, it is marked as the first process status label; If the process deviation characterization value is greater than or equal to the first threshold and less than the second threshold, it is marked as the second process status label; If the process deviation characterization value is greater than or equal to the second threshold, it is marked as the third process status label.

6. The optimized method for nickel strip preparation based on production quality according to claim 5, characterized in that, The process of executing the parameter control path includes: If it is marked as the first process status label, then the existing process parameters remain unchanged; If it is marked as the second process status label, adjust the rolling pressure, tension control curve or heat treatment temperature setting; If the label is marked as the third process status label, then tape production is suspended.

7. The optimized method for nickel strip preparation based on production quality according to claim 1, characterized in that, When it is necessary to adjust the rolling pressure, tension control curve, or heat treatment temperature setting: Calculate the sensitivity of rolling pressure, tension control curves, and heat treatment temperature setpoints to the process deviation characterization value; select the parameter corresponding to the maximum sensitivity as the current adjustment target for adjustment. After adjustment, repeat the sensitivity calculation, determine the current adjustment object, and adjust again until the real-time process deviation characterization value is less than the first threshold, or the real-time process deviation characterization value is greater than or equal to the second threshold. The sensitivity is obtained by the following method: For each parameter constituting the process deviation characterization value, take the partial derivative with respect to the target parameter, and determine the sensitivity of the current target parameter to the process deviation characterization value according to the chain rule.

8. The optimized method for nickel strip preparation based on production quality according to claim 1, characterized in that, The difference between the process deviation characterization value and the first threshold is calculated and denoted as the first difference. Calculate the difference between the second threshold and the process deviation characterization value, and denot it as the second difference; When the current adjustment target is determined to be adjusted, the adjustment range is directly proportional to the first difference, or the adjustment range is inversely proportional to the second difference.

9. The method for optimizing nickel strip preparation based on production quality according to claim 1, characterized in that, When calculating the weighted summation of characteristic parameter factors, process fluctuation factors, or process deviation characterization values, the weighting coefficients are obtained through statistical regression analysis of historical batch production data and test results, specifically including: A linear regression model of the target quality deviation and each parameter factor is constructed. The parameter weights are fitted using the least squares method or principal component regression. After normalizing the weight coefficients, the final weight coefficients are obtained.

10. A nickel strip preparation optimization system based on production quality, characterized in that, To implement the method according to any one of claims 1-9, comprising: The acquisition module is configured to acquire real-time production data during the nickel strip preparation process in order to construct nickel strip characteristic parameter factors and process fluctuation factors; The first calculation module is configured to calculate the process deviation characterization value of the nickel strip based on the characteristic parameter factor and the process fluctuation factor. The second calculation module is configured to divide process status labels based on the process deviation characterization value; The adjustment module is configured to execute a parameter control path based on the process status label to adjust the rolling pressure, tension control curve, and heat treatment temperature setting during the nickel strip manufacturing process.

Images