A data-driven pump head design parameter intelligent optimization system and method

Abstract

The application discloses a kind of data-driven pump head design parameter intelligent optimization system and method, it is related to computer aided design technical field, including: the viscosity value of target emulsion, target liquid discharge and maximum allowable rebound time are obtained;Based on the spring elastic coefficient of pump head model, maximum compression stroke and fluid resistance peak, spring thrust-fluid resistance matching degree is calculated;Combining measured liquid discharge, measured rebound time and emulsion viscosity data, calculate liquid discharge adaptation, rebound speed matching index and viscosity difference degree;Fusion is carried out to each evaluation index, and comprehensive performance matching index is generated;According to the comprehensive performance matching index, the pump head model is sorted, and the optimal pump head model recommendation result and parameter adjustment suggestion are output.The application solves the technical problems that it is difficult to quickly and accurately determine the pump head model and optimization parameters matched with the target emulsion in the prior art.

Description

Technical Field

[0001] This invention relates to the field of computer-aided design technology, specifically to a data-driven intelligent optimization system and method for pump head design parameters. Background Technology

[0002] With the rapid development of the daily chemical, cosmetic, pharmaceutical, and food packaging industries, the variety of emulsion products is constantly increasing, and different products vary significantly in terms of viscosity, flow characteristics, and usage requirements. As a crucial component in emulsion packaging, the structural parameters of the pump head directly affect the product's dispensing volume, pressing feel, rebound speed, and long-term stability. Therefore, selecting or optimizing the appropriate pump head model based on the characteristics of the target emulsion has become a key issue in pump head design and product development.

[0003] In existing technologies, the selection of pump head models and parameter design mainly rely on engineering experience, repeated prototyping tests, or comparison of single performance indicators. For example, pump head models are selected solely based on the required liquid output, or simple matching analysis is performed based only on spring parameters. However, in practical applications, pump head performance is affected by multiple factors, including spring constant, maximum compression stroke, fluid resistance, and emulsion viscosity, with complex coupling relationships among these factors. Existing methods struggle to comprehensively evaluate the matching between pump head thrust and fluid resistance, and also fail to simultaneously consider the impact of liquid output requirements, rebound time requirements, and differences in emulsion viscosity on actual performance. Furthermore, the utilization rate of historical test data for different emulsions is low, failing to fully explore performance matching patterns in historical samples, resulting in low pump head selection efficiency, long optimization cycles, and insufficient result stability.

[0004] Therefore, there is an urgent need for a data-driven intelligent optimization system for pump head design parameters. This system should be able to comprehensively utilize emulsion viscosity, target output volume, rebound time requirements, and historical test data to quantitatively analyze the matching degree between pump head models and target application requirements. This would enable intelligent recommendation of pump head models and parameter optimization, thereby improving the accuracy of pump head selection and design efficiency. Summary of the Invention

[0005] This invention provides a data-driven intelligent optimization system and method for pump head design parameters to address the problems in the prior art where pump head selection and parameter design mainly rely on experience-based judgment, making it difficult to comprehensively consider the coupling relationship between multiple factors such as emulsion viscosity, target output volume, and rebound performance. This results in insufficient accuracy in assessing the compatibility between the pump head and the emulsion, low design optimization efficiency, and the inability to achieve intelligent prediction and parameter optimization of pump head performance based on historical test data.

[0006] The technical solution of the present invention to solve the above-mentioned technical problems is as follows: In a first aspect, the present invention provides a data-driven intelligent optimization system for pump head design parameters, comprising: The data acquisition module is used to acquire the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of the candidate pump head models. The thrust-drag matching analysis module, connected to the data acquisition module, is used to analyze and obtain the spring thrust-fluid resistance matching degree of each candidate pump head model for the target emulsion based on the spring elastic coefficient, maximum compression stroke and fluid resistance peak value in the specification parameters and historical test data. The performance adaptation evaluation module is connected to the data acquisition module. It is used to combine the measured liquid output, measured rebound time and corresponding emulsion viscosity in historical test data to calculate the liquid output adaptation degree, rebound speed matching index and viscosity difference. The comprehensive performance analysis module is connected to the thrust-drag matching analysis module and the performance adaptation evaluation module, respectively. It is used to perform integrated analysis on the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference, and generate a comprehensive performance matching index. Intelligent recommendation and optimization module. Connected to the comprehensive performance analysis module, it sorts candidate pump head models based on the comprehensive performance matching index, outputs the optimal pump head model recommendation result and parameter adjustment suggestions.

[0007] Secondly, this invention provides a data-driven intelligent optimization method for pump head design parameters, comprising: Obtain the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of the candidate pump head models. The specifications include the spring constant and maximum compression stroke, and the historical test data includes the peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity of each pump head model under different emulsion viscosity. Based on the spring elastic coefficient, maximum compression stroke and peak fluid resistance, the spring thrust-fluid resistance matching degree of each pump head model corresponding to the target emulsion is analyzed and obtained. By combining the deviation between the measured liquid output and the target liquid output, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion and the viscosity of each corresponding emulsion, the liquid output matching degree, rebound speed matching index and viscosity difference are calculated and obtained. The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference are integrated into a comprehensive performance matching index; The pump head models are sorted according to the comprehensive performance matching index, and the optimal pump head model recommendation and parameter adjustment suggestions are output.

[0008] One or more technical solutions provided in this invention have at least the following technical effects or advantages: This invention provides a data-driven intelligent optimization system and method for pump head design parameters. By acquiring the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, and combining the specifications of candidate pump head models and historical test data, it constructs multi-dimensional performance evaluation indicators such as spring thrust-fluid resistance matching degree, output volume adaptability, rebound speed matching index, and viscosity difference, thereby realizing quantitative matching analysis between pump head performance and target application requirements.

[0009] Furthermore, by integrating and calculating the comprehensive performance matching index of various evaluation indicators, and sorting and optimizing the pump head models based on the comprehensive performance matching index, the pump head selection process has been transformed from experience-based judgment to data-driven decision-making.

[0010] By using the above methods, the compatibility between different pump head models and target emulsions can be comprehensively evaluated, thereby improving the accuracy of pump head selection and the efficiency of design optimization, reducing the cost of experimental verification, and providing reliable technical support for the design, development, and parameter optimization of pump head products. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of a data-driven intelligent optimization system module for pump head design parameters provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a data-driven intelligent optimization method for pump head design parameters provided in an embodiment of the present invention.

[0012] In the attached diagram, the components represented by each number are as follows: Data acquisition module 11, thrust-drag matching analysis module 12, performance adaptation evaluation module 13, comprehensive performance analysis module 14, and intelligent recommendation optimization module 15. Detailed Implementation

[0013] This invention provides a data-driven intelligent optimization system and method for pump head design parameters, which specifically solves the technical problem that existing technologies cannot quickly and accurately determine the pump head model and optimization parameters that match the target emulsion.

[0014] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0015] Example 1, as Figure 1As shown, this embodiment of the invention provides a data-driven intelligent optimization system for pump head design parameters, including: Data acquisition module 11 is used to acquire the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of candidate pump head models, including: The viscosity value, target output volume, and maximum allowable rebound time of the target emulsion are obtained. The viscosity value is the dynamic viscosity value measured by a standard viscometer at a specified temperature and speed. The target output volume is the volume of emulsion expected to be pumped out in a single standard press stroke. The maximum allowable rebound time is the longest time allowed for the pump head to bounce back from the lowest point to the highest point. Obtain the spring constant and maximum compression stroke of each pump head model as specification parameters. The spring constant is the force required for the spring to produce a unit compression deformation within its elastic range, and the maximum compression stroke is the maximum displacement of the pump head from its initial position to the bottom. The peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity were recorded during the dispensing test of each pump head model under emulsions of different viscosity. These were used as historical test data. The peak fluid resistance was the maximum fluid resistance encountered by the piston during the standard pressing process. The measured output volume was the actual volume of emulsion that flowed out under the standard pressing stroke. The measured rebound time was the time from the end of pressing to the moment when the pump head rebounded to the initial position.

[0016] In this embodiment, the target emulsion viscosity value refers to the dynamic viscosity value measured by a standard viscometer under preset temperature and rotation speed conditions, which is used to characterize the rheological properties and flow resistance of the target emulsion during the flow process.

[0017] The spring constant refers to the restoring force corresponding to a unit compression displacement within the elastic deformation range of a spring, and is used to characterize the rebound driving capability of a pump head spring.

[0018] Peak fluid resistance refers to the maximum fluid resistance encountered by the piston during standard pressing, used to characterize the degree of obstruction of emulsion flow to the pump head outlet and rebound process.

[0019] First, obtain the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion to determine the corresponding output requirements and rebound performance requirements of the target emulsion.

[0020] Subsequently, the spring constant and maximum compression stroke corresponding to each pump head model were obtained as specification parameters, and a correspondence between pump head model and specification parameters for quality inspection was established. Since the spring constant determines the magnitude of the rebound driving force after the pressure head is released, and the maximum compression stroke determines the pump cavity volume change capability and theoretical liquid output capacity, the two can reflect the influence of pump head structural characteristics on liquid output performance and rebound performance.

[0021] Furthermore, the peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity were recorded during dispensing tests of each pump head model under different emulsion viscosity conditions, serving as historical test data. All tests were conducted under a standardized pressing stroke. A standard pressing stroke refers to a complete pressing action performed using a standardized testing fixture according to preset pressing parameters. This includes continuously pressing the pump head from its initial position to its maximum compression stroke at a preset pressing speed, holding it at the lowest point for a preset time, and then releasing it, allowing the pump head to naturally rebound to its initial position. The pressing speed, pressing depth, holding time, and release method were kept consistent to ensure the comparability and repeatability of test results for different pump head models.

[0022] The peak fluid resistance is defined as the maximum fluid resistance experienced by the piston during standard compression. Specifically, a pressure sensor is placed inside the pump chamber or in a flow channel connected to the pump chamber during the test to collect fluid pressure data in real time. The fluid resistance during piston movement is determined based on the pressure signal, and the maximum fluid resistance within the entire standard compression stroke is defined as the peak fluid resistance. Subsequently, the test results are correlated with the spring constant and maximum compression stroke of the corresponding pump head model to form a historical sample dataset.

[0023] The input parameters in the historical sample dataset include emulsion viscosity, spring constant, maximum compression stroke, and peak fluid resistance. The output parameters include measured liquid output and measured rebound time. By establishing the correspondence between structural parameters, fluid characteristic parameters, and performance result parameters, the performance of different pump head structures under different emulsion conditions is comprehensively reflected, providing training data samples for subsequent construction of pump head performance prediction models and design parameter optimization models.

[0024] For example, the historical dataset includes pump heads P-01 and P-02. P-01 has a spring of 25 N / mm and a maximum compression stroke of 12 mm. When testing an emulsion at 1500 mPa·s, the peak fluid resistance is 12 N, the measured output is 1.8 mL, and the measured rebound time is 0.35 s. When testing an emulsion at 3000 mPa·s, the peak fluid resistance is 18 N, the measured output is 1.7 mL, and the measured rebound time is 0.42 s. P-02 has a spring of 30 N / mm and a maximum compression stroke of 10 mm. When testing an emulsion at 1500 mPa·s, the peak fluid resistance is 14 N, the measured output is 1.9 mL, and the measured rebound time is 0.33 s. When testing an emulsion at 3000 mPa·s, the peak fluid resistance is 20 N, the measured output is 1.8 mL, and the measured rebound time is 0.40 s.

[0025] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0026] In summary, by acquiring the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, and establishing a historical sample dataset containing pump head specifications and historical test data, a correlation mapping between emulsion rheological properties, pump head structural parameters, and actual performance results was achieved. This comprehensively reflects the output performance and rebound performance of different pump head structures under different emulsion operating conditions, providing a reliable data foundation for subsequent construction of pump head performance prediction models, intelligent pump head selection, and design parameter optimization, thereby improving the accuracy, adaptability, and optimization efficiency of pump head design.

[0027] The thrust-resistance matching analysis module 12, based on the spring constant, maximum compression stroke, and peak fluid resistance, analyzes and obtains the spring thrust-fluid resistance matching degree for the target emulsion corresponding to each pump head model, including: Multiply the spring constant by the maximum compression stroke to obtain the maximum spring rebound thrust; Calculate the maximum spring rebound thrust by dividing it by the sum of the maximum spring rebound thrust and the peak fluid resistance to obtain the spring thrust-fluid resistance matching degree.

[0028] In this embodiment, the maximum spring rebound thrust refers to the maximum outward thrust generated when the spring is released after being compressed to its maximum stroke. It is used to characterize the ability of the spring to drive the pump head to rebound and reset, as well as the strength of its ability to overcome fluid resistance, sealing friction resistance, and mechanism motion resistance.

[0029] The spring thrust-fluid resistance matching degree refers to the ratio of the maximum spring rebound thrust to the sum of the maximum spring rebound thrust and the peak fluid resistance. It is used to characterize the degree of matching between the spring rebound capability and the fluid resistance. The closer this parameter value is to 1, the better the spring rebound thrust can overcome the fluid resistance generated by the target viscosity emulsion, and the more sufficient the pump head rebound margin. The closer this parameter value is to 0, the higher the proportion of fluid resistance, the relatively insufficient spring thrust, and the risk of rebound lag or insufficient reset during the pump head rebound process.

[0030] First, obtain the spring constant and the maximum compression stroke of the pump head. The maximum rebound thrust of the spring is calculated as follows: maximum rebound thrust of the spring = spring constant × maximum compression stroke.

[0031] Furthermore, the spring thrust-fluid resistance matching degree is calculated as follows: Spring thrust-fluid resistance matching degree = Maximum spring rebound thrust ÷ (Maximum spring rebound thrust + Peak fluid resistance): For example, when the spring constant is 800 N / m and the maximum compression stroke is 0.02 m, the maximum spring rebound thrust is 800 × 0.02 = 16 N. When the peak fluid resistance is 10 N, the spring thrust-fluid resistance matching degree is approximately 16 ÷ (16 + 10) = 0.615, indicating that the spring rebound thrust and fluid resistance have good matching, which can ensure stable pump head rebound and smooth liquid discharge.

[0032] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0033] In summary, by obtaining the spring elastic coefficient, maximum compression stroke, and peak fluid resistance of the pump head, and constructing an evaluation index for the matching degree of spring thrust and fluid resistance, we can quantitatively characterize the matching relationship between the pump head's rebound driving force and fluid resistance, accurately evaluate the supporting effect of the spring rebound capability on the emulsion delivery process, and thus provide a reliable basis for subsequent pump head liquid discharge performance analysis, rebound performance evaluation, and structural parameter optimization, thereby improving the pump head's rebound stability, liquid discharge consistency, and overall adaptability under target emulsion conditions.

[0034] The performance adaptation evaluation module 13, combining the deviation between the measured output volume and the target output volume, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion and the viscosity of each corresponding emulsion, calculates and obtains the output volume adaptation degree, rebound speed matching index, and viscosity difference degree, including: Calculate the deviation between the measured liquid output and the target liquid output, obtain the liquid output deviation ratio, and calculate the liquid output fit based on the liquid output deviation ratio. The liquid output fit is negatively correlated with the liquid output deviation ratio. The ratio of the measured rebound time to the maximum allowable rebound time is calculated as the rebound time ratio, and the rebound speed matching index is calculated based on the rebound time ratio. The rebound speed matching index is negatively correlated with the rebound time ratio. The viscosity deviation ratio is obtained by calculating the ratio of the absolute difference between the viscosity value of the target emulsion and the viscosity of the corresponding emulsion to the maximum permissible deviation of viscosity. Based on the viscosity deviation ratio, the viscosity difference degree is calculated, where the viscosity difference degree is inversely proportional to the viscosity deviation ratio.

[0035] In this embodiment, the liquid output deviation ratio refers to the ratio of the absolute difference between the measured liquid output and the target liquid output to the target liquid output, which is used to characterize the degree to which the actual liquid output performance of the pump head deviates from the design target. Dispensing volume matching degree refers to the degree of matching between the actual dispensing volume of the pump head and the target dispensing volume, which can be obtained by subtracting the dispensing volume deviation ratio from 1. The closer the dispensing volume matching degree is to 1, the closer the actual dispensing volume is to the target dispensing volume, and the higher the dispensing performance matching degree of the pump head; the closer it is to 0, the greater the deviation of the dispensing volume from the target, and there is a risk of insufficient or excessive dispensing. The rebound time ratio refers to the ratio between the measured rebound time of the pump head and the maximum allowable rebound time, and is used to characterize the degree of deviation of the pump head rebound speed from the design requirements. The rebound speed matching index refers to the degree of matching between the actual rebound speed of the pump head and the target rebound speed requirement, which can be obtained by subtracting the rebound time ratio from 1. The closer the rebound speed matching index is to 1, the closer the rebound speed is to or better than the design requirement; the closer it is to 0, the closer the rebound speed is to 0, the lower the rebound speed is, and the greater the risk of rebound lag. Viscosity deviation ratio refers to the ratio of the absolute difference between the target emulsion viscosity value and the corresponding emulsion viscosity to the maximum permissible viscosity deviation, and is used to characterize the degree of difference in rheological properties between the two. Viscosity difference refers to the degree of similarity between the target emulsion and the corresponding emulsion in terms of rheological properties, which can be obtained by subtracting the viscosity deviation ratio from 1. The closer the viscosity difference is to 1, the higher the viscosity match between the target emulsion and the corresponding emulsion, and the higher the reference value of historical samples for the target emulsion; the closer it is to 0, the lower the matching degree, and the limited reference value of historical samples.

[0036] In this embodiment, the liquid output matching degree, rebound speed matching index, and viscosity difference degree are all normalized evaluation indicators, and their value range is limited to 0 to 1. When the indicator value obtained according to the corresponding calculation method is less than 0, it is corrected to 0; when the calculation result is greater than 1, it is corrected to 1, so as to ensure that each evaluation indicator has a uniform dimension and avoid outliers from having an excessive impact on the subsequent comprehensive performance evaluation results.

[0037] First, the deviation between the measured output volume and the target output volume is calculated to obtain the output volume deviation ratio. The output volume deviation ratio is calculated as follows: Output volume deviation ratio = |Measured output volume - Target output volume| ÷ Target output volume. Then, based on the output volume deviation ratio, the output volume fit is calculated as follows: Output volume fit = 1 - Output volume deviation ratio, to characterize the ability of the current pump head sample to meet the target output requirements. If the calculated output volume fit is less than 0, it is corrected to 0; if the calculated result is greater than 1, it is corrected to 1, to characterize the ability of the current pump head sample to meet the target output requirements.

[0038] Subsequently, the ratio between the measured rebound time and the maximum permissible rebound time is calculated to obtain the rebound time ratio. The rebound time ratio is calculated as follows: Rebound Time Ratio = Measured Rebound Time ÷ Maximum Permissible Rebound Time. Based on the rebound time ratio, the rebound speed matching index is calculated as follows: Rebound Speed ​​Matching Index = 1 - Rebound Time Ratio, to characterize the ability of the current pump head sample to meet the target rebound performance requirements. If the calculated rebound speed matching index is less than 0, it is corrected to 0; if the calculated result is greater than 1, it is corrected to 1, to characterize the ability of the current pump head sample to meet the target rebound performance requirements.

[0039] In this embodiment, the maximum permissible rebound time is determined through a pre-calibration test. Specifically, under uniform test conditions, the rebound time is gradually increased, and the continuous liquid dispensing stability, pump chamber reset status, and liquid dispensing qualification rate are monitored in real time. When the test results approach the design requirement boundary, the rebound time adjustment step size is reduced to continuously approximate the critical range until the preset calibration accuracy is reached; the maximum rebound time that meets the design requirements is determined as the maximum permissible rebound time. For example, the maximum permissible rebound time obtained after calibration is 0.50s.

[0040] Furthermore, the viscosity deviation ratio is obtained by calculating the ratio of the absolute difference between the target emulsion viscosity value and the corresponding emulsion viscosity to the maximum permissible deviation of viscosity. The viscosity deviation ratio is calculated as follows: Viscosity Deviation Ratio = |Target Emulsion Viscosity Value - Corresponding Emulsion Viscosity| ÷ Maximum Permissible Deviation of Viscosity. Based on the viscosity deviation ratio, the viscosity difference is calculated as follows: Viscosity Difference = 1 - Viscosity Deviation Ratio, to characterize the similarity of rheological properties between the historical sample emulsion and the target emulsion. If the calculated viscosity difference is less than 0, it is corrected to 0; if the result is greater than 1, it is corrected to 1, to characterize the similarity of rheological properties between the historical sample emulsion and the target emulsion.

[0041] In this embodiment, the maximum permissible viscosity deviation is determined through a pre-calibration test. Since different emulsions have different rheological properties, the maximum permissible viscosity deviation for different target emulsions may vary. Specifically, using the target emulsion viscosity as a benchmark, the viscosity difference between the test emulsion and the target emulsion is gradually increased under uniform testing conditions, while the measured output volume, measured rebound time, and overall performance changes of the corresponding emulsion are monitored in real time. When the test results approach the boundary of the product design requirements, the viscosity difference adjustment step size is reduced to continuously approximate the critical range until the preset calibration accuracy is reached; the maximum viscosity difference that meets the product design requirements is determined as the maximum permissible viscosity deviation for that target emulsion. A parameter library can be pre-established for the maximum permissible viscosity deviation for each target emulsion, and the corresponding parameter can be called according to the viscosity value or emulsion type of the target emulsion. For example, for a target emulsion with a viscosity of 6000 mPa·s, the corresponding maximum permissible viscosity deviation is 1000 mPa·s after calibration.

[0042] For example, the target output volume is 2.0 mL, the actual output volume is 1.8 mL, the output volume deviation ratio is calculated to be (2.0-1.8)÷2.0=0.1, and the output volume fit is 1-0.1=0.9; the maximum allowable rebound time is 0.5 s, the actual rebound time is 0.4 s, the rebound time ratio is calculated to be 0.4÷0.5=0.8, and the rebound speed matching index is 1-0.8=0.2; the target emulsion viscosity is 6000 mPa·s, the corresponding emulsion viscosity is 5500 mPa·s, the maximum allowable viscosity deviation is 1000 mPa·s, the viscosity deviation ratio is calculated to be |6000-5500|÷1000=0.5, and the viscosity difference is 0.5.

[0043] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0044] In summary, by calculating the liquid volume compatibility, rebound speed matching index, and viscosity difference, the dispensing accuracy, rebound performance, and rheological property compatibility of pump head samples under target emulsion conditions can be quantified. This enables performance evaluation and comparative analysis of historical pump head samples, providing a reliable basis for pump head structure optimization, performance prediction, and intelligent selection, and improving the accuracy and adaptability of the overall pump head design.

[0045] The comprehensive performance analysis module 14 integrates the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference into a comprehensive performance matching index, including: Consistency analysis was performed on the spring thrust-fluid resistance matching degree, liquid output adaptability and rebound speed matching index to obtain the performance self-consistency coefficient of each pump head model. Based on viscosity difference and rebound speed matching index, the viscosity-rebound coupling confidence level is calculated and obtained. The matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted based on the performance self-consistency coefficient, and the matching weights of the rebound speed matching index are corrected based on the viscosity-rebound coupling confidence degree. The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference are weighted and integrated to generate a comprehensive performance matching index.

[0046] First, a consistency analysis was conducted on the spring thrust-fluid resistance matching degree, liquid output adaptability, and rebound speed matching index to obtain the performance self-consistency coefficient of each pump head model and quantify the degree of coordination between various performance indicators.

[0047] Subsequently, the viscosity-rebound coupling confidence level was calculated based on the viscosity difference and rebound speed matching index to evaluate the reliability of the pump head's rebound performance under the target emulsion viscosity conditions.

[0048] Furthermore, the matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted according to the performance self-consistency coefficient, and the matching weights of the rebound speed matching index are corrected according to the viscosity-rebound coupling confidence degree, so as to achieve adaptive adjustment of the importance of different performance indicators.

[0049] Finally, the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference are weighted and fused to generate a comprehensive performance matching index. This index is used to evaluate the overall performance of the pump head samples from multiple dimensions, thereby providing a quantitative basis for pump head structural parameter optimization, sample selection, and target emulsion adaptation, and improving the matching accuracy between pump head design and practical application.

[0050] Consistency analysis was performed on the spring thrust-fluid resistance matching degree, liquid output adaptability, and rebound speed matching index to obtain the performance self-consistency coefficient for each pump head model, including: Obtain the maximum and minimum values ​​among the spring thrust-fluid resistance matching degree, liquid output matching degree, and rebound speed matching index; Calculate the maximum value minus the minimum value, and use the difference as the three-dimensional range; Obtain the preset upper limit of the three-dimensional range, divide the three-dimensional range by the upper limit of the three-dimensional range, and obtain the performance dispersion. The performance self-consistency coefficient is obtained by calculating the performance dispersion, where the performance self-consistency coefficient is inversely proportional to the performance dispersion.

[0051] In this embodiment, the three-dimensional range refers to the difference between the maximum and minimum values ​​of the three indicators: spring thrust-fluid resistance matching degree, liquid output matching degree, and rebound speed matching index. The three-dimensional range is used to reflect the consistency between the multi-dimensional performance indicators of the pump head. The larger the value, the higher the dispersion between the performance indicators and the worse the overall performance coordination of the pump head. The smaller the value, the more balanced the performance indicators are and the higher the overall performance consistency and stability of the pump head. Performance dispersion refers to the ratio of the three-dimensional range to a preset upper limit for the three-dimensional range, used to quantify the degree of difference between the three performance indicators. The smaller the performance dispersion, the closer the performance indicators are; the larger the performance dispersion, the more obvious the differences between the performance indicators. The performance self-consistency coefficient is a comprehensive evaluation index calculated based on performance dispersion. It is used to characterize the degree of coordination and consistency between spring thrust-fluid resistance matching, liquid output matching, and rebound speed matching index. The performance self-consistency coefficient is obtained by subtracting the performance dispersion from 1. The closer its value is to 1, the more coordinated the various performance indicators are; the closer its value is to 0, the greater the difference between the various performance indicators and the lower the overall performance consistency.

[0052] First, obtain the spring thrust-fluid resistance matching degree, liquid output matching degree, and rebound speed matching index of the pump head, and determine the maximum and minimum values ​​of the three respectively; Subsequently, the three-dimensional range is calculated. The three-dimensional range is calculated as follows: Three-dimensional range = maximum value - minimum value, which is used to characterize the degree of dispersion among the three key performance indicators of the pump head.

[0053] Furthermore, a preset upper limit for the three-dimensional range is obtained, and the three-dimensional range is divided by this upper limit to obtain the performance dispersion. The performance dispersion is calculated as follows: performance dispersion = three-dimensional range ÷ upper limit for the three-dimensional range, in order to quantify the fluctuation of the pump head performance index.

[0054] The upper limit of the three-dimensional range is determined based on the statistical distribution of the ranges of three indicators in historical sample data: spring thrust-fluid resistance matching degree, liquid output matching degree, and rebound speed matching index. The three-dimensional range values ​​of each historical sample are obtained, and their arithmetic mean and standard deviation are calculated. The arithmetic mean plus twice the standard deviation is used as the upper limit of the three-dimensional range. When historical sample data is insufficient, the upper limit of the three-dimensional range is set to 0.5.

[0055] Finally, the performance self-consistency coefficient is calculated based on the performance dispersion. The calculation method for the performance self-consistency coefficient is: Performance self-consistency coefficient = 1 - Performance dispersion. The performance self-consistency coefficient is inversely proportional to the performance dispersion; the smaller the performance dispersion, the higher the performance self-consistency coefficient. This quantifies the coordination among the three key performance indicators of the pump head, providing a scientific basis for subsequent optimization of pump head structural parameters and performance evaluation, and improving the reliability and consistency of the pump head design results.

[0056] For example, if the spring thrust-fluid resistance matching degree of a certain pump head sample is 0.615, the liquid output matching degree is 0.90, and the rebound speed matching index is 0.80, then the maximum value is 0.90, the minimum value is 0.80, and the three-dimensional range is 0.90-0.80=0.10. When the preset upper limit of the three-dimensional range is 0.50, the performance dispersion is calculated to be 0.10÷0.50=0.20, and the performance self-consistency coefficient is further obtained as 1-0.20=0.80, indicating that the various performance indicators of the pump head sample have high consistency and coordination.

[0057] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0058] Based on viscosity difference and rebound velocity matching index, the viscosity-rebound coupling confidence level is calculated, including: Multiply the viscosity difference by the rebound speed matching index to obtain the viscosity-rebound coupling confidence level.

[0059] In this embodiment, the rebound speed matching index refers to the degree of matching between the actual rebound speed of the pump head and the target rebound speed, and is used to evaluate whether the rebound performance of the pump head meets the design requirements.

[0060] Viscosity-rebound deviation refers to the degree of difference between viscosity difference and rebound speed matching index, and is used to quantify the matching between the rebound performance and rheological properties of the pump head under emulsion viscosity conditions.

[0061] The viscosity-rebound coupling confidence score is an index calculated based on the viscosity-rebound deviation. It is used to characterize the reliability of the pump head's rebound performance under specific emulsion viscosity conditions. The viscosity-rebound coupling confidence score is inversely proportional to the viscosity-rebound deviation; the smaller the deviation, the higher the coupling confidence score.

[0062] First, the viscosity difference between the target emulsion and historical sample emulsions, as well as the pump head rebound speed matching index, are obtained.

[0063] Subsequently, the viscosity difference is multiplied by the rebound speed matching index to obtain the viscosity-rebound coupling confidence level. The viscosity-rebound coupling confidence level is calculated as follows: Viscosity-rebound coupling confidence = viscosity difference × rebound speed matching index.

[0064] Since viscosity difference reflects the similarity of rheological properties between historical sample emulsions and target emulsions, and rebound speed matching index reflects the degree to which the pump head's rebound performance meets the target requirements, their product is used as the viscosity-rebound coupling confidence score, allowing both indicators to jointly contribute to the final evaluation result. When both viscosity difference and rebound speed matching index are high, the calculated viscosity-rebound coupling confidence score is high, indicating that historical samples have high migration reference value, and the corresponding rebound performance is well applicable to the target emulsion's operating conditions. When either indicator decreases, the viscosity-rebound coupling confidence score decreases simultaneously, indicating that the rebound performance of historical samples is greatly affected by changes in emulsion viscosity, reducing its reliability as a design optimization reference.

[0065] For example, the viscosity difference between the target emulsion and the historical sample emulsion is 0.85, and the rebound speed matching index is 0.80. The calculated viscosity-rebound coupling confidence level is 0.85 × 0.80 = 0.68. Since both the viscosity difference and the rebound speed matching index remain at a high level, the obtained viscosity-rebound coupling confidence level also remains at a high level, indicating that the historical sample emulsion and the target emulsion have good consistency in rheological properties, and the corresponding pump head can meet the target rebound performance requirements.

[0066] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0067] The matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted based on the performance self-consistency coefficient, and the matching weight of the rebound speed matching index is corrected based on the viscosity-rebound coupling confidence degree. A weighted fusion of the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference is then performed to generate a comprehensive performance matching index, including: Obtain the preset thrust base weight, liquid discharge base weight, rebound base weight, and viscosity base weight, wherein the sum of the four preset base weights is 1; The performance self-consistency coefficient is used to correct the basic weight of the liquid output to obtain the initial liquid output adaptation weight. The basic weight of rebound is corrected by using the performance self-consistency coefficient and viscosity-rebound coupling confidence to obtain the initial rebound adaptation weight; The initial liquid discharge adaptation weight, initial rebound adaptation weight, thrust base weight, and viscosity base weight are normalized and calculated to obtain a comprehensive weight reassembly. A comprehensive performance matching index is generated by weighting and integrating the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference.

[0068] In this embodiment, the comprehensive weight set refers to the set of weights obtained after normalizing the thrust base weight, viscosity base weight, initial liquid discharge adaptation weight, and initial rebound adaptation weight, which is used to ensure that the sum of each weight is 1. The comprehensive performance matching index refers to the comprehensive evaluation result formed by weighting and integrating the spring thrust-fluid resistance matching degree, liquid output adaptability, rebound speed matching index and viscosity difference, and is used to characterize the overall matching degree between the pump head model and the target emulsion.

[0069] First, obtain the preset basic weights for thrust, liquid discharge, rebound, and viscosity, and ensure that the sum of the four basic weights is 1.

[0070] Subsequently, the performance self-consistency coefficient was used to correct the initial liquid discharge baseline weight. Specifically, the initial liquid discharge adaptation weight was calculated as follows: Initial liquid discharge adaptation weight = Liquid discharge baseline weight × Performance self-consistency coefficient, enabling the liquid discharge performance evaluation to be dynamically adjusted according to the overall performance coordination. Simultaneously, the performance self-consistency coefficient and viscosity-rebound coupling confidence level were used to jointly correct the rebound baseline weight. Specifically, the initial rebound adaptation weight was calculated as follows: Initial rebound adaptation weight = Rebound baseline weight × Performance self-consistency coefficient × Viscosity-rebound coupling confidence level, ensuring that the rebound performance evaluation not only reflects the overall performance coordination but also the impact of emulsion viscosity changes on rebound performance.

[0071] Furthermore, the initial liquid discharge adaptation weight, initial rebound adaptation weight, thrust base weight, and viscosity base weight are normalized. Specifically, the initial liquid discharge adaptation weight, initial rebound adaptation weight, thrust base weight, and viscosity base weight are summed, and each weight is normalized by dividing it by the sum of the weights to obtain a comprehensive weighting, so that the sum of all weights is normalized back to 1. The calculation method for the total weight is: Total weight = Thrust base weight + Viscosity base weight + Initial liquid discharge adaptation weight + Initial rebound adaptation weight; the calculation method for the comprehensive thrust weight is: Thrust comprehensive weight = Thrust base weight ÷ Total weight; the calculation method for the comprehensive liquid discharge weight is: Liquid discharge comprehensive weight = Initial liquid discharge adaptation weight ÷ Total weight; the calculation method for the comprehensive rebound weight is: Rebound comprehensive weight = Initial rebound adaptation weight ÷ Total weight; the calculation method for the comprehensive viscosity weight is: Viscosity comprehensive weight = Viscosity base weight ÷ Total weight.

[0072] Finally, a comprehensive performance matching index is generated by weighting and fusing the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference degree using a comprehensive weighting system. The comprehensive performance matching index is calculated as follows: Comprehensive performance matching index = Thrust comprehensive weight × Spring thrust-fluid resistance matching degree + Liquid output comprehensive weight × Liquid output matching degree + Rebound comprehensive weight × Rebound speed matching index + Viscosity comprehensive weight × Viscosity difference degree; For example, the thrust-based weight, liquid discharge-based weight, rebound-based weight, and viscosity-based weight are 0.25, 0.25, 0.30, and 0.20, respectively, with a performance self-consistency coefficient of 0.80 and a viscosity-rebound coupling confidence level of 0.90. The liquid discharge-based weight is corrected using the performance self-consistency coefficient to obtain an initial liquid discharge adaptation weight of 0.25 × 0.80 = 0.20. The rebound-based weight is then corrected using the performance self-consistency coefficient and the viscosity-rebound coupling confidence level to obtain an initial rebound adaptation weight of 0.30 × 0.80 × 0.90. =0.216; then, the weights were normalized to obtain the thrust matching weight 0.25÷(0.25+0.20+0.216+0.20)=0.289, the liquid output matching weight 0.20÷(0.25+0.20+0.216+0.20)=0.231, the rebound matching weight 0.216÷(0.25+0.20+0.216+0.20)=0.249 and the viscosity matching weight 0.20÷(0.25+0.20+0.216+0.20)=0.231. The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference were weighted and integrated. The spring thrust-fluid resistance matching degree was set to 0.86, the liquid output matching degree to 0.81, the rebound speed matching index to 0.83, and the viscosity matching index to 0.80. The final comprehensive performance matching index was 0.289×0.86+0.231×0.81+0.249×0.83+0.231×0.80=0.8271.

[0073] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0074] In summary, by constructing a performance self-consistency coefficient, a viscosity-rebound coupling confidence level, and a comprehensive performance matching index, a synergistic analysis and comprehensive evaluation of spring thrust performance, liquid discharge performance, rebound performance, and emulsion viscosity adaptation performance can be achieved. The performance self-consistency coefficient quantifies the degree of coordination and consistency among various performance indicators, while the viscosity-rebound coupling confidence level assesses the reliability of emulsion rheological properties and rebound performance. Based on these two factors, the weights of each evaluation indicator are dynamically corrected and adaptively allocated, thereby enhancing the comprehensive performance matching index's ability to characterize the actual working performance of the pump head. This provides a reliable basis for intelligent pump head selection, structural parameter optimization, and target emulsion adaptation, improving the scientific rigor, reliability, and engineering application value of pump head design results.

[0075] The intelligent recommendation and optimization module 15 sorts each pump head model according to the comprehensive performance matching index, and outputs the optimal pump head model recommendation result and parameter adjustment suggestions, including: The pump head models are sorted from largest to smallest according to the comprehensive performance matching index to obtain the matching degree sequence, and the pump head model ranked first in the matching degree sequence is selected as the optimal pump head model recommendation result. When the overall performance matching index of the optimal pump head model recommendation result is lower than the preset recommendation confidence threshold, compare the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference degree, and take the dimension with the smallest value as the performance bottleneck dimension. If the performance bottleneck is the spring thrust-fluid resistance matching degree, the parameter adjustment suggestion is to increase the spring elastic coefficient or increase the maximum compression stroke. If the performance bottleneck is the liquid output matching, the parameter adjustment suggestion is to adjust the pump body cavity volume or the valve channel diameter. If the performance bottleneck is the rebound speed matching index, the parameter adjustment suggestion is to reduce the fit clearance between the piston and the pump body or increase the valve opening. If the performance bottleneck dimension is viscosity difference, the parameter adjustment suggestion is to select the pump head model that ranks second in the matching degree sequence as the optimal pump head model recommendation result, and then conduct further analysis.

[0076] In this embodiment, the matching degree sequence refers to the arrangement of pump head models sorted from high to low according to the comprehensive performance matching index, which is used to reflect the order of merit of each candidate pump head model; The optimal pump head model recommendation result refers to the pump head model with the highest comprehensive performance matching index in the matching degree sequence, which is used as the preferred recommendation scheme for the current target emulsion. The performance bottleneck dimension refers to the evaluation dimension with the smallest value among spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference degree, which is used to characterize the key factors that limit the improvement of the overall performance of the pump head.

[0077] After obtaining the comprehensive performance matching index for each candidate pump head model, they are first sorted from largest to smallest according to the comprehensive performance matching index to generate a matching degree sequence. The pump head model with the highest ranking is then selected as the optimal pump head model recommendation. In this way, the pump head solution with the highest degree of matching with the target emulsion's discharge requirements, rebound requirements, and rheological properties can be selected first.

[0078] Furthermore, when the comprehensive performance matching index corresponding to the optimal pump head model recommendation result is lower than the preset recommendation confidence threshold, it is considered that there is no pump head solution in the current historical samples that can fully meet the target application requirements. Therefore, the spring thrust-fluid resistance matching degree, liquid output adaptability, rebound speed matching index and viscosity difference are compared and analyzed, and the evaluation dimension with the smallest value is determined as the performance bottleneck dimension in order to identify the main factors affecting the overall performance matching degree.

[0079] Specifically, when the performance bottleneck dimension is the spring thrust-fluid resistance matching degree, it indicates insufficient spring rebound capacity or excessive fluid resistance. Parameter adjustment suggestions are generated to increase the spring elastic coefficient or the maximum compression stroke to improve the spring rebound thrust. When the performance bottleneck dimension is the liquid output matching degree, it indicates a deviation between the actual liquid output performance of the pump head and the target liquid output requirements. Parameter adjustment suggestions are generated to adjust the pump body cavity volume or the valve channel diameter to improve the single-volume liquid output. When the performance bottleneck dimension is the rebound speed matching index, it indicates insufficient pump head rebound performance. Parameter adjustment suggestions are generated to reduce the fit clearance between the piston and the pump body or increase the valve opening to reduce flow resistance and improve rebound efficiency. When the performance bottleneck dimension is the viscosity difference degree, it indicates a significant difference in rheological properties between the current historical sample emulsion and the target emulsion. The pump head model ranked second in the matching degree sequence is selected as the new optimal pump head model recommendation, and a comprehensive performance analysis is re-executed to improve the suitability of the recommendation results for the target emulsion.

[0080] For example, the comprehensive performance matching indices of pump heads P-01, P-02, and P-03 are 0.824, 0.781, and 0.735, respectively. These are then sorted by matching indices from largest to smallest to form a matching degree sequence P-01, P-02, and P-03, with P-01 being the recommended optimal pump head model. When the preset recommended confidence threshold is 0.85, since the comprehensive performance matching index of P-01 (0.824) is lower than the recommended confidence threshold, further analysis is conducted on the spring thrust-fluid resistance matching degree (0.85), liquid output adaptability (0.90), rebound speed matching index (0.80), and viscosity difference (0.88). The rebound speed matching index is the smallest, therefore, rebound performance is identified as the current performance bottleneck. Parameter adjustment suggestions are generated to reduce the clearance between the piston and pump body or increase the valve opening to improve the pump head's rebound performance and overall matching level.

[0081] It should be noted that the above values ​​are for illustrative purposes only and do not constitute a limitation on the present invention.

[0082] In summary, by ranking and screening the comprehensive performance matching index of each candidate pump head model, the optimal pump head model can be automatically recommended. When the recommendation result does not meet the confidence threshold, the performance shortcomings can be located by comparing and analyzing multi-dimensional performance indicators, thereby clarifying the key factors affecting the overall matching effect of the pump head. At the same time, by generating corresponding structural parameter optimization suggestions based on different shortcomings or by achieving iterative optimization through a re-screening mechanism of alternative pump heads, the reliability, pertinence, and adaptation accuracy of the pump head selection results can be effectively improved, providing a decision-making basis for pump head structure optimization and matching with target emulsion applications.

[0083] Example 2, as Figure 2As shown, based on the same inventive concept as the data-driven intelligent optimization system for pump head design parameters provided in Embodiment 1, this embodiment of the invention also provides a data-driven intelligent optimization method for pump head design parameters, the method comprising: S100: Obtain the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of the candidate pump head models; S200: Based on the spring elastic coefficient, maximum compression stroke and peak fluid resistance, analyze and obtain the spring thrust-fluid resistance matching degree of the target emulsion for each pump head model; S300: By combining the deviation between the measured liquid output and the target liquid output, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion and the viscosity of each corresponding emulsion, the liquid output adaptability, rebound speed matching index and viscosity difference are calculated and obtained. S400: The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference are integrated into a comprehensive performance matching index; S500: Sorts each pump head model according to the comprehensive performance matching index, and outputs the optimal pump head model recommendation and parameter adjustment suggestions.

[0084] First, obtain the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of the candidate pump head models, including: The viscosity value, target output volume, and maximum allowable rebound time of the target emulsion are obtained. The viscosity value is the dynamic viscosity value measured by a standard viscometer at a specified temperature and speed. The target output volume is the volume of emulsion expected to be pumped out in a single standard press stroke. The maximum allowable rebound time is the longest time allowed for the pump head to bounce back from the lowest point to the highest point. Obtain the spring constant and maximum compression stroke of each pump head model as specification parameters. The spring constant is the force required for the spring to produce a unit compression deformation within its elastic range, and the maximum compression stroke is the maximum displacement of the pump head from its initial position to the bottom. The peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity were recorded during the dispensing test of each pump head model under emulsions of different viscosity. These were used as historical test data. The peak fluid resistance was the maximum fluid resistance encountered by the piston during the standard pressing process. The measured output volume was the actual volume of emulsion that flowed out under the standard pressing stroke. The measured rebound time was the time from the end of pressing to the moment when the pump head rebounded to the initial position.

[0085] Secondly, based on the spring constant, maximum compression stroke, and peak fluid resistance, the spring thrust-fluid resistance matching degree for each pump head model corresponding to the target emulsion is analyzed and obtained, including: Multiply the spring constant by the maximum compression stroke to obtain the maximum spring rebound thrust; Calculate the maximum spring rebound thrust by dividing it by the sum of the maximum spring rebound thrust and the peak fluid resistance to obtain the spring thrust-fluid resistance matching degree.

[0086] Furthermore, by combining the deviation between the measured liquid output and the target liquid output, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion and the viscosity of each corresponding emulsion, the liquid output matching degree, rebound speed matching index and viscosity difference degree are calculated and obtained. Calculate the deviation between the measured liquid output and the target liquid output, obtain the liquid output deviation ratio, and calculate the liquid output fit based on the liquid output deviation ratio. The liquid output fit is negatively correlated with the liquid output deviation ratio. The ratio of the measured rebound time to the maximum allowable rebound time is calculated as the rebound time ratio, and the rebound speed matching index is calculated based on the rebound time ratio. The rebound speed matching index is negatively correlated with the rebound time ratio. The viscosity deviation ratio is obtained by calculating the ratio of the absolute difference between the viscosity value of the target emulsion and the viscosity of the corresponding emulsion to the maximum permissible deviation of viscosity. Based on the viscosity deviation ratio, the viscosity difference degree is calculated, where the viscosity difference degree is inversely proportional to the viscosity deviation ratio.

[0087] Furthermore, the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference degree are integrated into a comprehensive performance matching index, including: Consistency analysis was performed on the spring thrust-fluid resistance matching degree, liquid output adaptability and rebound speed matching index to obtain the performance self-consistency coefficient of each pump head model. Based on viscosity difference and rebound speed matching index, the viscosity-rebound coupling confidence level is calculated and obtained. The matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted based on the performance self-consistency coefficient, and the matching weights of the rebound speed matching index are corrected based on the viscosity-rebound coupling confidence degree. The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference are weighted and integrated to generate a comprehensive performance matching index.

[0088] Specifically, a consistency analysis was conducted on the spring thrust-fluid resistance matching degree, liquid output adaptability, and rebound speed matching index to obtain the performance self-consistency coefficient for each pump head model, including: Obtain the maximum and minimum values ​​among the spring thrust-fluid resistance matching degree, liquid output matching degree, and rebound speed matching index; Calculate the maximum value minus the minimum value, and use the difference as the three-dimensional range; Obtain the preset upper limit of the three-dimensional range, divide the three-dimensional range by the upper limit of the three-dimensional range to obtain the performance dispersion; calculate the performance self-consistency coefficient based on the performance dispersion, where the performance self-consistency coefficient is inversely proportional to the performance dispersion.

[0089] Specifically, based on the viscosity difference and rebound rate matching index, the viscosity-rebound coupling confidence level is calculated, including: Multiply the viscosity difference by the rebound speed matching index to obtain the viscosity-rebound coupling confidence level.

[0090] Specifically, the matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted based on the performance self-consistency coefficient, and the matching weight of the rebound speed matching index is corrected based on the viscosity-rebound coupling confidence degree. A weighted fusion of the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference is then performed to generate a comprehensive performance matching index, including: Obtain the preset thrust base weight, liquid discharge base weight, rebound base weight, and viscosity base weight, wherein the sum of the four preset base weights is 1; The performance self-consistency coefficient is used to correct the basic weight of the liquid output to obtain the initial liquid output adaptation weight. The basic weight of rebound is corrected by using the performance self-consistency coefficient and viscosity-rebound coupling confidence to obtain the initial rebound adaptation weight; The initial liquid discharge adaptation weight, initial rebound adaptation weight, thrust base weight, and viscosity base weight are normalized and calculated to obtain a comprehensive weight reassembly. A comprehensive performance matching index is generated by weighting and integrating the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference.

[0091] Finally, based on the comprehensive performance matching index, the pump head models are ranked, and the optimal pump head model recommendation and parameter adjustment suggestions are output, including: The pump head models are sorted from largest to smallest according to the comprehensive performance matching index to obtain the matching degree sequence, and the pump head model ranked first in the matching degree sequence is selected as the optimal pump head model recommendation result. When the overall performance matching index of the optimal pump head model recommendation result is lower than the preset recommendation confidence threshold, compare the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference degree, and take the dimension with the smallest value as the performance bottleneck dimension. If the performance bottleneck is the spring thrust-fluid resistance matching degree, the parameter adjustment suggestion is to increase the spring elastic coefficient or increase the maximum compression stroke; if the performance bottleneck is the output flow rate matching degree, the parameter adjustment suggestion is to adjust the pump body cavity volume or valve channel diameter. If the performance bottleneck is the rebound speed matching index, the parameter adjustment suggestion is to reduce the fit clearance between the piston and the pump body or increase the valve opening. If the performance bottleneck dimension is viscosity difference, the parameter adjustment suggestion is to select the pump head model that ranks second in the matching degree sequence as the optimal pump head model recommendation result, and then conduct further analysis.

[0092] In summary, this method acquires the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, and constructs a data-driven analysis foundation by combining pump head specifications and historical test data. Furthermore, it establishes evaluation indicators such as spring thrust-fluid resistance matching degree, output volume adaptability, rebound speed matching index, and viscosity difference to achieve quantitative analysis of the pump head's output performance, rebound performance, and emulsion compatibility. Based on this, it constructs a performance self-consistency coefficient, viscosity-rebound coupling confidence degree, and comprehensive performance matching index to collaboratively evaluate and dynamically integrate various performance indicators, improving the ability of the comprehensive performance evaluation results to characterize the actual working performance of the pump head. Finally, based on the comprehensive performance matching index, it completes the sorting and screening of candidate pump head models, recommends the optimal model, and generates parameter optimization suggestions, achieving intelligent decision-making for pump head selection and structural design. By employing the above methods, we can fully leverage the value of historical test data, accurately assess the compatibility between the pump head and the target emulsion, improve the accuracy of pump head selection, design optimization efficiency, and product adaptability, reduce testing and verification costs, and provide reliable technical support for the design, development, structural optimization, and engineering application of emulsion pump head products.

[0093] It should be noted that the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0095] This specification and accompanying drawings are merely illustrative examples of the invention and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of the invention. Clearly, those skilled in the art can make various alterations and modifications to the invention without departing from its scope. Therefore, if such modifications and modifications fall within the scope of the invention and its equivalents, the invention is intended to include these modifications and modifications.

Claims

1. A data-driven intelligent optimization system for pump head design parameters, characterized in that, include: The data acquisition module is used to acquire the viscosity value, target output volume, and maximum allowable rebound time of the target emulsion, as well as the specifications and historical test data of the candidate pump head models. The thrust-resistance matching analysis module is used to analyze and obtain the spring thrust-fluid resistance matching degree of the target emulsion corresponding to each candidate pump head model based on the spring elastic coefficient, maximum compression stroke and fluid resistance peak value in the specified parameters and the historical test data. The performance adaptation evaluation module is used to combine the measured liquid output, measured rebound time and corresponding emulsion viscosity in the historical test data to calculate and obtain the liquid output adaptation degree, rebound speed matching index and viscosity difference degree. The comprehensive performance analysis module is used to perform a fusion analysis on the spring thrust-fluid resistance matching degree, the liquid output matching degree, the rebound speed matching index, and the viscosity difference degree to generate a comprehensive performance matching index. The intelligent recommendation and optimization module is used to sort the candidate pump head models according to the comprehensive performance matching index, and output the optimal pump head model recommendation result and parameter adjustment suggestions.

2. The data-driven intelligent optimization system for pump head design parameters according to claim 1, characterized in that, The acquisition of the target emulsion's viscosity value, target output volume, and maximum permissible rebound time, as well as the specifications and historical test data of the candidate pump head models, includes: The viscosity value, target output volume, and maximum allowable rebound time of the target emulsion are obtained. The viscosity value is the dynamic viscosity value measured by a standard viscometer at a specified temperature and rotation speed. The target output volume is the volume of emulsion expected to be pumped out in a single standard press stroke. The maximum allowable rebound time is the longest time allowed for the pump head to bounce back from the lowest point to the highest point. The spring elastic coefficient and the maximum compression stroke of each pump head model are obtained as the specification parameters. The spring elastic coefficient is the force required for the spring to produce a unit compression deformation within its elastic range, and the maximum compression stroke is the maximum displacement of the pump head from its initial position to the bottom. The peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity recorded during the dispensing test of each pump head model under emulsions of different viscosity were obtained as the historical test data. The peak fluid resistance is the maximum fluid resistance encountered by the piston movement during the standard pressing process. The measured output volume is the actual volume of emulsion flowing out under the standard pressing stroke. The measured rebound time is the time from the end of pressing to the moment when the pump head rebounds to the initial position.

3. The data-driven intelligent optimization system for pump head design parameters according to claim 1, characterized in that, The process of analyzing and obtaining the spring thrust-fluid resistance matching degree for each pump head model corresponding to the target emulsion based on the spring elastic coefficient, maximum compression stroke, and peak fluid resistance includes: Multiply the spring elastic coefficient by the maximum compression stroke to obtain the maximum spring rebound thrust; The spring thrust-fluid resistance matching degree is obtained by dividing the maximum spring rebound thrust by the sum of the maximum spring rebound thrust and the peak fluid resistance.

4. The data-driven intelligent optimization system for pump head design parameters according to claim 1, characterized in that, The method combines the deviation between the measured liquid output and the target liquid output, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion with the viscosity of each corresponding emulsion to calculate and obtain the liquid output matching degree, rebound speed matching index, and viscosity difference degree, including: Calculate the deviation between the measured liquid output and the target liquid output, obtain the liquid output deviation ratio, and calculate the liquid output fit based on the liquid output deviation ratio, wherein the liquid output fit is negatively correlated with the liquid output deviation ratio; The ratio of the measured rebound time to the maximum allowable rebound time is calculated as the rebound time ratio, and the rebound speed matching index is calculated based on the rebound time ratio, wherein the rebound speed matching index and the rebound time ratio are negatively correlated. The viscosity deviation ratio is obtained by calculating the ratio of the absolute difference between the viscosity value of the target emulsion and the viscosity of the corresponding emulsion to the maximum permissible deviation of viscosity. Based on the viscosity deviation ratio, the viscosity difference is calculated, wherein the viscosity difference is inversely proportional to the viscosity deviation ratio.

5. The data-driven intelligent optimization system for pump head design parameters according to claim 1, characterized in that, The process of integrating the spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index, and viscosity difference into a comprehensive performance matching index includes: Consistency analysis was performed on the spring thrust-fluid resistance matching degree, liquid output adaptability and rebound speed matching index to obtain the performance self-consistency coefficient of each pump head model; Based on the viscosity difference and the rebound speed matching index, the viscosity-rebound coupling confidence level is calculated and obtained. The matching weights of the liquid output matching degree and the rebound speed matching index are dynamically adjusted according to the performance self-consistency coefficient, and the matching weights of the rebound speed matching index are corrected according to the viscosity-rebound coupling confidence degree. The spring thrust-fluid resistance matching degree, the liquid output matching degree, the rebound speed matching index and the viscosity difference are weighted and fused to generate a comprehensive performance matching index.

6. The data-driven intelligent optimization system for pump head design parameters according to claim 5, characterized in that, The consistency analysis of the spring thrust-fluid resistance matching degree, liquid output adaptability, and rebound speed matching index is performed to obtain the performance self-consistency coefficient of each pump head model, including: Obtain the maximum and minimum values ​​among the spring thrust-fluid resistance matching degree, the liquid output matching degree, and the rebound speed matching index; The difference between the maximum value and the minimum value is calculated and used as the three-dimensional range. Obtain the preset upper limit of the three-dimensional range, and divide the three-dimensional range by the upper limit of the three-dimensional range to obtain the performance dispersion; The performance self-consistency coefficient is calculated based on the performance dispersion, wherein the performance self-consistency coefficient is inversely proportional to the performance dispersion.

7. The data-driven intelligent optimization system for pump head design parameters according to claim 5, characterized in that, The calculation of the viscosity-spring coupling confidence level based on the viscosity difference and the springback speed matching index includes: Multiply the viscosity difference by the rebound speed matching index to obtain the viscosity-rebound coupling confidence level.

8. The data-driven intelligent optimization system for pump head design parameters according to claim 5, characterized in that, The process involves dynamically adjusting the matching weights of the liquid output matching degree and the rebound speed matching index based on the performance self-consistency coefficient, and correcting the matching weights of the rebound speed matching index based on the viscosity-rebound coupling confidence level. A weighted fusion of the spring thrust-fluid resistance matching degree, the liquid output matching degree, the rebound speed matching index, and the viscosity difference is then performed to generate a comprehensive performance matching index, including: Obtain the preset thrust base weight, liquid discharge base weight, rebound base weight, and viscosity base weight, wherein the sum of the four preset base weights is 1; The performance self-consistency coefficient is used to correct the basic weight of the liquid discharge to obtain the initial liquid discharge adaptation weight. The performance self-consistency coefficient and the viscosity-springiness coupling confidence level are used to correct the springiness base weights to obtain the initial springiness adaptation weights. The initial liquid discharge adaptation weight, the initial rebound adaptation weight, the thrust base weight, and the viscosity base weight are normalized and calculated to obtain a comprehensive weight reassembly. The comprehensive weighted combination is used to weight and fuse the spring thrust-fluid resistance matching degree, the liquid output matching degree, the rebound speed matching index, and the viscosity difference degree to generate a comprehensive performance matching index.

9. The data-driven intelligent optimization system for pump head design parameters according to claim 1, characterized in that, The process of sorting the pump head models according to the comprehensive performance matching index and outputting the optimal pump head model recommendation and parameter adjustment suggestions includes: The pump head models are sorted from largest to smallest according to the comprehensive performance matching index to obtain a matching degree sequence, and the pump head model ranked first in the matching degree sequence is selected as the optimal pump head model recommendation result. When the comprehensive performance matching index of the optimal pump head model recommendation result is lower than the preset recommendation confidence threshold, the magnitudes of the spring thrust-fluid resistance matching degree, the liquid output adaptability, the rebound speed matching index, and the viscosity difference are compared, and the dimension with the smallest value is taken as the performance bottleneck dimension. If the performance bottleneck is the spring thrust-fluid resistance matching degree, then the parameter adjustment suggestion is to increase the spring elastic coefficient or increase the maximum compression stroke; If the performance bottleneck is the liquid output adaptability, then the parameter adjustment suggestion is to adjust the pump body cavity volume or the valve channel diameter. If the performance bottleneck is the rebound speed matching index, then the parameter adjustment suggestion is to reduce the fit clearance between the piston and the pump body or increase the valve opening. If the performance bottleneck dimension is the viscosity difference, then the parameter adjustment suggestion is to select the pump head model ranked second in the matching degree sequence as the optimal pump head model recommendation result, and then conduct further analysis.

10. A data-driven intelligent optimization method for pump head design parameters, the method comprising implementing the system module described in any one of claims 1 to 9, including: The viscosity value, target output volume, and maximum allowable rebound time of the target emulsion are obtained, as well as the specifications and historical test data of the candidate pump head models. The specifications include the spring elasticity coefficient and maximum compression stroke, and the historical test data includes the peak fluid resistance, measured output volume, measured rebound time, and corresponding emulsion viscosity of each pump head model under different emulsion viscosity. Based on the spring elastic coefficient, maximum compression stroke, and peak fluid resistance, the spring thrust-fluid resistance matching degree for each pump head model corresponding to the target emulsion is analyzed and obtained. By combining the deviation between the measured liquid output and the target liquid output, the deviation between the measured rebound time and the maximum allowable rebound time, and the viscosity value of the target emulsion and the viscosity of each corresponding emulsion, the liquid output matching degree, rebound speed matching index, and viscosity difference degree are calculated and obtained. The spring thrust-fluid resistance matching degree, liquid output matching degree, rebound speed matching index and viscosity difference are integrated into a comprehensive performance matching index; Based on the comprehensive performance matching index, each pump head model is sorted, and the optimal pump head model recommendation and parameter adjustment suggestions are output.

Images