High-precision emulsification control method and device

Abstract

The invention discloses a high-precision emulsification control method and device, and belongs to the field of emulsification control, and the method comprises the steps: extracting a high-precision emulsification target, and analyzing the emulsification target to determine an index vector which has a constraint condition; establishing an influence pairing relationship between an emulsification target and an emulsification pump control parameter, and configuring the control parameter according to the influence pairing relationship to obtain a multi-target control parameter item; the multi-target control parameter items are optimized, and a single-pump optimization control scheme is determined; emulsifying pump control is carried out, multi-production-line monitoring data are synchronously collected, multi-pump collaboration analysis is carried out, and collaboration control parameter deviation information is obtained; and compensation control is carried out on cooperative control parameter deviation information, and adaptive compensation control is carried out by matching with a single-pump optimization control scheme. By establishing the influence pairing relation between the emulsification targets and the control parameters, multi-target optimization and multi-pump cooperative compensation control are carried out, and the technical effects of improving the emulsification precision and ensuring the batch consistency are achieved.

Description

Technical Field

[0001] The present invention relates to the field of emulsification control, and in particular to a high-precision emulsification control method and device. Background Art

[0002] In the fields of chemical industry, food, medicine, etc., emulsification technology is widely used to prepare uniform and stable emulsion products. However, the existing emulsification control methods are still insufficient in achieving high precision and high consistency. First, it is difficult for the existing methods to comprehensively consider multiple emulsification targets such as particle size distribution and stability, and there is a lack of quantitative control methods for different indicators, resulting in low emulsification accuracy. Secondly, the existing methods have limited collaborative control capabilities for different batches and different production lines, making it difficult to ensure batch consistency of product quality. Summary of the invention

[0003] The present application provides a high-precision emulsification control method and device, aiming to solve the technical problems of low precision and poor batch consistency in the existing emulsification control methods in the prior art.

[0004] In view of the above problems, the present application provides a high-precision emulsification control method and device.

[0005] The first aspect disclosed in the present application provides a high-precision emulsification control method, which includes: extracting a high-precision emulsification target, the emulsification target includes particle size distribution, stability, and batch consistency, analyzing the emulsification target to determine an index vector, the index vector has constraints, and the constraints are the restricted value range of the index vector; establishing an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configuring the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain multi-objective control parameter items; optimizing the multi-objective control parameter items according to the mutual influence of the particle size distribution and stability emulsification targets and the constraints of the index vector, and determining a single pump optimization control scheme; controlling the emulsification pump based on the single pump optimization control scheme, and synchronously collecting multi-production line monitoring data, performing multi-pump synergy analysis, and obtaining collaborative control parameter deviation information; compensating for the collaborative control parameter deviation information according to the index vector and constraints of the batch consistency emulsification target, and matching the single pump optimization control scheme for adaptive compensation control.

[0006] Another aspect disclosed in the present application provides a high-precision emulsification control device, which includes: an emulsification target extraction module, which is used to extract high-precision emulsification targets, the emulsification targets include particle size distribution, stability, and batch consistency, and the emulsification targets are analyzed to determine an index vector, the index vector has a constraint condition, and the constraint condition is a restricted value range of the index vector; a control parameter configuration module, which is used to establish an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configure the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain multi-objective control parameter items; a parameter optimization module, which is used to optimize the multi-objective control parameter items according to the mutual influence of the particle size distribution and stability emulsification targets and the constraint conditions of the index vector, and determine a single pump optimization control scheme; a multi-pump collaborative analysis module, which is used to control the emulsification pump based on the single pump optimization control scheme, and simultaneously collect multi-production line monitoring data, perform multi-pump collaborative analysis, and obtain collaborative control parameter deviation information; a compensation control module, which is used to perform compensation control on the collaborative control parameter deviation information according to the index vector and constraint conditions of the batch consistency emulsification target, and match the single pump optimization control scheme for adaptive compensation control.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] Due to the use of extracting high-precision emulsification targets, the emulsification targets include particle size distribution, stability, and batch consistency. The emulsification targets are analyzed to determine the index vector. The index vector has constraints, which are the range of values ​​of the index vector, laying the foundation for subsequent parameter optimization and control; an influence pairing relationship between the emulsification target and the emulsification pump control parameter is established, and the control parameters of the particle size distribution and stability emulsification targets are configured based on the influence pairing relationship to obtain multi-objective control parameter items. Through the influence pairing relationship and multi-objective parameter configuration, a control parameter combination that takes into account different indicators can be obtained to improve the comprehensive control effect; according to the mutual influence of the particle size distribution and stability emulsification targets and the constraints of the index vector, the multi-objective control parameter items are optimized to determine the single pump optimization control scheme to achieve high-precision control of the emulsification process; based on the single pump optimization control scheme, the emulsification pump is controlled, and the monitoring data of multiple production lines are collected simultaneously for multi-pump Synergy analysis is performed to obtain the deviation information of collaborative control parameters, and the optimized single-pump control scheme is applied to actual production. At the same time, by collecting data from multiple production lines, the synergy between different pumps is analyzed, and the deviation information of collaborative control parameters is obtained to provide a basis for achieving batch consistency control; according to the indicator vector and constraints of the batch consistency emulsification target, the collaborative control parameter deviation information is compensated and controlled, and the single pump optimization control scheme is matched for adaptive compensation control. For the batch consistency target, compensation control is performed based on the indicator vector and constraints. Adaptive compensation is achieved by matching the single pump optimization scheme to ensure the high consistency of product quality in different batches. This technical solution solves the technical problems of low precision and poor batch consistency in the existing emulsification control methods. By establishing the influence pairing relationship between the emulsification target and the control parameters, multi-objective optimization and multi-pump collaborative compensation control are performed to achieve the technical effect of improving emulsification accuracy and ensuring batch consistency.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a high-precision emulsification control method is provided for an embodiment of the present application;

[0011] Figure 2 A structural schematic diagram of a high-precision emulsification control device is provided for an embodiment of the present application.

[0012] Explanation of reference numerals: emulsification target extraction module 11 , control parameter configuration module 12 , parameter optimization module 13 , multi-pump collaborative analysis module 14 , compensation control module 15 . DETAILED DESCRIPTION

[0013] The overall idea of ​​the technical solution provided by this application is as follows:

[0014] The embodiments of the present application provide a high-precision emulsification control method and device. First, by extracting key emulsification targets such as particle size distribution, stability, batch consistency, and quantitatively characterizing the indicators, a quantitative model that accurately reflects the emulsification quality is established. On this basis, an influence pairing relationship between the emulsification target and the emulsification pump control parameters is constructed, and through multi-objective parameter optimization, a multi-objective control parameter item that takes into account various indicators and meets the constraints is obtained. Furthermore, a multi-pump collaborative compensation mechanism is introduced. By collecting monitoring data from multiple production lines, analyzing the synergy between different pumps, obtaining the collaborative control parameter deviation, and performing compensation control accordingly, the high consistency of product quality in different batches is effectively ensured.

[0015] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.

[0016] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a high-precision emulsification control method, the method comprising:

[0017] S1: extracting high-precision emulsification targets, including particle size distribution, stability, and batch consistency, analyzing the emulsification targets to determine index vectors, wherein the index vectors have constraints, and the constraints are the restricted value range of the index vectors.

[0018] Specifically, first, we need to clarify the goal to be achieved by high-precision emulsification control, that is, the high-precision emulsification goal. By analyzing the emulsification process, we can conclude that the key indicators that affect the emulsification effect include particle size distribution, stability, and batch consistency. Among them, particle size distribution reflects the size distribution of emulsion droplets in the emulsified product, which is related to the quality of the emulsified product; stability characterizes the ability of the emulsified system to remain uniform for a certain period of time without stratification or aggregation; batch consistency measures the degree of consistency in performance between different batches of products, which is the guarantee for achieving large-scale production.

[0019] After the emulsification target is clearly defined, it is further quantified into an indicator vector that can be measured and controlled. For example, the volume average particle size, polydispersity coefficient Span value and other parameters are used to characterize the particle size distribution; the Zeta potential, viscosity change of the emulsion and other indicators are used to evaluate the stability; the standard deviation of the particle size distribution of each batch of products is used to measure the consistency level. When constructing the indicator vector, a value range is set for each indicator as a constraint for optimization and control. The setting of these constraints requires comprehensive consideration of process requirements, equipment conditions, cost-effectiveness and other factors. For example, from a process perspective, the droplet size is required to be controlled within a certain range to ensure optimal performance; from an equipment perspective, factors such as production capacity and power will limit the range of optional process parameters; and from a cost perspective, it is necessary to minimize energy and material consumption while meeting quality requirements.

[0020] By analyzing the emulsification process, the key factors affecting the emulsification quality are identified, and then a quantitative target indicator system is established, and the constraint range of each indicator is reasonably set to guide subsequent process optimization and process control.

[0021] S2: establishing an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configuring the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain multi-objective control parameter items.

[0022] Specifically, first, a series of experiments are designed to evaluate the performance of the obtained emulsified products, including particle size distribution, stability and other indicators, under different settings of emulsification pump control parameters. Through statistical analysis of experimental data, it is found that there is a significant correlation between certain control parameter combinations and specific emulsification targets. For example, high shear rate and long pumping time often correspond to smaller droplet size and narrower particle size distribution. Then, based on the statistical analysis results, the influence pairing relationship between the emulsification pump control parameters and the emulsification target is established, and the influence trend and degree of each parameter on the target are described in an intuitive and qualitative way, such as "the higher the speed, the smaller the particle size", "the longer the pumping time, the more uniform the distribution", etc. Subsequently, based on the influence pairing relationship, the corresponding control parameter range or combination is set to achieve specific particle size distribution and stability targets. For example, to obtain an emulsion with small particle size and high stability, the parameters of high speed, long pumping time and low flow rate can be selected to configure the control parameters and obtain multi-objective control parameter items.

[0023] S3: According to the mutual influence of the particle size distribution and the stability emulsification objectives and the constraints of the index vector, the multi-objective control parameter items are optimized to determine the single pump optimization control scheme.

[0024] Specifically, first, the mutual influence and constraint relationship between various emulsification targets should be clarified. For example, reducing the droplet size will reduce the stability of the emulsion; although extending the pumping time is conducive to uniform dispersion, it will also lead to increased energy consumption. The contradiction between these targets requires trade-offs and compromises when optimizing parameters. At the same time, each target indicator is also constrained by factors such as process conditions, equipment performance, and product standards. These constraints constitute the boundaries of parameter selection.

[0025] After clarifying the mutual influence of the emulsification targets and the constraints of the index vector, the optimization algorithm is used to search and combine the control parameters to find the parameter settings with the best overall performance under the premise that all indicators meet the requirements. Among them, the optimization methods include heuristic search, evolutionary algorithm, particle swarm algorithm, etc. During the optimization process, based on the influence pairing relationship, a directional search is performed in the parameter space, the objective function value of each parameter combination is evaluated, and it is updated and screened according to the rules of the optimization algorithm to gradually approach the optimal solution. The optimized control parameter combination can achieve the overall optimal index while meeting the constraints of each emulsification target, representing the best process solution for emulsification pump control as a single pump optimization control solution.

[0026] Through multi-objective optimization, on the basis of considering the constraints of various emulsification indicators, the control parameter combination that meets the optimal overall performance is solved, and the coordinated control of the emulsification pump is realized.

[0027] S4: Based on the single-pump optimization control scheme, the emulsification pump is controlled, and the monitoring data of multiple production lines are collected simultaneously to perform multi-pump synergy analysis to obtain the synergy control parameter deviation information.

[0028] Specifically, the emulsification pump is controlled according to the obtained single pump optimization control scheme. At the same time, real-time monitoring data from multiple production lines are collected, and multi-pump synergy analysis is performed on these data to obtain the deviation information of the synergistic control parameters. Specifically, various sensors and detection equipment are installed on each emulsification pump to collect key parameters reflecting the emulsification process and product quality in real time, such as temperature, pressure, flow rate, particle size distribution, etc. Through statistical analysis of these monitoring data, the operating status and control effects of different emulsification pumps are compared, and the consistency and synergy between them are quantitatively evaluated. If it is found that the control parameters or product indicators of some pumps are significantly different from the overall level, it means that there is a deviation in the synergistic control parameters, and the deviation information of the synergistic control parameters is obtained. This deviation may be caused by factors such as performance differences of the equipment itself, inconsistent parameter settings, and fluctuations in raw material properties. For example, it is found that the actual speed of an emulsification pump is lower than the set value, or the average particle size of its product is always larger than that of other pumps.

[0029] Through the collaborative analysis of multi-pump monitoring data, the collaborative control parameter deviation information is obtained to provide support for achieving high consistency control of multiple pumps. These deviation information provides an important basis and direction for optimizing control strategies, improving equipment performance, and improving product quality stability, and is the basis for subsequent dynamic optimization and adaptive control.

[0030] S5: According to the index vector and constraint conditions of the batch consistency emulsification target, the collaborative control parameter deviation information is compensated and controlled, and the single pump optimization control scheme is matched to perform adaptive compensation control.

[0031] Specifically, first, extract the indicator vector and constraints set for the batch consistency target, including the consistency requirements of different batches of products in terms of key quality attributes such as particle size distribution and stability, as well as the allowable deviation range of each indicator. Then, compare the collaborative control parameter deviation information with the indicator vector of the batch consistency target, evaluate the consistency level under the current production state, and determine whether the preset constraints are met. If the deviation exceeds the allowable range, compensatory control is required to adjust the control parameters of the relevant emulsification pump to reduce batch differences and improve consistency.

[0032] The specific method of compensation control is to introduce an adaptive correction mechanism based on the single pump optimization control scheme. According to the size and direction of the collaborative control parameter deviation, the key parameters in the single pump optimization control scheme are adjusted and corrected to better meet the actual needs under the current production state. For example, when the particle size of a batch of products is too large, the shear rate of the relevant emulsification pump is appropriately increased or the shear time is extended to compensate for this deviation, ensuring that the particle size distribution of subsequent batches of products is closer to the target value.

[0033] By compensating for the deviation information of collaborative control parameters and dynamically adjusting the single pump optimization control scheme, adaptive optimization of batch consistency is achieved. Through the intelligent feedback adjustment mechanism, the stability and controllability of product quality are continuously improved, achieving a high level of batch consistency control.

[0034] Furthermore, the embodiment of the present application also includes:

[0035] Collect emulsification process monitoring data, including control parameters and emulsification effect indicators; extract first-order features and second-order features of the monitoring data, where the first-order features are the rate of change of the data and the second-order features are the acceleration of the data change, to construct a training data set; perform deep learning on the training data set, using the first-order features and second-order features as input data and the influence of control parameter changes on emulsification targets as output results, to construct a machine analysis model, and obtain the influence pairing relationship between the emulsification target and the emulsification pump control parameters.

[0036] In a preferred embodiment, first, various monitoring data during the emulsification process are collected, including the control parameters of the emulsification pump (such as rotation speed, pumping time, shear rate, etc.) and various indicators reflecting the emulsification effect (such as droplet size, particle size distribution, Zeta potential, etc.). These data come from various sensors and detection equipment arranged on the production line, covering the entire cycle of the emulsification process, and laying a data foundation for subsequent analysis.

[0037] Next, the collected monitoring data is feature extracted and processed. Specifically, the first-order and second-order feature extraction methods are used, where the first-order feature represents the rate of change of the data, that is, the first-order derivative of the data over time; the second-order feature represents the acceleration of the data change, that is, the second-order derivative of the data over time. By extracting the first-order and second-order features of the monitoring data, the dynamic change trend of the data can be better characterized and the temporal laws contained therein can be captured.

[0038] Subsequently, deep learning technology was used to model and analyze the training data set. The extracted first-order and second-order features were used as the input of the model, and the influence of control parameter changes on various emulsification targets was used as the output of the model to build a machine analysis model. Through training and optimization, the model can automatically learn and reveal the intrinsic connection and influence rules between control parameters and emulsification targets. After the model is established, the degree and direction of influence on emulsification targets such as particle size distribution and stability can be predicted and evaluated based on the changes in the input control parameters, thereby obtaining the influence pairing relationship between the emulsification target and the emulsification pump control parameters.

[0039] By collecting comprehensive monitoring data, extracting high-order dynamic features, and using deep learning technology for modeling and analysis, the relationship between the emulsification target and the emulsification pump control parameters was established. This not only revealed the influence of each parameter on the emulsification effect, but also provided an important basis for subsequent process optimization and parameter design.

[0040] Furthermore, the embodiment of the present application also includes:

[0041] The multi-objective control parameter items include the control parameter schemes for the particle size distribution and stability emulsification targets, which are respectively used as the first control parameter scheme and the second control parameter scheme; taking the particle size distribution and stability as optimization targets, and constructing an evaluation function based on the influence pairing relationship between the emulsification target and the emulsification pump control parameters; constructing an optimization space according to the constraints of the indicator vector and the evaluation function; taking the first control parameter scheme as the starting point and the second control parameter scheme as the optimization direction, using the optimization space for iterative optimization through crossover, mutation and selection search, and selecting the control scheme with the largest optimization target as the single pump optimization control scheme.

[0042] In a preferred embodiment, first, the contents included in the multi-objective control parameter items are clearly defined. Among them, the control parameter scheme related to the particle size distribution target is defined as the first control parameter scheme, and the control parameter scheme related to the stability target is defined as the second control parameter scheme, which is helpful to consider and process the control strategies corresponding to different targets separately in the subsequent optimization. Next, based on the established influence pairing relationship between the emulsification target and the emulsification pump control parameters, an evaluation function is constructed to quantitatively evaluate the contribution of a specific control parameter combination to the realization of the particle size distribution and stability targets. Through the influence pairing relationship, the influence direction and weight of each control parameter on the target are determined, and then an evaluation function is constructed as the objective function of the optimization problem.

[0043] At the same time, according to the determined index vector constraints and combined with the evaluation function, the optimization space is constructed. The optimization space refers to the multidimensional search domain composed of all feasible control parameter combinations, and its boundary is determined by the value range of the index vector. In this space, each point represents a possible control scheme, and its quality can be measured by the evaluation function. The construction of the optimization space provides a clear scope and direction for subsequent optimization searches. After that, the heuristic search algorithm is used to perform iterative optimization in the optimization space to find the optimal single pump control scheme. Taking the first control parameter scheme as the starting point and the second control parameter scheme as the search direction, the candidate solutions are combined and evolved through genetic algorithm operations such as crossover and mutation. At the same time, the advantages and disadvantages of each scheme are selected and eliminated according to the evaluation function, and the control parameter combination is continuously updated and improved. After multiple rounds of iterations, it finally converges to the control scheme with the best evaluation index as the best strategy for the single pump optimization control scheme.

[0044] By constructing a multi-objective evaluation function and optimization space, and using a heuristic search algorithm for iterative optimization, the optimal single-pump control scheme was found under the constraints of particle size distribution and stability objectives, and the requirements of various indicators were weighed to achieve overall optimization of the emulsification effect.

[0045] Furthermore, the embodiment of the present application also includes:

[0046] Sensors are arranged at each emulsification pump to collect monitoring signals of each pump; the monitoring signals are aligned according to the collection time, the similarity of the aligned signals is calculated, and the signal similarity coefficient is determined; deviation comparison is performed based on the signal similarity coefficient to obtain the collaborative control parameter deviation information.

[0047] In a feasible implementation, first, sensors are arranged on each emulsification pump to collect various monitoring signals reflecting the operating status and process parameters of the pump, including temperature sensors, pressure sensors, speed sensors, etc., which are used to monitor the key control parameters and process variables of the emulsification pump, respectively, so as to comprehensively and accurately obtain the real-time operation data of each pump, laying the foundation for subsequent analysis. Then, the collected multi-pump monitoring signals are time-aligned and similarity calculated. Since the start and stop times and sampling frequencies of different emulsification pumps are different, all monitoring data are first aligned to a unified time axis according to the timestamp of the signal. Then, using signal processing and data analysis technology, through similarity measurement methods such as correlation coefficient, cross-correlation function, and dynamic time warping, the similarity between the aligned multi-pump signals is calculated to obtain a quantitative similarity coefficient.

[0048] Afterwards, multi-pump deviation comparison and analysis are performed based on the calculated signal similarity coefficient. By setting a similarity threshold, it is determined whether the operating status and control parameters of different emulsification pumps are consistent and synchronized. For pumps with a similarity coefficient lower than the threshold, it means that their control parameters deviate from other pumps and require special attention and analysis. By comparing the control parameter differences between the deviation pump and the normal pump, the specific items and values ​​of the deviation are located, thereby obtaining detailed collaborative control parameter deviation information.

[0049] By placing sensors on the emulsification pumps, collecting monitoring signals from multiple production lines, and performing time alignment, similarity calculation and deviation comparison on the signals, we obtained the collaborative control parameter deviation information, which reflects the consistency and synchronization of different emulsification pumps when executing a unified single pump optimization control scheme, and provides an important basis for subsequent parameter compensation and dynamic optimization.

[0050] Furthermore, the embodiment of the present application also includes:

[0051] Rotation speed sensors, shear force sensors and temperature sensors are arranged, and the monitoring signals include rotation speed, shear force and temperature; based on the acquisition timestamp of the monitoring signals, the rotation speed, shear force and temperature are aligned to the same time axis; the mean and standard deviation characteristics of the rotation speed, shear force and temperature are extracted; based on the time alignment relationship, the extracted features of each monitoring signal are fused using principal component analysis to obtain a consistency index; the root mean square error and standard deviation are calculated using the consistency index to obtain the signal similarity coefficient.

[0052] In a preferred embodiment, first, the types of sensors arranged on the emulsification pump and the contents of the monitoring signals are clearly defined. Among them, the speed sensor is used to monitor the real-time speed of the emulsification pump, the shear force sensor is used to monitor the shear force during the emulsification process, and the temperature sensor is used to monitor the working temperature of the emulsification pump. These three types of signals respectively reflect the mechanical operating state, fluid shear characteristics and thermodynamic characteristics of the emulsification pump, and are key indicators for evaluating the stability and consistency of the emulsification process. Since these signals come from different sensors and acquisition devices, their sampling times and frequencies may differ. Therefore, the collected speed, shear force and temperature signals are time-aligned and aligned to the same time axis to ensure the time consistency of subsequent analysis.

[0053] Subsequently, statistical features are extracted from the aligned rotation speed, shear force and temperature signals. Specifically, the mean and standard deviation of each signal within a certain time window are calculated. The mean reflects the average level of the signal, and the standard deviation reflects the degree of fluctuation of the signal. Through these statistics, the time series signal is converted into a discrete feature vector, which is convenient for subsequent feature fusion and similarity calculation. Then, the principal component analysis technology is used to fuse the extracted features of each monitoring signal to obtain a comprehensive consistency index. The principal component analysis technology maps the original features to a new orthogonal space through linear transformation, and extracts the main patterns and trends of the data. Among them, the mean and standard deviation features of the rotation speed, shear force, and temperature are used as the input of the principal component analysis. Through eigenvalue decomposition and reconstruction, a more compact and comprehensive consistency index is obtained, which reflects the overall correlation and synchronization between different monitoring signals.

[0054] Then, the root mean square error and standard deviation are calculated based on the consistency index as quantitative indicators to measure the signal similarity. The root mean square error indicates the degree of deviation of the consistency index between different pumps, and the standard deviation indicates the degree of dispersion of this deviation. The higher the signal similarity, the closer the monitoring signals of each pump are, and the better the collaborative control effect; conversely, the lower the signal similarity, the more obvious the deviation is, and the control strategy needs to be adjusted and optimized in time.

[0055] Through similarity-based analysis and evaluation, abnormal deviations in the multi-pump control process can be discovered in a timely manner, providing a quantitative basis for fault diagnosis and parameter optimization, thereby ensuring the stability and consistency of the quality of emulsified products, and laying the foundation for realizing intelligent monitoring and optimized control of the emulsification process.

[0056] Furthermore, the embodiment of the present application also includes:

[0057] According to the collaborative control parameter deviation information, the emulsification target and the influence pairing relationship between the emulsification pump control parameters, the stability emulsification target deviation and the particle size distribution emulsification target deviation are obtained respectively; the stability emulsification target deviation and the particle size distribution emulsification target deviation are compensated and analyzed according to the indicator vector and constraint conditions to determine the target compensation; based on the collaborative control parameter deviation information, parameter positioning is performed and the equipment deviation coefficient is determined; according to the parameter positioning, the target compensation amount is corrected using the equipment deviation coefficient, and compensation control is performed according to the corrected parameter compensation amount.

[0058] In a feasible implementation, first, the deviation of the stability target and the particle size distribution target is calculated respectively by using the collaborative control parameter deviation information, the emulsification target and the influence pairing relationship of the control parameters. The collaborative control parameter deviation information reflects the actual parameter differences of different emulsification pumps in executing a unified single pump optimization control scheme. These differences may come from factors such as equipment aging and inconsistent performance. Through the influence pairing relationship, the influence of the control parameter deviation on the emulsification targets such as stability and particle size distribution is quantitatively evaluated to obtain the corresponding target deviation. Then, according to the constraints of the indicator vector, the deviation of the stability and particle size distribution targets is compensated and analyzed to determine the corresponding target compensation. Specifically, the target deviation is compared with the allowable range of the indicator vector to determine whether the deviation exceeds the preset control limit, and the target amount to be compensated is determined accordingly. The size of the compensation amount should be able to effectively reduce the target deviation so that it meets the indicator constraints, and avoid over-compensation to cause new deviations or instability.

[0059] Next, based on the collaborative control parameter deviation information, the control parameters are located and the equipment deviation coefficient is calculated. Parameter location refers to identifying the key control parameters that cause target deviations, such as speed, temperature, flow, etc. At the same time, considering the performance differences of different equipment, the equipment deviation coefficient is introduced to quantify the deviation characteristics of the equipment itself, such as the nonlinearity, hysteresis, noise, etc. of the equipment, to provide a correction basis for subsequent compensation control. Next, the target compensation amount is corrected using the equipment deviation coefficient to obtain the final corrected parameter compensation amount, and the control parameters of the emulsification pump are adjusted according to the compensation amount to achieve compensation control. Specifically, the target compensation amount is multiplied by the equipment deviation coefficient to obtain the corrected compensation amount that takes into account the equipment's own deviation, and then it is superimposed on the original control parameters to generate a new control instruction, which is sent to the emulsification pump for execution. Through adaptive compensation control, the impact of equipment differences and parameter deviations on the emulsification target can be effectively offset, and the consistency of product quality of different batches can be improved.

[0060] By comprehensively utilizing the collaborative control parameter deviation information, the influencing pairing relationship and the equipment deviation characteristics, the difference in product quality between batches can be effectively reduced and the stability and consistency of the emulsification process can be improved. Compared with the traditional fixed compensation method, it can dynamically adjust the compensation strategy according to the real-time deviation information and equipment status, has stronger adaptability and robustness, and realizes intelligent and precise emulsification control.

[0061] Furthermore, the embodiment of the present application also includes:

[0062] Continuous collaborative control parameter deviation information is obtained according to the timing relationship, and the continuity collaborative control parameter deviation information is extracted using a sliding window to obtain a multi-window deviation change; the multi-window deviation change is used to fit the timing change relationship of the deviation change; an adaptive compensation mechanism is set according to the timing change relationship to perform timing adaptive compensation on the target deviation device.

[0063] In a preferred embodiment, first, multiple batches of collaborative control parameter deviation information are obtained in chronological order to form a time series deviation data set, including continuous collaborative control parameter deviation information. Then, the sliding window technology is used to process the data set. Specifically, a time window of fixed length is set, and the window is slid on the data set. Each time, a subset of the deviation data in the window is extracted, and the change in the deviation amount in the subset is calculated, such as the mean, variance, trend and other statistical characteristics of the deviation. By continuously sliding the window, a series of multi-window deviation changes are obtained, which reflects the dynamic change characteristics of the deviation at different time scales.

[0064] Next, the time series model of deviation change is established by using the multi-window deviation change, so as to fit the time series change relationship of the deviation change. By fitting the multi-window deviation change, the time correlation and periodic law of the deviation change are portrayed, and the change trend of the deviation in the future can be predicted. Subsequently, according to the time series change relationship of the deviation change, an adaptive compensation mechanism is designed to perform more accurate and long-term compensation control on the target deviation equipment. Specifically, the time series model is used to predict the deviation change trend in the future, and the compensation strategy and parameters are dynamically adjusted in combination with the current actual deviation and compensation effect. For example, when the predicted deviation gradually increases, the compensation is started in advance and the compensation intensity is appropriately increased; when the predicted deviation tends to be stable, the compensation intensity is reduced to avoid over-compensation. Through time series adaptive compensation, the control performance of the emulsification pump is continuously optimized on different time scales, so that it is always in the best working state, thereby stabilizing product quality.

[0065] In summary, the high-precision emulsification control method provided in the embodiments of the present application has the following technical effects:

[0066] Extract high-precision emulsification targets, which include particle size distribution, stability, and batch consistency. Analyze the emulsification targets to determine the index vector. The index vector has constraints, which are the restricted value range of the index vector, providing a basis and basis for subsequent parameter optimization and control. Establish an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configure the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain multi-objective control parameter items, laying the foundation for high-precision control. According to the mutual influence of the particle size distribution and stability emulsification targets and the constraints of the index vector, optimize the multi-objective control parameter items, determine the single pump optimization control scheme, and provide support for high-precision control of a single batch of emulsification processes. Based on the single pump optimization control scheme, perform emulsification pump control, and simultaneously collect multi-production line monitoring data, perform multi-pump synergy analysis, and obtain collaborative control parameter deviation information to provide necessary data support for consistency control of multiple batches and multiple production lines. According to the index vector and constraint conditions of the batch consistency emulsification target, the collaborative control parameter deviation information is compensated and controlled, and the single pump optimization control scheme is matched to perform adaptive compensation control to ensure the high consistency of product quality in different batches and improve the stability of emulsification production.

[0067] Embodiment 2 is based on the same inventive concept as a high-precision emulsification control method in the above embodiment. Figure 2 As shown, the embodiment of the present application provides a high-precision emulsification control device, which includes:

[0068] An emulsification target extraction module 11 is used to extract high-precision emulsification targets, including particle size distribution, stability, and batch consistency, and to analyze the emulsification targets to determine an index vector, wherein the index vector has a constraint condition, and the constraint condition is a restricted value range of the index vector;

[0069] A control parameter configuration module 12 is used to establish an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configure the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain a multi-objective control parameter item;

[0070] A parameter optimization module 13 is used to optimize the multi-objective control parameter items according to the mutual influence of the particle size distribution and the stability emulsification target and the constraint conditions of the index vector, and determine the single pump optimization control scheme;

[0071] The multi-pump coordination analysis module 14 is used to control the emulsification pump based on the single pump optimization control scheme, and simultaneously collect monitoring data of multiple production lines to perform multi-pump coordination analysis to obtain coordination control parameter deviation information;

[0072] The compensation control module 15 is used to perform compensation control on the collaborative control parameter deviation information according to the index vector and constraint conditions of the batch consistency emulsification target, and to match the single pump optimization control scheme to perform adaptive compensation control.

[0073] Furthermore, the control parameter configuration module 12 includes the following execution steps:

[0074] Collect emulsification process monitoring data, including control parameters and emulsification effect indicators;

[0075] Extracting first-order features and second-order features from the monitoring data, wherein the first-order feature is the rate of change of the data, and the second-order feature is the acceleration of the change of the data, and constructing a training data set;

[0076] The training data set is subjected to deep learning, the first-order features and the second-order features are used as input data, the influence of the control parameter changes on the emulsification target is used as the output result, a machine analysis model is constructed, and the influence pairing relationship between the emulsification target and the emulsification pump control parameters is obtained.

[0077] Furthermore, the parameter optimization module 13 includes the following execution steps:

[0078] The multi-objective control parameter items include the control parameter schemes for the particle size distribution and the stability emulsification objectives, which are respectively used as the first control parameter scheme and the second control parameter scheme;

[0079] Taking the particle size distribution and stability as optimization targets, and constructing an evaluation function based on the influence pairing relationship between the emulsification target and the emulsification pump control parameters;

[0080] Constructing an optimization space according to the constraint conditions of the indicator vector and the evaluation function;

[0081] The first control parameter scheme is taken as the starting point, the second control parameter scheme is taken as the optimization direction, and the optimization space is used for iterative optimization through crossover, mutation and selection search to select the control scheme with the largest optimization target as the single pump optimization control scheme.

[0082] Furthermore, the multi-pump collaborative analysis module 14 includes the following execution steps:

[0083] Install sensors on each emulsification pump to collect monitoring signals from each pump;

[0084] Aligning the monitoring signals according to the acquisition time, calculating the similarity of the aligned signals, and determining the signal similarity coefficient;

[0085] A deviation comparison is performed based on the signal similarity coefficient to obtain the collaborative control parameter deviation information.

[0086] Furthermore, the multi-pump collaborative analysis module 14 also includes the following execution steps:

[0087] A rotation speed sensor, a shear force sensor, and a temperature sensor are arranged, and the monitoring signals include rotation speed, shear force, and temperature;

[0088] Based on the acquisition timestamp of the monitoring signal, aligning the rotation speed, shear force, and temperature onto the same time axis;

[0089] Extracting the mean and standard deviation characteristics of the rotation speed, shear force, and temperature;

[0090] Based on the time alignment relationship, the extracted features of each monitoring signal are fused using principal component analysis to obtain the consistency index;

[0091] The root mean square error and standard deviation are calculated through the consistency index to obtain the signal similarity coefficient.

[0092] Furthermore, the compensation control module 15 includes the following execution steps:

[0093] According to the collaborative control parameter deviation information, the emulsification target and the influence pairing relationship of the emulsification pump control parameter, the stability emulsification target deviation and the particle size distribution emulsification target deviation are obtained respectively;

[0094] Perform compensation analysis on the stability emulsification target deviation and the particle size distribution emulsification target deviation according to the index vector and the constraint conditions to determine the target compensation amount;

[0095] Perform parameter positioning and determine the equipment deviation coefficient based on the collaborative control parameter deviation information;

[0096] The target compensation amount is positioned according to the parameter, the target compensation amount is corrected using the device deviation coefficient, and compensation control is performed according to the corrected parameter compensation amount.

[0097] Furthermore, the compensation control module 15 further includes the following execution steps:

[0098] Acquire the continuity cooperative control parameter deviation information according to the time sequence relationship, extract the continuity cooperative control parameter deviation information by using a sliding window, and obtain a multi-window deviation variation;

[0099] Using the multi-window deviation variation to fit the time series variation relationship of the deviation variation;

[0100] An adaptive compensation mechanism is set according to the timing variation relationship to perform timing adaptive compensation on the target deviation device.

[0101] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0102] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A high-precision emulsification control method, characterized in that: The high-precision emulsification control method comprises: Extracting high-precision emulsification targets, the emulsification targets include particle size distribution, stability, and batch consistency, analyzing the emulsification targets to determine an index vector, the index vector having a constraint condition, and the constraint condition being a restricted value range of the index vector; Establishing an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configuring the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain a multi-objective control parameter item; According to the mutual influence of the particle size distribution and the stability emulsification target and the constraint conditions of the index vector, the multi-objective control parameter items are optimized to determine the single pump optimization control scheme; Based on the single pump optimization control scheme, the emulsification pump is controlled, and the monitoring data of multiple production lines are collected simultaneously to perform multi-pump synergy analysis and obtain the synergy control parameter deviation information; According to the index vector and constraint conditions of the batch consistency emulsification target, the collaborative control parameter deviation information is compensated and controlled, and the single pump optimization control scheme is matched to perform adaptive compensation control.

2. The high-precision emulsification control method according to claim 1, characterized in that: The establishing of the influence pairing relationship between the emulsification target and the emulsification pump control parameter includes: Collect emulsification process monitoring data, including control parameters and emulsification effect indicators; Extracting first-order features and second-order features from the monitoring data, wherein the first-order feature is the rate of change of the data, and the second-order feature is the acceleration of the change of the data, and constructing a training data set; The training data set is subjected to deep learning, the first-order features and the second-order features are used as input data, the influence of the control parameter changes on the emulsification target is used as the output result, a machine analysis model is constructed, and the influence pairing relationship between the emulsification target and the emulsification pump control parameters is obtained.

3. The high-precision emulsification control method according to claim 1, characterized in that: According to the mutual influence of the particle size distribution, stability emulsification objectives and the constraint conditions of the index vector, the multi-objective control parameter items are optimized to determine the single pump optimization control scheme, including: The multi-objective control parameter items include the control parameter schemes for the particle size distribution and the stability emulsification objectives, which are respectively used as the first control parameter scheme and the second control parameter scheme; Taking the particle size distribution and stability as optimization targets, and constructing an evaluation function based on the influence pairing relationship between the emulsification target and the emulsification pump control parameters; Constructing an optimization space according to the constraint conditions of the indicator vector and the evaluation function; The first control parameter scheme is taken as the starting point, the second control parameter scheme is taken as the optimization direction, and the optimization space is used for iterative optimization through crossover, mutation and selection search to select the control scheme with the largest optimization target as the single pump optimization control scheme.

4. The high-precision emulsification control method according to claim 1, characterized in that: Based on the single pump optimization control scheme, the emulsification pump is controlled, and the monitoring data of multiple production lines are collected synchronously to perform multi-pump synergy analysis and obtain the synergy control parameter deviation information, including: Install sensors on each emulsification pump to collect monitoring signals from each pump; Aligning the monitoring signals according to the acquisition time, calculating the similarity of the aligned signals, and determining the signal similarity coefficient; A deviation comparison is performed based on the signal similarity coefficient to obtain the collaborative control parameter deviation information.

5. The high-precision emulsification control method according to claim 4, characterized in that: The monitoring signals are aligned according to the acquisition time, the aligned signal similarity is calculated, and the signal similarity coefficient is determined, including: A rotation speed sensor, a shear force sensor, and a temperature sensor are arranged, and the monitoring signals include rotation speed, shear force, and temperature; Based on the acquisition timestamp of the monitoring signal, aligning the rotation speed, shear force, and temperature onto the same time axis; Extracting the mean and standard deviation characteristics of the rotation speed, shear force, and temperature; Based on the time alignment relationship, the extracted features of each monitoring signal are fused using principal component analysis to obtain the consistency index; The root mean square error and standard deviation are calculated through the consistency index to obtain the signal similarity coefficient.

6. The high-precision emulsification control method according to claim 2, characterized in that: The method of performing compensation control on the collaborative control parameter deviation information according to the index vector and constraint conditions of the batch consistency emulsification target and matching the single pump optimization control scheme to perform adaptive compensation control includes: According to the collaborative control parameter deviation information, the emulsification target and the influence pairing relationship of the emulsification pump control parameter, the stability emulsification target deviation and the particle size distribution emulsification target deviation are obtained respectively; Perform compensation analysis on the stability emulsification target deviation and the particle size distribution emulsification target deviation according to the index vector and the constraint conditions to determine the target compensation amount; Perform parameter positioning and determine the equipment deviation coefficient based on the collaborative control parameter deviation information; The target compensation amount is positioned according to the parameter, the target compensation amount is corrected using the device deviation coefficient, and compensation control is performed according to the corrected parameter compensation amount.

7. The high-precision emulsification control method according to claim 6, characterized in that: The high-precision emulsification control method further comprises: Acquire the continuity cooperative control parameter deviation information according to the time sequence relationship, extract the continuity cooperative control parameter deviation information by using a sliding window, and obtain a multi-window deviation variation; Using the multi-window deviation variation to fit the time series variation relationship of the deviation variation; An adaptive compensation mechanism is set according to the timing variation relationship to perform timing adaptive compensation on the target deviation device.

8. A high-precision emulsification control device, characterized in that: A high-precision emulsification control method for implementing any one of claims 1 to 7, wherein the high-precision emulsification control system comprises: An emulsification target extraction module, which is used to extract high-precision emulsification targets, including particle size distribution, stability, and batch consistency, and to analyze the emulsification targets to determine an index vector, wherein the index vector has a constraint condition, and the constraint condition is a restricted value range of the index vector; A control parameter configuration module, wherein the control parameter configuration module is used to establish an influence pairing relationship between the emulsification target and the emulsification pump control parameter, and configure the control parameters of the particle size distribution and stability emulsification targets based on the influence pairing relationship to obtain a multi-objective control parameter item; A parameter optimization module, wherein the parameter optimization module is used to optimize the multi-objective control parameter items according to the mutual influence of the particle size distribution and the stability emulsification target and the constraint conditions of the index vector, and determine the single pump optimization control scheme; A multi-pump collaborative analysis module, which is used to control the emulsification pump based on the single pump optimization control scheme, and synchronously collect monitoring data of multiple production lines to perform multi-pump collaborative analysis to obtain collaborative control parameter deviation information; A compensation control module is used to perform compensation control on the collaborative control parameter deviation information according to the index vector and constraint conditions of the batch consistency emulsification target, and to match the single pump optimization control scheme to perform adaptive compensation control.

Images